MTGL-ADMET: A Novel Multi-task Graph Learning Framework for ADMET Prediction Enhanced by Status-Theory and Maximum Flow

Abstract

It is a vital step to evaluate drug-like compounds in terms of absorption, distribution, metabolism, excretion, and toxicity (ADMET) in drug design. Classical single-task learning based on abundant labels has achieved inspiring progress in predicting individual ADMET endpoints. Multi-task learning (MTL), having the low requirement of endpoint labels, can predict multiple ADMET endpoints simultaneously. Nonetheless, it is still an ongoing issue that the performance of existing MTL-based approaches depends on how appropriate participating tasks are. Furthermore, there is a need to elucidate what substructures are crucial to specific ADMET endpoints. To address these issues, this work constructs a Multi-Task Graph Learning framework for predicting multiple ADMET properties of drug-like small molecules (MTGL-ADMET) under a new paradigm of MTL, ‘one primary, multiple auxiliaries’. It first leverages the status theory and the maximum flow to select appropriate auxiliary tasks of a specific ADMET endpoint task. Then, it designs a novel primary-centered multi-task learning model, which consists of a task-shared atom embedding module, a task-specific molecular embedding module, a primary task-centered gating module, and a multi-task predictor. The comparison with state-of-the-art MTL-based methods demonstrates the superiority of MTGL-ADMET. More elaborate experiments validate its contributions, including the status theory-based auxiliary selection algorithm and the novel MTL architecture. Furthermore, a case study illustrates the interpretability of MTGL-ADMET by indicating crucial substructures w.r.t. the primary task. It’s anticipated that this work can boost pharmacokinetic and toxicity analysis in drug discovery. The code and data underlying this article are freely available at https://github.com/dubingxue/MTGL-ADMET .