Discovering NDM-1 inhibitors using molecular substructure embeddings representations

• Published in: Journal of integrative bioinformatics Vol. 20; no. 2; pp. 629 - 55
• Main Authors: Papastergiou, Thomas, Azé, Jérôme, Bringay, Sandra, Louet, Maxime, Poncelet, Pascal, Rosales-Hurtado, Miyanou, Vo-Hoang, Yen, Licznar-Fajardo, Patricia, Docquier, Jean-Denis, Gavara, Laurent
• Format: Journal Article
• Language: English
• Published: Germany De Gruyter 28.07.2023; Informationsmanagement in der Biotechnologie e.V. (IMBio e.V.)
• Subjects: Anti-Bacterial Agents / chemistry; Anti-Bacterial Agents / pharmacology; Bacteria; beta-Lactamases / chemistry; Chemical Sciences; Computer Science; drug discovery; Human-Computer Interaction; Life Sciences; machine learning; multiple instance learning; NDM-1 inhibitors; Pharmaceutical sciences; Workshop; NDM-1 inhibitors; drug discovery; machine learning; multiple instance learning; Drug discovery; Multiple instance learning; Machine learning
• ISSN: 1613-4516; 1613-4516
• DOI: 10.1515/jib-2022-0050

NDM-1 (New-Delhi-Metallo-β-lactamase-1) is an enzyme developed by bacteria that is implicated in bacteria resistance to almost all known antibiotics. In this study, we deliver a new, curated NDM-1 bioactivities database, along with a set of unifying rules for managing different activity properties and inconsistencies. We define the activity classification problem in terms of Multiple Instance Learning, employing embeddings corresponding to molecular substructures and present an ensemble ranking and classification framework, relaying on a k-fold Cross Validation method employing a per fold hyper-parameter optimization procedure, showing promising generalization ability. The MIL paradigm displayed an improvement up to 45.7 %, in terms of Balanced Accuracy, in comparison to the classical Machine Learning paradigm. Moreover, we investigate different compact molecular representations, based on atomic or bi-atomic substructures. Finally, we scanned the Drugbank for strongly active compounds and we present the top-15 ranked compounds.