<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>0121-1129</journal-id>
<journal-title><![CDATA[Revista Facultad de Ingeniería]]></journal-title>
<abbrev-journal-title><![CDATA[Rev. Fac. ing.]]></abbrev-journal-title>
<issn>0121-1129</issn>
<publisher>
<publisher-name><![CDATA[Universidad Pedagógica y Tecnológica de Colombia]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0121-11292017000100167</article-id>
<article-id pub-id-type="doi">10.19053/01211129.v26.n44.2017.5834</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Assessing the behavior of machine learning methods to predict the activity of antimicrobial peptides]]></article-title>
<article-title xml:lang="es"><![CDATA[Evaluación del comportamiento de métodos de machine learning para predecir la actividad de péptidos antimicrobianos]]></article-title>
<article-title xml:lang="pt"><![CDATA[Avaliação do comportamento de métodos de machine learning para predizer a atividade de peptídeos antimicrobianos]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Camacho]]></surname>
<given-names><![CDATA[Francy Liliana]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Torres-Sáez]]></surname>
<given-names><![CDATA[Rodrigo]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Ramos-Pollán]]></surname>
<given-names><![CDATA[Raúl]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad Industrial de Santander  ]]></institution>
<addr-line><![CDATA[Bucaramanga Santander]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universidad Industrial de Santander  ]]></institution>
<addr-line><![CDATA[Bucaramanga Santander]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af3">
<institution><![CDATA[,Universidad Industrial de Santander  ]]></institution>
<addr-line><![CDATA[Bucaramanga Santander]]></addr-line>
<country>Colombia</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>04</month>
<year>2017</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>04</month>
<year>2017</year>
</pub-date>
<volume>26</volume>
<numero>44</numero>
<fpage>167</fpage>
<lpage>180</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_arttext&amp;pid=S0121-11292017000100167&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_abstract&amp;pid=S0121-11292017000100167&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_pdf&amp;pid=S0121-11292017000100167&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract This study demonstrates the importance of obtaining statistically stable results when using machine learning methods to predict the activity of antimicrobial peptides, due to the cost and complexity of the chemical processes involved in cases where datasets are particularly small (less than a few hundred instances). Like in other fields with similar problems, this results in large variability in the performance of predictive models, hindering any attempt to transfer them to lab practice. Rather than targeting good peak performance obtained from very particular experimental setups, as reported in related literature, we focused on characterizing the behavior of the machine learning methods, as a preliminary step to obtain reproducible results across experimental setups, and, ultimately, good performance. We propose a methodology that integrates feature learning (autoencoders) and selection methods (genetic algorithms) thorough the exhaustive use of performance metrics (permutation tests and bootstrapping), which provide stronger statistical evidence to support investment decisions with the lab resources at hand. We show evidence for the usefulness of 1) the extensive use of computational resources, and 2) adopting a wider range of metrics than those reported in the literature to assess method performance. This approach allowed us to guide our quest for finding suitable machine learning methods, and to obtain results comparable to those in the literature with strong statistical stability.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen Este trabajo demuestra la importancia de obtener resultados estadísticamente estables cuando se emplean métodos de aprendizaje computacional para predecir la actividad de péptidos antimicrobianos donde, debido al costo y la complejidad de los procesos químicos, los conjuntos de datos son particularmente pequeños (menos de unos cientos de instancias). Al igual que en otros campos con problemas similares, esto produce grandes variabilidades en el rendimiento de los modelos predictivos, lo que dificulta cualquier intento por transferirlos a la práctica. Por ello, a diferencia de otros trabajos que reportan rendimientos predictivos máximos obtenidos en configuraciones experimentales muy particulares, nos enfocamos en caracterizar el comportamiento de los métodos de aprendizaje de máquina, como paso previo a obtener resultados reproducibles, estadísticamente estables y, finalmente, con una capacidad predictiva competitiva. Para este propósito se diseñó una metodología que integra el aprendizaje de características (autoencoders) y métodos de selección (algoritmos genéticos) a través del uso exhaustivo de métricas de rendimiento (test de permutaciones y bootstrapping), permitiendo obtener la evidencia estadística suficiente como para soportar la toma de decisiones de inversión con los recursos disponibles del laboratorio. En este trabajo se muestra evidencia de la utilidad de: 1) el uso extensivo de los recursos computacionales y 2) la adopción de una gama más amplia de métricas que las reportadas en la literatura para evaluar el funcionamiento de los métodos. Este enfoque permitió orientar la búsqueda de métodos de aprendizaje de máquinas adecuados y, además, se obtuvieron resultados comparables a los de la literatura con una gran estabilidad estadística.]]></p></abstract>
