NOTHING feels as good as not knowing how to solve a problem and then obsessively locking in and thinking about it and finding a few promising paths

I’ve been obsessed with KLK2 as a prostate cancer target KLK2 was known to be a great diagnostic marker for 2 decades (~1990 - 2010s) … but its therapeutic potential was ignored until @JNJNews started building a KLK2 empire in the last decade open.substack.com/pub/katkaj…

(asking for a friend) What equity would you give a founding scientist at a biotech co? What’s industry standard? (Boston)

Personalized medicine (in nof1 world especially) is reinventing which IP is actually valuable. The asset itself doesn’t really have a value prop like it would in off the shelf drugs The thing that matters is the process and ability to run the pipeline fast & cost effectively

And to the latter point - very hard to make things in biotech cheaply (and quickly) at small scale

Distance running is such a beautiful way to train your mind and body to do difficult things

And even when you hit a PR you can very easily be humbled the next day Just an incredible way to learn resilience and hard work Throw in some races and you also get a taste of competition Incredible hobby

Frustrating part of AI models for bio is lack of clarity in what types of data we should be collecting and the sampling rate that provides biological significance. If you look at autonomous driving, progress in that field wasn’t just due to algorithms. Companies had a lot of continuous training data. Imagine training a self driving car with some snapshots from intersections. This is close to the types of data we currently have in biology (sparse snapshots and yet ppl are trying to dynamic systems). Need more/different types of data (more tech?tools?), better sampling rate in many cases (including more informed ways of modeling it).