Li Shen
Course Director Of Machine Learning For Biomedical Data Science
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolLi Shen is an AI scientist and academic leader with 14 years of experience applying machine learning and bioinformatics to biomedical data, currently directing the Machine Learning for Biomedical Data Science course and the MS in Biomedical Data Science at Mount Sinai. He has a strong track record of developing practical tools and analyses for large-scale next-generation sequencing and epigenomics, moving research methods into teachable and deployable workflows. His open-source contributions include enhancing hyperopt-sklearn—adding regressors, time-series lag selectors, and new models—demonstrating hands-on expertise in hyperparameter optimization within the scikit-learn ecosystem. Trained in computer engineering (PhD) and computer science (BS), he blends deep academic research with software engineering to improve disease diagnosis and make AI-driven biomedical tools more accessible. An often overlooked strength is his history of building web-based genomics applications and production-ready pipelines early in his career, bridging lab science and scalable software.
14 years of coding experience
16 years of employment as a software developer
B.S., Computer Science and Engineering, B.S., Computer Science and Engineering at Fudan UniversityPh.D., Computer Engineering, Ph.D., Computer Engineering at Nanyang Technological University
Github Skills (11)
data-analysis10
scikit10
hyperparameter-optimization10
machine-learning10
time-series10
python10
scikit-learn10
multiple-selection9
feature-selection9
variable-selection9
computer-engineering8
Programming languages (6)
Github contributions (5)
hyperopt/hyperopt-sklearn
Jun 2016 - Aug 2016
Hyper-parameter optimization for sklearn
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:23 commits, 2 PRs, 6 comments in 1 month
Contributions summary:Li focused on enhancing the hyperparameter optimization capabilities of the sklearn models within the `hyperopt-sklearn` repository. They added support for sklearn regressors, corrected search spaces, and fixed associated bugs. The contributions also included implementing time series lag selectors, refactoring code for better modularity, and adding new models such as AdaBoost and GradientBoosting. These changes improved the functionality and flexibility of the hyperparameter optimization process within the context of the scikit-learn ecosystem.
sklearnoptimizationhyper-parameter-optimizationmachine-learningparameter
shenlab-sinai/ngsplot
May 2012 - Jan 2022
Quick mining and visualization of NGS data by integrating genomic databases
Contributions:143 commits, 2 PRs, 27 pushes in 9 years 9 months
pythonminingngsgenomicsdatabases
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.