Sam Friedman
Senior Group Leader at Broad Institute of MIT and Harvard
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolSam Freesun Friedman is a Research Scientist and ML practitioner with 11 years of experience applying machine learning to cardiovascular disease, genetics, and psychedelics, affiliated with the Broad Institute of MIT and Harvard and based in Portland, Maine. He blends backend engineering and data science, contributing to high-profile open-source genomics tooling—most notably the Broad’s GATK repository—where he implemented 1D and 2D CNN scoring for variant analysis and developed training and tensor-writing utilities. His work includes tranche-based variant filtering and cross-language numerical consistency fixes between Python and Java, reflecting a focus on making research models robust and production-ready. Comfortable at the intersection of research and engineering, he accelerates reproducible genomic ML by shipping reliable tooling that bridges experiments and pipelines.
11 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at The Graduate Center, City University of New York
Github Skills (19)
fasterrcnn10
biom10
python10
bio-informatics10
data-science10
java10
mask-rcnn10
javas10
keras10
tensorflow210
gatk10
tensorflow10
bioinformatics10
faster-rcnn10
ng9
Programming languages (4)
Github contributions (5)
broadinstitute/gatk
Oct 2017 - Aug 2021
Official code repository for GATK versions 4 and up
Role in this project:
Backend Developer & Data Scientist
Backend Developer & Data ScientistContributions:1 review, 217 commits, 26 PRs in 3 years 11 months
Contributions summary:Sam's commits primarily focus on modifications and additions related to the CNN (Convolutional Neural Network) framework for variant analysis within the GATK (Genome Analysis Toolkit) project. They implemented features for CNN scoring of variants using 1D and 2D models, developed tools for training, and for writing tensors. Significant work was done on filtering variants using tranches and improving the accuracy of model scoring, and fixing numerical consistency between python and java. The commits also include improvements and updates to the existing code and workflows.
genomesciencednaspark-mlngs
broadinstitute/ml4h
Apr 2019 - Jan 2023
Contributions:4 releases, 75 reviews, 764 commits in 3 years 10 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.