pBRICS: A Novel Fragmentation Method for Explainable Property Prediction of Drug-Like Small Molecules
- 16 August 2023
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 63 (16) , 5066-5076
Abstract
Generative artificial intelligence algorithms have shown to be successful in exploring large chemical spaces and designing novel and diverse molecules. There has been considerable interest in developing predictive models using artificial intelligence for drug-like properties, which can potentially reduce the late-stage attrition of drug candidates or predict the properties of novel AI-designed molecules. Concurrently, it is important to understand the contribution of functional groups toward these properties and modify them to obtain property-optimized lead compounds. As a result, there is an increasing interest in the development of explainable property prediction models. However, current explainable approaches are mostly atom-based, where, often, only a fraction of a fragment is shown to be significant. To address the above challenges, we have developed a novel domain-aware molecular fragmentation approach termed post-processing of BRICS (pBRICS), which can fragment small molecules into their functional groups. Multitask models were developed to predict various properties, including the absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. The fragment importance was explained using the gradient-weighted class activation mapping (Grad-CAM) approach. The method was validated on data sets of experimentally available matched molecular pairs (MMPs). The explanations from the model can be useful for medicinal chemists to identify the fragments responsible for poor drug-like properties and optimize the molecule. The explainability approach was also used to identify the reason behind false positive and false negative MMP predictions. Based on evidence from the existing literature and our analysis, some of these mispredictions were justified. We propose that the quantity, quality, and diversity of the training data will improve the accuracy of property prediction algorithms for novel molecules.Keywords
This publication has 49 references indexed in Scilit:
- An analysis of the attrition of drug candidates from four major pharmaceutical companiesNature Reviews Drug Discovery, 2015
- Chemical predictive modelling to improve compound qualityNature Reviews Drug Discovery, 2013
- Knowledge-Based, Central Nervous System (CNS) Lead Selection and Lead Optimization for CNS Drug DiscoveryACS Chemical Neuroscience, 2011
- PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprintsJournal of Computational Chemistry, 2010
- On the Art of Compiling and Using 'Drug‐Like' Chemical Fragment SpacesChemMedChem, 2008
- Can the pharmaceutical industry reduce attrition rates?Nature Reviews Drug Discovery, 2004
- ADMET in silico modelling: towards prediction paradise?Nature Reviews Drug Discovery, 2003
- The effect of halogenation on blood–brain barrier permeability of a novel peptide drug☆Peptides, 1999
- RECAPRetrosynthetic Combinatorial Analysis Procedure: A Powerful New Technique for Identifying Privileged Molecular Fragments with Useful Applications in Combinatorial ChemistryJournal of Chemical Information and Computer Sciences, 1998
- The Properties of Known Drugs. 1. Molecular FrameworksJournal of Medicinal Chemistry, 1996