MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter

TL;DR

MolCA enhances language models with 2D molecular graph understanding using a cross-modal projector and adapter, enabling improved performance on molecular tasks while retaining open-ended text generation.

Contribution

Introduces MolCA, a novel framework that integrates 2D molecular graph perception into language models via a cross-modal projector and uni-modal adapter, preserving generative capabilities.

Findings

Significantly outperforms baselines on molecule captioning.

Improves IUPAC name prediction accuracy.

Enhances molecule-text retrieval performance.

Abstract

Language Models (LMs) have demonstrated impressive molecule understanding ability on various 1D text-related tasks. However, they inherently lack 2D graph perception - a critical ability of human professionals in comprehending molecules' topological structures. To bridge this gap, we propose MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter. MolCA enables an LM (e.g., Galactica) to understand both text- and graph-based molecular contents via the cross-modal projector. Specifically, the cross-modal projector is implemented as a Q-Former to connect a graph encoder's representation space and an LM's text space. Further, MolCA employs a uni-modal adapter (i.e., LoRA) for the LM's efficient adaptation to downstream tasks. Unlike previous studies that couple an LM with a graph encoder via cross-modal contrastive learning, MolCA retains the LM's ability of open-ended text generation and augments it with 2D graph information. To showcase its effectiveness, we extensively benchmark MolCA on tasks of molecule captioning, IUPAC name prediction, and molecule-text retrieval, on which MolCA significantly outperforms the baselines. Our codes and checkpoints can be found at https://github.com/acharkq/MolCA.