<?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="2023-09-08T15:13:06" ID="ABES.STAR.THESE_203915.METS_HEADER" LASTMODDATE="2024-05-26T04:50:10Z" 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_203915.METS_HEADER.ALTERNATE" TYPE=""/>
</mets:metsHdr>
<mets:dmdSec ID="ABES.STAR.THESE_203915.DESCRIPTION_BIBLIOGRAPHIQUE">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_desc_these">
<mets:xmlData>
<tef:thesisRecord>
<dc:title xml:lang="fr">Réseaux neuronaux à base de graphes pour la génération de structures moléculaires synthétiquement accessibles</dc:title>
<dcterms:alternative xml:lang="en">Graph-based neural networks for generation of synthetically accessible molecular structures</dcterms:alternative>
<dc:subject xml:lang="fr">Inverse Qsar</dc:subject>
<dc:subject xml:lang="fr">Rétrosynthèse</dc:subject>
<dc:subject xml:lang="fr">Apprentissage profond</dc:subject>
<dc:subject xml:lang="fr">Réseaux de neurones sur graphes</dc:subject>
<dc:subject xml:lang="fr">Génération moléculaire</dc:subject>
<dc:subject xml:lang="en">Inverse Qsar</dc:subject>
<dc:subject xml:lang="en">Retrosynthesis</dc:subject>
<dc:subject xml:lang="en">Deep learning</dc:subject>
<dc:subject xml:lang="en">Graph neural networks</dc:subject>
<dc:subject xml:lang="en">Molecular generation</dc:subject>
<dc:subject xsi:type="dcterms:DDC">541</dc:subject>
<dc:subject xsi:type="dcterms:DDC">004</dc:subject>
<tef:sujetRameau xml:lang="fr">
<tef:vedetteRameauNomCommun>
<tef:elementdEntree autoriteExterne="05658346X" autoriteSource="Sudoc">QSAR (biochimie)</tef:elementdEntree>
</tef:vedetteRameauNomCommun>
<tef:vedetteRameauNomCommun>
<tef:elementdEntree autoriteExterne="223540633" autoriteSource="Sudoc">Apprentissage profond</tef:elementdEntree>
</tef:vedetteRameauNomCommun>
</tef:sujetRameau>
<dcterms:abstract xml:lang="fr">Cette thèse est dédiée au développement de génératifs par réseaux de neurones artificiels de graphes et d'un outil de planification rétrosynthétique amélioré par des méthodes d’apprentissage automatique profond. Les modèles génératifs s'appuient sur le concept d'autoencodeur, très populaire dans les tâches de conception moléculaire de novo et d'analyse QSAR inverse. L'architecture proposée, HyFactor, basée sur le graphe étiqueté par le nombre d'hydrogènes par atome, se révèle performante et utile pour générer des analogues moléculaires. La seconde architecture proposée, VQGAE, donne des résultats comparables à ceux d'HyFactor dans la tâche de reconstruction, mais la représentation latente se montre plus performante pour la recherche par similarité et pour le QSAR. Ces performances sont illustrées par la génération de ligands très actifs pour les récepteurs A2A. La faisabilité synthétique des structures générées a été vérifiée à l'aide d'un nouvel outil de rétrosynthèse, GSLRetro. Cet outil est conçu sur le concept d'auto-apprentissage qui améliore la stabilité des solutions grâce aux précédentes solutions proposées. Le protocole de curation des données de réaction ainsi que de nouvelles techniques de validation croisée pour les modèles QSPR basés sur les réactions sont également présentés. En somme, la combinaison de ces outils constitue une étape importante vers la conception automatisée de molécules.</dcterms:abstract>
