Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Representational Alignment with Chemical Induced Fit for Molecular Relational Learning

About

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.

Peiliang Zhang, Jingling Yuan, Qing Xie, Yongjun Zhu, Lin Li• 2025

Related benchmarks

TaskDatasetResultRank
Drug-Drug Interaction predictionZhangDDI
Accuracy89.43
36
Molecular Interaction PredictionCombiSolv
RMSE0.316
29
Solute-Solvent InteractionMNSol
RMSE0.539
18
Drug-Drug Interaction predictionHetionetDDI
Accuracy0.9239
17
Drug-Drug Interaction predictionDrugBankDDI
Accuracy95.62
17
Molecular property predictionFreeSolv
RMSE0.796
15
DDI PredictionZhangDDI Rule-based Partitioning (P1)
Accuracy78.82
13
DDI PredictionHetionteDDI (Rule-based Partitioning (P1))
Accuracy76.55
13
DDI PredictionDrugBankDDI Rule-based Partitioning (P1)
Accuracy82.41
13
DDI PredictionZhangDDI (Scaffold-based Partitioning (P2))
Accuracy60.85
13
Showing 10 of 17 rows

Other info

Follow for update