aiqbench analysis
This research introduces ReAlignFit, a method that integrates chemical inductive bias into molecular relational learning to address instability caused by data distribution shifts. By simulating conformational changes and refining substructure pairs, the approach improves model robustness across nine datasets without relying solely on attention mechanisms. The work demonstrates that embedding domain-specific chemical knowledge directly into the learning process yields superior performance in predicting molecular binding compatibility.
Representational Alignment with Chemical Induced Fit for Molecular Relational Learning
arXiv:2502.07027v4 Announce Type: replace 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.
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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2502.07027 [cs.LG]
(or arXiv:2502.07027v4 [cs.LG] for this version)
Full text under the publisher's open licence · 190 words
Related coverage
SIGMA: Semantic Identifier Grouping for Molecular Autoregression
arXiv · Aug 4, 2026
Foundation Neural-Network Quantum States for Molecular Potential Energy Surfaces in Second Quantization
arXiv · Sep 30, 2026
A General-Purpose Framework for Chemical Reaction Representation with Atomic Correspondence and Flexible Condition Adaptation
arXiv · Aug 27, 2026
ConfRetro: a 3D-aware template-free method for enhancing retrosynthesis via molecular conformer information
arXiv · Aug 19, 2026