<dcterms:abstract xml:lang="en">This thesis is dedicated to the development of graph-based generative neural networks and a retrosynthetic planning tool enhanced by deep learning architectures. The generative networks are based on the autoencoder concept, which has gained popularity in de novo molecular design and inverse QSAR tasks. The proposed architecture, HyFactor, based on the hydrogen number labelled graph, was computationally efficient and helpful in generating molecular analogues. The following architecture, VQGAE, performed as well as HyFactor in the reconstruction task, while its latent vectors showed the best performance in the similarity search and QSAR tasks. As a proof of concept, VQGAE was used to generate highly potent ligands of A2A receptors. The synthetic feasibility of the generated structures was verified using a new retrosynthesis tool, GSLRetro. This tool is based on a self-learning concept by which it can improve the search quality by training on previous searches' results. In addition to the retrosynthetic planning tool, the protocol of reaction data curation and new cross-validation techniques for reaction-based QSPR models were proposed. Finally, the combination of these tools represents a significant step towards automated molecular design.</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_203915.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>28995021</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-04208499</dc:identifier>
</tef:edition>
</mets:xmlData>
</mets:mdWrap>
</mets:dmdSec>
<mets:dmdSec ID="ABES.STAR.THESE_203915.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>28042564</dcterms:extent>
<dc:identifier xsi:type="dcterms:URI">https://publication-theses.unistra.fr/public/theses_doctorat/2023/Akhmetshin_Tagir_2023_ED222.pdf</dc:identifier>
<dc:identifier xsi:type="dcterms:URI">http://www.theses.fr/2023STRAF010/abes</dc:identifier>
<dc:identifier xsi:type="dcterms:URI"/>
<dc:identifier xsi:type="dcterms:URI">https://theses.hal.science/tel-04208499</dc:identifier>
<dc:identifier xsi:type="dcterms:URI">https://theses.hal.science/tel-04208499</dc:identifier>
</tef:edition>
</mets:xmlData>
</mets:mdWrap>
</mets:dmdSec>
<mets:amdSec>
<mets:techMD ID="ABES.STAR.THESE_203915.ADMINISTRATION">
<mets:mdWrap MDTYPE="OTHER" OTHERMDTYPE="tef_admin_these">
<mets:xmlData>
<tef:thesisAdmin>
<tef:auteur>
<tef:nom>Akhmetshin</tef:nom>
<tef:prenom>Tagir</tef:prenom>
<tef:dateNaissance>1996-03-31</tef:dateNaissance>
<tef:nationalite scheme="ISO-3166-1">RU</tef:nationalite>
<tef:autoriteExterne autoriteSource="Sudoc">257782877</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="INE">0EFB1U03OQ4</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="CodeEtu">21917584</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="DiplomeSISE42">4200003</tef:autoriteExterne>
</tef:auteur>
<dc:identifier xsi:type="tef:nationalThesisPID">http://www.theses.fr/2023STRAF010</dc:identifier>
<dc:identifier xsi:type="tef:NNT">2023STRAF010</dc:identifier>
<dcterms:dateAccepted xsi:type="dcterms:W3CDTF">2023-03-17</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.grantor>
<tef:nom>Kazanskij gosudarstvennyj universitet im. V. I. Ulʹânova (Kazanʹ)</tef:nom>
<tef:autoriteInterne>MADS_ETABLISSEMENT_DE_COTUTELLE_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">098205838</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>Varnek</tef:nom>
<tef:prenom>Alexandre</tef:prenom>
<tef:autoriteInterne>MADS_DIRECTEUR_DE_THESE_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">124416993</tef:autoriteExterne>
</tef:directeurThese>
<tef:directeurThese>
<tef:nom>Madzhidov</tef:nom>
<tef:prenom>Timur</tef:prenom>
<tef:autoriteInterne>MADS_DIRECTEUR_DE_THESE_2</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">231484666</tef:autoriteExterne>
</tef:directeurThese>
<tef:presidentJury>
<tef:nom>Kellenberger</tef:nom>
<tef:prenom>Esther</tef:prenom>
<tef:autoriteInterne>MADS_PRESIDENT_DU_JURY</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">16406883X</tef:autoriteExterne>
</tef:presidentJury>
<tef:rapporteur>
<tef:nom>Stoven</tef:nom>
<tef:prenom>Véronique</tef:prenom>
<tef:autoriteInterne>MADS_RAPPORTEUR_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">149662025</tef:autoriteExterne>
</tef:rapporteur>
<tef:rapporteur>
<tef:nom>Lepailleur</tef:nom>
