<html lang="en">

  <head>
    <title>epitopepredict: a tool for integrated MHC binding prediction</title>
    <meta charset="utf-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <meta http-equiv="X-UA-Compatible" content="ie=edge">
    <link href="https://unpkg.com/@stencila/thema@2/dist/themes/giga/styles.css" rel="stylesheet">
    <script src="https://unpkg.com/@stencila/thema@2/dist/themes/giga/index.js"
      type="text/javascript"></script>
    <script
      src="https://unpkg.com/@stencila/components@&lt;=1/dist/stencila-components/stencila-components.esm.js"
      type="module"></script>
    <script
      src="https://unpkg.com/@stencila/components@&lt;=1/dist/stencila-components/stencila-components.js"
      type="text/javascript" nomodule=""></script>
  </head>

  <body>
    <main role="main">
      <article itemscope="" itemtype="http://schema.org/Article" data-itemscope="root">
        <h1 itemprop="headline">epitopepredict: a tool for integrated MHC binding prediction</h1>
        <meta itemprop="image"
          content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=epitopepredict:%20a%20tool%20for%20integrated%20MHC%20binding%20prediction">
        <ol data-itemprop="authors">
          <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
            <meta itemprop="name" content="Damien Farrell"><span data-itemprop="givenNames"><span
                itemprop="givenName">Damien</span></span><span data-itemprop="familyNames"><span
                itemprop="familyName">Farrell</span></span><span data-itemprop="emails"><a
                itemprop="email"
                href="mailto:farrell.damien@gmail.com">farrell.damien@gmail.com</a></span><span
              data-itemprop="affiliations"><a itemprop="affiliation"
                href="#author-organization-1">1</a></span>
          </li>
        </ol>
        <ol data-itemprop="affiliations">
          <li itemscope="" itemtype="http://schema.org/Organization" itemid="#author-organization-1"
            id="author-organization-1"><span itemprop="name">UCD School of Veterinary Medicine,
              University College Dublin, Ireland.</span></li>
        </ol><span itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher">
          <meta itemprop="name" content="Unknown"><span itemscope=""
            itemtype="http://schema.org/ImageObject" itemprop="logo">
            <meta itemprop="url"
              content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Unknown">
          </span>
        </span>
        <ul data-itemprop="keywords">
          <li itemprop="keywords">Software and Workflows</li>
          <li itemprop="keywords">Biomedical Science</li>
          <li itemprop="keywords">Bioinformatics</li>
        </ul>
        <section data-itemprop="description">
          <h2 data-itemtype="http://schema.stenci.la/Heading">Abstract</h2>
          <meta itemprop="description"
            content="A key step in the cellular adaptive immune response is the presentation of antigens to T cells. Computational prediction of T cell epitopes has many applications in vaccine design and immuno-diagnostics. This is the basis of immunoinformatics, which allows in silico screening of peptides before experiments are performed. With the availability of whole genomes for many microbial species it is now feasible to computationally screen whole proteomes for candidate peptides. epitopepredict is a programmatic framework and command line tool designed to aid this process. It provides access to multiple binding prediction algorithms under a single interface and scales for whole genomes using multiple target MHC alleles. A web interface is provided to assist visualization and filtering of the results. The software is freely available under an open-source license from https://github.com/dmnfarrell/epitopepredict">
          <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">A key step in the cellular
            adaptive immune response is the presentation of antigens to T cells. Computational
            prediction of T cell epitopes has many applications in vaccine design and
            immuno-diagnostics. This is the basis of immunoinformatics, which allows <em
              itemscope="" itemtype="http://schema.stenci.la/Emphasis">in silico</em> screening of
            peptides before experiments are performed. With the availability of whole genomes for
            many microbial species it is now feasible to computationally screen whole proteomes for
            candidate peptides. epitopepredict is a programmatic framework and command line tool
            designed to aid this process. It provides access to multiple binding prediction
            algorithms under a single interface and scales for whole genomes using multiple target
            MHC alleles. A web interface is provided to assist visualization and filtering of the
            results. The software is freely available under an open-source license from <a
              href="https://github.com/dmnfarrell/mhcpredict" itemscope=""
              itemtype="http://schema.stenci.la/Link">https://github.com/dmnfarrell/epitopepredict</a>
          </p>
        </section>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="background">Background</h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">An essential step in provoking
          adaptive immunity, delivered by the activated CD8+ or CD4+ T cells, is the recognition of
          epitopes by T cell receptors (TCR). During this process, short peptides processed from
          self or foreign proteins may be presented on the surface of the cell and bound to major
          histocompatibility complex (MHC) proteins for binding to T cell receptors. Those
          peptide-MHC combinations that bind and activate an immune response are called epitopes.
          This is the major determinant step and is computationally predictable. The most effective
          approach is to estimate the binding affinity of a given peptide fragment to MHC class I or
          II molecules. Algorithms that can identify MHC-class I or MHC-class II binding peptides
          rapidly and accurately are essential for vaccine development, neo-epitope discovery, and
          immunogenicity screening of protein therapeutics. Many MHC binding prediction methods
          exist for both class I and II and have been comprehensively reviewed <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref1"><span>1</span><span>Lundegaard
                et al., 2010</span></a></cite>⁠. Currently the most effective methods are machine
          learning (ML) based approaches, which are trained on existing binding affinity data for a
          given MHC molecule. To do this, the peptide sequence is encoded and these features fit
          against the known affinity. To date, artificial neural networks (ANN) perform better at
          this task than other models such as linear regression. This is likely because the hidden
          layers in such networks are better able to account for the contribution of intrapeptide
          residue-residue interactions to the binding affinity. All methods vary in accuracy over
          MHC alleles depending on the availability of quality datasets. Pan-allele tools have been
          developed to deal with this issue <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref2"><span>2</span><span>Backert and
                Kohlbacher, 2015</span></a></cite>⁠. These approaches can impute affinities for
          unknown alleles on the basis of neighboring MHC alleles with the highest sequence
          similarity and which have sufficient training data.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">By convention, peptides are
          selected using an arbitrary score threshold. For affinities, a threshold value of 500 nM
          is considered a binder and 50 nM a strong binder. The algorithms perform best at this
          classification task rather than re-producing exact affinities. This problem is intrinsic
          to ML-based approaches: the effect of the most dominant features is penalized
          intentionally to achieve better generalization on blind test data <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref3"><span>3</span><span>Domingos,
                2012</span></a></cite>⁠. Another source of the inaccuracy is the loss of sensitivity
          of experimental assays at either very high or low binding affinity regimes. As a
          consequence, epitope candidates for subsequent experimental validation selected by ranking
          the affinities may not necessarily be the best approach. Percentage ranking is now often
          the recommended method <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref4"><span>4</span><span>Chaves et al., 2012</span></a></cite>⁠. However, the
          exact approach probably depends on the study in question. For example, searching a small
          number of proteins might mean taking the top ranked percentile from each sequence
          regardless of score. Threshold selection is discussed later in the examples.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="strategies-for-epitope-selection">Strategies for epitope selection</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">A typical approach to binder
          selection is to select the top n<sup itemscope=""
            itemtype="http://schema.stenci.la/Superscript">th</sup> percentile per protein rather
          than using an absolute threshold value; however, for whole proteome studies, this is
          likely to introduce multiple false positives from peptides in proteins that would
          otherwise score very low globally. We therefore include in our method a global
          standardization of the score over the entire proteome, similar to that used by Bremel et
          al. <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref5"><span>5</span><span>Bremel and Homan, 2010</span></a></cite>⁠ and others,
          by setting a global cut-off based on the top percentage of scores from the entire
          proteome. In addition, some alleles have a significantly higher score distribution and
          will dominate the results if a uniform score cut-off is applied; this applies in general
          to MHC binding predictors. Thus, separating global cut-off per allele so that low scoring
          alleles would be better represented is also advisable. This approach is consistent with
          recent work by Paul et al. <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref6"><span>6</span><span>Paul et al., 2013</span></a></cite>⁠ regarding
          allele-specific thresholds in MHC-I prediction. Three such alternative threshold
          strategies are provided in this library and discussed below.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading" id="binding-promiscuity">Binding
          promiscuity</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Promiscuous MHC binders are
          defined in this context as those above the cutoffs in more than a given number of alleles.
          The rationale for this is that a peptide is more likely to be immunogenic in your target
          population if it is a binder in multiple alleles.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="tools-for-epitope-selection">Tools for epitope selection</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Software for T cell vaccine
          development or neoepitope prediction currently concentrates on using the binding
          prediction or eluted ligand likelihood as the main selection methods. Typically, when a
          binding prediction tool is published, the authors will provide a binary that can be used
          on the command line or via a web interface. Some tools provide both. Command line tools
          offer better control and perhaps higher throughput but may be harder to use for a general
          user. Virtually, all of these tools require users to input each sequence and its allele
          separately. It is then difficult or impossible to integrate results from multiple
          sequences and alleles. The results are often in different formats and it is not possible
          to compare between algorithms, for example.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">There are several computational
          pipelines that help a researcher to predict epitopes [<cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref7"><span>7</span><span>Schubert et
                al., 2013</span></a></cite>; <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref8"><span>8</span><span>Soria-Guerra
                et al., 2015</span></a></cite>]⁠⁠. Other commercial desktop software applications
          for epitope discovery are EpiMatrix <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref9"><span>9</span><span>De Groot and
                Martin, 2009</span></a></cite>⁠. Commercial tools may be of high quality but are
          neither free nor open source, raising issues of reproducibility for academics. There is
          therefore a limited choice for users in readily available and easy to use tools.</p>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="implementation">
          Implementation</h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">This software is implemented
          entirely in Python <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref10"><span>10</span><span>Farrell, 2021</span></a></cite>. To achieve some
          level of uniformity between prediction methods, a standardized programmatic interface for
          executing the binding prediction methods and processing the results was designed. The
          results from each method can then be processed and visualized in a consistent manner.
          Prediction methods are implemented by inheriting from a Predictor object. Each predictor
          may wrap methods from other Python packages or call command line predictors. For example
