MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts

TL;DR

MolTailor leverages language models to customize molecular representations based on task-specific natural language descriptions, improving predictive accuracy in drug discovery applications.

Contribution

This paper introduces MolTailor, a novel method that uses language models as an agent to tailor molecular representations to specific tasks, enhancing relevance and performance.

Findings

MolTailor outperforms baseline methods in molecular property prediction.

Task-specific natural language prompts improve molecular representation relevance.

Language model-guided optimization enhances molecular learning efficiency.

Abstract

Deep learning is now widely used in drug discovery, providing significant acceleration and cost reduction. As the most fundamental building block, molecular representation is essential for predicting molecular properties to enable various downstream applications. Most existing methods attempt to incorporate more information to learn better representations. However, not all features are equally important for a specific task. Ignoring this would potentially compromise the training efficiency and predictive accuracy. To address this issue, we propose a novel approach, which treats language models as an agent and molecular pretraining models as a knowledge base. The agent accentuates task-relevant features in the molecular representation by understanding the natural language description of the task, just as a tailor customizes clothes for clients. Thus, we call this approach MolTailor. Evaluations demonstrate MolTailor's superior performance over baselines, validating the efficacy of enhancing relevance for molecular representation learning. This illustrates the potential of language model guided optimization to better exploit and unleash the capabilities of existing powerful molecular representation methods. Our code is available at https://github.com/SCIR-HI/MolTailor.