<?xml version="1.0" encoding="UTF-8"?><mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:mads="http://www.loc.gov/mads/" xmlns:metsRights="http://cosimo.stanford.edu/sdr/metsrights/" xmlns:suj="http://www.theses.fr/namespace/sujets" xmlns:tef="http://www.abes.fr/abes/documents/tef" xmlns:tefextension="http://www.abes.fr/abes/documents/tefextension" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.loc.gov/METS/ http://www.abes.fr/abes/documents/tef/recommandation/tef_schemas.xsd">
<mets:metsHdr CREATEDATE="2023-06-21T04:17:52" ID="ABES.STAR.THESE_201984.METS_HEADER" LASTMODDATE="2024-05-26T05:04:36Z" RECORDSTATUS="valide">
<mets:agent ROLE="CREATOR">
<mets:name/>
<mets:note>Note</mets:note>
</mets:agent>
<mets:agent ROLE="DISSEMINATOR">
<mets:name>ABES</mets:name>
</mets:agent>
<mets:altRecordID ID="ABES.STAR.THESE_201984.METS_HEADER.ALTERNATE" TYPE=""/>
</mets:metsHdr>
<mets:dmdSec ID="ABES.STAR.THESE_201984.DESCRIPTION_BIBLIOGRAPHIQUE">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_desc_these">
<mets:xmlData>
<tef:thesisRecord>
<dc:title xml:lang="en">Design and application of deep learning methods to structure-based drug design</dc:title>
<dcterms:alternative xml:lang="fr">Application de réseaux de neurones profonds à des stratégies de drug design basées sur la structure de protéines cibles</dcterms:alternative>
<dc:subject xml:lang="fr">Affinité</dc:subject>
<dc:subject xml:lang="fr">Fonctions de scores</dc:subject>
<dc:subject xml:lang="fr">In silico</dc:subject>
<dc:subject xml:lang="fr">Machine d'apprentissage</dc:subject>
<dc:subject xml:lang="fr">Réseaux de neurones de graphes</dc:subject>
<dc:subject xml:lang="fr">Docking</dc:subject>
<dc:subject xml:lang="fr">Biais</dc:subject>
<dc:subject xml:lang="en">BindingAffinity prediction</dc:subject>
<dc:subject xml:lang="en">Scoring functions</dc:subject>
<dc:subject xml:lang="en">In silico</dc:subject>
<dc:subject xml:lang="en">Machine learning</dc:subject>
<dc:subject xml:lang="en">Graph neural networks</dc:subject>
<dc:subject xml:lang="en">Docking</dc:subject>
<dc:subject xml:lang="en">Bias</dc:subject>
<dc:subject xsi:type="dcterms:DDC">541</dc:subject>
<tef:sujetRameau xml:lang="fr">
<tef:vedetteRameauNomCommun>
<tef:elementdEntree autoriteExterne="027831663" autoriteSource="Sudoc">Affinité chimique</tef:elementdEntree>
</tef:vedetteRameauNomCommun>
<tef:vedetteRameauNomCommun>
<tef:elementdEntree autoriteExterne="26204885X" autoriteSource="Sudoc">Réseaux neuronaux graphiques</tef:elementdEntree>
</tef:vedetteRameauNomCommun>
<tef:vedetteRameauNomCommun>
<tef:elementdEntree autoriteExterne="187923388" autoriteSource="Sudoc">Simulation de docking moléculaire</tef:elementdEntree>
</tef:vedetteRameauNomCommun>
</tef:sujetRameau>
