TacoGFN: Target-conditioned GFlowNet for Structure-based Drug Design

arXiv:2310.03223v4 Announce Type: replace
Abstract: Searching the vast chemical space for drug-like and synthesizable molecules with high binding affinity to a protein pocket is a challenging task in drug discovery. Recently, molecular deep generative models have been introduced which promise to be more efficient than exhaustive virtual screening, by directly generating molecules based on the protein structure. However, since they learn the distribution of a limited protein-ligand complex dataset, the existing methods struggle with generating novel molecules with significant property …

abstract arxiv cs.lg deep generative models design discovery drug design drug discovery generative generative models molecules protein screening searching space type vast virtual