<abstract abstract-type="short" xml:lang="pt"><p><![CDATA[Resumo Este trabalho demonstra a importância de obter resultados estatisticamente estáveis quando empregam-se métodos de aprendizagem computacional para predizer a atividade de peptídeos antimicrobianos onde, devido ao custo e à complexidade dos processos químicos, os conjuntos de dados são particularmente pequenos (menos de algumas centenas de instâncias). Igualmente, em outros campos com problemas similares, isto produz grandes variabilidades no rendimento dos modelos preditivos, o que dificulta qualquer intento por transferi-los à prática. Consequentemente, ao contrario de outros trabalhos que reportam rendimentos preditivos máximos obtidos em configurações experimentais muito particulares, enfocamo-nos em caracterizar o comportamento dos métodos de aprendizagem de máquina, como passo prévio para obter resultados reproduzíveis, estatisticamente estáveis e, finalmente, com uma capacidade preditiva competitiva. Para este propósito, desenhou-se uma metodologia que integra a aprendizagem de características (autoencoders) e métodos de seleção (algoritmos genéticos) através do uso exaustivo de métricas de rendimento (teste de permutações e bootstrapping), permitindo obter a evidência estatística suficiente como para suportar a tomada de decisões de inversão com os recursos disponíveis do laboratório. Neste trabalho mostra-se evidência da utilidade de: 1) o uso extensivo dos recursos computacionais e 2) a adoção de uma gama mais ampla de métricas que as reportadas na literatura para avaliar o funcionamento dos métodos. Este enfoque permitiu orientar a busca de métodos de aprendizagem de máquina adequados e, além disso, obter resultados comparáveis aos da literatura com uma grande estabilidade estatística.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[antimicrobial peptides]]></kwd>
<kwd lng="en"><![CDATA[learning curves]]></kwd>
<kwd lng="en"><![CDATA[machine learning]]></kwd>
<kwd lng="en"><![CDATA[statistical stability]]></kwd>
<kwd lng="en"><![CDATA[support vector regression]]></kwd>
<kwd lng="es"><![CDATA[aprendizaje de máquina]]></kwd>
<kwd lng="es"><![CDATA[curvas de aprendizaje]]></kwd>
<kwd lng="es"><![CDATA[estabilidad estadística]]></kwd>
<kwd lng="es"><![CDATA[péptidos antimicrobianos]]></kwd>
<kwd lng="es"><![CDATA[regresión de vectores de soporte]]></kwd>
<kwd lng="pt"><![CDATA[Peptídeos antimicrobianos]]></kwd>
<kwd lng="pt"><![CDATA[Aprendizagem de máquina]]></kwd>
<kwd lng="pt"><![CDATA[Estabilidade estatística]]></kwd>
<kwd lng="pt"><![CDATA[Regressão de Vetores de Suporte]]></kwd>
<kwd lng="pt"><![CDATA[Curvas de aprendizagem]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<label>[1]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Taboureau]]></surname>
<given-names><![CDATA[O]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Methods for Building Quantitative Structure-Activity Relationship (QSAR) Descriptors and Predictive Models for Computer-Aided Design of Antimicrobial Peptides]]></article-title>
<source><![CDATA[Antimicrobial Peptides, Methods in Molecular Biology]]></source>
<year>2010</year>
<volume>8</volume>
<numero>6</numero>
<issue>6</issue>
<page-range>77-86</page-range></nlm-citation>
</ref>
<ref id="B2">
<label>[2]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Borkar]]></surname>
<given-names><![CDATA[M. R]]></given-names>
</name>
<name>
<surname><![CDATA[Pissurlenkar]]></surname>
<given-names><![CDATA[R. R. S]]></given-names>
</name>
<name>
<surname><![CDATA[Coutinho]]></surname>
<given-names><![CDATA[E. C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[HomoSAR: Bridging comparative protein modeling with quantitative structural activity relationship to design new peptides]]></article-title>
<source><![CDATA[Journal of Computational Chemistry]]></source>
<year>2013</year>
<volume>34</volume>
<page-range>2635-46</page-range></nlm-citation>
</ref>
<ref id="B3">
<label>[3]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Shu]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Yu]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Lin]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Predicting the Activity of Antimicrobial Peptides with Amino Acid Topological Information]]></article-title>
<source><![CDATA[Medicinal Chemistry]]></source>
<year>2013</year>
<volume>9</volume>
<page-range>32-44</page-range></nlm-citation>
</ref>
<ref id="B4">
<label>[4]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Torrent]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Andreu]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Nogues]]></surname>
