The Geisel School of Medicine Events Calendar
The Geisel School of Medicine Events - ( Subscribe )
|
|||||
|
Please join the Geisel Class of 2024 as they present their team quality improvement projects from their senior Capstone course on Thursday, March 21. 16 student groups have been working in teams with faculty mentors on clinical and medical education quality improvement projects since November 2023 and will be presenting the results of their work at the event. The session will occur in Auditorium G with oral presentations from three teams from 4:00-5:00 PM followed by poster viewing from 5:00 - 6:00 PM in the Williamson Building atrium. Beverages and appetizers will be served.
The Department of Biomedical Data Science at Geisel invites you to attend a Grand Rounds presentation by Zhi Wei, PhD, Professor of Computer science and Statistics at the New Jersey Institute of Technology, on Thursday, March 21 from 1:30-2:30pm at DHMC, Auditorium H (or via Zoom).
Talk title: “Model-based deep embedding for the analysis of single-cell RNA sequencing data”
Host: Jiang Gui, PhD
Location: In-person at DHMC, Auditorium H or via Zoom (no registration required)
Please see link below for more details.
Zoom meeting ID: 503 779 5102
Zoom passcode: 6501974
URL: https://dartmouth.zoom.us/j/5037795102
Phone (if needed for audio only, or to join by phone only): 669-900-6833
Presentation Summary
Single-cell RNA sequencing (scRNA-seq) promises to provide high resolution of cellular differences. However, the analysis of scRNA-seq data remains a statistical and computational challenge, due to the pervasive dropout events obscuring the high dimensional data matrix with prevailing ‘false’ zero count observations. Furthermore, subsequent differential expression analysis after clustering incurs the so-called “double use of data" problem, which will compromise type I error control for standard statistical tests. In this talk, I will introduce model-based deep autoencoders to address these issues. The proposed approaches leverage the most recent developments in feature representation learning in deep learning and feature selection in statistical learning, as well as prior information from domain scientists. Extensive experiments on both simulated and real datasets demonstrate that the proposed methods can boost clustering performance significantly while effectively filtering out most irrelevant genes. Our methods can generate more biologically meaningful clusters with enhanced interpretability as desired by biologists.
Biography
Dr. Wei is currently a professor of computer science and statistics (joint appointment) at the New Jersey Institute of Technology. He also serves as an adjunct professor at the University of Pennsylvania Perelman School of Medicine and the Wistar Cancer Center. Dr. Wei earned his PhD from the University of Pennsylvania. His research interests include machine learning, statistical modeling, and advanced data analytics, with a particular focus on applications in cancer genomics and genetics. Dr. Wei’s methodological work has been published in prestigious AI and machine learning journals and conferences, as well as in leading statistics and biostatistics journals. Beyond methodological research, Dr. Wei is actively engaged in collaborative research, leading to publications in top-tier scientific journals including Nature, Science, Cell, Nature Medicine, and Nature Genetics, among others. To date, he has authored or co-authored more than 150 journal publications, with 18,000 citations and an H-index of 61. Dr. Wei is an IEEE Fellow and has been honored with the Adobe Data Science Research Award.
Talk title: “Model-based deep embedding for the analysis of single-cell RNA sequencing data”
Host: Jiang Gui, PhD
Location: In-person at DHMC, Auditorium H or via Zoom (no registration required)
Please see link below for more details.
Zoom meeting ID: 503 779 5102
Zoom passcode: 6501974
URL: https://dartmouth.zoom.us/j/5037795102
Phone (if needed for audio only, or to join by phone only): 669-900-6833
Presentation Summary
Single-cell RNA sequencing (scRNA-seq) promises to provide high resolution of cellular differences. However, the analysis of scRNA-seq data remains a statistical and computational challenge, due to the pervasive dropout events obscuring the high dimensional data matrix with prevailing ‘false’ zero count observations. Furthermore, subsequent differential expression analysis after clustering incurs the so-called “double use of data" problem, which will compromise type I error control for standard statistical tests. In this talk, I will introduce model-based deep autoencoders to address these issues. The proposed approaches leverage the most recent developments in feature representation learning in deep learning and feature selection in statistical learning, as well as prior information from domain scientists. Extensive experiments on both simulated and real datasets demonstrate that the proposed methods can boost clustering performance significantly while effectively filtering out most irrelevant genes. Our methods can generate more biologically meaningful clusters with enhanced interpretability as desired by biologists.
Biography
Dr. Wei is currently a professor of computer science and statistics (joint appointment) at the New Jersey Institute of Technology. He also serves as an adjunct professor at the University of Pennsylvania Perelman School of Medicine and the Wistar Cancer Center. Dr. Wei earned his PhD from the University of Pennsylvania. His research interests include machine learning, statistical modeling, and advanced data analytics, with a particular focus on applications in cancer genomics and genetics. Dr. Wei’s methodological work has been published in prestigious AI and machine learning journals and conferences, as well as in leading statistics and biostatistics journals. Beyond methodological research, Dr. Wei is actively engaged in collaborative research, leading to publications in top-tier scientific journals including Nature, Science, Cell, Nature Medicine, and Nature Genetics, among others. To date, he has authored or co-authored more than 150 journal publications, with 18,000 citations and an H-index of 61. Dr. Wei is an IEEE Fellow and has been honored with the Adobe Data Science Research Award.