# Improving the accuracy and generalizability of molecular property regression models with a substructure-substitution-rule-informed framework

arXiv: https://arxiv.org/abs/2511.08314 · HTML: https://mlsanity.com/paper/2511.08314/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 74 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 13 of 13)

- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Characterizing possible failure modes in physics-informed neural networks](https://mlsanity.com/paper/2109.01050/) (2021)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction](https://mlsanity.com/paper/2106.06130/) (2021)
- [An Expert's Guide to Training Physics-informed Neural Networks](https://mlsanity.com/paper/2308.08468/) (2023)
- [Loss Functions and Metrics in Deep Learning](https://mlsanity.com/paper/2307.02694/) (2023)
- [Generating 3D Binding Molecules Using Shape-Conditioned Diffusion Models with Guidance](https://mlsanity.com/paper/2502.06027/) (2025)
- [Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation](https://mlsanity.com/paper/2311.02798/) (2023)
- [Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey](https://mlsanity.com/paper/2402.07249/) (2024)
- [BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models](https://mlsanity.com/paper/2505.01912/) (2025)
- [MaskMol: Knowledge-guided Molecular Image Pre-Training Framework for Activity Cliffs](https://mlsanity.com/paper/2409.12926/) (2024)
- [Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction](https://mlsanity.com/paper/2411.13688/) (2024)
- [Robust Molecular Property Prediction via Densifying Scarce Labeled Data](https://mlsanity.com/paper/2506.11877/) (2025)

## Abstract (arXiv)

Artificial Intelligence (AI)-aided drug discovery is an active research field, yet AI models often exhibit poor accuracy in regression tasks for molecular property prediction, and perform catastrophically poorly for out-of-distribution (OOD) molecules. Here, we present MolRuleLoss, a substructure-substitution-rule-informed framework that improves the accuracy and generalizability of multiple molecular property regression models (MPRMs) such as GEM and UniMol for diverse molecular property prediction tasks. MolRuleLoss incorporates partial derivative constraints for substructure substitution rules (SSRs) into an MPRM's loss function. When using GEM models for predicting lipophilicity, water solubility, and solvation-free energy (using lipophilicity, ESOL, and freeSolv datasets from MoleculeNet), the root mean squared error (RMSE) values with and without MolRuleLoss were 0.587 vs. 0.660, 0.777 vs. 0.798, and 1.252 vs. 1.877, respectively, representing 2.6-33.3% performance improvements. We show that both the number and the quality of SSRs contribute to the magnitude of prediction accuracy gains obtained upon adding MolRuleLoss to an MPRM. MolRuleLoss improved the generalizability of MPRMs for "activity cliff" molecules in a lipophilicity prediction task and improved the generalizability of MPRMs for OOD molecules in a melting point prediction task. In a molecular weight prediction task for OOD molecules, MolRuleLoss reduced the RMSE value of a GEM model from 29.507 to 0.007. We also provide a formal demonstration that the upper bound of the variation for property change of SSRs is positively correlated with an MPRM's error. Together, we show that using the MolRuleLoss framework as a bolt-on boosts the prediction accuracy and generalizability of multiple MPRMs, supporting diverse applications in areas like cheminformatics and AI-aided drug discovery.