Comprehensive Multi-Factor Toxicity Prediction of Biopharmaceuticals through Multiple Model Approach
CSEF · 2026 Medicine & Physiology (Senior Division)
Overview
The popularization of machine learning has prompted the introduction of specialized predictor and generator models utilized for the analysis of toxicity and assessment of chemicals. However, these methods lack the true complexity required to evaluate the effectiveness not just from a singular toxicity standpoint, but also the real world feasibility required for real world pharmaceutical uses, such as testing multiple forms of toxicity. In this study, we propose a novel strategy to utilize a multi-model approach to predicting toxicity on five different toxicity categories on multiple datasets. We trained XGBoost classification and regression models based on acute toxicity, mutagenicity, carcinogenicity, DART, and hepatotoxicity, with accuracies between 67.76% and 80.68%, and AT RMSE of 0.9644, with Streamlit combining all models under one frontend app. We propose this predictor system being utilized at not only as a ranking system of chemicals on toxicity that closely resembles human responses to chemicals, but as an multifaceted, effective reward system in a reinforcement-learning generation model that will produce safer, less-toxic drugs on multiple toxicity categories.
Competition history
- CSEF 2026
Related projects
ISEF · 2026
H.E.P.A.R (Hepatic Ensemble Predictive Analysis Resource): A Convergent Machine Learning Architecture for Drug-Induced Liver Injury Prediction
CSEF · 2026
Predicting Synergistic Cancer Drug Combinations Using a Disease-Agnostic Machine Learning Approach
ISEF · 2016
Predictive Modeling of Optimal Cancer Therapies
JSHS · 2024
A Two-Pronged Method for the Identification of Highly Biocompatible Nanomaterials
ISEF · 2023
A Novel Approach to Systemic in silico Drug Discovery Using a Machine Learning-Based Prediction of Binding Affinity
ISEF · 2024
Combating the Drug Epidemic: A Machine-Learning Framework to Predict Novel Drug-Drug Interaction Risks of Illicit Drug Abuse
CSEF · 2026
The Effect of Using Machine Learning Algorithms on the Accuracy of the Prediction of Dopamine Neurotransmitters
CWSF · 2026
Modeling Drug Side-Effect Burden on Organ Systems
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects