Machine Learning for Toxicity Prediction in Low-Sample Molecular Classes
- 1Johns Hopkins Applied Physics Laboratory
Abstract
Deep learning models such as Chemprop have advanced quantitative molecular property prediction, but their reliance on large training sets limits use in data-scarce domains. We propose a framework that fine-tunes a general baseline model trained on publicly available data on small, class-specific datasets. The resulting models retain the baseline's generalization ability while gaining class-specific accuracy and produce probabilistic outputs that capture uncertainty in the training data. We demonstrate the approach on three toxicity classes defined by a common core structure, target, or mode of action: (i) organophosphates, (ii) androgen receptor antagonists, and (iii) estrogen receptor beta antagonists. Each fine-tuned model outperforms classical machine-learning methods and the EPA TEST tool. The probabilistic nature of the predictions enables prioritization of compounds for experimental validation and seamless integration with data streams of varying quality, supporting iterative decision-making in chemical safety and drug discovery.
Related
- A comparative analysis of graph neural networks and classical machine learning for carbapenem-resistance prediction and genomic interpretation in Acinetobacter baumannii
- A novel LLM-based GPT-neo transformer with machine learning architecture for promoters prediction in Agrobacterium
- Breath molecular feature profiling with machine learning for noninvasive diagnosis of gout: a single-center case-control study
- Immune-related molecular links between asthma and Alzheimer’s disease identified by multi-omics, machine learning and single-cell analysis
- A Two-Stage ESM-Based Machine Learning Pipeline for Robust Hierarchically Evaluated Enzyme Function Prediction
BibTeX
@misc{barajas2026machine,
title = {{Machine Learning for Toxicity Prediction in Low-Sample Molecular Classes}},
author = {C. Barajas and L. Dunphy and L. Mullany and O. Tiburzi and E. Lloyd},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.16.751426},
url = {https://www.biorxiv.org/content/10.64898/2026.09.16.751426v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Machine Learning for Toxicity Prediction in Low-Sample Molecular Classes
AU - C. Barajas
AU - L. Dunphy
AU - L. Mullany
AU - O. Tiburzi
AU - E. Lloyd
PY - 2026
DA - 2026/09/16
PB - bioRxiv
DO - 10.64898/2026.09.16.751426
UR - https://www.biorxiv.org/content/10.64898/2026.09.16.751426v1
AB - Deep learning models such as Chemprop have advanced quantitative molecular property prediction, but their reliance on large training sets limits use in data-scarce domains. We propose a framework that fine-tunes a general baseline model trained on publicly available data on small, class-specific datasets. The resulting models retain the baseline's generalization ability while gaining class-specific accuracy and produce probabilistic outputs that capture uncertainty in the training data. We demonstrate the approach on three toxicity classes defined by a common core structure, target, or mode of action: (i) organophosphates, (ii) androgen receptor antagonists, and (iii) estrogen receptor beta antagonists. Each fine-tuned model outperforms classical machine-learning methods and the EPA TEST tool. The probabilistic nature of the predictions enables prioritization of compounds for experimental validation and seamless integration with data streams of varying quality, supporting iterative decision-making in chemical safety and drug discovery.
ER -