I’m really excited to share our new pre-print “Functional protein mining with conformal guarantees”, with Seyone Chithrananda Anastasios Nikolas Angelopoulos Peter Hyungjun Yoon Michael Jordan Doudna Lab biorxiv.org/content/10.110… 🧵

beautiful day to be reminded i have no career in mathematics

I’m starting a company. An internet-scale dataset is created every day that can be used to cure diseases. ㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤ Yet decisions for developing new drugs use a tiny fraction of it. ㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤㅤ After years of building and investing in therapeutics

kubernetes is the most over engineered pile of hot garbage to ever cosplay as a legitimate contribution to software

traveling to boston: - i do sales now - do not have time to program computers - impeccable dress - copy of hatcher and janeway for morning reading at mit - seeking biotechnology executives

Congratulations to our partner Fluent BioSciences on their acquisition by Illumina. The future of single-cell technology is bright. bit.ly/3XYQdPk

Because many classes of analysis problems in biology involve searching, manipulating or otherwise moving around large amounts of file data, progress in systems programming will have a large impact on therapeutics development and basic biology research alike. But while the pace

do we all see whats happening

Latch has been building quietly with some incredible biotechs over the past year and will be shipping a lot of this product over the next 6 weeks. Disproportionate attention has been placed on bioinformatics workflows and GUIs. We have learned that structured metadata capture,

Lux Capital is running a Bio x ML Hackathon with Lux fam cos EvolutionaryScale and Enveda Biosciences from Oct 10-20! Build on top of latest foundation models like ESM3 (98B params, GPU access) & proprietary datasets to develop next-gen biology applications. Open globally:

I've got some exciting news... Year 2 of S3 is a go.

latch is a fun place to work

We should encourage more high quality blog posts to disseminate scientific progress but have a higher bar for methods and units. It is hard to critically evaluate this work. I do not even know what the other design methods are. It is not impossible one of the design methods used