Genomics and AI on Cloud Foundry
summary
Claims using machine learning to prioritize wet‑lab experiments cut years and save millions by searching an n‑dimensional protocol space where wet‑lab experiments cost $10k–$100k and most fail from protocol variables. Work runs Python and Jupyter notebooks on Cloud Foundry against petabytes of genomic data mapped into a petabyte data browser that connects visualization and analysis tools. Concrete biology aims include partial reprogramming with Yamanaka factors as a route to rejuvenation; regulatory timeline estimates roughly a decade.
AI-written summary · about
chapters (9)
- 0:00Introduction and motivation
- 3:49Machine learning basics
- 8:21Genomics and regenerative health
- 13:58Data browser in genomics
- 16:07Machine learning in wet lab experiments
- 17:53Biological age reversal research
- 20:40Timeline and regulatory process
- 21:43Happiness project and micro RNA
- 22:25Ravi River Child Wellness Project
related talks
10mGenesis Final Round - Drylab AI
21mMachine Learning and Microbiology in the Cloud Through Ray
42mHow Novel Compute Technology Transforms Life Science Research
06mReproducible Genome-Wide Analysis With Cloud Computing
22mOperationalising Data Science on Cloud Foundry
22mReimaging Healthcare
14mBig data, AI, the genome, and everything
06mGenesis Startup Competition Pitch - Drylab AI