معرفی
Dr. Slade Matthews is a Senior Lecturer at the Sydney Pharmacy School, University of Sydney, where he coordinates third-year toxicology courses PCOL3011 and PCOL3911. He is a member of The Centre for Drug Discovery Innovation and leads the Computational Pharmacology and Toxicology Laboratory (CPT Laboratory), which focuses on using computer technologies to uncover new relationships in biomedical data for drug development applications.
Dr. Matthews' research interests center on computational pharmacology and toxicology, with particular emphasis on using computerized data management, machine learning techniques, and mathematical molecular representation to build predictive models relevant to drug development and regulatory assessment. His work spans multiple areas including computational toxicology, cancer research, biostatistics, and computational biology, with a strong focus on developing in silico models for early detection of drug toxicity.
His recent publications demonstrate a clear trend toward increasingly sophisticated machine learning approaches for toxicity prediction, particularly in mutagenicity and skin sensitization. He has made significant contributions to the Ames/QSAR international challenge project and has developed novel approaches like mechanistic task groupings and multiple instance learning to improve mutagenicity prediction accuracy.
- 2012 Sydney Medical School Award for Outstanding Teaching
- 2009 Coop Bookshop Excellence in teaching award
Dr. Matthews supervises several research students including Samuel FEENEY (working on metal chelators), Luke THOMPSON (focusing on Transformers for Molecular Representation Learning), and Hongdan WANG (studying bronchial epithelial cell-derived extracellular vesicles). He has received research funding including a 2019 Ignition Seed Fund Grant for 'Metabolism-Aware Strain-Specific Model for Ames Mutagenicity Prediction Using Multitask Deep Learning' and contributed to a 2013 NHMRC Equipment Grant for clinical observation equipment.
His CPT Laboratory employs principles of computerized data management, machine learning, and mathematical molecular representation to build predictive models with relevance to drug development and regulatory assessment. The lab's work is particularly focused on in silico toxicology approaches that aim to detect toxic effects early in drug development to avoid the enormous costs associated with late-stage toxicity detection.