<dcterms:abstract xml:lang="fr">Prédire l'affinité d'un ligand pour sa protéine à partir d'informations structurales est un enjeu majeur pour le développement de médicaments. Malgré les récentes avancées dues à l'utilisation de machines d'apprentissage, de nombreux biais restent à résoudre quant à la capacité de ces modèles à extrapoler à des complexes nouveaux. Dans cette étude, nous avons utilisé une architecture de réseaux de neurones profonds à transmission de message (MPNN) qui lit directement les graphes moléculaires du ligand, de la protéine et des interactions protéine-ligand. Les biais des divers modèles développés ont été évalués, concernant notamment la composition des jeux d'entrainement et de test, la densité des matrices d'apprentissage et la complexité des graphe d'interaction. Nous avons enfin appliqué des modèles non biaisés à la prédiction d'affinité à partir de poses de docking en couplant un modèle binaire de pertinence de pose de docking et un modèle de prédiction d'affinité pour des applications de criblage virtuel.</dcterms:abstract>
<dcterms:abstract xml:lang="en">The accurate binding affinity prediction of protein-ligand complexes from structural data remains a relevant problem in drug discovery. Despite the recent progress in the development of machine learning-based scoring functions relying on novel neural network architectures, there are multiple evidences of potential biases in commonly used training and test sets, which lead to limited generalization capabilities of these models. In the current study we propose an MPNN-based neural network architecture operating on graph inputs of protein, ligand, and interactions derived from the structural data, as well as on their combinations. The potential biases of our models are evaluated with consideration of factors such as training set composition and sparsity, training sample memorization, ligand buriedness and graph complexity are also evaluated. We also introduce a pipeline consisting of a docking pose classifier and binding affinity predictor for potential virtual screening applications.</dcterms:abstract>
<dc:type>Electronic Thesis or Dissertation</dc:type>
<dc:type xsi:type="dcterms:DCMIType">Text</dc:type>
<dc:language xsi:type="dcterms:RFC3066">en</dc:language>
</tef:thesisRecord>
</mets:xmlData>
</mets:mdWrap>
</mets:dmdSec>
<mets:dmdSec ID="ABES.STAR.THESE_201984.VERSION_COMPLETE.DESCRIPTION.EDITION_ARCHIVAGE">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_desc_edition">
<mets:xmlData>
<tef:edition>
<dcterms:medium xsi:type="dcterms:IMT">PDF</dcterms:medium>
<dcterms:extent>26172784</dcterms:extent>
<tef:editeur>
<tef:nom>Université de Strasbourg</tef:nom>
<tef:place>Strasbourg</tef:place>
</tef:editeur>
<dcterms:issued xsi:type="dcterms:W3CDTF">2023-12-31</dcterms:issued>
<dc:identifier xsi:type="dcterms:URI">https://theses.hal.science/tel-04216850</dc:identifier>
</tef:edition>
</mets:xmlData>
</mets:mdWrap>
</mets:dmdSec>
<mets:dmdSec ID="ABES.STAR.THESE_201984.VERSION_COMPLETE.DESCRIPTION.EDITION_1">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_desc_edition">
<mets:xmlData>
<tef:edition>
<dcterms:medium xsi:type="dcterms:IMT">application/pdf</dcterms:medium>
<dcterms:extent>26157024</dcterms:extent>
<dc:identifier xsi:type="dcterms:URI">https://publication-theses.unistra.fr/public/theses_doctorat/2023/Volkov_Mikhail_2023_ED222.pdf</dc:identifier>
<dc:identifier xsi:type="dcterms:URI">http://www.theses.fr/2023STRAF016/abes</dc:identifier>
<dc:identifier xsi:type="dcterms:URI"/>
<dc:identifier xsi:type="dcterms:URI">https://theses.hal.science/tel-04216850</dc:identifier>