          the TepitopePredictor uses the epitopepredict.tepitope module provided with this package.
          This approach allows us to integrate a new prediction method in a relatively
          straightforward and consistent manner. The prediction methods always return a Pandas
          DataFrame (Pandas, RRID:SCR_018214)[11]⁠ in a standard format. The predict_sequences
          method is used for multiple protein sequences and can be run in parallel. This can take a
          GenBank or fasta file as input. For large numbers of sequences the prediction function
          should be called with save=True so that the results are saved as each protein is completed
          to avoid memory issues, since many alleles might be called for each protein. Results are
          saved with one file per protein/sequence in csv format. More details on how to use the
          Python API are given in the online documentation and in the example notebooks referencing
          the examples below.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">The web application is
          implemented in Tornado <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref12"><span>12</span></a></cite>⁠ using the Bokeh <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref13"><span>13</span><span>,
                2010</span></a></cite>⁠ visualization library for making interactive plots.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="supported-mhc-binding-prediction-tools">Supported MHC binding prediction tools</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">The following MHC binding
          prediction methods are supported through the API. This means they can be utilized via the
          command line tool. The first two are built into the package, the others require
          installation of external software by the user. NetMHC tools in particular have to be
          installed separately as they have a more restrictive academic license that does not allow
          them to be distributed by a third party or via a repository. Only the ‘pan specific’
          versions of these tools are supported as they provide the best allelic coverage.</p>
        <ul itemscope="" itemtype="http://schema.org/ItemList">
          <li itemscope="" itemtype="http://schema.org/ListItem" itemprop="itemListElement">
            <meta itemprop="position" content="1">
            <meta itemprop="url" content="#1">TEPITOPEpan <cite itemscope=""
              itemtype="http://schema.stenci.la/Cite"><a href="#ref14"><span>14</span><span>Zhang et
                  al., 2012</span></a></cite>⁠ is a position specific scoring matrix (PSSM) based
            algorithm. It uses 11 scoring matrices derived from combinatorial competitive binding
            assays on 11 HLA-DR alleles <cite itemscope=""
              itemtype="http://schema.stenci.la/Cite"><a
                href="#ref15"><span>15</span><span>Sturniolo et al., 1999</span></a></cite>⁠. This
            method is pan specific and covers 700 HLA-DR molecules with unknown binding
            specificities based on pocket similarity to the original set of 11 library sequences. We
            have implemented this algorithm as a Python module, thus it comes with the package. It
            is fast but not as accurate in benchmarks as netMHCIIpan with fewer alleles covered.
          </li>
          <li itemscope="" itemtype="http://schema.org/ListItem" itemprop="itemListElement">
            <meta itemprop="position" content="2">
            <meta itemprop="url" content="#2">The BasicMHC1 predictor is a built-in MHC-I prediction
            method further detailed below. It is implemented using the scikit-learn <cite
              itemscope="" itemtype="http://schema.stenci.la/Cite"><a
                href="#ref16"><span>16</span><span>Abraham et al., 2014</span></a></cite>⁠ package.
            It only covers 103 MHC-I alleles and cannot currently be extrapolated for use with
            similar alleles (i.e. not pan specific) but provides a convenient alternative to the
            external tools.
          </li>
          <li itemscope="" itemtype="http://schema.org/ListItem" itemprop="itemListElement">
            <meta itemprop="position" content="3">
            <meta itemprop="url" content="#3">MHCflurry <cite itemscope=""
              itemtype="http://schema.stenci.la/Cite"><a
                href="#ref17"><span>17</span><span>O'Donnell et al., 2018</span></a></cite> is an
            MHC-I predictor also using ANNs trained on affinity measurements. It currently covers
            112 human alleles. This is an open-source tool available via pip and thus easy to
            install. It is recommended for MHC-I predictions unless there are alleles not covered.
            The latest supported version is 2.0.1.
          </li>
          <li itemscope="" itemtype="http://schema.org/ListItem" itemprop="itemListElement">
            <meta itemprop="position" content="4">
            <meta itemprop="url" content="#4">NetMHCpan <cite itemscope=""
              itemtype="http://schema.stenci.la/Cite"><a href="#ref18"><span>18</span><span>Jurtz et
                  al., 2017</span></a></cite>⁠ is an artificial neural network algorithm covering
            many human and animal MHC-I alleles. This is trained on both MS eluted ligand data and
            binding affinity data. It therefore returns two properties: either the likelihood of a
            peptide becoming a natural ligand, or the predicted binding affinity. Version 4.1 is
            currently supported.
          </li>
          <li itemscope="" itemtype="http://schema.org/ListItem" itemprop="itemListElement">
            <meta itemprop="position" content="5">
            <meta itemprop="url" content="#5">NetMHCIIpan <cite itemscope=""
              itemtype="http://schema.stenci.la/Cite"><a href="#ref19"><span>19</span><span>Nielsen
                  et al., 2010</span></a></cite>⁠ is also an ANN, trained on binding data for
            multiple MHC-II alleles. Predictions are now extended to all HLA-DR, DQ and DP known
            sequences as from version 3.0 <cite itemscope=""
              itemtype="http://schema.stenci.la/Cite"><a
                href="#ref20"><span>20</span><span>Karosiene et al., 2013</span></a></cite>⁠. Both
            this tool and netMHCpan have the broadest species support of any algorithms. They both
            have good web interfaces but are covered by free non-commercial academic licenses and
            the local versions must be installed separately. Version 3.0 is supported.
          </li>
        </ul>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="available-threshold-methods">Available threshold methods</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Thresholds for considering a
          peptide to be a binder are somewhat arbitrary. This tool provides three threshold methods.
          The results from each will overlap but will not be identical. These are applied per
          sequence/protein and per each allele using the currently loaded data. These three
          threshold methods are also available when calculating promiscuous binders. Ultimately,
          these are simply alternative methods of achieving the same result - reducing the set of
          predicted peptides.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph"><strong itemscope=""
            itemtype="http://schema.stenci.la/Strong">rank</strong> – Selects the top ranking
          peptides in each sequence above a rank cutoff. This is the most frequently recommended
          method of binder selection in general.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph"><strong itemscope=""
            itemtype="http://schema.stenci.la/Strong">score</strong> - Uses a single score cutoff
          for all peptides. Most binding predictors produce a binding affinity score (ic50) and a
          cutoff of 500 nM is common. There is no rule over which score cutoff is optimal, however.
          Some alleles will tend to produce higher scores. Also, unless some limit is placed on the
          number of peptides, large proteins will produce a lot of peptides compared to smaller
          sequences.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph"><strong itemscope=""
            itemtype="http://schema.stenci.la/Strong">global</strong> - Allele specific ‘global’
          cutoffs, this uses a percentile cutoff to select peptides using pre-calculated quantile
          scores for each allele. The global quantile scores were calculated for each prediction
          method using a set of sequences from known human antigens such as apical membrane antigen,
          Tetanus toxin, thrombopoietin, and interferon beta. Therefore, peptides can be selected as
          measured against a standard scale as opposed to their ‘within protein’ ranking. A typical
          value would be using the top 5% in each allele across all sequences. This technique is
          designed for selection of a small set of candidates from very large numbers of proteins,
          such as across a bacterial proteome. There is limited evidence to suggest that this
          selection method is superior to the other methods but we have used it for selectiing a
          small set of candidates from large numbers of proteins, detailed in example 2 below.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading" id="a-basic-mhc-i-predictor">A
          basic MHC-I predictor</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">This section details the
          built-in method for MHC-I binding prediction. It is implemented in Python using
          scikit-learn. The typical method of building such an algorithm is to encode the peptide
          amino acid sequences numerically in a manner that captures the properties important for
          binding. Then these features can be fit against their known binding affinities (or eluted
          ligand data) using a regression model of some kind. Several peptide encoding schemes were
          tested, including the NLF encoding scheme <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref21"><span>21</span><span>Nanni and
                Lumini, 2011</span></a></cite>⁠, OETMAP <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref22"><span>22</span><span>Gök and
                Özcerit, 2011</span></a></cite>⁠, a Blosum62 matrix, and a simple ‘one hot’ encoding
          method. One hot encoding was found to be adequate and the more complex schemes did not
          appear to offer any significant advantage. This may require further testing. For now, it
          is possible to create and train the predictor with any of these encoders. The regression
          model used is the <em itemscope=""
            itemtype="http://schema.stenci.la/Emphasis">MLPRegressor</em> from sklearn, an
          implementation of a multilayer perceptron (MLP), a class of artificial neural networks.
          The data set used for training was primarily from the IEDB and was curated by the authors
          of MHCflurry <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref17"><span>17</span><span>O'Donnell et al., 2018</span></a></cite>⁠ from
          various sources. The regression model must be trained for each allele. When this is done,
          the model is persisted with the joblib module and can be re-loaded for new predictions for
          that allele. All of this functionality is encapsulated in the <em itemscope=""
            itemtype="http://schema.stenci.la/Emphasis">BasicMHCIPredictor</em> class in
          epitopepredict. The predictor only supports 103 alleles currently and is not pan specific
          as of yet.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">To test performance, a separate
          evaluation set of peptides originally created by Kim et al. <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref23"><span>23</span><span>Kim et
                al., 2014</span></a></cite>⁠ was downloaded from the IEDB. The training set
          sequences were subtracted from this set leaving 25,948 9-mer peptides. Only alleles for
          which there were more than 200 peptides were evaluated to give a reasonable performance
          estimate. This left 40 HLA alleles for testing. Both the Pearson correlation coefficient
          and the ROC AUC metric (with a threshold of below 500 nM set as a positive binder) were
          used as metrics. The results in Figure 1 show that our predictor performs similarly to the
          others with this test set. It is not meant to provide a definitive benchmark since these
          other tools have been more comprehensively benchmarked elsewhere. In particular, it can be
          hard to obtain a benchmark set of peptides that has not been used for training in one or
          more of the models.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">In practical use, this
          predictor can be run directly from the API or command line without installing any other
          program. Models are trained once as needed for each allele/length combination using the
          current installed versions of scikit-learn and joblib. Once trained, each model is saved
          and can be re-used. Training only takes a matter of seconds for each model.</p>
        <figure itemscope="" itemtype="http://schema.stenci.la/Figure" title="Figure 1"><label
            data-itemprop="label">Figure 1</label>
          <stencila-code-chunk itemscope="" itemtype="http://schema.stenci.la/CodeChunk"
            data-execution_count="2" data-programminglanguage="python">
            <pre class="language-python" itemscope="" itemtype="http://schema.stenci.la/CodeBlock"
              slot="text"><code># Code based on the following notebook with the following changes:
# - pre-calculated benchmark.csv file is used if possible
# - commented out code removed
# https://github.com/dmnfarrell/epitopepredict/blob/v0.5.0/notebooks/benchmarking.ipynb

