Similarity-Quantized Relative Difference Learning for Improved Molecular Activity Prediction

Karina Zadorozhny, Kangway V. Chuang, Bharath Sathappan, Ewan Wallace, Vishnu Sresht, Colin A Grambow

Keywords: molecular activity prediction, drug discovery, graph neural networks, machine learning, low-data regimes, molecular similarity, relative difference learning, activity cliffs, benchmarking, chemical informatics, deep learning, medicinal chemistry

Abstract: Accurate prediction of molecular activities is crucial for efficient drug discovery, yet remains challenging due to limited and noisy datasets. We introduce Similarity-Quantized Relative Learning (SQRL), a learning framework that reformulates molecular activity prediction as relative difference learning between structurally similar pairs of compounds. SQRL uses precomputed molecular similarities to enhance training of graph neural networks and other architectures, and significantly improves accuracy and generalization in low-data regimes common in drug discovery. We demonstrate its broad applicability and real-world potential through benchmarking on public datasets as well as proprietary industry data. Our findings demonstrate that leveraging similarity-aware relative differences provides an effective paradigm for molecular activity prediction.

Submission Number: 10