<dc:identifier xsi:type="dcterms:URI">https://theses.hal.science/tel-04216850</dc:identifier>
<dc:identifier xsi:type="dcterms:URI">https://theses.hal.science/tel-04216850</dc:identifier>
<dc:identifier xsi:type="dcterms:URI">https://theses.hal.science/tel-04216850</dc:identifier>
</tef:edition>
</mets:xmlData>
</mets:mdWrap>
</mets:dmdSec>
<mets:amdSec>
<mets:techMD ID="ABES.STAR.THESE_201984.ADMINISTRATION">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_admin_these">
<mets:xmlData>
<tef:thesisAdmin>
<tef:auteur>
<tef:nom>Volkov</tef:nom>
<tef:prenom>Mikhail</tef:prenom>
<tef:dateNaissance>1996-04-30</tef:dateNaissance>
<tef:nationalite scheme="ISO-3166-1">FR</tef:nationalite>
<tef:autoriteExterne autoriteSource="Sudoc">272056200</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="INE">0EFB1U06FZ7</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="CodeEtu">21924364</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="DiplomeSISE42">4200003</tef:autoriteExterne>
</tef:auteur>
<dc:identifier xsi:type="tef:nationalThesisPID">https://theses.fr/2023STRAF016</dc:identifier>
<dc:identifier xsi:type="tef:NNT">2023STRAF016</dc:identifier>
<dc:identifier xsi:type="tef:DOI">https://doi.org/10.70675/d4a7b752z9818z4196zab21z61e5493b7907</dc:identifier>
<dcterms:dateAccepted xsi:type="dcterms:W3CDTF">2023-06-05</dcterms:dateAccepted>
<tef:thesis.degree>
<tef:thesis.degree.discipline xml:lang="fr">Chimie informatique et théorique</tef:thesis.degree.discipline>
<tef:thesis.degree.grantor>
<tef:nom>Strasbourg</tef:nom>
<tef:autoriteExterne autoriteSource="Sudoc">131056549</tef:autoriteExterne>
</tef:thesis.degree.grantor>
<tef:thesis.degree.level>Doctorat</tef:thesis.degree.level>
<tef:thesis.degree.name xml:lang="fr">Docteur es</tef:thesis.degree.name>
</tef:thesis.degree>
<tef:theseSurTravaux>non</tef:theseSurTravaux>
<tef:avisJury>oui</tef:avisJury>
<tef:directeurThese>
<tef:nom>Rognan</tef:nom>
<tef:prenom>Didier</tef:prenom>
<tef:autoriteInterne>MADS_DIRECTEUR_DE_THESE_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">034127445</tef:autoriteExterne>
</tef:directeurThese>
<tef:presidentJury>
<tef:nom>Varnek</tef:nom>
<tef:prenom>Alexandre</tef:prenom>
<tef:autoriteInterne>MADS_PRESIDENT_DU_JURY</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">124416993</tef:autoriteExterne>
</tef:presidentJury>
<tef:membreJury>
<tef:nom>Oliveira Santos</tef:nom>
<tef:prenom>Jana de</tef:prenom>
<tef:autoriteInterne>MADS_MEMBRE_DU_JURY_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">140753702</tef:autoriteExterne>
</tef:membreJury>
<tef:membreJury>
<tef:nom>Gaston-Mathe</tef:nom>
<tef:prenom>Yann</tef:prenom>
<tef:autoriteInterne>MADS_MEMBRE_DU_JURY_2</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">272056626</tef:autoriteExterne>
</tef:membreJury>
<tef:rapporteur>
<tef:nom>Bonnet</tef:nom>
<tef:prenom>Pascal</tef:prenom>
<tef:autoriteInterne>MADS_RAPPORTEUR_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">069441405</tef:autoriteExterne>
</tef:rapporteur>
<tef:rapporteur>
<tef:nom>Montes</tef:nom>
<tef:prenom>Matthieu</tef:prenom>
<tef:autoriteInterne>MADS_RAPPORTEUR_2</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">121837505</tef:autoriteExterne>