import os, sys, math

import numpy as np

import pandas as pd
pd.set_option(&#39;display.width&#39;, 130)

%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt

import seaborn as sns
sns.set_context(&quot;notebook&quot;, font_scale=1.4)

import epitopepredict as ep
from epitopepredict import sequtils, base, peptutils, mhclearn

# Change into notebooks folder if not already in it
if not os.getcwd().endswith(&#39;notebooks&#39;):
  os.chdir(&#39;notebooks&#39;)

# If benchmark results are already available, then read them
# in for plotting, otherwise generate them
if os.path.exists(&#39;benchmarks.csv&#39;):

  c = pd.read_csv(&#39;benchmarks.csv&#39;)

else:

  def evaluate_predictor(P, allele):
      data = mhclearn.get_evaluation_set1(allele, length=9)
      print (len(data))
      if len(data) &lt; 200:
          return None,None,None
      P.predict_peptides(list(data.peptide), alleles=allele, cpus=14)
      x = P.get_scores(allele)
      x = data.merge(x,on=&#39;peptide&#39;) 
      auc = round(ep.auc_score(x.ic50,x.score,cutoff=500),3)
      import scipy
      pr = scipy.stats.pearsonr(x.ic50, x.score)[0]
      return auc, pr, data

  def run_tests():
      preds = [base.get_predictor(&#39;basicmhc1&#39;),
              base.get_predictor(&#39;netmhcpan&#39;,scoring=&#39;affinity&#39;),
              ep.get_predictor(&#39;mhcflurry&#39;)]
      comp=[]
      test_alleles = mhclearn.get_allele_names()#[:20]
      print (len(test_alleles))
      for P in preds:
          m=[]
          for a in test_alleles:
              print (a)
              if not a.startswith(&#39;HLA&#39;): continue
              try:
                  auc,pr,df = evaluate_predictor(P, a)
                  if auc==None:
                      continue
                  m.append((a,auc,pr,len(df)))            
              except Exception as e:
                  print (a,e)
                  pass
              print (P, auc, pr)
          m=pd.DataFrame(m,columns=[&#39;allele&#39;,&#39;auc&#39;,&#39;pearson r&#39;,&#39;size&#39;])
          m[&#39;name&#39;] = P.name
          comp.append(m)
      return comp

  comp = run_tests()
  c = pd.concat(comp)
  c.to_csv(&#39;benchmarks.csv&#39;)

a = pd.pivot_table(c,index=[&#39;allele&#39;,&#39;size&#39;],columns=&#39;name&#39;,values=&#39;auc&#39;)
r = pd.pivot_table(c,index=[&#39;allele&#39;,&#39;size&#39;],columns=&#39;name&#39;,values=&#39;pearson r&#39;)

def highlight_max(s):
    is_max = s == s.max()
    return [&#39;background-color: yellow&#39; if v else &#39;&#39; for v in is_max]

fig = plt.figure(constrained_layout=True,figsize=(15,6))
gs = fig.add_gridspec(1, 2, hspace=1)
ax = fig.add_subplot(gs[0])
sns.barplot(data=c,y=&#39;pearson r&#39;,x=&#39;name&#39;,ax=ax)
ax.set_title(&#39;pearson r&#39;)

ax = fig.add_subplot(gs[1])
sns.boxplot(data=c,y=&#39;auc&#39;,x=&#39;name&#39;,ax=ax)
t=ax.set_title(&#39;AUC&#39;)</code></pre>
            <figure slot="outputs"><img src="index.html.media/bb7ed5935c69578c9438a0b862f54eea.png"
                alt="" itemscope="" itemtype="http://schema.org/ImageObject"></figure>
          </stencila-code-chunk>
          <figcaption>
            <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Performance of the
              basicmhc1 predictor compared to netMHCpan and MHCflurry for 40 human alleles. (a) Mean
              Pearson r and (b) mean AUC scores over all alleles. Only alleles with evaluation data
              for over more than 200 peptides were used. This test dataset used 9-mer peptides only.
            </p>
          </figcaption>
        </figure>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="results">Results</h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">In the following, we use
          several examples to illustrate the use of this package in practice with real data. These
          examples are available as Jupyter notebooks stored at <a
            href="https://github.com/dmnfarrell/epitopepredict/tree/master/examples" itemscope=""
            itemtype="http://schema.stenci.la/Link">https://github.com/dmnfarrell/epitopepredict/tree/master/examples</a>.
          They are also archived permanently on Zenodo and the latest version is available there
          <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref24"><span>24</span><span>Pisoni, 2020</span></a></cite>. Some of these
          notebooks are also reproducible using the epitopepredict examples Code Ocean capsule (see
          Figure 2 <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref25"><span>25</span><span>Farrell, 2021</span></a></cite>).</p>
        <figure itemscope="" itemtype="http://schema.stenci.la/Figure" title="Figure 2"><label
            data-itemprop="label">Figure 2</label><img src="index.html.media/figure2.png" alt=""
            itemscope="" itemtype="http://schema.org/ImageObject">
          <figcaption>
            <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">An executable Code Ocean
              compute capsule for epitopepredict that can be launched on a cloud workstation.</p>
          </figcaption>
        </figure>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="example-1-predictions-for-selected-antigens-in-mycobacterium-tuberculosis--comparison-with-experimental-data">
          Example 1: Predictions for selected antigens in <em itemscope=""
            itemtype="http://schema.stenci.la/Emphasis">Mycobacterium Tuberculosis</em> – comparison
          with experimental data</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">A typical use of epitope
          prediction tools is to select a candidate list of peptides for testing from a large
          sequence space representing multiple potential antigens. This example provides a
          comparison of the three different selection methods in epitopepredict using a realistic
          example. It uses a set of known CD4 epitopes discovered in a study by measuring IFN-γ T
          cell responses to <em itemscope="" itemtype="http://schema.stenci.la/Emphasis">M.
            tuberculosis</em> (Mtb) antigens in a healthy South African cohort <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref26"><span>26</span><span>Lindestam
                Arlehamn et al., 2016</span></a></cite>⁠. The test data is available as
          supplementary tables in that paper. It comprises 75 15-mer epitopes selected from a set of
          known Mtb antigens.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Here, we performed a simple
          benchmark to find the percentage coverage of predicted MHC-II binders in two predictors,
          netMHCIIpan and Tepitope, using the three threshold methods for selecting promiscuous
          binders described above. These were then compared across a selection of cut-offs that each
          yielded a certain number of binders. Ideally we would want to produce as small a number of
          predicted binders as possible to reduce the number to be experimentally tested.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">The sequences of all 29
          proteins represented in the target set were retrieved and split into 15-mers. Then
          predictions were made for each of the 27 alleles in the target population tested in the
          study. This produced a list of 9,299 peptides predicted for each allele. With
          epitopepredict, selection of promiscuous binders can be done easily with a single command.
          Binders promiscuous above thresholds in at least five alleles were selected.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">The results are shown in Figure
          3, with the plots showing the percentage of experimental peptides covered versus the
          number of predicted binders, corresponding to a certain cut-off in each method. It is seen
          that the ‘rank’ method is superior in both cases as it achieves a higher coverage with the
          lowest number of binders. All the curves level off at about 80% coverage. The ‘rank’
          method may work better in this case partly because some of the epitopes were originally
          selected by prediction algorithms using a similar approach.</p>
        <figure itemscope="" itemtype="http://schema.stenci.la/Figure" title="Figure 3"><label
            data-itemprop="label">Figure 3</label>
          <stencila-code-chunk itemscope="" itemtype="http://schema.stenci.la/CodeChunk"
            data-execution_count="6" data-programminglanguage="python">
            <pre class="language-python" itemscope="" itemtype="http://schema.stenci.la/CodeBlock"
              slot="text"><code>#Note: this cell can take a long time to run!


#load exp data
sette = pd.read_csv(&#39;../examples/sette_SA_MTB_epitopes.csv&#39;)
mtb = sequtils.genbank_to_dataframe(base.mtb_genome,cds=True)
mtb = mtb[mtb.locus_tag.isin(sette.name)]

df = pd.merge(sette, mtb[[&#39;locus_tag&#39;,&#39;translation&#39;]],left_on=&#39;name&#39;,right_on=&#39;locus_tag&#39;)
df[&#39;start&#39;] = df.apply( lambda x: x.translation.find(x.sequence), 1 )
df[&#39;end&#39;] = df.start+df.sequence.str.len()
#for i,r in df[df.start==-1].iterrows():
#    print (r.locus_tag, r.sequence, r.translation)
df=df.drop(&#39;translation&#39;,1)
df=df[df.start&gt;=0]
prots = df.name.unique()
exp = df

donoralleles = pd.read_csv(&#39;../examples/sa_mtb_donor_alleles.csv&#39;)
donoralleles = donoralleles.set_index(&#39;Donor ID&#39;)
donoralleles = donoralleles.apply(lambda x: &#39;HLA-&#39;+x)
x = donoralleles.apply(lambda x : x.value_counts())
x = x.sum(1).sort_values(ascending=False)
x = x[x&gt;=2]
drballeles = x[x.index.str.contains(&#39;DRB&#39;)]
drballeles = list(drballeles.index)

#run predictions
Pt=ep.get_predictor(&#39;tepitope&#39;)
Pt.predict_sequences(mtb, alleles=drballeles,path=&#39;/tmp/mtbsa_tepitope&#39;, length=15, overwrite=False, threads=4)
Pt.load(path=&#39;/tmp/mtbsa_tepitope&#39;)
Pn=ep.get_predictor(&#39;netmhciipan&#39;)
Pn.predict_sequences(mtb, alleles=drballeles,path=&#39;/tmp/mtbsa_netmhciipan&#39;, length=15, overwrite=False, threads=4)
Pn.load(path=&#39;/tmp/mtbsa_netmhciipan&#39;)

def get_hits(P,n,m,cutoffs):
    import difflib
    res = []
    for c in cutoffs:
        rb = P.promiscuous_binders(cutoff_method=m,cutoff=c,n=n,limit=30)        
        df=exp#[exp.name==name].copy()
        def find_matches(x, p):
            return len(difflib.get_close_matches(x.sequence, p, n=10, cutoff=.6))

        df.loc[:,&#39;hits&#39;] = df.apply(lambda x: find_matches(x, rb.peptide),1)        
        f = len(df[df.hits&gt;0])/len(df)*100 
        res.append({&#39;cutoff&#39;:c,&#39;binders&#39;:len(rb),m:f})
    res = pd.DataFrame(res)
    return res


cuts = {&#39;rank&#39;:range(2,40,3),&#39;global&#39;:np.arange(.99,.86,-.01),&#39;score&#39;:range(50,1000,100)}

fig,axs=plt.subplots(1,2,figsize=(14,5),facecolor=&#39;white&#39;)
axs=axs.flat
i=0
[&#39;rank&#39;,&#39;global&#39;,&#39;score&#39;]
for P in [Pn,Pt]:    
    res1 = get_hits(P,5,&#39;rank&#39;,cuts[&#39;rank&#39;])
    if P.name==&#39;tepitope&#39;:
        scuts = np.arange(5,0,-.4)
    else:
        scuts=cuts[&#39;score&#39;]    
    res2 = get_hits(P,5,&#39;score&#39;,scuts)
    res3 = get_hits(P,5,&#39;global&#39;,cuts[&#39;global&#39;])
    
    res1.plot(x=&#39;binders&#39;,y=&#39;rank&#39;,lw=2,ax=axs[i])
    res2.plot(x=&#39;binders&#39;,y=&#39;score&#39;,lw=2,ax=axs[i])
    res3.plot(x=&#39;binders&#39;,y=&#39;global&#39;,lw=2,ax=axs[i])    
    axs[i].set_xlabel(&#39;no. predicted binders&#39;)
    axs[i].set_ylabel(&#39;% coverage&#39;)    
    i+=1

