Dr. Emily Alsentzer is an Assistant Professor in Biomedical Data Science and, by courtesy, Computer Science at Stanford University. Her research leverages machine learning (ML) and natural language processing (NLP) to augment clinical decision-making and broaden access to high quality healthcare. She focuses on integrating medical expertise into ML models to ensure responsible deployment in clinical workflows. Dr. Alsentzer completed a postdoctoral fellowship at Brigham and Women’s Hospital where she worked to deploy ML models within the Mass General Brigham healthcare system. She received her PhD from the Health Sciences and Technology program at MIT and Harvard Medical School and holds degrees in computer science (BS) and biomedical informatics (MS) from Stanford University. She has served as General Chair for the Machine Learning for Health Symposium and founding organizer for SAIL and the Conference on Health, Inference, and Learning (CHIL).
Genetic variation does not only underlie phenotypic diversity among individuals, but also documents the evolutionary history of a species. Research in our laboratory aims to uncover the evolutionary forces that have shaped the patterns of genetic variation in humans, to elucidate the genetics basis of complex traits, and to shed light on the mechanisms that lead to diverse phenotypes and disparate disease risk among populations. We approach these questions by developing statistical and computational approaches, by analyzing large-scale genomic data, and by collaborating with experts in a variety of fields.
- The Sherlock lab uses genomic approaches to shed light on biological systems, particularly employing high throughput sequencing and rigorous analyses of the resulting data. We are characterizing adaptive evolution at the molecular level to understand the adaptive landscape that yeast populations traverse when evolving under a selective pressure. Specifically, we want to know what are the mutational and fitness trajectories taken as a population explores the landscape. We have sequenced the genomes of many adaptive clones and identified the genes and pathways that are the targets of adaptive mutation under a particular selective pressure. We are currently sequencing DNA from entire populations, developing rigorous statistical models to identify low frequency mutations and distinguish them from sequence errors. In a second project, we are using high throughput sequencing to sequence the transcriptome of the human fungal pathogen, Candida albicans. Candida albicans is an obligate diploid, and in many ways, different alleles of the same gene can be thought of a paralogs, as they never go through a haploid phase where deleterious alleles would be exposed. This should result in a relaxed evolutionary constraint, and possible lead to allele specific transcription. We are focusing our efforts on understanding the RNA sequencing data to look for allele specific events, which requires significant bioinformatics expertise. We have recently phased SNPs in the diploid genome, which gives us greater power to detect such events. Finally, we are also looking at changes that occur in cancer. We have profiled DNA methylation changes in prostate cancer, and found that there are large scale genome wide difference between normal and tumor prostate tissue. We are currently working to understand the origins of these changes.
Three main topics are studied in the lab: 1) mutation and evolution of global genomic properties, 2) evolution and population dynamic of transposable elements in eukaryotes, and 3) evolution and population dynamic of transposable elements in eukaryotes.