</tef:rapporteur>
<tef:ecoleDoctorale>
<tef:nom>École doctorale des Sciences chimiques (Strasbourg ; 1995-....)</tef:nom>
<tef:autoriteInterne>MADS_ECOLE_DOCTORALE_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Annuaire des formations doctorales et des unités de recherche">222</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="Sudoc">156504081</tef:autoriteExterne>
</tef:ecoleDoctorale>
<tef:partenaireRecherche type="laboratoire">
<tef:nom>Laboratoire d'innovation thérapeutique (Strasbourg ; 2009-....)</tef:nom>
<tef:autoriteInterne>MADS_PARTENAIRE_DE_RECHERCHE_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="labTEL">207869</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="Sudoc">157623483</tef:autoriteExterne>
</tef:partenaireRecherche>
<tef:oaiSetSpec>ddc:540</tef:oaiSetSpec>
<tef:MADSAuthority authorityID="MADS_DIRECTEUR_DE_THESE_1" type="personal">
<tef:personMADS>
<mads:namePart type="family">Rognan</mads:namePart>
<mads:namePart type="given">Didier</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_PRESIDENT_DU_JURY" type="personal">
<tef:personMADS>
<mads:namePart type="family">Varnek</mads:namePart>
<mads:namePart type="given">Alexandre</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_MEMBRE_DU_JURY_1" type="personal">
<tef:personMADS>
<mads:namePart type="family">Oliveira Santos</mads:namePart>
<mads:namePart type="given">Jana de</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_MEMBRE_DU_JURY_2" type="personal">
<tef:personMADS>
<mads:namePart type="family">Gaston-Mathe</mads:namePart>
<mads:namePart type="given">Yann</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_RAPPORTEUR_1" type="personal">
<tef:personMADS>
<mads:namePart type="family">Bonnet</mads:namePart>
<mads:namePart type="given">Pascal</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_RAPPORTEUR_2" type="personal">
<tef:personMADS>
<mads:namePart type="family">Montes</mads:namePart>
<mads:namePart type="given">Matthieu</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_ECOLE_DOCTORALE_1" type="corporate">
<tef:personMADS>
<mads:namePart type="family">École doctorale Sciences chimiques (Strasbourg ; 1995-....)</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_PARTENAIRE_DE_RECHERCHE_1" type="corporate">
<tef:personMADS>
<mads:namePart type="family">Laboratoire d'innovation thérapeutique (Strasbourg)</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
</tef:thesisAdmin>
</mets:xmlData>
</mets:mdWrap>
</mets:techMD>
<mets:techMD ID="ABES.STAR.THESE_201984.VERSION_COMPLETE.EDITION_ARCHIVAGE.TECH_FICHIER.DOSSIER_1.DOSSIER_1.FICHIER_1">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_tech_fichier">
<mets:xmlData>
<tef:meta_fichier>
<tef:formatFichier>PDF</tef:formatFichier>
<tef:taille>26172784</tef:taille>
</tef:meta_fichier>
</mets:xmlData>
</mets:mdWrap>
</mets:techMD>
<mets:rightsMD ID="ABES.STAR.THESE_201984.DROITS_UNIVERSITE">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_etablissement_these">
<mets:xmlData>
<metsRights:RightsDeclarationMD RIGHTSCATEGORY="CONTRACTUAL">
<metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
