Sai Zhang is an assistant professor at the Department of Epidemiology. His research lies at the interface of machine learning, genomics and precision medicine. Sai's long-term goal is to build artificial intelligence systems to assist scientific discovery, clinical decision making and personal health management. The focus of his ongoing research is the development of machine learning algorithms (e.g., deep learning and probabilistic graphical models) which exploit massive genetic, multiomic and clinical data to uncover the genomic basis of complex human diseases.
Areas of Expertise (5)
Media Appearances (4)
Severe covid-19 symptoms linked to more than 1300 genetic variants
New Scientist online
More than 1000 genes may contribute to a person’s risk of developing severe covid-19, on top of life circumstances such as their age, ethnicity and any health conditions. Most of the genes, discovered in a study of more than 1 million people, affect the functioning of two kinds of immune cell.
Researchers identify more than 1,000 genes linked to severe COVID-19
Stanford Medicine News Center online
Since the start of the coronavirus pandemic, scientists and clinicians have struggled to understand why some people with the infection become seriously ill or die while others have few, if any, symptoms. Age, body mass index and pre-existing health problems account for some of the disparities, but genetics is known to play a significant role.
Study reveals new ALS risk genes
Nature Reviews Neurology online
A recent study has used a machine learning approach to identify genetic risk factors for amyotrophic lateral sclerosis (ALS). Sai Zhang, Johnathan Cooper-Knock, Michael Snyder and colleagues report a previously unrecognized association between ALS and KANK1, which encodes a protein implicated in distal axon function in motor neurons.
New AI model helps discover causes of motor neurone disease
University of Sheffield News online
Scientists have developed a new machine learning model for the discovery of genetic risk factors for diseases such as Motor Neurone Disease (MND). Designed by researchers from the University of Sheffield and the Stanford University School of Medicine in the US, the machine learning tool, named RefMap, has already been utilised by the team to discover 690 risk genes for motor neurone disease, many of which are new discoveries.
Multiomic analysis reveals cell-type-specific molecular determinants of COVID-19 severityCell Systems
Sai Zhang, et. al
The determinants of severe COVID-19 in healthy adults are poorly understood, which limits the opportunity for early intervention. We present a multiomic analysis using machine learning to characterize the genomic basis of COVID-19 severity. We use single-cell multiome profiling of human lungs to link genetic signals to cell-type-specific functions. We discover >1,000 risk genes across 19 cell types, which account for 77% of the SNP-based heritability for severe disease.
Genome-wide identification of the genetic basis of amyotrophic lateral sclerosisNeuron
Sai Zhang, et. al
Amyotrophic lateral sclerosis (ALS) is a complex disease that leads to motor neuron death. Despite heritability estimates of 52%, genome-wide association studies (GWASs) have discovered relatively few loci. We developed a machine learning approach called RefMap, which integrates functional genomics with GWAS summary statistics for gene discovery.
Decoding the genomics of abdominal aortic aneurysmCell
Jingjing Li, et. al
A key aspect of genomic medicine is to make individualized clinical decisions from personal genomes. We developed a machine-learning framework to integrate personal genomes and electronic health record (EHR) data and used this framework to study abdominal aortic aneurysm (AAA), a prevalent irreversible cardiovascular disease with unclear etiology. Performing whole-genome sequencing on AAA patients and controls, we demonstrated its predictive precision solely from personal genomes.