Efficient Models For Molecular Property Prediction

Sairam Narendra Babu, Rishabh Bhattacharya

Keywords: Molecular Property Prediction, Drug Discovery, Efficient models, Graph Transformers, Graph Neural Networks, Molecular Graph Transformer (MGT), Linformer, PAMNet, Hybrid architecture, Metal–organic frameworks (MOFs), QMOF, Efficient attention, Training efficiency

TL;DR: A hybrid Linformer–PAMNet fusion model delivers accuracy higher than existing transformer models on MOF property prediction with up to 7× faster training.

Abstract: Molecular property evaluation units are essential components of property-driven drug-discovery pipelines, as their accuracy and generalizability directly influence the success of compound synthesis and optimization. Existing approaches either employ lightweight models optimized for small molecules or heavyweight architectures capable of handling large molecular systems, each with trade-offs in scope and computational cost. Here, we propose and evaluate a hybrid framework that balances these considerations—delivering broad generalization across diverse molecular sizes while maintaining efficiency during both training and inference. Our results demonstrate that this middle-ground strategy achieves performance on par with large-scale predictors for complex targets, yet retains the speed and resource footprint of more compact models, making it well suited for practical drug-discovery workflows.All our results and code are available in our \href{https://github.com/rbSparky/MGT-PlusPlus/tree/saigum}{GitHub repository}.

Submission Number: 105