• Home
  • Search
  • Active Stacking-Deep Learning with Strategic Samplingfor Small and Imbalanced Chemical Toxicity Prediction
  • Cite Icon1
  • https://doi.org/10.1021/acsomega.5c04016Copy DOI Icon

Active Stacking-Deep Learning with Strategic Samplingfor Small and Imbalanced Chemical Toxicity Prediction

  • Nov 4, 2025
  • ACS Omega
  • Darlene Nabila Zetta +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Major challengesin toxicity prediction include dealing with imbalancedand limited data sets, especially when evaluating the harmful potentialof chemicals. These issues often lead to poor predictive model performance.Stacking ensemble learning enhances performance by combining predictionsfrom multiple base models, enabling the stack model to improve overallgeneralization. Active learning (AL), on the other hand, reduces theneed for large-scale data sets by effectively training models usingcarefully selected samples. One effective approach to address dataimbalance is the use of strategic sampling techniques. Hereby, weintroduce an active stacking-deep learning framework that integratesdeep neural networks (DNNs), including a convolutional neural network(CNN), a bidirectional long short-term memory (BiLSTM), and an attentionmechanism, with strategic data sampling to tackle challenges posedby imbalanced and limited data, ultimately improving the performanceof a chemical risk assessment predictive model. In this study, wefocused on thyroid-disrupting chemicals (TDCs) that target thyroidperoxidase, as they are linked to thyroid dysfunction, making it essentialto evaluate their risks to human health. Using stacking ensemble learningwith strategic sampling within an AL framework, our approach achievedan MCC of 0.51, AUROC of 0.824, and AUPRC of 0.851. Although performancedecreased across varying test ratios, our uncertainty-based methoddemonstrated superior stability under severe class imbalance. Whilea full-data stacking ensemble trained with strategic sampling performsslightly better in MCC, our method achieves marginally higher AUROCand AUPRC, requiring up to 73.3% less labeled data. Molecular dockingfurther validated our predictions, especially for highly toxic compounds,reinforcing the reliability of our framework in identifying TDCs.These findings highlight how active stacking-deep learning with strategicsampling can transform toxicity prediction, offering a more accurateand data-efficient alternative to traditional chemical risk assessmentmethods.

Similar Papers
  • Research Article

Data-efficient learning for accurate identification of MAPK1 inhibitors using an active meta-deep learning framework.

  • Feb 03, 2026
  • Journal of cheminformatics
  • Darlene Nabila Zetta +1
  • Conference Article
  • Citations31

Similarity-Based Active Learning for Image Classification Under Class Imbalance

  • Nov 01, 2018
  • Chuanhai Zhang +5
  • Research Article
  • Citations31

Active Deep Learning with Fisher Information for Patch-wise Semantic Segmentation.

  • Jan 01, 2018
  • Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support : 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, held in conjunction with MICCAI 2018, Granada, Spain, S...
  • Jamshid Sourati +4
  • Conference Article
  • Citations580

Deep Bayesian active learning with image data

  • Nov 27, 2017
  • Apollo (University of Cambridge)
  • Yarin Gal +2
  • Book Chapter
  • Citations1

Gujarati Task Oriented Dialogue Slot Tagging Using Deep Neural Network Models

  • Jan 01, 2021
  • Rachana Parikh +1
  • Research Article
  • Citations48

A CNN-based active learning framework to identify mycobacteria in digitized Ziehl-Neelsen stained human tissues

  • Jul 25, 2020
  • Computerized Medical Imaging and Graphics
  • Mu Yang +3
  • Research Article
  • Citations5

Accelerating Data Set Population for Training Machine Learning Potentials with Automated System Generation and Strategic Sampling.

  • Jul 02, 2025
  • Journal of chemical theory and computation
  • Alberto Pacini +2
  • Conference Article

Drift Calibration for Machine Olfaction with an Online Active Learning Approach

  • Nov 01, 2018
  • Tao Liu +4
  • Conference Article

U-Net based Active Learning Framework for Enhancing Cancer Immunotherapy

  • Mar 03, 2021
  • Vishwanshi Joshi
  • Book Chapter

Framework for Technology-Enriched Active Class Learning of Physics in Secondary Schools in Kenya

  • Jan 01, 2021
  • Elizabeth Sarange Bosire Abenga +3
  • Research Article
  • Citations20

Active learning for classifying long‐duration audio recordings of the environment

  • Jul 05, 2018
  • Methods in Ecology and Evolution
  • Mahnoosh Kholghi +4
  • Research Article
  • Citations8

Advancing Preauthorization Task in Healthcare: An Application of Deep Active Incremental Learning for Medical Text Classification

  • Dec 05, 2023
  • Engineering, Technology & Applied Science Research
  • Aishat Salau +3
  • Research Article
  • Citations76

Active learning: a step towards automating medical concept extraction.

  • Aug 07, 2015
  • Journal of the American Medical Informatics Association
  • Mahnoosh Kholghi +3
  • Research Article
  • Citations25

Active learning of many-body configuration space: Application to the Cs+-water MB-nrg potential energy function as a case study.

  • Apr 10, 2020
  • The Journal of Chemical Physics
  • Yaoguang Zhai +3
  • Preprint Article
  • Citations5

Active Learning of Many-Body Configuration Space: Application to the Cs+–water MB-nrg Potential Energy Function as a Case Study

  • Jan 23, 2020
  • ChemRxiv
  • Yaoguang Zhai +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.