axs[0].set_title(&#39;(a) netMHCIIpan&#39;,fontsize=20)
axs[1].set_title(&#39;(b) Tepitope&#39;,fontsize=20)
plt.tight_layout()
</code></pre>
            <figure slot="outputs"><img src="index.html.media/7d0f753dde64a06309dc42518c6273a2.png"
                alt="" itemscope="" itemtype="http://schema.org/ImageObject"></figure>
          </stencila-code-chunk>
          <figcaption>
            <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Performance of three binder
              selection methods showing the percentage coverage of experimental positive peptides by
              predicted binders at different cutoff levels. The higher the cutoff the more binders
              are predicted until the curves level off. Results are shown for (a) netMHCIIpan and
              (b) Tepitope.</p>
          </figcaption>
        </figure>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="example-2-scanning-the-proteome-of-mycobacterium-bovis-for-cd4-epitopes">Example 2:
          Scanning the proteome of <em itemscope=""
            itemtype="http://schema.stenci.la/Emphasis">Mycobacterium bovis</em> for CD4+ epitopes
        </h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">We have previously used this
          package to prioritize CD4+ epitopes in the proteome of M. bovis (<em itemscope=""
            itemtype="http://schema.stenci.la/Emphasis">Mycobacterium tuberculosis</em> variant
          bovis AF2122/97) for potential use in novel antigens for bovine tuberculosis <cite
            itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref27"><span>27</span><span>Farrell et al., 2016</span></a></cite>⁠. The
          results are documented in the paper. Briefly, we performed binding predictions over the
          entire <em itemscope="" itemtype="http://schema.stenci.la/Emphasis">M.</em> <em
            itemscope="" itemtype="http://schema.stenci.la/Emphasis">bovis</em> proteome using two
          different binding predictors, netMHCIIpan <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref20"><span>20</span><span>Karosiene
                et al., 2013</span></a></cite>⁠, Tepitope <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref14"><span>14</span><span>Zhang et
                al., 2012</span></a></cite>⁠. For each set of results we found only promiscuous
          binders above an allele specific cutoff using the ‘global’ selection strategy. In
          addition, clusters of binders were detected to find areas of high binder density in each
          sequence. The assumption underlying this method is that ~20mer peptides covering these
          regions will be more likely to yield at least one true positive epitope and hence elicit a
          T cell response. The results are a set of clusters for both prediction methods, ranked by
          number of binders per unit length. This has also been referred to as the ‘epitope density’
          method <span itemscope="" itemtype="http://schema.stenci.la/CiteGroup"><cite itemscope=""
              itemtype="http://schema.stenci.la/Cite"><a href="#ref28"><span>28</span><span>Santos
                  et al., 2013</span></a></cite></span>⁠. We further contrasted this cluster
          selection with the more conventional ranking of top scoring binders. We also included
          random non-high-scoring peptides as a control. 20-mer peptides derived from these sets
          were synthesized and tested for IFN-γ responses in M. bovis naturally infected cattle.
          Approximately 24% out of 270 peptides had high responses (using known epitopes as the
          baseline response). The random controls had no responses above this threshold.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">This workflow was performed
          using an older version of this software. A newer and somewhat simplified form of the same
          analysis is now available as a notebook in the examples folder. Results from this output
          will be slightly different to our previous analysis since some of the extra steps have
          been removed, but the methodology is the same.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="example-3-predicting-cross-reactive-t-cell-epitopes-in-sars-cov-2">Example 3:
          Predicting cross-reactive T cell epitopes in Sars-CoV-2</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Eight months after the initial
          outbreak, puzzles remained about the human immune response to the SARS-CoV-2 virus. By
          then, a significant proportion in some large cities, such as New York, had been exposed.
          However antibody tests often revealed lower than expected rates of seropositivity in
          populations where the virus had spread <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref29"><span>29</span><span>Doshi,
                2020</span></a></cite>⁠. It is almost certain that other components of the immune
          system were important in protecting individuals just as in other infectious diseases.
          Robust innate immune responses were one candidate. Another possibility is T cells.
          SARS-CoV-2 reactive CD4+ T cells had been reported in unexposed individuals, suggesting
          pre-existing cross-reactive T cell memory in 20-50% of people <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref30"><span>30</span><span>Grifoni et
                al., 2020</span></a></cite>⁠. It is possible that these were memory T cells
          generated from previous exposures to the human common cold coronaviruses (HCoVs), which
          circulate widely.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Mateus et al. <cite
            itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref31"><span>31</span><span>Mateus et al., 2020</span></a></cite>⁠ identified
          such cross-reactive CD4+ epitopes by generating 42 short term T cell lines specific to
          previously identified epitopes in PBMCs from unexposed donors. Then homologs to these
          peptides in the HCoVs were tested against these cell lines for a response. These tests
          were done in both unexposed and convalescent COVID19 patients. Cross reactivity was found
          in 10/42 of the T cell lines. Responding cells in unexposed donors were predominantly
          found in the effector memory CD4+ T cell population, though the consequences of this for
          protective immunity are not yet known.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Here we show how it’s possible
          to predict such potential cross-reactive CD4+ epitopes just using the sequences.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">The method used is as follows:
        </p>
        <ul itemscope="" itemtype="http://schema.org/ItemList">
          <li itemscope="" itemtype="http://schema.org/ListItem" itemprop="itemListElement">
            <meta itemprop="position" content="1">
            <meta itemprop="url" content="#1">Predict MHC-binders in each SARS-CoV-2 protein
            sequence and selected the top scoring candidates. Here, we use epitopepredict to predict
            the most promiscuous binders across the 8 most representative human MHC-II alleles. Each
            protein sequence is split into 15-mer peptides and scored.
          </li>
          <li itemscope="" itemtype="http://schema.org/ListItem" itemprop="itemListElement">
            <meta itemprop="position" content="2">
            <meta itemprop="url" content="#2">Select the top scoring peptides in each protein. In
            this case we select the peptides using the global cutoff method in the top 5% percentile
            for each allele. We also limit the total for each protein to 70 to prevent a very long
            protein like ORF1ab from dominating the selection.
          </li>
          <li itemscope="" itemtype="http://schema.org/ListItem" itemprop="itemListElement">
            <meta itemprop="position" content="3">
            <meta itemprop="url" content="#3">Calculate conservation of each peptide with it’s
            closest homologous sequence in each of the other four HCoVs. Then rank them by
            percentage identity.
          </li>
        </ul>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Using a limit of 70 peptides
          per protein, we found 282 predicted peptides. Out of these, 162 were conserved with
          &gt;67% identity in at least one HCoV (most commonly with SARS-Cov-1). Note that for a
          peptide to be cross-reactive, it does not necessarily have to share all residues in common
          with its homolog. The 9-mer core binding sequence could be conserved with perhaps similar
          residues at the ends. We finally checked our 162 peptides against the 10 epitopes
          identified by Mateus et al. We found a hit in 6/10 cases, shown in Table 1. Some hits are
          two peptides overlapping in our set, which probably indicates the same core epitope.</p>
        <table itemscope="" itemtype="http://schema.org/Table">
          <caption><label data-itemprop="label">Table 1</label>
            <div itemprop="caption">
              <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Matches to the 10 cross
                reactive peptides found by Mateus et al. from our predicted binders shows hits in
                6/10 cases.</p>
            </div>
          </caption>
          <thead>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <th itemscope="" itemtype="http://schema.stenci.la/TableCell">Sequence</th>
              <th itemscope="" itemtype="http://schema.stenci.la/TableCell">Protein</th>
              <th itemscope="" itemtype="http://schema.stenci.la/TableCell">Start</th>
              <th itemscope="" itemtype="http://schema.stenci.la/TableCell">Hit from Predicted Set
              </th>
            </tr>
          </thead>
          <tbody>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">PSGTWLTYTGAIKLD</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">N</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">326</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">GTWLTYTGAIKLDDK</td>
            </tr>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">SFIEDLLFNKVTLAD</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">S</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">816</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">FIEDLLFNKVTLADA,
                DLLFNKVTLADAGFI</td>
            </tr>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">YEQYIKWPWYIWLGF</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">S</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">1206</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">None</td>
            </tr>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">VLKKLKKSLNVAKSE</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">nsp8</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">3976</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">VVLKKLKKSLNVAKS,
                EVVLKKLKKSLNVAK</td>
            </tr>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">KLLKSIAATRGATVV</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">nsp12</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">4966</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">RQFHQKLLKSIAATR</td>
            </tr>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">EFYAYLRKHFSMMIL</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">nsp12</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">5136</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">NEFYAYLRKHFSMMI,
                YLRKHFSMMILSDDA</td>
            </tr>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">LMIERFVSLAIDAYP</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">nsp12</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">5246</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">None</td>
            </tr>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">TSHKLVLSVNPYVCN</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">nsp13</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">5361</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">None</td>
            </tr>
            <tr itemscope="" itemtype="http://schema.stenci.la/TableRow">
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">NVNRFNVAITRAKVG</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">nsp13</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">5881</td>
              <td itemscope="" itemtype="http://schema.stenci.la/TableCell">VNRFNVAITRAKVGI</td>
            </tr>
          </tbody>
        </table>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="usage">Usage</h2>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading" id="command-line-interface">
          Command Line Interface</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Installing the package provides
          a command line tool that is run from a terminal. It is envisaged that most users will
          utilize the package using this tool since it requires no programming knowledge. It
          provides pre-defined functionality with all inputs and settings specified in a text
          configuration file. One advantage of using configuration files is in avoiding long
          commands with multiple arguments that may be prone to causing errors. Also, configuration
          files can be kept to recall what setting was used for a particular workflow. Using this
          strategy, you can make MHC predictions with your chosen alleles and predictors in one run.
          If settings are left out generally defaults will be used so one can use a minimal file,
          simplifying usage. Other useful features of the tool are the ability to run predictions in
          parallel using multiple processing cores, the use of preset lists of alleles and resuming
          runs that have been interrupted without overwriting previous predictions. Results are
          saved to disk as text files and can be reread in a subsequent run of the tool without
          having to recalculate binding predictions.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">By default, the command line
          tool will calculate the promiscuous binders to give you a unique list of peptides and
          include the number of alleles in which it is a binder. The table is ranked by this value
          and the maximum score over the alleles tested.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading" id="api-usage">API usage</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">A very basic example of how to
          use the library from the Python API is given here. More complex usage is detailed in the
          documentation.</p>
        <pre itemscope="" itemtype="http://schema.stenci.la/CodeBlock"><code>import epitopepredict as ep
P = ep.get_predictor(&#39;basicmhc1&#39;)
from epitopepredict import peptutils
#get some random peptides, returns a list
seqs = peptutils.create_random_sequences(10)
#run predictions
res = P.predict_peptides(seqs, alleles=&#39;HLA-A*01:01&#39;)</code></pre>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph"><strong itemscope=""
            itemtype="http://schema.stenci.la/Strong">The above code returns a pandas DataFrame
            sorted by allele and rank.</strong></p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading" id="plotting">Plotting</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">The API includes the ability to
          plot results for individual protein sequences for one or more predictor. In such plots,
          binders are shown as colored blocks at their position in the protein with multiple tracks,
          one per allele/method. This allows ready comparisons between methods. An example is shown
          in Figure 4. This shows binders for three MHC-class I predictors for an antigenic Mtb
          protein, Rv3875. Six HLA alleles are shown. We can see that each method has some overlap
          with the others.</p>
        <figure itemscope="" itemtype="http://schema.stenci.la/Figure" title="Figure 4"><label
            data-itemprop="label">Figure 4</label>
          <stencila-code-chunk itemscope="" itemtype="http://schema.stenci.la/CodeChunk"
            data-execution_count="23" data-programminglanguage="python">
            <pre class="language-python" itemscope="" itemtype="http://schema.stenci.la/CodeBlock"
              slot="text"><code>from epitopepredict import plotting
m1_alleles = ep.get_preset_alleles(&#39;mhc1_supertypes&#39;)
prots = ep.genbank_to_dataframe(base.mtb_genome, cds=True)
proteins = [&#39;Rv3615c&#39;,&#39;Rv3875&#39;]

