Speakers: Jianlin (Jack) Cheng, PhD

Jianlin (Jack) Cheng, PhD

Curators’ Distinguished Professor
Paul K. and Diane Shumaker Professor
Department of Electrical Engineering and Computer Science
NextGen Precision Health
University of Missouri

 

Dr. Jianlin Cheng is a Curators’ Distinguished Professor and Paul & Diane Shumaker Professor in the Department of Electrical Engineering and Computer Science at the University of Missouri–Columbia (MU) and an investigator with MU’s NextGen Precision Health Initiative. He earned his PhD in computer science from the University of California, Irvine, in 2006. His research spans bioinformatics, machine learning, and artificial intelligence (AI). Dr. Cheng has authored or co-authored over 270 publications cited more than 25,000 times, with an h-index of 72. His AI-based methods for protein structure prediction consistently ranked among the top performers in the last 10 rounds of the international Critical Assessment of Structure Prediction (CASP7–16) from 2006 to 2024. His work has been supported by the U.S. National Institutes of Health (NIH), National Science Foundation (NSF), Department of Energy (DOE), and Department of Agriculture (USDA). Dr. Cheng is a fellow of both the American Association for the Advancement of Science (AAAS) and the American Institute for Medical and Biological Engineering (AIMBE), and he serves as an associate editor for Bioinformatics.

 

Visualizing Single-cell 3D Chromosome Structures With Geometric Deep Learning

The spatial conformation of chromosomes and genomes of single cells is relevant to cellular function and useful for elucidating the mechanism underlying gene expression and genome methylation. The chromosomal contacts (i.e. chromosomal regions in spatial proximity) entailing the three-dimensional (3D) structure of the genome of a single cell can be obtained by single-cell chromosome conformation capture techniques, such as single-cell Hi-C (ScHi-C). However, due to the sparsity of chromosomal contacts in ScHi-C data, it is still challenging for traditional 3D conformation optimization methods to reconstruct and visualize the 3D chromosome structures from ScHi-C data. Here, we present a geometric deep learning method based on a novel SO(3)-equivariant graph neural network (HiCEGNN) to reconstruct 3D structures of chromosomes of single cells from ScHi-C data. HiCEGNN consistently outperforms existing methods across diverse cells, different structural resolutions, and different noise levels of the data.