• Home
  • Search
  • Structure\u2013activity relationship-based chemical classification of highly imbalanced Tox21 datasets
  • Cite Icon83
  • https://doi.org/10.1186/s13321-020-00468-xCopy DOI Icon

Structure\u2013activity relationship-based chemical classification of highly imbalanced Tox21 datasets

Show More
  • Abstract
  • Highlights & Summary
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The specificity of toxicant-target biomolecule interactions lends to the very imbalanced nature of many toxicity datasets, causing poor performance in Structure–Activity Relationship (SAR)-based chemical classification. Undersampling and oversampling are representative techniques for handling such an imbalance challenge. However, removing inactive chemical compound instances from the majority class using an undersampling technique can result in information loss, whereas increasing active toxicant instances in the minority class by interpolation tends to introduce artificial minority instances that often cross into the majority class space, giving rise to class overlapping and a higher false prediction rate. In this study, in order to improve the prediction accuracy of imbalanced learning, we employed SMOTEENN, a combination of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbor (ENN) algorithms, to oversample the minority class by creating synthetic samples, followed by cleaning the mislabeled instances. We chose the highly imbalanced Tox21 dataset, which consisted of 12 in vitro bioassays for > 10,000 chemicals that were distributed unevenly between binary classes. With Random Forest (RF) as the base classifier and bagging as the ensemble strategy, we applied four hybrid learning methods, i.e., RF without imbalance handling (RF), RF with Random Undersampling (RUS), RF with SMOTE (SMO), and RF with SMOTEENN (SMN). The performance of the four learning methods was compared using nine evaluation metrics, among which F1 score, Matthews correlation coefficient and Brier score provided a more consistent assessment of the overall performance across the 12 datasets. The Friedman’s aligned ranks test and the subsequent Bergmann-Hommel post hoc test showed that SMN significantly outperformed the other three methods. We also found that a strong negative correlation existed between the prediction accuracy and the imbalance ratio (IR), which is defined as the number of inactive compounds divided by the number of active compounds. SMN became less effective when IR exceeded a certain threshold (e.g., > 28). The ability to separate the few active compounds from the vast amounts of inactive ones is of great importance in computational toxicology. This work demonstrates that the performance of SAR-based, imbalanced chemical toxicity classification can be significantly improved through the use of data rebalancing.

Similar Papers
  • Research Article
  • Citations4

Comparative analysis of resampling algorithms in the prediction of stroke diseases

  • Mar 30, 2023
  • UMYU Scientifica
  • Sani Dauda Abdullahi +2
  • Research Article

Supervised machine learning algorithms for classifications of gender-based violence in Somalia: a comparison of oversampling techniques.

  • May 28, 2026
  • Scientific reports
  • Seyifemickael Amare Yilema +5
  • Research Article
  • Citations4

Analyzing Resampling Techniques for Addressing the Class Imbalance in NIDS using SVM with Random Forest Feature Selection

  • Sep 30, 2024
  • International Journal of Experimental Research and Review
  • K Swarnalatha +3
  • Research Article
  • Citations2

Flight delay prediction: Evaluating machine learning algorithms for enhanced accuracy

  • Dec 08, 2025
  • PLOS One
  • Sarah Ahmed A Albassam +1
  • Research Article
  • Citations4

Feature-based ensemble modeling for addressing diabetes data imbalance using the SMOTE, RUS, and random forest methods: a prediction study.

  • Apr 30, 2025
  • Ewha medical journal
  • Younseo Jang
  • Research Article
  • Citations4

Influence of Preprocessing Methods of Automated Milking Systems Data on Prediction of Mastitis with Machine Learning Models

  • Sep 18, 2024
  • AgriEngineering
  • Olivier Kashongwe +7
  • PDF
  • Research Article
  • Citations70

A hybrid sampling algorithm combining synthetic minority over-sampling technique and edited nearest neighbor for missed abortion diagnosis

  • Dec 29, 2022
  • BMC Medical Informatics and Decision Making
  • Fangyuan Yang +5
  • Research Article
  • Citations2

Drug usage classification based on personality and demographic features using a combination of sampling and machine learning algorithms

  • Jul 07, 2025
  • Computer Methods in Biomechanics and Biomedical Engineering
  • Shuoxu Zhang
  • Research Article
  • Citations13

Prediction of low Apgar score at five minutes following labor induction intervention in vaginal deliveries: machine learning approach for imbalanced data at a tertiary hospital in North Tanzania

  • Apr 01, 2022
  • BMC Pregnancy and Childbirth
  • Clifford Silver Tarimo +9
  • Research Article
  • Citations37

Applying machine learning methods to predict geology using soil sample geochemistry

  • Aug 11, 2022
  • Applied Computing and Geosciences
  • Timothy C.C Lui +4
  • Research Article

The implementation of the Random Forest Algorithm with Resampling and Without Resampling on the Hepatitis C Disease Dataset

  • Jul 05, 2025
  • Journal of Computer Networks, Architecture and High Performance Computing
  • I Gede Hendrayana +4
  • Research Article

Evaluation of the Effectiveness of SMOTE and Random Under Sampling in Emotion Classification of Tweets

  • Dec 23, 2024
  • INFORMATICS FOR EDUCATORS AND PROFESSIONAL : Journal of Informatics
  • I Komang Dharmendra +2
  • Research Article
  • Citations21

Enhancing Machine Learning Models Through PCA, SMOTE-ENN, and Stochastic Weighted Averaging

  • Oct 25, 2024
  • Applied Sciences
  • Youngjin Han +1
  • PDF
  • Research Article
  • Citations125

Stroke Prediction with Machine Learning Methods among Older Chinese.

  • Mar 01, 2020
  • International Journal of Environmental Research and Public Health
  • Yafei Wu +1
  • Research Article
  • Citations2

Evaluating the performance of different machine learning algorithms based on SMOTE in predicting musculoskeletal disorders in elementary school students

  • Oct 02, 2025
  • BMC Medical Research Methodology
  • Sara Manoochehri +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.