Similarity-Quantized Relative Difference Learning for Improved Molecular Activity Prediction

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zadorozhny, Karina, Chuang, Kangway V., Sathappan, Bharath, Wallace, Ewan, Sresht, Vishnu, Grambow, Colin A.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913652193361920
author Zadorozhny, Karina
Chuang, Kangway V.
Sathappan, Bharath
Wallace, Ewan
Sresht, Vishnu
Grambow, Colin A.
author_facet Zadorozhny, Karina
Chuang, Kangway V.
Sathappan, Bharath
Wallace, Ewan
Sresht, Vishnu
Grambow, Colin A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09103
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Similarity-Quantized Relative Difference Learning for Improved Molecular Activity Prediction
Zadorozhny, Karina
Chuang, Kangway V.
Sathappan, Bharath
Wallace, Ewan
Sresht, Vishnu
Grambow, Colin A.
Machine Learning
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.
title Similarity-Quantized Relative Difference Learning for Improved Molecular Activity Prediction
topic Machine Learning
url https://arxiv.org/abs/2501.09103