P1 = base.get_predictor(&#39;basicmhc1&#39;)
binders = P1.predict_sequences(prots, names=proteins, alleles=m1_alleles, length=9, threads=4)
pb1 = P1.promiscuous_binders(n=2, cutoff=5, cutoff_method=&#39;rank&#39;)
P2 = base.get_predictor(&#39;netmhcpan&#39;)
P2.predict_sequences(prots, names=proteins, alleles=m1_alleles, length=9, threads=4)
P3 = base.get_predictor(&#39;mhcflurry&#39;)
P3.predict_sequences(prots, names=proteins, alleles=m1_alleles, length=9)

#plot a single protein as tracks
ax = plotting.plot_tracks([P1,P2,P3],name=&#39;Rv3875&#39;,cutoff=5,cutoff_method=&#39;rank&#39;,n=2,legend=True,figsize=(12,6))
plt.tight_layout()
</code></pre>
            <figure slot="outputs">
              <pre class="language-text" itemscope="" itemtype="http://schema.stenci.la/CodeBlock"><code>predictions done for 2 sequences in 6 alleles
</code></pre>
              <pre class="language-text" itemscope="" itemtype="http://schema.stenci.la/CodeBlock"><code>/home/damien/gitprojects/epitopepredict/epitopepredict/base.py:702: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  binders[&#39;core&#39;] = binders.peptide
</code></pre>
              <pre class="language-text" itemscope="" itemtype="http://schema.stenci.la/CodeBlock"><code>predictions done for 2 sequences in 6 alleles
predictions done for 2 sequences in 6 alleles
</code></pre><img src="index.html.media/5a3d0ed4553f8513e71f444889afecc1.png" alt="" itemscope=""
                itemtype="http://schema.org/ImageObject">
            </figure>
          </stencila-code-chunk>
          <figcaption>
            <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Predicted promiscuous
              binders in a sample sequence for three methods. Each method will have some overlapping
              peptides but they are usually likely to differ.</p>
          </figcaption>
        </figure>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading" id="testing">Testing</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">The command line tool can be
          tested by calling <strong itemscope=""
            itemtype="http://schema.stenci.la/Strong">epitopepredict -t,</strong> which runs a set
          of sample Ebola virus sequences with the available prediction methods. Outputs are saved
          to a folder called zaire_test. It should be noted that this is not used as a benchmark
          test since the algorithms used have all been tested independently. This is an example run
          for the user to check that the command line workflow is working and to inspect the
          outputs.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading" id="web-application">Web
          Application</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">A web interface that is
          launched from the command line can be used to view results from a set of predictions that
          have been previously made. This is an improved and much easier to use form of a previous
          web interface called epitopemap <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a href="#ref32"><span>32</span><span>Bednar,
                2020</span></a></cite>⁠ and replaces it. Widgets can be used to select thresholds
          and the kind of plot shown. Currently two kinds of plots can be viewed, a sequence view
          and one that shows the peptides as colored blocks in tracks along the sequence, as shown
          in Figure 5. This web interface can be tested by running the test command above and then
          launching the web app using the zaire_test folder as input.</p>
        <figure itemscope="" itemtype="http://schema.stenci.la/Figure" title="Figure 5"><label
            data-itemprop="label">Figure 5</label><img src="index.html.media/figure5.png" alt=""
            itemscope="" itemtype="http://schema.org/ImageObject">
          <figcaption>
            <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Web application showing
              results for a single protein sequence. Widgets can be used to select protein, cut-off
              levels and the type of plot.</p>
          </figcaption>
        </figure>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="conclusions">Conclusions
        </h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">This software provides a
          programmatic framework and command line interface for running multiple MHC binding
          prediction algorithms. This will be especially useful for performing high throughput
          calculations in many sequences and alleles. It is designed to scale for proteome scanning
          by allowing multiple processing threads to be used with any of the prediction methods. The
          API can also be easily applied to single sequences or small numbers of antigens. A web
          interface allows users to readily review results if they wish.</p>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="availability-and-requirements">Availability and requirements</h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Project name: epitopepredict
        </p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Project home page: <a
            href="https://github.com/dmnfarrell/mhcpredict" itemscope=""
            itemtype="http://schema.stenci.la/Link">https://github.com/dmnfarrell/epitopepredict</a>
        </p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Archived version: v0.5.0 (DOI:
          10.5281/zenodo.4056421)</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">SciCrunch Identifier:
          SCR_019221</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Operating system(s): Linux,
          Unix</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Programming language: Python
        </p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Other requirements: biopython,
          pandas, numpy, matplotlib, scikit-learn</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Optional requirements: bokeh,
          panel (web app only)[33]</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">License: GNU General Public
          License v 3.0</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Any restrictions to use by
          non-academics: None</p>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="funding">Funding</h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">This work was supported by the
          Irish Department of Agriculture Food and the Marine grant 15/S/651 (NEXUSMAP). DF was
          previously funded under an Irish Research Council Postdoctoral Fellowship (GOIPD/2015/475)
          for part of this work. The funders had no role in study design, data collection and
          analysis, decision to publish, or preparation of the manuscript.</p>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="acknowledgments">
          Acknowledgments</h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Thanks to Dr. Joseph Crispell
          for useful discussions on machine learning. Thanks also to Prof. Stephen Gordon for
          support during the development of this software.</p>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="data-availability">Data
          Availability</h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">All computational work
          described here was implemented using Python. The code is provided as a Python package
          called epitopepredict under the Apache license. Extensive use was made of the IPython
          (Jupyter) notebook environment <cite itemscope=""
            itemtype="http://schema.stenci.la/Cite"><a
              href="#ref34"><span>34</span><span>Silaparasetty, 2020</span></a></cite>⁠ in
          prototyping the codebase.</p>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Documentation for users is
          available at <a href="http://epitopepredict.readthedocs.io/" itemscope=""
            itemtype="http://schema.stenci.la/Link">http://epitopepredict.readthedocs.io</a>.
          Snapshots of the code are available in the <em itemscope=""
            itemtype="http://schema.stenci.la/Emphasis">GigaScience</em> GigaDB respository <cite
            itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref35"><span>35</span><span>Farrell, 2021</span></a></cite>, and a CodeOcean
          capsule is also available <cite itemscope="" itemtype="http://schema.stenci.la/Cite"><a
              href="#ref25"><span>25</span><span>Farrell, 2021</span></a></cite>.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading" id="installation">Installation
        </h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">This software should be run on
          a Linux operating system. Ubuntu is recommended but most major distributions will work
          well. Windows is not supported. If using Windows or macOS (OS X), users can simply install
          Linux using virtual machine software such as Oracle VM VirtualBox (<a
            href="https://www.virtualbox.org/" itemscope=""
            itemtype="http://schema.stenci.la/Link"><strong itemscope=""
              itemtype="http://schema.stenci.la/Strong">https://www.virtualbox.org</strong></a>).
          Software is then installed using the online documentation. The installation process is
          very simple, requiring only a single typed command. Externally used MHC binding prediction
          algorithms do need to be installed separately, these are all freely available.</p>
        <h3 itemscope="" itemtype="http://schema.stenci.la/Heading"
          id="installing-netmhcpan-and-netmhciipan">Installing netMHCpan and netMHCIIpan</h3>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">Due to license restrictions,
          these specific programs must be installed separately. They are free for academic users but
          require registration for the non-webserver version. You can go to <a
            href="https://services.healthtech.dtu.dk/" itemscope=""
            itemtype="http://schema.stenci.la/Link">https://services.healthtech.dtu.dk</a> to fill
          in the forms that will give you access to the install file for the respective programs.
          The install instructions can then be found in the readme files when you untar the
          downloaded file, e.g. netMHCpan-4.1.readme. There are four steps detailed and the process
          is relatively simple. Remember to test that the software is working before you use it in
          epitopepredict.</p>
        <h2 itemscope="" itemtype="http://schema.stenci.la/Heading" id="abbreviations">Abbreviations
        </h2>
        <p itemscope="" itemtype="http://schema.stenci.la/Paragraph">ANN: artificial neural
          networks; hCoV: human common cold coronaviruses; MHC: major histocompatibility complex;
          ML: machine learning; MLP: multilayer perceptron; PSSM: position specific scoring matrix;
          TCR: T cell receptor</p>
        <section data-itemprop="references">
          <h2 data-itemtype="http://schema.stenci.la/Heading">References</h2>
          <ol>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref1">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Claus Lundegaard"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Claus</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Lundegaard</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ilka Hoof"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Ilka</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Hoof</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ole Lund"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Ole</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Lund</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Morten Nielsen"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Morten</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Nielsen</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2010">2010</time><a itemprop="url"
                href="http://dx.doi.org/10.1186/1745-7580-6-s2-s3"><span itemprop="headline">State
                  of the art and challenges in sequence based T-cell epitope
                  prediction</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber">Suppl 2</span><span itemscope=""
                  itemtype="http://schema.org/PublicationVolume" itemprop="isPartOf"><span
                    itemprop="volumeNumber" data-itemtype="http://schema.org/Number">6</span><span
                    itemscope="" itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Immunome Research</span></span></span></span><span
                itemprop="pagination">S3</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=State%20of%20the%20art%20and%20challenges%20in%20sequence%20based%20T-cell%20epitope%20prediction">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref2">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Linus Backert"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Linus</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Backert</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Oliver Kohlbacher"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Oliver</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Kohlbacher</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2015-11-20">2015</time><a itemprop="url"
                href="http://dx.doi.org/10.1186/s13073-015-0245-0"><span
                  itemprop="headline">Immunoinformatics and epitope prediction in the age of genomic
                  medicine</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">1</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">7</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Genome Medicine</span></span></span></span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Immunoinformatics%20and%20epitope%20prediction%20in%20the%20age%20of%20genomic%20medicine">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref3">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Pedro Domingos"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Pedro</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Domingos</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2012-10-01">2012</time><a itemprop="url"
                href="http://dx.doi.org/10.1145/2347736.2347755"><span itemprop="headline">A few
                  useful things to know about machine learning</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">10</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">55</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Communications of the ACM</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">78</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">87</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Association for Computing Machinery (ACM)</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Association%20for%20Computing%20Machinery%20(ACM)">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=A%20few%20useful%20things%20to%20know%20about%20machine%20learning">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref4">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Francisco A. Chaves"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Francisco
                      A.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Chaves</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alvin H. Lee"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Alvin
                      H.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Lee</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jennifer L. Nayak"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Jennifer
                      L.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Nayak</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Katherine A. Richards"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Katherine
                      A.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Richards</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Andrea J. Sant"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Andrea
                      J.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Sant</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2012-03-30">2012</time><a itemprop="url"
                href="http://dx.doi.org/10.4049/jimmunol.1103640"><span itemprop="headline"
                  content="The Utility and Limitations of Current Web-Available Algorithms To Predict Peptides Recognized by CD4 T Cells…">The
                  Utility and Limitations of Current Web-Available Algorithms To Predict Peptides
                  Recognized by CD4 T Cells in Response to Pathogen Infection</span></a><span
                itemscope="" itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">9</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">188</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">The Journal of Immunology</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">4235</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">4248</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">The American Association of Immunologists</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=The%20American%20Association%20of%20Immunologists">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=The%20Utility%20and%20Limitations%20of%20Current%20Web-Available%20Algorithms%20To%20Predict%20Peptides%20Recognized%20by%20CD4%20T%20Cells%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref5">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Robert D Bremel"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Robert
                      D</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Bremel</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="E Homan"><span data-itemprop="givenNames"><span
                      itemprop="givenName">E</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Homan</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2010">2010</time><a itemprop="url"
                href="http://dx.doi.org/10.1186/1745-7580-6-8"><span itemprop="headline"
                  content="An integrated approach to epitope analysis II: A system for proteomic-scale prediction of immunological chara…">An
                  integrated approach to epitope analysis II: A system for proteomic-scale
                  prediction of immunological characteristics</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">1</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">6</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Immunome Research</span></span></span></span><span
                itemprop="pagination">8</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=An%20integrated%20approach%20to%20epitope%20analysis%20II:%20A%20system%20for%20proteomic-scale%20prediction%20of%20immunological%20chara%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref6">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Sinu Paul"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Sinu</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Paul</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Daniela Weiskopf"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Daniela</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Weiskopf</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Michael A. Angelo"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Michael
                      A.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Angelo</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="John Sidney"><span data-itemprop="givenNames"><span
                      itemprop="givenName">John</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Sidney</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Bjoern Peters"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Bjoern</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Peters</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alessandro Sette"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Alessandro</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sette</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2013-11-04">2013</time><a itemprop="url"
                href="http://dx.doi.org/10.4049/jimmunol.1302101"><span itemprop="headline"
                  content="HLA Class I Alleles Are Associated with Peptide-Binding Repertoires of Different Size, Affinity, and Immunoge…">HLA
