Few-shot molecular property optimization <i>via</i> a domain-specialized large language model.

ABSTRACT: Large language models (LLMs) have revolutionized machine learning with their few-shot learning and reasoning capabilities, demonstrating impressive results in fields like natural language processing and computer vision. However, when applied to the domains of biology and chemistry, current LLMs face substantial limitations, particularly in capturing the nuanced relationships between the molecular structure and pharmacochemical properties. This challenge has constrained the application of few-shot learning for small-molecule generation and optimization in drug discovery. Here, we introduce DrugLLM, a novel LLM tailored specifically for molecular optimization. DrugLLM leverages Functional Group Tokenization (FGT), which effectively tokenizes molecules for LLM learning, achieving over 53% tok

SUBMITTER: Guo Y 

PROVIDER: S-EPMC12895671 | biostudies-literature | 2026 Feb

REPOSITORIES: biostudies-literature