DeepMoLM: Leveraging Visual and Geometric Structural Information for Molecule-Text Modeling

TL;DR

DeepMoLM introduces a dual-view framework that combines high-resolution molecular images with geometric invariants to improve molecule-text modeling, enhancing captioning accuracy and property prediction without relying on atom coordinates.

Contribution

It presents a novel approach that fuses visual and geometric information using cross-attention, advancing molecular language modeling beyond traditional string or graph-based methods.

Findings

12.3% relative METEOR gain in PubChem captioning

Valid numeric outputs for property queries with MAE 13.64 g/mol

Exceeds baselines in ChEBI-20 description generation

Abstract

AI models for drug discovery and chemical literature mining must interpret molecular images and generate outputs consistent with 3D geometry and stereochemistry. Most molecular language models rely on strings or graphs, while vision-language models often miss stereochemical details and struggle to map continuous 3D structures into discrete tokens. We propose DeepMoLM: Deep Molecular Language M odeling, a dual-view framework that grounds high-resolution molecular images in geometric invariants derived from molecular conformations. DeepMoLM preserves high-frequency evidence from 1024 $\times$ 1024 inputs, encodes conformer neighborhoods as discrete Extended 3-Dimensional Fingerprints, and fuses visual and geometric streams with cross-attention, enabling physically grounded generation without atom coordinates. DeepMoLM improves PubChem captioning with a 12.3% relative METEOR gain over the strongest generalist baseline while staying competitive with specialist methods. It produces valid numeric outputs for all property queries and attains MAE 13.64 g/mol on Molecular Weight and 37.89 on Complexity in the specialist setting. On ChEBI-20 description generation from images, it exceeds generalist baselines and matches state-of-the-art vision-language models. Code is available at https://github.com/1anj/DeepMoLM.