ADMET Predictor is the flagship artificial intelligence/machine learning (AI/ML) platform developed by Simulations Plus for predicting Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties of chemical compounds. It is an essential tool for drug discovery and chemical risk assessment scientists, enabling them to quickly screen large compound libraries and prioritize molecules with optimal pharmacokinetic and safety profiles.
Key Benefits and Capabilities:
- High-Throughput Prediction: Quickly and accurately predicts over 175 properties, including aqueous and biorelevant solubility, logD vs. pH curves, pKa, CYP and UGT metabolism outcomes, and key toxicity endpoints (e.g., Ames mutagenicity, Drug-Induced Liver Injury - DILI).
- AI-Driven Drug Design (AIDD): Features an upgraded AIDD engine that combines AI/ML with mechanistic High-Throughput PBPK (HT-PBPK) simulations, powered by the integrated GastroPlus® software, for faster and smarter decision-making at the intersection of chemistry and pharmacokinetics.
- Custom Model Building: The ADMET Modeler™ module allows researchers to build their own high-quality QSAR/QSPR models using state-of-the-art machine learning algorithms and ADMET Predictor's extensive set of molecular descriptors.
- Enterprise Automation: Offers enterprise-ready automation via a REST API, Python scripting support, and components for third-party informatics platforms like KNIME and BIOVIA Pipeline Pilot, allowing seamless deployment into existing R&D workflows.
- Visualization and Analysis: Includes customizable visualization tools like star plots, distribution and 2D/3D scatter plots, and the integrated MedChem Studio™ module for advanced cheminformatics features like R-group analysis, clustering, and compound selection.
ADMET Predictor models are built on premium datasets and have been consistently ranked as highly accurate in independent published comparisons, making it a reliable and powerful platform for optimizing lead compounds and reducing the risk of late-stage drug failure.
