AI Paper Atlas

Research map / Large language models / Agents, code and math

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

Carl Edwards, Chi Han, Gawon Lee, Thao Nguyen, Sara Szymkuć, Chetan Kumar Prasad, Bowen Jin, Jiawei Han, Ying Diao, Ge Liu, Hao Peng, Bartosz Andrzej Grzybowski and 2 more

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GNN encoding of building blocks (ablation)mCLM · FDA drugs, synthesis-guaranteed blocksvalidity (%): 45.21 -> 100.0Improved
add GNN encoding of building blocks (ablation)mCLM · FDA drugs, synthesis-guaranteed blocksmakeability (%): 42.8 -> 98.23Improved
add GNN encoding of building blocks (ablation)mCLM · FDA drugs, synthesis-guaranteed blockssynthetic accessibility SA: 2.97 -> 2.43Improved
add synthesis-guaranteed tokenizer (ablation)mCLM · FDA drugs, synthesis-guaranteed blockssynthesizability (%): 73.65 -> 98.23Improved
add synthesis-guaranteed tokenizer (ablation)mCLM · FDA drugs, synthesis-guaranteed blockssynthetic accessibility SA: 3.09 -> 2.43Improved
add synthesis-guaranteed tokenizer (ablation)mCLM · FDA drugs, synthesis-guaranteed blocksvalidity (%): 100.0 -> 100.0No clear effect
use building-block tokens with property training instead of atom-level text-based editingmCLM vs baselines · FDA drugs, synthesis-guaranteed blocksaverage improvement (%): 15.0 vs 6.98 (Gemini-2.5-Flash), 2.45 (GPT-4o)Improved
apply mCLM to out-of-distribution drugs with unseen blocksmCLM · FDA drugs with 3+ blocks (430)property scores: mean improvement 12.87; PGP 66.0 -> 68.0Mixed
add mCLM to fallen angel drugs for iterative multi-property refinementmCLM · Evobrutinib and TNG348DILIImproved
use MoleculeSTM for iterative refinement instead of mCLMMoleculeSTM · Evobrutinib and TNG348molecule validityHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy