[2505.12565] mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules

Computer Science > Artificial Intelligence arXiv:2505.12565 (cs) [Submitted on 18 May 2025 (v1), last revised 1 Mar 2026 (this version, v3)] Title:mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules Authors:Carl Edwards, Chi Han, Gawon Lee, Thao Nguyen, Sara Szymkuć, Chetan Kumar Prasad, Bowen Jin, Jiawei Han, Ying Diao, Ge Liu, Hao Peng, Bartosz A. Grzybowski, Martin D. Burke, Heng Ji View a PDF of the paper titled mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules, by Carl Edwards and 13 other authors View PDF HTML (experimental) Abstract:Despite their ability to understand chemical knowledge, large language models (LLMs) remain limited in their capacity to propose novel molecules with desired functions (e.g., drug-like properties). In addition, the molecules that LLMs propose can often be challenging to make, and are almost never compatible with automated synthesis approaches. To better enable the discovery of functional small molecules, LLMs need to learn a new molecular language that is more effective in predicting properties and inherently synced with automated synthesis technology. Current molecule LLMs are limited by representing molecules based on atoms. In this paper, we argue that just like tokenizing texts into meaning-bearing (sub-)word tokens instead of characters, molecules should be tokenized at the level of functional building blocks, i.e., parts of molecules that bring unique funct...