Nicholas Bernstein
Principal Data Scientist
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolNicholas Bernstein is a Principal Data Scientist based in the San Francisco Bay Area with 11 years of experience applying genetics, statistics, and software engineering to deliver clinically actionable insights. He builds and scales bioinformatics methods and web apps for diagnostics and research, having led deep learning solutions for doublet detection in scRNA-seq and multimodal meta-analyses across UKBB, TCGA, GTEx and other large consortia. Nicholas has driven scientific OKRs and partnered closely with wet labs to design experiments whose results are integrated into production-ready ML models. An active contributor to scvi-tools, he improved the SOLO model’s training and doublet-scoring capabilities, reflecting a blend of open-source rigor and production focus. He brings a rare mix of hands-on algorithm development, pipeline automation for CLIA assays, and cross-disciplinary leadership that accelerates translation from data to patient-facing content.
11 years of coding experience
6 years of employment as a software developer
Bachelor of Arts (B.A.) Neuroscience with minors in Mathematics and Chemistry, Bachelor of Arts (B.A.) Neuroscience with minors in Mathematics and Chemistry at Colorado College
Github Skills (8)
pytorch10
machine-learning10
python10
sc9
early-stopping9
deep-learning9
rna-seq9
seq9
Programming languages (9)
Github contributions (5)
scverse/scvi-tools
Feb 2021 - Jun 2021
Deep probabilistic analysis of single-cell and spatial omics data
Role in this project:
ML Engineer
ML EngineerContributions:12 reviews, 19 commits, 4 PRs in 3 months
Contributions summary:Nicholas primarily contributed to the SOLO model, adding features such as the ability to get scores for simulated doublets and modifying the handling of doublet ratios. They also implemented early stopping in the SOLO model, and incorporated changes related to training plans. Furthermore, the user made code formatting adjustments and incorporated updates from another repository.
hierarchicaldeep-generative-modelmixture-of-expertssingle-cell-rna-seqsingle-cell
calico/solo
Feb 2019 - Dec 2021
software to detect doublets
Contributions:4 releases, 15 reviews, 169 commits in 2 years 9 months
detectdoubletspython
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.