                  Class I Alleles Are Associated with Peptide-Binding Repertoires of Different Size,
                  Affinity, and Immunogenicity</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">12</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">191</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">The Journal of Immunology</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">5831</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">5839</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">The American Association of Immunologists</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=The%20American%20Association%20of%20Immunologists">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=HLA%20Class%20I%20Alleles%20Are%20Associated%20with%20Peptide-Binding%20Repertoires%20of%20Different%20Size,%20Affinity,%20and%20Immunoge%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref7">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="B. Schubert"><span data-itemprop="givenNames"><span
                      itemprop="givenName">B.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Schubert</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="O. Lund"><span data-itemprop="givenNames"><span
                      itemprop="givenName">O.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Lund</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="M. Nielsen"><span data-itemprop="givenNames"><span
                      itemprop="givenName">M.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Nielsen</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2013-09-17">2013</time><a itemprop="url"
                href="http://dx.doi.org/10.1111/tan.12199"><span itemprop="headline">Evaluation of
                  peptide selection approaches for epitope-based vaccine design</span></a><span
                itemscope="" itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">4</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">82</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Tissue Antigens</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">243</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">251</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Wiley</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Wiley">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Evaluation%20of%20peptide%20selection%20approaches%20for%20epitope-based%20vaccine%20design">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref8">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ruth E. Soria-Guerra"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Ruth E.</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Soria-Guerra</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ricardo Nieto-Gomez"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Ricardo</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Nieto-Gomez</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Dania O. Govea-Alonso"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Dania
                      O.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Govea-Alonso</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Sergio Rosales-Mendoza"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Sergio</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Rosales-Mendoza</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2015-02-01">2015</time><a itemprop="url"
                href="http://dx.doi.org/10.1016/j.jbi.2014.11.003"><span itemprop="headline">An
                  overview of bioinformatics tools for epitope prediction: Implications on vaccine
                  development</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationVolume" itemprop="isPartOf"><span
                  itemprop="volumeNumber" data-itemtype="http://schema.org/Number">53</span><span
                  itemscope="" itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                    itemprop="name">Journal of Biomedical Informatics</span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">405</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">414</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Elsevier BV</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Elsevier%20BV">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=An%20overview%20of%20bioinformatics%20tools%20for%20epitope%20prediction:%20Implications%20on%20vaccine%20development">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref9">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Anne S. De Groot"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Anne S.</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">De Groot</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="William Martin"><span
                    data-itemprop="givenNames"><span itemprop="givenName">William</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Martin</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2009-05-01">2009</time><a itemprop="url"
                href="http://dx.doi.org/10.1016/j.clim.2009.01.009"><span
                  itemprop="headline">Reducing risk, improving outcomes: Bioengineering less
                  immunogenic protein therapeutics</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">2</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">131</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Clinical Immunology</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">189</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">201</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Elsevier BV</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Elsevier%20BV">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Reducing%20risk,%20improving%20outcomes:%20Bioengineering%20less%20immunogenic%20protein%20therapeutics">
            </li>
            <li itemscope="" itemtype="http://schema.org/CreativeWork" itemprop="citation"
              id="ref10">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Damien Farrell"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Damien</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Farrell</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2021-02-07">2021</time><a itemprop="url"
                href="http://dx.doi.org/10.1101/2021.02.05.429892"><span
                  itemprop="headline">epitopepredict: A tool for integrated MHC binding
                  prediction</span></a><span itemscope="" itemtype="http://schema.org/Organization"
                itemprop="publisher"><span itemprop="name">Cold Spring Harbor Laboratory</span><span
                  itemscope="" itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Cold%20Spring%20Harbor%20Laboratory">
                </span></span>
            </li>
            <li itemscope="" itemtype="http://schema.org/CreativeWork" itemprop="citation"
              id="ref11">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Fabio Nelli"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Fabio</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Nelli</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2015">2015</time><a itemprop="url"
                href="http://dx.doi.org/10.1007/978-1-4842-0958-5_4"><span itemprop="headline">The
                  pandas Library—An Introduction</span></a><span itemscope=""
                itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                  itemprop="name">Python Data Analytics</span></span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Apress</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Apress">
                </span></span>
            </li>
            <li itemprop="citation" id="ref12">Tornado Developers (2020). Tornado: Python web
              framework and asynchronous networking library (Version 6.1).
              https://www.tornadoweb.org/en/stable/</li>
            <li itemscope="" itemtype="http://schema.org/CreativeWork" itemprop="citation"
              id="ref13">
              <ol data-itemprop="authors"></ol><time itemprop="datePublished"
                datetime="2010">2010</time><a itemprop="url"
                href="http://dx.doi.org/10.5040/9781350088733.0029"><span
                  itemprop="headline">Bokeh</span></a><span itemscope=""
                itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                  itemprop="name">The Visual Dictionary of Photography</span></span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">AVA Publishing SA Distributed by Thames &amp; Hudson (ex-North
                  America) Distributed in the USA &amp; Canada by: English Language Support
                  Office</span><span itemscope="" itemtype="http://schema.org/ImageObject"
                  itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=AVA%20Publishing%20SA%20Distributed%20by%20Thames%20&amp;%20Hudson%20(ex-North%20America)%20Distributed%20in%20the%20USA%20&amp;%20Canada%20by:%20Engli%E2%80%A6">
                </span></span>
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref14">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Lianming Zhang"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Lianming</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Zhang</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Yiqing Chen"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Yiqing</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Chen</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Hau-San Wong"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Hau-San</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Wong</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Shuigeng Zhou"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Shuigeng</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Zhou</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Hiroshi Mamitsuka"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Hiroshi</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Mamitsuka</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Shanfeng Zhu"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Shanfeng</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Zhu</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2012-02-23">2012</time><a itemprop="url"
                href="http://dx.doi.org/10.1371/journal.pone.0030483"><span
                  itemprop="headline">TEPITOPEpan: Extending TEPITOPE for Peptide Binding Prediction
                  Covering over 700 HLA-DR Molecules</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">2</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">7</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">PLoS ONE</span></span></span></span><span
                itemprop="pagination">e30483</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Public Library of Science (PLoS)</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Public%20Library%20of%20Science%20(PLoS)">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=TEPITOPEpan:%20Extending%20TEPITOPE%20for%20Peptide%20Binding%20Prediction%20Covering%20over%20700%20HLA-DR%20Molecules">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref15">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Tiziana Sturniolo"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Tiziana</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sturniolo</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Elisa Bono"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Elisa</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Bono</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jiayi Ding"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Jiayi</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Ding</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Laura Raddrizzani"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Laura</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Raddrizzani</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Oezlem Tuereci"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Oezlem</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Tuereci</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ugur Sahin"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Ugur</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Sahin</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Michael Braxenthaler"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Michael</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Braxenthaler</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Fabio Gallazzi"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Fabio</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Gallazzi</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Maria Pia Protti"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Maria
                      Pia</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Protti</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Francesco Sinigaglia"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Francesco</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sinigaglia</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Juergen Hammer"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Juergen</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Hammer</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="1999-06-01">1999</time><a itemprop="url"
                href="http://dx.doi.org/10.1038/9858"><span itemprop="headline"
                  content="Generation of tissue-specific and promiscuous HLA ligand databases using DNA microarrays and virtual HLA clas…">Generation
                  of tissue-specific and promiscuous HLA ligand databases using DNA microarrays and
                  virtual HLA class II matrices</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">6</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">17</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Nature Biotechnology</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">555</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">561</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Generation%20of%20tissue-specific%20and%20promiscuous%20HLA%20ligand%20databases%20using%20DNA%20microarrays%20and%20virtual%20HLA%20clas%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref16">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alexandre Abraham"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Alexandre</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Abraham</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Fabian Pedregosa"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Fabian</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Pedregosa</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Michael Eickenberg"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Michael</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Eickenberg</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Philippe Gervais"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Philippe</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Gervais</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Andreas Mueller"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Andreas</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Mueller</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jean Kossaifi"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Jean</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Kossaifi</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alexandre Gramfort"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Alexandre</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Gramfort</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Bertrand Thirion"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Bertrand</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Thirion</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Gaël Varoquaux"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Gaël</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Varoquaux</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2014">2014</time><a itemprop="url"
                href="http://dx.doi.org/10.3389/fninf.2014.00014"><span itemprop="headline">Machine
                  learning for neuroimaging with scikit-learn</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationVolume" itemprop="isPartOf"><span
                  itemprop="volumeNumber" data-itemtype="http://schema.org/Number">8</span><span
                  itemscope="" itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                    itemprop="name">Frontiers in Neuroinformatics</span></span></span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Frontiers Media SA</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Frontiers%20Media%20SA">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Machine%20learning%20for%20neuroimaging%20with%20scikit-learn">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref17">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Timothy J. O'Donnell"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Timothy
                      J.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">O'Donnell</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alex Rubinsteyn"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Alex</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Rubinsteyn</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Maria Bonsack"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Maria</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Bonsack</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Angelika B. Riemer"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Angelika
                      B.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Riemer</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Uri Laserson"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Uri</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Laserson</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jeff Hammerbacher"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Jeff</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Hammerbacher</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2018-07-01">2018</time><a itemprop="url"
                href="http://dx.doi.org/10.1016/j.cels.2018.05.014"><span
                  itemprop="headline">MHCflurry: Open-Source Class I MHC Binding Affinity
                  Prediction</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">1</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">7</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Cell Systems</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">129</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">132</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Elsevier BV</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Elsevier%20BV">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=MHCflurry:%20Open-Source%20Class%20I%20MHC%20Binding%20Affinity%20Prediction">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref18">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Vanessa Jurtz"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Vanessa</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Jurtz</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Sinu Paul"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Sinu</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Paul</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Massimo Andreatta"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Massimo</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Andreatta</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Paolo Marcatili"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Paolo</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Marcatili</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Bjoern Peters"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Bjoern</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Peters</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Morten Nielsen"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Morten</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Nielsen</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2017-10-04">2017</time><a itemprop="url"
