Samuel Lee
Senior Machine Learning Scientist I at Broad Institute of MIT and Harvard
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolSamuel Lee is a Senior Machine Learning Scientist II at the Broad Institute with 11 years of experience applying statistical modeling and software engineering to genomic and biophysical problems. Trained as a physicist (BS MIT) and astrophysicist (PhD Caltech), he transitioned from theoretical dark-matter research into production-grade bioinformatics, where he designs and implements tools for variant calling and read-level analysis. His contributions to the widely used GATK project include implementing GetHetCoverage and refactoring core pulldown and allelic-count components, reflecting deep expertise in BAM processing, likelihood methods, and scalable Java back-end development. Based in Cambridge, MA, he brings a rare combination of rigorous probabilistic modeling, hands-on code craftsmanship, and a track record of shipping tools that bridge statistical theory and genomics practice.
11 years of coding experience
12 years of employment as a software developer
Bachelor of Science (BS), Physics, Bachelor of Science (BS), Physics at Massachusetts Institute of TechnologyCalifornia Institute of Technology
Github Skills (12)
bioinformatics10
javas10
statistical-models10
variants10
java10
data-analysis10
testing9
fileio9
file-access9
file-handling9
file-processing9
genomics8
Programming languages (6)
Github contributions (5)
broadinstitute/gatk
Jun 2015 - Jan 2023
Official code repository for GATK versions 4 and up
Role in this project:
Back-end Developer & Bioinformatics Engineer
Back-end Developer & Bioinformatics EngineerContributions:164 reviews, 577 commits, 233 PRs in 7 years 8 months
Contributions summary:Samuel primarily worked on implementing the "GetHetCoverage" tool for retrieving ref/alt counts at heterozygous SNPs. Their contributions involved writing Java code to analyze BAM files, apply filters, and perform calculations related to SNP pulldown. The user refactored existing code, including the "Pulldown" and "AllelicCountCollection" classes, and implemented methods for testing the compatibility of read counts with heterozygous allele fractions, indicating a focus on data processing within the broader domain of bioinformatics. The commits also demonstrate the integration of a new "SNPSegmenter" tool, with refactoring of existing code to work with it, and addition of a "CalculatePulldownPhasePosteriors" tool suggesting a deep understanding of statistical methodologies for variant calling.
genomesciencednaspark-mlngs
samuelklee/taxi-strategy
Apr 2015 - Aug 2015
Contributions:58 commits, 23 pushes, 1 branch in 4 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.