<given-names><![CDATA[V. M]]></given-names>
</name>
<name>
<surname><![CDATA[Boix]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Connecting peptide physicochemical and antimicrobial properties by a rational prediction model]]></article-title>
<source><![CDATA[PLoS ONE]]></source>
<year>2011</year>
<volume>6</volume>
</nlm-citation>
</ref>
<ref id="B5">
<label>[5]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Ding]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Wen]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Lin]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Hu]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Xia]]></surname>
<given-names><![CDATA[Q]]></given-names>
</name>
<name>
<surname><![CDATA[Lin]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[QSAR Modeling and Design of Cationic Antimicrobial Peptides Based on Structural Properties of Amino Acids]]></article-title>
<source><![CDATA[Combinatorial Chemistry &amp; High Throughput Screening]]></source>
<year>2012</year>
<volume>15</volume>
<page-range>347-53</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>[6]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lin]]></surname>
<given-names><![CDATA[Z. H]]></given-names>
</name>
<name>
<surname><![CDATA[Long]]></surname>
<given-names><![CDATA[H. X]]></given-names>
</name>
<name>
<surname><![CDATA[Bo]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Y. Q]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[Y. Z]]></given-names>
</name>
</person-group>
<source><![CDATA[New descriptors of amino acids and their application to peptide QSAR study]]></source>
<year>2008</year>
</nlm-citation>
</ref>
<ref id="B7">
<label>[7]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhou]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Dai]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Zou]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[QSAR modeling of peptide biological activity by coupling support vector machine with particle swarm optimization algorithm and genetic algorithm]]></article-title>
<source><![CDATA[Journal of Molecular Graphics and Modelling]]></source>
<year>2010</year>
<volume>29</volume>
<page-range>188-96</page-range></nlm-citation>
</ref>
<ref id="B8">
<label>[8]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cortes]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Vapnik]]></surname>
<given-names><![CDATA[V]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Support-vector networks]]></article-title>
<source><![CDATA[Machine Learning]]></source>
<year>1995</year>
<volume>20</volume>
<numero>3</numero>
<issue>3</issue>
<page-range>273-97</page-range></nlm-citation>
</ref>
<ref id="B9">
<label>[9]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Camacho]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Torres]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Ramos Pollán]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Feature learning using stacked autoencoders to predict the activity of antimicrobial peptides]]></article-title>
<source><![CDATA[Computational Methods in Systems Biology]]></source>
<year>2015</year>
</nlm-citation>
</ref>
<ref id="B10">
<label>[10]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kiralj]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Ferreira]]></surname>
<given-names><![CDATA[M. M. C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Basic validation procedures for regression models in QSAR and QSPR studies: Theory and application]]></article-title>
<source><![CDATA[Journal of the Brazilian Chemical Society]]></source>
<year>2009</year>
<volume>20</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>770-87</page-range></nlm-citation>
</ref>
<ref id="B11">
<label>[11]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tropsha]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Best Practices for QSAR Model Development, Validation and Exploitation]]></article-title>
<source><![CDATA[Molecular Informatics]]></source>
<year>2010</year>
<volume>29</volume>
<page-range>476-88</page-range></nlm-citation>
</ref>
<ref id="B12">
<label>[12]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bäck]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
</person-group>
<source><![CDATA[Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms]]></source>
<year>1996</year>
<publisher-name><![CDATA[Oxford university press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B13">
<label>[13]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cherkasov]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Jankovic]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Application of 'inductive' QSAR descriptors for quantification of antibacterial activity of cationic polypeptides]]></article-title>
<source><![CDATA[Molecules]]></source>
<year>2004</year>
<volume>9</volume>
<page-range>1034-52</page-range></nlm-citation>
</ref>
<ref id="B14">
<label>[14]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Z. R]]></given-names>
</name>
<name>
<surname><![CDATA[Lin]]></surname>
<given-names><![CDATA[H. H]]></given-names>
</name>
<name>
