Substrate Scope Contrastive Learning: Repurposing Human Bias to Learn Atomic Representations

arXiv:2402.16882v1 Announce Type: cross
Abstract: Learning molecular representation is a critical step in molecular machine learning that significantly influences modeling success, particularly in data-scarce situations. The concept of broadly pre-training neural networks has advanced fields such as computer vision, natural language processing, and protein engineering. However, similar approaches for small organic molecules have not achieved comparable success. In this work, we introduce a novel pre-training strategy, substrate scope contrastive learning, which learns atomic representations tailored to chemical reactivity. This method …

abstract advanced arxiv bias computer computer vision concept cs.ai cs.lg data engineering fields human language language processing learn machine machine learning modeling natural natural language natural language processing networks neural networks physics.chem-ph pre-training processing protein protein engineering q-bio.bm representation success training type vision