                href="http://dx.doi.org/10.4049/jimmunol.1700893"><span itemprop="headline"
                  content="NetMHCpan-4.0: Improved Peptide–MHC Class I Interaction Predictions Integrating Eluted Ligand and Peptide Bin…">NetMHCpan-4.0:
                  Improved Peptide–MHC Class I Interaction Predictions Integrating Eluted Ligand and
                  Peptide Binding Affinity Data</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">9</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">199</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">The Journal of Immunology</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">3360</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">3368</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">The American Association of Immunologists</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=The%20American%20Association%20of%20Immunologists">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=NetMHCpan-4.0:%20Improved%20Peptide%E2%80%93MHC%20Class%20I%20Interaction%20Predictions%20Integrating%20Eluted%20Ligand%20and%20Peptide%20Bin%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref19">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Morten Nielsen"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Morten</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Nielsen</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Sune Justesen"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Sune</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Justesen</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ole Lund"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Ole</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Lund</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Claus Lundegaard"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Claus</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Lundegaard</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Søren Buus"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Søren</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Buus</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2010">2010</time><a itemprop="url"
                href="http://dx.doi.org/10.1186/1745-7580-6-9"><span itemprop="headline"
                  content="NetMHCIIpan-2.0 - Improved pan-specific HLA-DR predictions using a novel concurrent alignment and weight opti…">NetMHCIIpan-2.0
                  - Improved pan-specific HLA-DR predictions using a novel concurrent alignment and
                  weight optimization training procedure</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">1</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">6</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Immunome Research</span></span></span></span><span
                itemprop="pagination">9</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=NetMHCIIpan-2.0%20-%20Improved%20pan-specific%20HLA-DR%20predictions%20using%20a%20novel%20concurrent%20alignment%20and%20weight%20opti%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref20">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Edita Karosiene"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Edita</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Karosiene</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Michael Rasmussen"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Michael</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Rasmussen</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Thomas Blicher"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Thomas</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Blicher</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ole Lund"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Ole</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Lund</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Søren Buus"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Søren</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Buus</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Morten Nielsen"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Morten</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Nielsen</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2013-07-31">2013</time><a itemprop="url"
                href="http://dx.doi.org/10.1007/s00251-013-0720-y"><span itemprop="headline"
                  content="NetMHCIIpan-3.0, a common pan-specific MHC class II prediction method including all three human MHC class II …">NetMHCIIpan-3.0,
                  a common pan-specific MHC class II prediction method including all three human MHC
                  class II isotypes, HLA-DR, HLA-DP and HLA-DQ</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">10</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">65</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Immunogenetics</span></span></span></span><span
                itemprop="pageStart" data-itemtype="http://schema.org/Number">711</span><span
                itemprop="pageEnd" data-itemtype="http://schema.org/Number">724</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=NetMHCIIpan-3.0,%20a%20common%20pan-specific%20MHC%20class%20II%20prediction%20method%20including%20all%20three%20human%20MHC%20class%20II%20%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref21">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Loris Nanni"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Loris</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Nanni</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alessandra Lumini"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Alessandra</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Lumini</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2011-04-01">2011</time><a itemprop="url"
                href="http://dx.doi.org/10.1016/j.eswa.2010.09.005"><span itemprop="headline">A new
                  encoding technique for peptide classification</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">4</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">38</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Expert Systems with
                      Applications</span></span></span></span><span itemprop="pageStart"
                data-itemtype="http://schema.org/Number">3185</span><span itemprop="pageEnd"
                data-itemtype="http://schema.org/Number">3191</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Elsevier BV</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Elsevier%20BV">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=A%20new%20encoding%20technique%20for%20peptide%20classification">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref22">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Murat Gök"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Murat</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Gök</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ahmet Turan Özcerit"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Ahmet
                      Turan</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Özcerit</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2011-07-30">2011</time><a itemprop="url"
                href="http://dx.doi.org/10.1007/s11010-011-1000-5"><span itemprop="headline">OETMAP:
                  a new feature encoding scheme for MHC class I binding prediction</span></a><span
                itemscope="" itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber">1-2</span><span itemscope=""
                  itemtype="http://schema.org/PublicationVolume" itemprop="isPartOf"><span
                    itemprop="volumeNumber" data-itemtype="http://schema.org/Number">359</span><span
                    itemscope="" itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Molecular and Cellular
                      Biochemistry</span></span></span></span><span itemprop="pageStart"
                data-itemtype="http://schema.org/Number">67</span><span itemprop="pageEnd"
                data-itemtype="http://schema.org/Number">72</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=OETMAP:%20a%20new%20feature%20encoding%20scheme%20for%20MHC%20class%20I%20binding%20prediction">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref23">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Yohan Kim"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Yohan</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Kim</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="John Sidney"><span data-itemprop="givenNames"><span
                      itemprop="givenName">John</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Sidney</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Søren Buus"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Søren</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Buus</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alessandro Sette"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Alessandro</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sette</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Morten Nielsen"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Morten</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Nielsen</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Bjoern Peters"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Bjoern</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Peters</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2014">2014</time><a itemprop="url"
                href="http://dx.doi.org/10.1186/1471-2105-15-241"><span itemprop="headline"
                  content="Dataset size and composition impact the reliability of performance benchmarks for peptide-MHC binding predict…">Dataset
                  size and composition impact the reliability of performance benchmarks for
                  peptide-MHC binding predictions</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">1</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">15</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">BMC Bioinformatics</span></span></span></span><span
                itemprop="pagination">241</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Dataset%20size%20and%20composition%20impact%20the%20reliability%20of%20performance%20benchmarks%20for%20peptide-MHC%20binding%20predict%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/CreativeWork" itemprop="citation"
              id="ref24">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Enrico Pisoni"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Enrico</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Pisoni</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2020-10-01">2020</time><a itemprop="url"
                href="http://dx.doi.org/10.5194/gmd-2020-90-ac5"><span itemprop="headline">code on
                  Zenodo</span></a><span itemscope="" itemtype="http://schema.org/Organization"
                itemprop="publisher"><span itemprop="name">Copernicus GmbH</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Copernicus%20GmbH">
                </span></span>
            </li>
            <li itemscope="" itemtype="http://schema.org/CreativeWork" itemprop="citation"
              id="ref25">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Damien Farrell"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Damien</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Farrell</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2021-02-07">2021</time><a itemprop="url"
                href="http://dx.doi.org/10.1101/2021.02.05.429892"><span
                  itemprop="headline">epitopepredict: A tool for integrated MHC binding
                  prediction</span></a><span itemscope="" itemtype="http://schema.org/Organization"
                itemprop="publisher"><span itemprop="name">Cold Spring Harbor Laboratory</span><span
                  itemscope="" itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Cold%20Spring%20Harbor%20Laboratory">
                </span></span>
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref26">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Cecilia S. Lindestam Arlehamn"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Cecilia
                      S.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Lindestam Arlehamn</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Denise M. McKinney"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Denise
                      M.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">McKinney</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Chelsea Carpenter"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Chelsea</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Carpenter</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Sinu Paul"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Sinu</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Paul</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Virginie Rozot"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Virginie</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Rozot</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Edward Makgotlho"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Edward</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Makgotlho</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Yolande Gregg"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Yolande</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Gregg</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Michele van Rooyen"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Michele</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">van Rooyen</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Joel D. Ernst"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Joel D.</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Ernst</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Mark Hatherill"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Mark</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Hatherill</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Willem A. Hanekom"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Willem
                      A.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Hanekom</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Bjoern Peters"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Bjoern</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Peters</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Thomas J. Scriba"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Thomas
                      J.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Scriba</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alessandro Sette"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Alessandro</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sette</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2016-07-13">2016</time><a itemprop="url"
                href="http://dx.doi.org/10.1371/journal.ppat.1005760"><span itemprop="headline"
                  content="A Quantitative Analysis of Complexity of Human Pathogen-Specific CD4 T Cell Responses in Healthy M. tuberculo…">A
                  Quantitative Analysis of Complexity of Human Pathogen-Specific CD4 T Cell
                  Responses in Healthy M. tuberculosis Infected South Africans</span></a><span
                itemscope="" itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">7</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">12</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">PLOS Pathogens</span></span></span></span><span
                itemprop="pagination">e1005760</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Public Library of Science (PLoS)</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Public%20Library%20of%20Science%20(PLoS)">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=A%20Quantitative%20Analysis%20of%20Complexity%20of%20Human%20Pathogen-Specific%20CD4%20T%20Cell%20Responses%20in%20Healthy%20M.%20tuberculo%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref27">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Damien Farrell"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Damien</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Farrell</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Gareth Jones"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Gareth</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Jones</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Christopher Pirson"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Christopher</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Pirson</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Kerri Malone"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Kerri</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Malone</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Kevin Rue-Albrecht"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Kevin</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Rue-Albrecht</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Anthony J. Chubb"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Anthony
                      J.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Chubb</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Martin Vordermeier"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Martin</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Vordermeier</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Stephen V. Gordon"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Stephen
                      V.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Gordon</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2016-08-25">2016</time><a itemprop="url"
                href="http://dx.doi.org/10.1099/mgen.0.000071"><span itemprop="headline"
                  content="Integrated computational prediction and experimental validation identifies promiscuous T cell epitopes in the…">Integrated
                  computational prediction and experimental validation identifies promiscuous T cell
                  epitopes in the proteome of Mycobacterium bovis</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">8</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">2</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Microbial Genomics</span></span></span></span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Microbiology Society</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Microbiology%20Society">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Integrated%20computational%20prediction%20and%20experimental%20validation%20identifies%20promiscuous%20T%20cell%20epitopes%20in%20the%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref28">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Anderson R Santos"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Anderson
                      R</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Santos</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Vanessa Bastos Pereira"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Vanessa
                      Bastos</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Pereira</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Eudes Barbosa"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Eudes</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Barbosa</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jan Baumbach"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Jan</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Baumbach</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Josch Pauling"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Josch</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Pauling</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Richard Röttger"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Richard</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Röttger</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Meritxell Zurita Turk"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Meritxell
