Representational Alignment with Chemical Induced Fit for Molecular Relational Learning

TL;DR

ReAlignFit introduces a chemically-informed alignment method for molecular relational learning, improving stability and performance across diverse chemical data distributions.

Contribution

The paper proposes ReAlignFit, a novel chemically-guided alignment approach that enhances molecular relational learning stability by simulating chemical conformational changes.

Findings

ReAlignFit outperforms existing models on nine datasets.

It significantly improves stability in rule-shifted and scaffold-shifted data.

The method enhances molecular embedding quality.

Abstract

Molecular Relational Learning (MRL) is widely applied in natural sciences to predict relationships between molecular pairs by extracting structural features. The representational similarity between substructure pairs determines the functional compatibility of molecular binding sites. Nevertheless, aligning substructure representations by attention mechanisms lacks guidance from chemical knowledge, resulting in unstable model performance in chemical space (\textit{e.g.}, functional group, scaffold) shifted data. With theoretical justification, we propose the \textbf{Re}presentational \textbf{Align}ment with Chemical Induced \textbf{Fit} (ReAlignFit) to enhance the stability of MRL. ReAlignFit dynamically aligns substructure representation in MRL by introducing chemical Induced Fit-based inductive bias. In the induction process, we design the Bias Correction Function based on substructure edge reconstruction to align representations between substructure pairs by simulating chemical conformational changes (dynamic combination of substructures). ReAlignFit further integrates the Subgraph Information Bottleneck during fit process to refine and optimize substructure pairs exhibiting high chemical functional compatibility, leveraging them to generate molecular embeddings. Experimental results on nine datasets demonstrate that ReAlignFit outperforms state-of-the-art models in two tasks and significantly enhances model's stability in both rule-shifted and scaffold-shifted data distributions.