CV | PUBLICATIONS | TALKS | CROOKSHANKS | DR. PALLEROS |

   jmschr < at > stanford < dot > edu




I am a post-doc and Ruth L. Kirschsten awardee at Stanford University, studying regulatory genomics using large-scale machine learning methods with Anshul Kundaje. Previously, I was a graduate student at the University of Washington with Bill Noble. My research focus is to organize the massive amount of available genomics data into useful tools and meaningful discoveries. To this end, I have developed Ledidi, a method for editing biosequences to exhibit desired characteristics, Avocado, a deep tensor factorization approach for jointly modeling thousands of genome-wide regulatory experiments and imputing those that have not yet been performed, and a method that uses submodular optimization to guide future experimental efforts. These projects sometimes involve machine learning methods that are not mainstream, and so I routinely contribute to the Python open source community in the form of packages that implement general purpose versions of the algorithms that I apply to genomics. As such, I am the core developer of pomegranate, a package for flexible probabilistic modeling, apricot, a package for data summarization for machine learning, and in the past was a core developer for the scikit-learn project.

In addition to my research activities, I am also an editor at the Stanford AI Lab Blog, an editor at the Journal of Open Source Software, on the editorial board for the Journal of Machine Learning Research, and occasionally co-host podcasts on The Bioinformatics Chat. When I don't get much done in a week, I pretend these are the reasons why.

Research Software: tfmodisco-lite bpnet-lite yuzu Ledidi Avocado Rambutan PyPore

General Software: apricot pomegranate scikit-learn

Machine Learning | Submodular Optimization | Open Source Software | Big Data | Pitfalls | Computational Biology | Functional Genomics | Epigenomics