<metsRights:Permissions COPY="false" DELETE="false" DISPLAY="true" DUPLICATE="true" MODIFY="false" PRINT="true"/>
</metsRights:Context>
<metsRights:Context CONTEXTCLASS="INSTITUTIONAL AFFILIATE">
<metsRights:Permissions COPY="false" DELETE="false" DISPLAY="true" DUPLICATE="true" MODIFY="false" PRINT="true"/>
</metsRights:Context>
</metsRights:RightsDeclarationMD>
</mets:xmlData>
</mets:mdWrap>
</mets:rightsMD>
<mets:rightsMD ID="ABES.STAR.THESE_201984.DROITS_DOCTORANT">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_auteur_these">
<mets:xmlData>
<metsRights:RightsDeclarationMD RIGHTSCATEGORY="CONTRACTUAL">
<metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
<metsRights:Permissions COPY="false" DELETE="false" DISPLAY="true" DUPLICATE="true" MODIFY="false" PRINT="true"/>
</metsRights:Context>
<metsRights:Context CONTEXTCLASS="INSTITUTIONAL AFFILIATE">
<metsRights:Permissions COPY="false" DELETE="false" DISPLAY="true" DUPLICATE="true" MODIFY="false" PRINT="true"/>
</metsRights:Context>
</metsRights:RightsDeclarationMD>
</mets:xmlData>
</mets:mdWrap>
</mets:rightsMD>
<mets:rightsMD ID="ABES.STAR.THESE_201984.VERSION_COMPLETE.DROITS">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_droits_version">
<mets:xmlData>
<metsRights:RightsDeclarationMD RIGHTSCATEGORY="CONTRACTUAL">
<metsRights:Context CONTEXTCLASS="GENERAL PUBLIC">
<metsRights:Permissions COPY="false" DELETE="false" DISPLAY="true" DUPLICATE="true" MODIFY="false" PRINT="true"/>
</metsRights:Context>
<metsRights:Context CONTEXTCLASS="INSTITUTIONAL AFFILIATE">
<metsRights:Permissions COPY="false" DELETE="false" DISPLAY="true" DUPLICATE="true" MODIFY="false" PRINT="true"/>
</metsRights:Context>
</metsRights:RightsDeclarationMD>
</mets:xmlData>
</mets:mdWrap>
</mets:rightsMD>
</mets:amdSec>
<mets:fileSec>
<mets:fileGrp ID="ABES.STAR.THESE_201984.VERSION_COMPLETE.EDITION_ARCHIVAGE.FILEGRP" USE="archive">
<mets:file ADMID="ABES.STAR.THESE_201984.VERSION_COMPLETE.EDITION_ARCHIVAGE.TECH_FICHIER.DOSSIER_1.DOSSIER_1.FICHIER_1" ID="ABES.STAR.THESE_201984.VERSION_COMPLETE.EDITION_ARCHIVAGE.DOSSIER_1.DOSSIER_1.FICHIER_1" SEQ="1">
<mets:FLocat LOCTYPE="URL" xlink:href="STRA/THESE_201984/document/0/0/VOLKOV_Mikhail_2023_ED222_A.pdf"/>
</mets:file>
</mets:fileGrp>
</mets:fileSec>
<mets:structMap TYPE="logical">
<mets:div ADMID="ABES.STAR.THESE_201984.ADMINISTRATION ABES.STAR.THESE_201984.DROITS_UNIVERSITE ABES.STAR.THESE_201984.DROITS_DOCTORANT" CONTENTIDS="CONTENTIDS.ABES.STAR.THESE_201984" DMDID="ABES.STAR.THESE_201984.DESCRIPTION_BIBLIOGRAPHIQUE" TYPE="THESE">
<mets:div ADMID="ABES.STAR.THESE_201984.VERSION_COMPLETE.DROITS" CONTENTIDS="CONTENTIDS.ABES.STAR.THESE_201984.ABES.STAR.THESE_201984.VERSION_COMPLETE" TYPE="VERSION_COMPLETE">
<mets:div CONTENTIDS="CONTENTIDS.ABES.STAR.THESE_201984.VERSION_COMPLETE.EDITION_ARCHIVAGE" DMDID="ABES.STAR.THESE_201984.VERSION_COMPLETE.DESCRIPTION.EDITION_ARCHIVAGE" TYPE="EDITION">
<mets:fptr FILEID="ABES.STAR.THESE_201984.VERSION_COMPLETE.EDITION_ARCHIVAGE.FILEGRP"/>
</mets:div>
<mets:div CONTENTIDS="CONTENTIDS.ABES.STAR.THESE_201984.VERSION_COMPLETE.EDITION_1" DMDID="ABES.STAR.THESE_201984.VERSION_COMPLETE.DESCRIPTION.EDITION_1" TYPE="EDITION"/>
</mets:div>
</mets:div>
</mets:structMap>
</mets:mets>