Discovering NDM-1 inhibitors using molecular substructure embeddings representations

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.PMID:37498676 | PMC:PMC10389050 | DOI:10.1515/jib-2022-0050

Source: Journal of integrative bioinformatics - July 27, 2023 Category: Bioinformatics Authors: Thomas Papastergiou J érôme Azé Sandra Bringay Maxime Louet Pascal Poncelet Miyanou Rosales-Hurtado Yen Vo-Hoang Patricia Licznar-Fajardo Jean-Denis Docquier Laurent Gavara Source Type: research