<tef:prenom>Alban</tef:prenom>
<tef:autoriteInterne>MADS_RAPPORTEUR_2</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="Sudoc">109352599</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="Sudoc">156504081</tef:autoriteExterne>
</tef:ecoleDoctorale>
<tef:partenaireRecherche type="laboratoire">
<tef:nom>Chimie de la matière complexe (Strasbourg)</tef:nom>
<tef:autoriteInterne>MADS_PARTENAIRE_DE_RECHERCHE_1</tef:autoriteInterne>
<tef:autoriteExterne autoriteSource="labTEL">403339</tef:autoriteExterne>
<tef:autoriteExterne autoriteSource="Sudoc">157547027</tef:autoriteExterne>
</tef:partenaireRecherche>
<tef:oaiSetSpec>ddc:540</tef:oaiSetSpec>
<tef:oaiSetSpec>ddc:004</tef:oaiSetSpec>
<tef:MADSAuthority authorityID="MADS_ETABLISSEMENT_DE_COTUTELLE_1" type="corporate">
<tef:personMADS>
<mads:namePart type="family">Kazanskij gosudarstvennyj universitet im. V. I. Ulʹânova (Kazanʹ)</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_DIRECTEUR_DE_THESE_1" 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_DIRECTEUR_DE_THESE_2" type="personal">
<tef:personMADS>
<mads:namePart type="family">Madzhidov</mads:namePart>
<mads:namePart type="given">Timur</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_PRESIDENT_DU_JURY" type="personal">
<tef:personMADS>
<mads:namePart type="family">Kellenberger</mads:namePart>
<mads:namePart type="given">Esther</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_RAPPORTEUR_1" type="personal">
<tef:personMADS>
<mads:namePart type="family">Stoven</mads:namePart>
<mads:namePart type="given">Véronique</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
<tef:MADSAuthority authorityID="MADS_RAPPORTEUR_2" type="personal">
<tef:personMADS>
<mads:namePart type="family">Lepailleur</mads:namePart>
<mads:namePart type="given">Alban</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">Chimie de la matière complexe (Strasbourg)</mads:namePart>
</tef:personMADS>
</tef:MADSAuthority>
</tef:thesisAdmin>
</mets:xmlData>
</mets:mdWrap>
</mets:techMD>
<mets:techMD ID="ABES.STAR.THESE_203915.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>28995021</tef:taille>
</tef:meta_fichier>
</mets:xmlData>
</mets:mdWrap>
</mets:techMD>
<mets:rightsMD ID="ABES.STAR.THESE_203915.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_203915.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_203915.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_203915.VERSION_COMPLETE.EDITION_ARCHIVAGE.FILEGRP" USE="archive">
<mets:file ADMID="ABES.STAR.THESE_203915.VERSION_COMPLETE.EDITION_ARCHIVAGE.TECH_FICHIER.DOSSIER_1.DOSSIER_1.FICHIER_1" ID="ABES.STAR.THESE_203915.VERSION_COMPLETE.EDITION_ARCHIVAGE.DOSSIER_1.DOSSIER_1.FICHIER_1" SEQ="1">
<mets:FLocat LOCTYPE="URL" xlink:href="STRA/THESE_203915/document/0/0/AKHMETSHIN_Tagir_2023_ED222_A.pdf"/>
</mets:file>
</mets:fileGrp>
</mets:fileSec>
<mets:structMap TYPE="logical">
<mets:div ADMID="ABES.STAR.THESE_203915.ADMINISTRATION ABES.STAR.THESE_203915.DROITS_UNIVERSITE ABES.STAR.THESE_203915.DROITS_DOCTORANT" CONTENTIDS="CONTENTIDS.ABES.STAR.THESE_203915" DMDID="ABES.STAR.THESE_203915.DESCRIPTION_BIBLIOGRAPHIQUE" TYPE="THESE">
<mets:div ADMID="ABES.STAR.THESE_203915.VERSION_COMPLETE.DROITS" CONTENTIDS="CONTENTIDS.ABES.STAR.THESE_203915.ABES.STAR.THESE_203915.VERSION_COMPLETE" TYPE="VERSION_COMPLETE">
<mets:div CONTENTIDS="CONTENTIDS.ABES.STAR.THESE_203915.VERSION_COMPLETE.EDITION_ARCHIVAGE" DMDID="ABES.STAR.THESE_203915.VERSION_COMPLETE.DESCRIPTION.EDITION_ARCHIVAGE" TYPE="EDITION">
<mets:fptr FILEID="ABES.STAR.THESE_203915.VERSION_COMPLETE.EDITION_ARCHIVAGE.FILEGRP"/>
</mets:div>
<mets:div CONTENTIDS="CONTENTIDS.ABES.STAR.THESE_203915.VERSION_COMPLETE.EDITION_1" DMDID="ABES.STAR.THESE_203915.VERSION_COMPLETE.DESCRIPTION.EDITION_1" TYPE="EDITION"/>
</mets:div>
</mets:div>
</mets:structMap>
</mets:mets>