Log in
Log in


Our lab uses machine learning and artificial intelligence to do biomedical research, focusing on cancer evolution, gene regulation, clinical informatics, and gene function prediction. A key interest is the role of RNA-binding proteins (RBPs) in post-transcriptional regulation. We focus on developing computational and experimental techniques to determine the RNA specificities of RBPs (both sequence and structural) and use these specificities to predict their target transcripts, determine RBP function, and ultimately decipher the regulatory code. Another focus is reconstructing and modelling somatic evolution (pre- and post-cancer) using bulk and single-cell genomic data. In general, we are focused on using large, heterogeneous functional genomic datasets to uncover insights about gene function. Recently, we have becoming increasingly interested in using artificial intelligence and predictive analytics, along with electronic medical records, to inform patient care, particularly in the domain of auto-immune disease.
I’m an Assistant Professor in the Division of Oncology, where my focus is on developing and applying computational tools to provide insight into the origins and progression of cancer. I earned Bachelor degrees in Biology and Computer Science from Truman State University and my PhD in Computational Biology from Baylor College of Medicine. My core research interests include understanding the clonal architecture of tumors and how they evolve in response to therapy, with a special focus on hematologic cancers. I also study effective design and targeting of cancer immunotherapies, developing open-source software for interpreting and visualizing genomic data, and integrative analysis that translates multi-dimensional genomic data into both functional and actionable contexts.
I am currently the NGS sequencing core Manager/Research Investigator and member of the McCombie lab at Cold Spring Harbor Laboratory. I work in developing and adapting new technologies for Next-Generation sequencing routines and other applications. During my time here I have developed optimizations for the Pacific Biosciences RS instrument for large genome sequencing, evaluated rational pooling schemes for large cohort sequencing on Ilumina platforms, and I have developed applications for sequencing and error corrections on the Oxford Nanopore MinIon. Currently I am using optical mapping strategies to evaluation long structural variants in in cancer lines and Oxford Nanopore for CNV detection in clinical samples.
I conduct interdisciplinary research that integrates techniques and methods from machine learning, human computer interaction, and data visualization. I analyze data, build tools, and conduct evaluative studies. My research focuses on the intersection of Data Science and Data Visualization. I am especially interested in the way humans can collaboratively work together with ML/AI systems through visual interfaces. I completed my PhD in Computer Science at the University of British Columbia, where I was jointly advised by Tamara Munzner and Jennifer Gardy. Prior to my PhD, I was a research scientist at the British Columbia Centre for Disease Control and Decipher Biosciences, where I conducted research machine learning and data visualization research toward applications in infectious disease and cancer genomics.  My research has appeared in publications of the ACM (CHI), IEEE (TVCG, CG&A), Oxford Bioinformatics, and Nature.
Andrew McPherson is an Assistant Laboratory Member at the Memorial Sloan Kettering Cancer Center in the Department of Epidemiology and Biostatistics under the supervision of Dr. Sohrab Shah. Andrew completed a PhD in computing science at Simon Fraser University under the supervision of Dr. Cenk Sahinalp and Dr. Sohrab Shah, focusing on methods for sequencing analysis, including detection and characterization of genome rearrangements, and inference of clonal phylogenies. During his post-doctoral research at University of British Columbia with Dr. Sohrab Shah, Andrew focused on the development of computational methods and infrastructure for a novel single cell sequencing plaform, Direct Library Preparation. Andrew moved to MSKCC in May of 2019 and plans to build on his post-doctoral work in single cell genomics to understand genomic instability, mutational processes, clonal evolution and the role of the microenvironment in cancer development and progression.
I am an Associate Professor at the Paul Allen School of Computer Science and Engineering at University of Washington (UW). Before joining UW, I was an Assistant Professor at the Department of Statistics and the Department of Medical Genetics at University of British Columbia (UBC), and a faculty member at the Vector Institute. I also held a Canada Research Chair (CRC II) in Computational Biology (2015-2020), and a Canada CIFAR Chair in Artificial Intelligence (CIFAR-AI). Before joining UBC, I did my postdoctoral fellowship with Daphne Koller at Stanford University. I got my PhD in Computer Science from the University of Toronto in 2011, working with Quaid Morris. My PhD thesis was on integrating large-scale genomics and proteomics datasets to predict gene function. Check out GeneMANIA to find out more about this project!