Exploring QSAR models for activity-cliff prediction

• Published in: Journal of cheminformatics 2023-04, Vol.15 (1), p.47-47, Article 47
• Main Authors: Dablander, Markus, Hanser, Thierry, Lambiotte, Renaud, Morris, Garrett M.
• Format: Article
• Language: English
• Subjects: Activity cliff prediction; Activity cliffs; Analysis; Case studies; Chemistry; Chemistry and Materials Science; Cliffs; Computational Biology/Bioinformatics; Computer Applications in Chemistry; Deep learning; Documentation and Information in Chemistry; Dopamine; Dopamine D2 receptors; Fingerprints; Graph theory; Health aspects; Isomorphism; Machine learning; Molecular modelling; Molecular representation; Multilayer perceptrons; Optimization; Prediction models; QSAR modelling; Representations; Sensitivity analysis; Severe acute respiratory syndrome coronavirus 2; Structure-activity relationships; Theoretical and Computational Chemistry
• ISSN: 1758-2946; 1758-2946
• DOI: 10.1186/s13321-023-00708-w

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. Graphical Abstract