Parul Kudtarkar
ML & Genomics Researcher
20 years at the intersection of machine learning and genomics research. Currently the lead developer on multi-million dollar metabolic research at UC San Diego.
Technical expertise. Human empathy. Research that changes lives.
When not in the lab, you'll find me running trails, painting landscapes, or cooking for friends.
Work Experience
Common Metabolic Diseases Genome Atlas & PanKbase
Principal architect for cmdga.org ($57M FNIH AMP-CMD initiative) and data.pankbase.org ($10M NIH-funded), partnering with Amgen, Eli Lilly, Novo Nordisk and Pfizer. Executed single-cell multiomics analyses (ATAC-seq, RNA-seq) identifying disease-associated chromatin patterns for T1D and T2D. Built standardized multiomics pipelines and automated QC frameworks enabling researchers to analyze cohort-scale datasets. Architected scalable cloud solutions reducing costs while improving performance. Developed PerseusAI, integrating knowledge graphs, RAG and multi-agent LLMs for multiomics-driven biomarker discovery.
Echinobase
Built Echinobase and end-to-end sequence analysis for 7 echinoderm species. Built a comparative genomics platform serving 150+ labs worldwide. Integrated RNA-seq and ATAC-seq to infer transcriptional networks across 7 echinoderm species.
Cloud Computing for Comparative Genomics
Deployed distributed RSD algorithm on cloud platforms (Yahoo MapReduce, AWS ECS). Applied machine learning-based runtime prediction achieving 40% cost reduction, pioneering the first cloud-based comparative genomics system.
Intelligent Medical Devices
Built a regression-based in silico PCR algorithm for automated primer design within a Java diagnostic platform, improving accuracy across infectious disease, oncology and genetics applications
Education
Master of Science, Bioinformatics
Courses: Biochemistry, Molecular Biology, Programming, Database Management, Proteomics, Imaging, Ethics
Bachelor of Engineering, Biomedical Engineering
Courses: Medical Instrumentation, Anatomy, Embedded Systems, Hospital Management
MBA Certification
Courses: Business Strategy, Innovation, Venture Creation, Leadership
Business & Translational Training
NSF I-Corps: stakeholder interviews, product-market fit.
Business of Biotech: startup formation & IP strategy, funding strategy (VC, SBIR, IPO), drug development costs/timelines, business model design, market sizing (TAM/SAM/SOM).
Independent Research
Applying Evo2 and AlphaGenome to cancer-aging biology via generative sequence modeling and variant effect prediction. Developed the open-source AlphaGenome Coverage Explorer for community adoption of variant effect analyses.
Sorting My DNA — The Brief
A monthly, hand-curated deep dive tracking AI for life sciences, pharma & biotech across five key providers: Anthropic, OpenAI, Google DeepMind, NVIDIA, Arc Institute. Read and run firsthand; no AI writes the analysis.
Read the latest issue →Latest from the blog
View allGame Theory Didn't Change How I Think. It Named What I Was Already Doing.
Five principles from Dixit and Nalebuff's The Art of Strategy and how they already show up in genomic data infrastructure, research bets and model trust.
The cosmos of AI for science: everyone agreed on the plumbing, nobody's solved trust
Four scientific workbenches, one open skill standard and the validation layer nobody has built yet, the long read behind Sorting My DNA, Issue 1.
We Used to Optimize Code. Now We're Told to Just… Spend More?
A simple classification task, two approaches, and the coefficient problem hiding behind the spend-more-tokens culture.
Reviewing Experience
Editorial Board
Database: The Journal of Biological Databases and Curation
Journals Reviewed For
American Journal of Human Genetics, Bioinformatics, Evolutionary Bioinformatics, BMC Bioinformatics, PLOS Computational Biology, Journal of Endocrinology, Faculty of 1000, Diabetes
Conference Jury
Intel International Science and Engineering Fair (Computational Biology and Bioinformatics category), Chen Institute Symposium for AI Accelerated Science