Compressing Chemistry Reveals Functional Groups

📝 Original Info

• Title: Compressing Chemistry Reveals Functional Groups
• ArXiv ID: 2511.05728
• Date: 2025-11-07
• Authors: ** 논문에 명시된 저자 정보가 제공되지 않았습니다. (저자 명단이 필요하면 원문을 참고해 주세요.) **

📝 Abstract

We introduce the first formal large-scale assessment of the utility of traditional chemical functional groups as used in chemical explanations. Our assessment employs a fundamental principle from computational learning theory: a good explanation of data should also compress the data. We introduce an unsupervised learning algorithm based on the Minimum Message Length (MML) principle that searches for substructures that compress around three million biologically relevant molecules. We demonstrate that the discovered substructures contain most human-curated functional groups as well as novel larger patterns with more specific functions. We also run our algorithm on 24 specific bioactivity prediction datasets to discover dataset-specific functional groups. Fingerprints constructed from dataset-specific functional groups are shown to significantly outperform other fingerprint representations, including the MACCS and Morgan fingerprint, when training ridge regression models on bioactivity regression tasks.

💡 Deep Analysis

📄 Full Content

Reference