Journal of Cheminformatics · 2023 · 54 citations · 35 references
PharmacyMedicinal ChemistryPharmacologyComputational ChemistryDrug DiscoveryStructure-activity RelationshipsBinding Affinity PredictionComputational Drug DiscoveryMolecular DescriptorsMolecular Property PredictionQualitative Structure-activity RelationshipsQuantitative Structure-activity RelationshipsActivity Cliff PredictionComputational Structure-activity ModelingGraph IsomorphismGraph-based Activity Cliff ModelingMolecular RepresentationsPrediction ModelsPredictive Modeling Of BioactivityRandom Forests
INTRODUCTION AND METHODOLOGY: Pairs of similar compounds that only differ by a small structural modification but exhibit a large difference in their binding affinity for a given target are known as activity cliffs (ACs). It has been hypothesised that QSAR models struggle to predict ACs and that ACs thus form a major source of prediction error. However, the AC-prediction power of modern QSAR methods and its quantitative relationship to general QSAR-prediction performance is still underexplored. We systematically construct nine distinct QSAR models by combining three molecular representation methods (extended-connectivity fingerprints, physicochemical-descriptor vectors and graph isomorphism networks) with three regression techniques (random forests, k-nearest neighbours and multilayer perceptrons); we then use each resulting model to classify pairs of similar compounds as ACs or non-ACs and to predict the activities of individual molecules in three case studies: dopamine receptor D2, factor Xa, and SARS-CoV-2 main protease. RESULTS AND CONCLUSIONS: Our results provide strong support for the hypothesis that indeed QSAR models frequently fail to predict ACs. We observe low AC-sensitivity amongst the evaluated models when the activities of both compounds are unknown, but a substantial increase in AC-sensitivity when the actual activity of one of the compounds is given. Graph isomorphism features are found to be competitive with or superior to classical molecular representations for AC-classification and can thus be employed as baseline AC-prediction models or simple compound-optimisation tools. For general QSAR-prediction, however, extended-connectivity fingerprints still consistently deliver the best performance amongs the tested input representations. A potential future pathway to improve QSAR-modelling performance might be the development of techniques to increase AC-sensitivity.
35
Extended-Connectivity Fingerprints
David Rogers, Mathew Hahn · Journal of Chemical Information and Modeling · 2010 · 7.6K citations
Takuya Akiba, Shotaro Sano, Toshihiko Yanase et al. · 2019 · 7.4K citations
An open source chemical structure curation pipeline using RDKit
A. Patrícia Bento, Anne Hersey, Eloy Félix et al. · Journal of Cheminformatics · 2020 · 715 citations · Full text
Dejun Jiang, Chang‐Yu Hsieh, Guangyong Chen et al. · Journal of Cheminformatics · 2021 · 623 citations · Full text