Application of Quantitative Systems Toxicology and Machine Learning Models in the Assessment of Drug-Induced Liver Injury

Authors: Siler SQ, Yang K
Conference: ACS
Keywords: ACS 2025, admet predictor, DILIsym, drug induced liver injury (DILI), liver safety, machine learning (ML), QST modeling
Software: ADMET Predictor®, DILIsym®

Agenda

  • Quantitative systems toxicology (QST) modeling of DILI
    • Liver safety assessment using DILIsym
    • Case study: application of QST modeling in the liver safety assessment of CGRP receptor antagonists
  • Integrating QST and machine learning (ML) models for early assessment of hepatotoxic risk
    • Bridging compound structure to DILI mechanisms using ADMET Predictor
    • Application of QST-ML models in rank-ordering liver safety assessment of CGRP receptor antagonists
  • Conclusions and perspectives

By Scott Q Siler

ACS Fall National Meeting, August 17-21, 2025, Washington, DC