ASCPT Members-Only Webinar Presented by the Quantitative Pharmacology (QP) Network
: Application of Machine Learning in Drug Development (Two-Part Series)
Date and Time:
– Friday, November 2, 2018,
2:00 PM EDT
: Jagdeep Podichetty, PhD
: Daniela J. Conrado, PhD
: Machine learning (ML) is a computationally intensive approach with foundations in statistical theory. Broadly, machine learning integrates data from heterogeneous sources into a model that predicts an outcome. ML is being applied to a range of different areas including self-driving cars, practical speech recognition, effective web search, and drug development.
of this webinar series covered acquiring data and formulating problem statement, data curation and visualization, feature selection methods, supervised ML approach, unsupervised ML approach, and real-world applications of ML in drug development. Recording and slides available in the ASCPT Webinar Library
of the series will take a deep dive into development of an ML algorithm for predicting improvement in patients with schizophrenia using CATIE clinical trial data. The process of ML step-by-step per the ML workflow will be reviewed as well as some widely-used ML algorithms such as Random Forest, Naïve Bayes and Logistic Regression. Outcome prediction techniques will also be identified.
Registration Link for Part 2
: Endogenous Biomarkers of Membrane Transporters and Model-Based Prediction of Clinical Drug-Drug Interactions
Date and Time
: Monday, October 22, 2018 12:00 PM EDT
: Kenta Yoshida, PhD and Xinning Yang, PhD
: Ping Zhao, PhD
: Pharmacometrics & Systems Pharmacology
) and the ASCPT Journal Family are pleased to present this webinar to update attendees on using modeling and simulation (M&S) methods to predict clinical drug-drug interactions (DDIs) based on endogenous biomarker data for membrane transporters. Kenta Yoshida, PhD, Genentech, will review the recent PSP articles, Quantitative Prediction of OATP‐Mediated Drug‐Drug Interactions With Model‐Based Analysis of Endogenous Biomarker Kinetics by Yoshida, et al. and PBPK Modeling of Coproporphyrin I as an Endogenous Biomarker for Drug Interactions Involving Inhibition of Hepatic OATP1B1 and OATP1B3 by Yoshikado, et al. Following the presentation, Dr. Yoshida will be joined by Xinning Yang, PhD, US Food and Drug Administration, for a discussion on regulatory perspectives of using biomarker data to guide DDI strategy in general, and the readiness of updating regulatory recommendations on using M&S and biomarker data to predict transporter-based DDIs.