MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling

arXiv:2402.10387v1 Announce Type: cross
Abstract: Current generative models for drug discovery primarily use molecular docking to evaluate the quality of generated compounds. However, such models are often not useful in practice because even compounds with high docking scores do not consistently show experimental activity. More accurate methods for activity prediction exist, such as molecular dynamics based binding free energy calculations, but they are too computationally expensive to use in a generative model. We propose a multi-fidelity approach, Multi-Fidelity Bind (MFBind), …

abstract arxiv cs.lg current discovery drug discovery experimental fidelity generated generative generative modeling generative models modeling molecular docking practical practice q-bio.bm quality show type