<surname><![CDATA[Han]]></surname>
<given-names><![CDATA[L. Y]]></given-names>
</name>
<name>
<surname><![CDATA[Jiang]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[Y. Z]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Update of PROFEAT: A web server for computing structural and physicochemical features of proteins and peptides from amino acid sequence]]></article-title>
<source><![CDATA[Nucleic Acids Research]]></source>
<year>2006</year>
<volume>34</volume>
<page-range>W32-7</page-range></nlm-citation>
</ref>
<ref id="B15">
<label>[15]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cao]]></surname>
<given-names><![CDATA[D. S]]></given-names>
</name>
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[Q. S]]></given-names>
</name>
<name>
<surname><![CDATA[Liang]]></surname>
<given-names><![CDATA[Y. Z]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Propy: A tool to generate various modes of Chou's PseAAC]]></article-title>
<source><![CDATA[Bioinformatics]]></source>
<year>2013</year>
<volume>29</volume>
<page-range>960-2</page-range></nlm-citation>
</ref>
<ref id="B16">
<label>[16]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Prediction of antimicrobial peptides based on sequence alignment and feature selection methods]]></article-title>
<source><![CDATA[PLoS ONE]]></source>
<year>2011</year>
<volume>6</volume>
</nlm-citation>
</ref>
<ref id="B17">
<label>[17]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ruan]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Kurgan]]></surname>
<given-names><![CDATA[L. A]]></given-names>
</name>
<name>
<surname><![CDATA[Cios]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Highly accurate and consistent method for prediction of helix and strand content from primary protein sequences]]></article-title>
<source><![CDATA[Artificial Intelligence in Medicine]]></source>
<year>2005</year>
<volume>35</volume>
<numero>1-2</numero>
<issue>1-2</issue>
<page-range>19-35</page-range></nlm-citation>
</ref>
<ref id="B18">
<label>[18]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ng]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Ngiam]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Foo]]></surname>
<given-names><![CDATA[C.Y]]></given-names>
</name>
<name>
<surname><![CDATA[Mai]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Suen]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<source><![CDATA[Unsupervised Feature Learning and Deep Learning]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B19">
<label>[19]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Shin]]></surname>
<given-names><![CDATA[H. C]]></given-names>
</name>
<name>
<surname><![CDATA[Orton]]></surname>
<given-names><![CDATA[M. R]]></given-names>
</name>
<name>
<surname><![CDATA[Collins]]></surname>
<given-names><![CDATA[D. J]]></given-names>
</name>
<name>
<surname><![CDATA[Doran]]></surname>
<given-names><![CDATA[S. J]]></given-names>
</name>
<name>
<surname><![CDATA[Leach]]></surname>
<given-names><![CDATA[M. O]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Stacked Autoencoders for Unsupervised Feature Learning and Multiple Organ Detection in a Pilot Study Using 4D Patient Data]]></article-title>
<source><![CDATA[IEEE Transactions on Pattern Analysis and Machine Intelligence]]></source>
<year>2013</year>
<volume>35</volume>
<numero>8</numero>
<issue>8</issue>
<page-range>1930-43</page-range></nlm-citation>
</ref>
<ref id="B20">
<label>[20]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hastie]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Tibshirani]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Friedman]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<source><![CDATA[The Elements of Statistical Learning]]></source>
<year>2009</year>
<volume>18</volume>
<edition>second ed</edition>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B21">
<label>[21]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ng]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<source><![CDATA[Machine Learning]]></source>
<year>2009</year>
</nlm-citation>
</ref>
<ref id="B22">
<label>[22]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Golland]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Liang]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Mukherjee]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Panchenko]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Permutation Test for Classification]]></article-title>
<source><![CDATA[Journal of Machine Learning Research]]></source>
<year>2000</year>
<volume>1</volume>
<page-range>1-48</page-range></nlm-citation>
</ref>
<ref id="B23">
<label>[23]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ojala]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Garriga]]></surname>
<given-names><![CDATA[G. C]]></given-names>
</name>
</person-group>
<source><![CDATA[Permutation Tests for Studying Classifer Performance]]></source>
<year>2010</year>
<volume>11</volume>
<conf-name><![CDATA[ Proceedings - IEEE International Conference on Data Mining, ICDM]]></conf-name>
<conf-loc> </conf-loc>
<page-range>1833-63</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
