Journal of Chemical Information and Modeling · 2021 · 94 citations · 60 references
PharmacyMedicinal ChemistryPharmacologyDrug DesignDrug DiscoveryMachine LearningComputational Drug DiscoveryDe Novo Drug DesignDrug-target Interaction MappingDrug-target Interaction NetworksGraph-based LearningMolecular ModelingCytochrome P450 Enzyme InhibitionCytochrome P450 InhibitionCytochrome P450 Inhibition PredictionExplainable Artificial IntelligenceNetwork-based Drug DesignRational DesignTarget-ligand InteractionsTransparency
molecule generation. However, these models are considered "black-box" and "hard-to-debug". This study aimed to improve modeling transparency for rational molecular design by applying the integrated gradients explainable artificial intelligence (XAI) approach for graph neural network models. Models were trained for predicting plasma protein binding, hERG channel inhibition, passive permeability, and cytochrome P450 inhibition. The proposed methodology highlighted molecular features and structural elements that are in agreement with known pharmacophore motifs, correctly identified property cliffs, and provided insights into unspecific ligand-target interactions. The developed XAI approach is fully open-sourced and can be used by practitioners to train new models on other clinically relevant endpoints.
60
MoleculeNet: a benchmark for molecular machine learning
Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg et al. · Chemical Science · 2017 · 2.9K citations · Full text
A molecular basis for cardiac arrhythmia: HERG mutations cause long QT syndrome
Mark Curran, Igor Splawski, Katherine W. Timothy et al. · Cell · 1995 · 2.3K citations · Full text