BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv5.18.0//EN
X-ORIGINAL-URL:https://canssiontario.utoronto.ca/
BEGIN:VEVENT
UID:MEC-530f49aa780e4bb3a605e586094008e7@canssiontario.utoronto.ca
DTSTART:20250414T193000Z
DTEND:20250414T203000Z
DTSTAMP:20230512T195600Z
CREATED:20230512
LAST-MODIFIED:20250306
SUMMARY:CAST Seminar: Bingxin Zhao
DESCRIPTION:\nJoin us at the CANSSI Ontario Statistics Seminar with:\n\n\n\nBingxin Zhao\n\n\n\nAssistant Professor of Statistics and Data ScienceDepartment of Statistics and Data ScienceThe Wharton SchoolUniversity of Pennsylvania\n\n\n\nFree Hybrid (In-person/Online) Event | Registration Required\n\n\n\nTalk Title\n\n\n\nCloud computing ecosystems in genetic risk prediction\n\n\n\nAbstract\n\n\n\nPolygenic risk scores (PRS) model training is essential for risk prediction in precision medicine but face adoption challenges due to computational limitations, complex methodologies, and data privacy concerns. Here we introduce PennPRS (https://pennprs.org), a scalable cloud computing platform for online PRS model training in precision medicine. We developed novel pseudo-training algorithms and ensemble approaches, enabling model training without requiring individual-level data. These methods were rigorously validated through extensive simulations and large-scale real data analyses involving over 6,000 phenotypes across various data sources. PennPRS supports no-coding single- and multi-ancestry PRS training with seven methods, allowing users to upload their own data or query from more than 27,000 datasets in the GWAS Catalog, submit jobs, and download trained PRS models. Additionally, we applied our pseudo-training pipeline to train PRS models for over 8,000 phenotypes and made their PRS weights publicly accessible. In summary, PennPRS provides a cloud computing ecosystem to improve the accessibility of PRS applications and reduce disparities in computational resources for the global PRS research community. We will also discuss the general statistical properties of pseudo-training in prediction models.\n\n\n\nSpeaker Profile\n\n\n\nBingxin Zhao is an Assistant Professor in the Department of Statistics and Data Science at the Wharton School, University of Pennsylvania. His research focuses broadly on biomedical data science, leveraging computational approaches and complex data to real-world problems in science and medicine.\n\n\n\nHis work has contributed to the understanding of the human brain, inter-organ connections such as the heart-brain link, mental health, and brain disorders (https://www.bingxinzhao.com/).\n
URL:https://canssiontario.utoronto.ca/event/ares-bingxin-zhao/
ORGANIZER;CN=CANSSI Ontario:MAILTO:esther.berzunza@utoronto.ca
CATEGORIES:CANSSI Ontario Statistics Seminars
LOCATION:Zoom (Online)
ATTACH;FMTTYPE=image/png:https://canssiontario.utoronto.ca/wp-content/uploads/2023/05/48-b2cf46ad47657d282fe970d7b5c5833a_3815_361_v2.png
END:VEVENT
END:VCALENDAR