                      Zurita</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Turk</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Artur Silva"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Artur</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Silva</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Anderson Miyoshi"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Anderson</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Miyoshi</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Vasco Azevedo"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Vasco</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Azevedo</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2013">2013</time><a itemprop="url"
                href="http://dx.doi.org/10.1186/1471-2164-14-s6-s4"><span itemprop="headline"
                  content="Mature Epitope Density - A strategy for target selection based on immunoinformatics and exported prokaryotic …">Mature
                  Epitope Density - A strategy for target selection based on immunoinformatics and
                  exported prokaryotic proteins</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber">Suppl 6</span><span itemscope=""
                  itemtype="http://schema.org/PublicationVolume" itemprop="isPartOf"><span
                    itemprop="volumeNumber" data-itemtype="http://schema.org/Number">14</span><span
                    itemscope="" itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">BMC Genomics</span></span></span></span><span
                itemprop="pagination">S4</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Mature%20Epitope%20Density%20-%20A%20strategy%20for%20target%20selection%20based%20on%20immunoinformatics%20and%20exported%20prokaryotic%20%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref29">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Peter Doshi"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Peter</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Doshi</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2020-09-17">2020</time><a itemprop="url"
                href="http://dx.doi.org/10.1136/bmj.m3563"><span itemprop="headline">Covid-19: Do
                  many people have pre-existing immunity?</span></a><span itemscope=""
                itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                  itemprop="name">BMJ</span></span><span itemprop="pagination">m3563</span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">BMJ</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=BMJ">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Covid-19:%20Do%20many%20people%20have%20pre-existing%20immunity?">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref30">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alba Grifoni"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Alba</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Grifoni</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Daniela Weiskopf"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Daniela</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Weiskopf</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Sydney I. Ramirez"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Sydney
                      I.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Ramirez</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jose Mateus"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Jose</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Mateus</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jennifer M. Dan"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Jennifer
                      M.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Dan</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Carolyn Rydyznski Moderbacher"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Carolyn
                      Rydyznski</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Moderbacher</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Stephen A. Rawlings"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Stephen
                      A.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Rawlings</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Aaron Sutherland"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Aaron</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sutherland</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Lakshmanane Premkumar"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Lakshmanane</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Premkumar</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ramesh S. Jadi"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Ramesh
                      S.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Jadi</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Daniel Marrama"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Daniel</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Marrama</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Aravinda M. de Silva"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Aravinda
                      M.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">de Silva</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="April Frazier"><span
                    data-itemprop="givenNames"><span itemprop="givenName">April</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Frazier</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Aaron F. Carlin"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Aaron
                      F.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Carlin</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jason A. Greenbaum"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Jason
                      A.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Greenbaum</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Bjoern Peters"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Bjoern</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Peters</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Florian Krammer"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Florian</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Krammer</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Davey M. Smith"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Davey
                      M.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Smith</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Shane Crotty"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Shane</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Crotty</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alessandro Sette"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Alessandro</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sette</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2020-06-01">2020</time><a itemprop="url"
                href="http://dx.doi.org/10.1016/j.cell.2020.05.015"><span itemprop="headline"
                  content="Targets of T Cell Responses to SARS-CoV-2 Coronavirus in Humans with COVID-19 Disease and Unexposed Individua…">Targets
                  of T Cell Responses to SARS-CoV-2 Coronavirus in Humans with COVID-19 Disease and
                  Unexposed Individuals</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">7</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">181</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Cell</span></span></span></span><span itemprop="pageStart"
                data-itemtype="http://schema.org/Number">1489</span><span itemprop="pageEnd"
                data-itemtype="http://schema.org/Number">1501</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Elsevier BV</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Elsevier%20BV">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Targets%20of%20T%20Cell%20Responses%20to%20SARS-CoV-2%20Coronavirus%20in%20Humans%20with%20COVID-19%20Disease%20and%20Unexposed%20Individua%E2%80%A6">
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref31">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jose Mateus"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Jose</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Mateus</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alba Grifoni"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Alba</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Grifoni</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alison Tarke"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Alison</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Tarke</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="John Sidney"><span data-itemprop="givenNames"><span
                      itemprop="givenName">John</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Sidney</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Sydney I. Ramirez"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Sydney
                      I.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Ramirez</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jennifer M. Dan"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Jennifer
                      M.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Dan</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Zoe C. Burger"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Zoe C.</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Burger</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Stephen A. Rawlings"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Stephen
                      A.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Rawlings</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Davey M. Smith"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Davey
                      M.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Smith</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Elizabeth Phillips"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Elizabeth</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Phillips</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Simon Mallal"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Simon</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Mallal</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Marshall Lammers"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Marshall</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Lammers</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Paul Rubiro"><span data-itemprop="givenNames"><span
                      itemprop="givenName">Paul</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Rubiro</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Lorenzo Quiambao"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Lorenzo</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Quiambao</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Aaron Sutherland"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Aaron</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sutherland</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Esther Dawen Yu"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Esther
                      Dawen</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Yu</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Ricardo da Silva Antunes"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Ricardo</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">da Silva
                      Antunes</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Jason Greenbaum"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Jason</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Greenbaum</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="April Frazier"><span
                    data-itemprop="givenNames"><span itemprop="givenName">April</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Frazier</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alena J. Markmann"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Alena
                      J.</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Markmann</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Lakshmanane Premkumar"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Lakshmanane</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Premkumar</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Aravinda de Silva"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Aravinda</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">de Silva</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Bjoern Peters"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Bjoern</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Peters</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Shane Crotty"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Shane</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Crotty</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Alessandro Sette"><span
                    data-itemprop="givenNames"><span
                      itemprop="givenName">Alessandro</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Sette</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Daniela Weiskopf"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Daniela</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Weiskopf</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2020-08-04">2020</time><a itemprop="url"
                href="http://dx.doi.org/10.1126/science.abd3871"><span itemprop="headline">Selective
                  and cross-reactive SARS-CoV-2 T cell epitopes in unexposed humans</span></a><span
                itemscope="" itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">6512</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">370</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">Science</span></span></span></span><span itemprop="pageStart"
                data-itemtype="http://schema.org/Number">89</span><span itemprop="pageEnd"
                data-itemtype="http://schema.org/Number">94</span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">American Association for the Advancement of Science
                  (AAAS)</span><span itemscope="" itemtype="http://schema.org/ImageObject"
                  itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=American%20Association%20for%20the%20Advancement%20of%20Science%20(AAAS)">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Selective%20and%20cross-reactive%20SARS-CoV-2%20T%20cell%20epitopes%20in%20unexposed%20humans">
            </li>
            <li itemscope="" itemtype="http://schema.org/CreativeWork" itemprop="citation"
              id="ref32">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="James Bednar"><span
                    data-itemprop="givenNames"><span itemprop="givenName">James</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Bednar</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2020">2020</time><a itemprop="url"
                href="http://dx.doi.org/10.25080/majora-342d178e-028"><span
                  itemprop="headline">HoloViz: What's new and what's next</span></a><span
                itemscope="" itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                  itemprop="name">Proceedings of the Python in Science Conference</span></span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">SciPy</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=SciPy">
                </span></span>
            </li>
            <li itemscope="" itemtype="http://schema.org/Article" itemprop="citation" id="ref33">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Damien Farrell"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Damien</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Farrell</span></span>
                </li>
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Stephen V Gordon"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Stephen
                      V</span></span><span data-itemprop="familyNames"><span
                      itemprop="familyName">Gordon</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2015-07-14">2015</time><a itemprop="url"
                href="http://dx.doi.org/10.1186/s12859-015-0659-0"><span
                  itemprop="headline">Epitopemap: a web application for integrated whole proteome
                  epitope prediction</span></a><span itemscope=""
                itemtype="http://schema.org/PublicationIssue" itemprop="isPartOf"><span
                  itemprop="issueNumber" data-itemtype="http://schema.org/Number">1</span><span
                  itemscope="" itemtype="http://schema.org/PublicationVolume"
                  itemprop="isPartOf"><span itemprop="volumeNumber"
                    data-itemtype="http://schema.org/Number">16</span><span itemscope=""
                    itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                      itemprop="name">BMC Bioinformatics</span></span></span></span><span
                itemscope="" itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Springer Science and Business Media LLC</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Springer%20Science%20and%20Business%20Media%20LLC">
                </span></span>
              <meta itemprop="image"
                content="https://via.placeholder.com/1200x714/dbdbdb/4a4a4a.png?text=Epitopemap:%20a%20web%20application%20for%20integrated%20whole%20proteome%20epitope%20prediction">
            </li>
            <li itemscope="" itemtype="http://schema.org/CreativeWork" itemprop="citation"
              id="ref34">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Nikita Silaparasetty"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Nikita</span></span><span
                    data-itemprop="familyNames"><span
                      itemprop="familyName">Silaparasetty</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2020">2020</time><a itemprop="url"
                href="http://dx.doi.org/10.1007/978-1-4842-5967-2_7"><span
                  itemprop="headline">Python Programming in Jupyter Notebook</span></a><span
                itemscope="" itemtype="http://schema.org/Periodical" itemprop="isPartOf"><span
                  itemprop="name">Machine Learning Concepts with Python and the Jupyter Notebook
                  Environment</span></span><span itemscope=""
                itemtype="http://schema.org/Organization" itemprop="publisher"><span
                  itemprop="name">Apress</span><span itemscope=""
                  itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Apress">
                </span></span>
            </li>
            <li itemscope="" itemtype="http://schema.org/CreativeWork" itemprop="citation"
              id="ref35">
              <ol data-itemprop="authors">
                <li itemscope="" itemtype="http://schema.org/Person" itemprop="author">
                  <meta itemprop="name" content="Damien Farrell"><span
                    data-itemprop="givenNames"><span itemprop="givenName">Damien</span></span><span
                    data-itemprop="familyNames"><span itemprop="familyName">Farrell</span></span>
                </li>
              </ol><time itemprop="datePublished" datetime="2021-02-07">2021</time><a itemprop="url"
                href="http://dx.doi.org/10.1101/2021.02.05.429892"><span
                  itemprop="headline">epitopepredict: A tool for integrated MHC binding
                  prediction</span></a><span itemscope="" itemtype="http://schema.org/Organization"
                itemprop="publisher"><span itemprop="name">Cold Spring Harbor Laboratory</span><span
                  itemscope="" itemtype="http://schema.org/ImageObject" itemprop="logo">
                  <meta itemprop="url"
                    content="https://via.placeholder.com/600x60/dbdbdb/4a4a4a.png?text=Cold%20Spring%20Harbor%20Laboratory">
                </span></span>
            </li>
          </ol>
        </section>
      </article>
    </main>
  </body>

</html>