Compressing Chemistry Reveals Functional Groups
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Open Source Infrastructure for Differentiable Density Functional Theory
Learning exchange correlation functionals, used in quantum chemistry calculations, from data has become increasingly important in recent years, but training such a functional requires sophisticated software infrastructur…
Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction
Molecular property prediction using deep learning (DL) models has accelerated drug and materials discovery, but the resulting DL models often lack interpretability, hindering their adoption by chemists. This work propose…
Molecular Property PredictionSequential Pattern MiningBERT Learns (and Teaches) Chemistry
Modern computational organic chemistry is becoming increasingly data-driven. There remain a large number of important unsolved problems in this area such as product prediction given reactants, drug discovery, and metric-…
Drug DiscoveryFGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models
Large language models (LLMs) have gained significant attention in chemistry. However, most existing datasets center on molecular-level property prediction and overlook the role of fine-grained functional group (FG) infor…
Drug DiscoveryChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge
Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoning process that connects molecular structures with their properties and reacti…