cs.LGNov 1, 2026

Comparative Strategies for Handling Imbalanced QSAR Regression: A Case Study on hERG Activity Prediction

Authors: Ming-Yen Sung, Hsin Liu, Tung-Sheng Cho, Cheng-Wei Lee, Yufeng J. Tseng

Organizations: VIRTUALMAN, Fuxing Street, Taipei, 106030, Taiwan (ROC). · Graduate Institute of Biomedical Engineering and Bioinformatics, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei, 10617, Taiwan (ROC). · Department of Computer Science and Information Engineering, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei, 10617, Taiwan (ROC). · The Metabolomics Core Laboratory, Center of Genomic Medicine, National Taiwan University, No. 1, Sec. 1, Jen Ai Road, Taipei, 10617, Taiwan (ROC). · 

Abstract

Data imbalance frequently occurs in QSAR modeling, yet most studies focus on classification tasks, and few address regression tasks, as it is challenging to determine which regions of the data are sparse or dense. Data-level and algorithm-level imbalance-handling strategies can have different effects on model performance. In this study, we systematically compare various strategies across GCN and fingerprint-based machine learning models. To evaluate model performance more meaningfully, we partitioned the target region into several subregions based on both domain knowledge and data distribution. We focused on the region of greatest practical interest. Our results demonstrate that selecting models based on this interest-region metric leads to more reliable performance than using the total region metric. We also observed that different imbalance-handling strategies can have divergent effects depending on the model type. These findings highlight the importance of region-aware evaluation in regression QSAR modeling and provide practical guidance for selecting appropriate strategies for imbalanced datasets.

Figures & tables

Explore similar work

CardsList
  1. Hybrid Imbalanced Regression Through Unified Data-Level and Algorithm-Level Balancing

    May 31, 2026Shermin Shahbazi, Hossein Mohammadi, Mohsen AfsharchiClass-Imbalanced Learning

  2. A Systematic Evaluation of Imbalance Handling Methods in Biomedical Binary Classification

    May 13, 2026Jiandong Chen, Lingjie Su, Le Peng +3Class-Imbalanced LearningBinary Classification

  3. Model-agnostic Mitigation Strategies of Data Imbalance for Regression

    Jun 2, 2025Jelke Wibbeke, Sebastian Rohjans, Andreas RauhCost-Sensitive Learning