Speakers: Yanming Li, PhD

Yanming Li, PhD

Assistant Professor, Department of Biostatistics and Data Science
University of Kansas Medical Center

 

Dr. Yanming Li is an Assistant Professor in the Department of Biostatistics and Data Science, University of Kansas Medical Center (KUMC). He is an associated member of University of Kansas Cancer Center (KUCC) and University of Kansas Alzheimer’s Disease Research Center (KUADRC). He received his Ph.D. in Biostatistics from University of Michigan. His research has been focused on developing statistical methods and computational algorithms and building predictive models for analyzing big and complex-structured data, with applications to cancer-genomic, neuroimaging-genomics studies and electronic health record data analysis.

 

Transcriptomic Gene Network Profiling and Weak Signal Detection for Predicting Ovarian Cancer Occurrence, Survival, and Severity

A novel machine learning method was developed to identify predictive gene networks and their co-regulating genes with weak differential expression. By integrating network structures — including connection topology and strength — with these weak signals, our approach significantly enhances prediction performance for ovarian cancer occurrence, survival, and severity. We identified unique sets of signature genes associated with OC outcomes, confirming known prognostic genes such as EPCAM, UBE2C, CHD1L, TP53, CD24, WFDC2, and FANCI. Additionally, we discovered novel predictive co-regulating weak genes, including GIGYF2, GNPAT, RAD54L, and ELL, for the first time. Many of the identified predictive gene networks and co-regulating weak genes are involved in OC-related biological pathways, such as the KEGG tight junction, ribosome, and cell cycle pathways. These predictive gene networks provide insights into the molecular mechanisms underlying OC development and progression, potentially guiding new OC drug development.