owl
@owlposting1.bsky.social
ml eng at dyno therapeutics. i write about bio/ml at http://owlposting.com
Wonderful deep-dive into the always compelling, always confusing world of therapeutic cancer vaccines by @owlposting1.bsky.social: "How to build a cancer vaccine, and whether they will work this time" www.owlposting.com/p/how-to-bui...
How to build a cancer vaccine, and whether they will work this time
8.4k words, 38 minutes reading time
owlposting.com
Excellent, comprehensive rundown of the state of bio lab automation by @owlposting1.bsky.social In retrospect, it's an important topic that has had almost zero discussion over the years! A fun surprise to see some decade-old(!) work show up in there too. www.owlposting.com/p/heuristics...
The truth behind the 2026 J.P. Morgan Healthcare Conference www.owlposting.com/p/the-truth-... happy JPM to all those who celebrate! wrote up some notes and observations for the week. lots to look forward to
The truth behind the 2026 J.P. Morgan Healthcare Conference
2.8k words, 13 minutes reading time
owlposting.com
essay tomorrow morning over cancer, and the role machine intelligence will play in how we treat the disease subscribe to owlposting.com to read the first article that i literally could not have produced had i not been around oncology researchers for the last 5 months
Joining Noetik www.owlposting.com/p/joining-no... after a restful month of funemployment, i joined a biotech startup called Noetik last week. this essay explains my current beliefs about the ML-bio field, why I joined Noetik, and what they are working on 2.8k words, 14 minutes reading time
Joining Noetik
2.8k words, 14 minutes reading time
owlposting.com
I read this cool piece by @owlposting1.bsky.social on endometriosis on @scientificdiscovery.dev's recommendation www.owlposting.com/p/endometrio... One point is that endometriosis is very common, 10% of women according to the WHO. Which makes the paltry research (funding) even more galling.
Endometriosis is an incredibly interesting disease
5k words, 23 minutes reading time
owlposting.com
Endometriosis is an incredibly interesting disease 5k words, 23 minutes reading time covering one of the strangest conditions ive ever heard about link: www.owlposting.com/p/endometrio...
Endometriosis is an incredibly interesting disease
5k words, 23 minutes reading time
owlposting.com
What could Alphafold 4 look like? (Sergey Ovchinnikov, Ep #3) Substack: www.owlposting.com/p/what-could... Youtube: youtu.be/6_RFXNxy62c Spotify: open.spotify.com/episode/0wPs... Apple Podcasts: podcasts.apple.com/us/podcast/w... Transcript: www.owlposting.com/p/what-could...
What could Alphafold 4 look like? (Sergey Ovchinnikov, Ep #3)
2 hours listening time
owlposting.com
owl@owlposting1.bsky.social · last yr.tomorrow!
Endorse. @owlposting1.bsky.social is a great addition to the biotech blogosphere.
Saloni@scientificdiscovery.dev · last yr.This was such an interesting post! It's awesome how much bio and biotech blogging are happening now and this is one of my newest favourites.
This was such an interesting post! It's awesome how much bio and biotech blogging are happening now and this is one of my newest favourites.
What happened to pathology AI companies?
4k words, 19 minutes reading time
owlposting.com
new posters of @rowan, a molecular simulation company link to shop: owlpostingshop.com/products/rowan
www.owlposting.com/p/roundup-1-... some announcements, some links, and some job listings!
Roundup #1 (announcements, links, and jobs)
1.2k words, 6 minutes reading time
owlposting.com
Is there such a thing as an impossible protein? www.owlposting.com/p/is-there-s... tldr: no, but yes, but no, but yes tiny article today 1.3k words, 7 minute reading time
Is there such a thing as an impossible protein?
1.3k words, 7 minutes reading time
owlposting.com
Better antibodies by engineering targets, not engineering antibodies (Nabla Bio) www.owlposting.com/p/better-ant... another startup coverage article! the first one ive written over an antibody startup the interesting part about them? how they think about targets, not antibodies
Better antibodies by engineering targets, not engineering antibodies (Nabla Bio)
4k words, 19 minutes reading time
owlposting.com
spent the holiday making biology-themed posters here are my favorites
A primer on ML in cryo-electron microscopy (cryo-EM) www.owlposting.com/p/a-primer-o... confused about cryo-EM??? i explain why people do it, how it works and some ML problems in the area via explanations of 3 ellen zhong papers 7.9k words, 36 minutes reading time. ToC in thread❄️
A primer on machine learning in cryo-electron microscopy (cryo-EM)
7.9k words, 36 minutes reading time
owlposting.com
Can o1-preview find major mistakes amongst 59 NeurIPS '24 MLSB papers? www.owlposting.com/p/can-o1-pre... i feed (nearly) an entire workshops worth of papers through o1, and ask if there are any major scientific errors amongst them. it says there are 3. afaict, none of the 3 have errors
Can o1-preview find major mistakes amongst 59 NeurIPS '24 MLSB papers?
1.9k words, 9 minute reading time
owlposting.com
A retrospective on filming a science podcast www.owlposting.com/p/a-retrospe... its been about a week since i released my first podcast. i want to document the whole process and why i did it and how i did it and if ill do it again (i will) 2.5k words, 12 minutes reading time
A retrospective on filming a science podcast
2.5k words, 12 minutes reading time
owlposting.com
Can AI improve the current state of molecular simulation? www.owlposting.com/p/can-ai-imp... in my first podcast, I spend 2 hours interviewing Corin Wagen and Ari Wagen, two brothers who are building the next generation of molecular simulation for drug discovery and material science
Can AI improve the current state of molecular simulation? (Corin & Ari Wagen, Ep #1)
2.1 hours listening time
owlposting.com
i have discovered long term transcriptomic alterations in the scRNA-seq data of neurons of mice who have been exposed to five hour long podcasts. i dont know what this means but the paper is coming out in Nature tomorrow (auto accept). i will not be sharing the data
weird case of synchronicity where 4 independent people have published mechanistic interpretability work on biology models all in the same month, where there was basically nothing prior to them
posting will be a little delayed for a bit. winter is tough between being mildly sick for the last 1.5 weeks and doing two very ambitious blog projects at the same time, i think sticking to my an-essay-every-two-weeks timeline will not bring me Joy
very little posting going on at bluesky. there is culture yet to be written, meta’s yet to be established. will you stake your own claim on this untamed frontier, anon? or will you wait for someone else
Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging www.owlposting.com/p/why-recurs... After over a decade,Recursion Pharmaceuticals changed its primary assay. Why is that? I answer that question over 5.6k words (26 minutes to read) first journalism-y piece!
Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging
5.7k words, 26 minutes reading time
owlposting.com
predictive toxicology is one of those areas where ML was *supposed* to help, but it never did. why not? i wrote about it www.owlposting.com/p/a-primer-o...
A primer on why computational predictive toxicology is hard
3.4k words, 16 minutes reading time
owlposting.com
expanding my posting presence to bluesky i write a lot! here is a technical primer on how ML in antibody engineering works: www.owlposting.com/p/a-primer-o...
A primer on ML in antibody engineering
7.4k words, 34 minutes reading time
owlposting.com
