Classical Structural Priors Improve Neural Molecular Representations in Molecule Language Models
Year: 2026
Type: article
Abstract: Classical molecular similarity is central to chemical information systems, yet molecule-language models trained on paired structure–text data do not necessarily organize molecular embeddings according to graded structural relationships. Here, we introduce Structure-Aware Guided Alignment (SAGA), a training-only regularizer that uses Centered Kernel Alignment to align neural molecular representations with fingerprint-based Tanimoto similarity and requires no additional parameters or fingerprints at inference. In MolCA and Atomas, SAGA improves molecule–text retrieval, retrieves closer structural analogues, and raises average performance in scaffold-split property prediction, without clear degradation of molecular description or text-to-molecule generation. These results, together with control experiments that attribute the gains to the chemical content of the prior, show that established chemoinformatics priors can make molecule-language representations more chemically faithful while retaining their multimodal utility.
Language: English
Subfield: Drug Discovery
Domain: Life Sciences
Open Access status: green
Awards: G9001389477, G9001392084
OpenAlex ID: W7234439115
