Publications:1
Bin Zhang, PhD
About Me
Dr. Zhang is the Willard T.C. Johnson Research Professor of Neurogenetics in the Department of Genetics and Genomic Sciences, is Director of the Mount Sinai Center for Transformative Disease Modeling, and is a faculty member of the Icahn Genomics Institute. Dr. Zhang’s extensive experience in electrical engineering, computer science and computational biology empowers him to build up highly predictive models for very complex data from handwritten document images to large-scale cancer genomic data. Over the past decade, Dr. Zhang has developed and significantly contributed a series of influential gene network inference algorithms which have been extensively used for identification of novel pathways and gene targets, as well as development of drugs for a variety of human diseases such as cancer, atherosclerosis, Alzheimer's, obesity and diabetes. His latest research that uncovered dramatic changes in gene-gene interaction patterns in Alzheimer’s disease and pinpointed an immune/microglia gene network as the top pathway causally linked to the disease was just published in Cell. His recent research that sheds a new light on targeted therapies against breast cancer was featured by the Second AACR International Conference on Frontiers in Basic Cancer Research (San Francisco, September 14-18, 2011). His work on predicting genetic interactions was identified by Nature Biotechnology as one of the breakthroughs in the field of computational biology in 2010. The discovery of a gene cluster that is causally linked to obesity and diabetes was highlighted in Nature in 2008. His early research on image pattern recognition significantly contributed to several large-scale pattern recognition systems including U.S. Handwritten Address Identification System which has been adopted by US Postal Office. Dr. Zhang was a recipient of the Best Paper Award of ICDAR 2003 ─ the Seventh International Conference on Document Analysis and Recognition.
As a prolific researcher, Dr. Zhang has published a number of high profile papers in Nature, Science, Cell, Nature Genetics, and PNAS. As of April 2015, his publications have been cited 7131 times. Furthermore, he has been a leader of more than a dozen projects to identify novel drug targets for several pharmaceutical companies.
For more information about Dr. Zhang's research, please visit http://research.mssm.edu/multiscalenetwork .
Language
English
Position
PROFESSOR | Genetics and Genomic Sciences, PROFESSOR | Pharmacological Sciences, PROFESSOR | Artificial Intelligence and Human Health
Research Topics
Adipose, Aging, Allergy, Alzheimer's Disease, Anti-Tumor Therapy, Apoptosis/Cell Death, Autism, Autophagy, Axonal Growth and Degeneration, Bioinformatics, Bone Biology, Bone Metabolism, Brain, Cancer, Cancer Genetics, Cell Cycle, Cerebral Cortex, Cognitive Neuroscience, Computational Neuroscience, Diabetes, Epigenetics, Gene Discovery, Gene Expressions, Gene Regulation, Gene Therapy, Genetics, Genetics of Movement disorders, Genomics, Glutamate (NMDA & AMPA) Receptors, Glutathione, Hippocampus, Human Genetics and Genetic Disorders, Image Analysis, Immunology, Infectious Disease, Inflammation, Liver, Lung, Mathematical Modeling of Biomedical Systems, Mathematical and Computational Biology, Memory, Metastasis, Microarray, Microglia, Mitosis, Molecular Biology, Motor Control, Obesity, Oncogenes, Prefrontal Cortex, Protein Complexes, Protein Folding, RNA Splicing & Processing, Tumor Suppressor Genes, Tumorigenesis
Multi-Disciplinary Training Areas
Genetics and Genomic Sciences [GGS], Neuroscience [NEU]
Education
BE, Tongji University
MS, State University of New York at Buffalo
MS, Tsinghua University
PhD, State University of New York at Buffalo
Research
Enormous data from each single patient is being generated but it remains challenging how to make best use of the information for personalized medicine. ARCPS will take as inputs all pathological, clinical, genetic, genomic, proteomic, and metabolic information to classify patients, predict disease progression, determine drug response, and decide optimal treatments. Given the multi-modal nature of the input data, those complex high-dimension data types such as image, DNA, mRNA, protein and sequencing need go through different feature extractors to yield meaningful features for training and classification/prediction.