funding public datasets for health @FoundationOAI || writing/podcasts on https://xitter.twitterapi.xyz/t.co/QPTHsR3NoU || ex @noetik_ai @dyno_tx
San Francisco, CA
Joined March 2019
- Tweets6.1K
- Following968
- Followers18.3K
- Likes10K
owl retweeted
We used coding agents to automatically build baselines for 36 "AI for science" deep learning methods from Nature, Science, and Cell-family publications. These baselines recovered a median of ~95% of the score of the published method, and beat them in 33% of cases.
owl retweeted
Are you an unreasonably multi-disciplinary software engineer with deep biological/bioinformatics domain expertise?
Please apply for this: unc.peopleadmin.com/postings…
owl retweeted
I discussed this fairly extensively with @owl_posting on our podcast together, but I agree the "scale up existing assay" approach is quite flawed.
If we examine sequencing, imagine where the field would have stalled if we just tried to scale Sanger. This would have been somewhat helpful, but ultimately not transformative. Protein engineering is very reliant on data that comes from DNA sequencing, especially in the age of barcoded DNA libraries, but this would not have been possible even with 1000x scaled up Sanger. NGS broke open an entire industry's worth of applications that Sanger simply couldn't deliver.
This is why I find the fully automated labs concept quite fraught. Sure, it helps you commodify particular assays, but you just get leap-frogged whenever someone creates the next NGS. Obviously you need both, but right now we're getting 95% of one and 5% of the other, should be much closer to 50-50.
And obviously listen to our interview on @corememory open.spotify.com/episode/5Nf…
owl retweeted
@iskander and I are hiring a senior experimental scientist to work with us on our project funded by Open AI Foundation to discover tumor antigens, tumor antigen-associated T cell receptors, and assess TCR performance via functional studies of TCR-engineered T cells. Apply here ( unc.peopleadmin.com/postings… ) if interested!
owl retweeted
okay I’m just going to rapid fire this because I’ve gotta sleep and also this is just like talking as if you were a close friend:
-like half of bio is ~wrong, like the problem is us not AI- misleading in vitro models, misleading murine models and then all of our “rules” are highly context dependent and not applicable in at least 20% of in vivo contexts
-also everything is baked with people and politics which leads to certain narratives/models in the paradigm sense winning when they maybe shouldn’t- publishing is beyond corrupt, holding people’s livelihood ransom based on whether they generate positive results and hide the negative is just a bad system
-lit search synthesis by AI is therefore not at all close to god, just sort of a condensation of issues
-but it’s still good and bad- like astra max got thymic involution at peak human adolescence wrong on monday but I’ll have grad students use it for questions I don’t want to be bugged with
-protein folding tells you v little abt function- like timing, location, ptms, nearby molecular species, idrs, local environment etc
-no one is building a model that integrates different echelons of regulation for actual in vivo tissues
-everyone needs to undiscover the cell/discover tissues and organ systems and overall interacting physiology
-human data should be step 1 in everything
-idk as far as experimental stuff/basic research gaps- automation and scaling aren’t issues it’s just like if your goal is solving human health what are you starting at? I would love for RNA biology to be solved first- I’m still biased towards building an actual causative model of life
-I think this shit could all be way more variable based on the individual than anyone is ready to deal with but everyone violently disagrees with me on that- but like my baseline basophil count is in the CML range and I’m am biased as a weirdo
-I hate non-durable single target based therapies in oncology for solid tumors with a passion and in my schizophrenic head I’d rather have biological understandings that allowed us to develop actual curative treatments
-to be positive ML based DNA encoded libraries are absolutely sick and I have new molecular glues in like the picomolar range which means tox will probably be an issue but yolo
owl retweeted
Maybe controversial: the conversation about scientific bottlenecks is overfocused on automation. New measurement technologies deserve more attention. You could automate an assay that needs an entire facility – or you could REINVENT the assay so that it fits into just a few tubes.
owl retweeted
Five major databases of human surface proteins agree on only 188 of them. So we had Claude read the literature instead. Today @deliverome is releasing an open atlas of the accessible human surfaceome, with claims traced directly to quotes from their source 🎯
owl retweeted
Our first paper is out! An open, evidence-backed atlas of the accessible human surfaceome. Explore every protein's surface verdict and the literature quotes behind it 👇🎯
Five major databases of human surface proteins agree on only 188 of them. So we had Claude read the literature instead. Today @deliverome is releasing an open atlas of the accessible human surfaceome, with claims traced directly to quotes from their source 🎯
owl retweeted
Our newest book is finally here!
Making the Modern Laboratory is a spectacular 504-page hardcover that tells the story of everything in the research laboratory and how it came to be, from pipettes to heat-resistant glass to microscopes and more.
It features dozens of articles (most of which will never appear in print), 100+ full-color images, and original writing from 36 authors. It's printed on Arena Natural Rough paper from Fedrigoni. These books are THICC and would make a great gift for both the science-curious and the working scientist. :)
We have spent the last year working on this project. It has been an insane labor of love. The best way to support our independent science journalism is to buy a copy. <3
Pre-order for $49, with free shipping: press.asimov.com/articles/mo…
owl retweeted
In light of @KarlDeisseroth’s well-deserved Nobel, now is a better time than ever to check out my guest piece on optogenetics with @owl_posting! With the new influx of hype I’m excited to see if it does in fact change the world in the near future :)
owlposting.com/p/optogenetic…
owl retweeted
Biosecurity is too important for security theater.
In a quick test with Raygun, we found that DeepMind's SynthIDBio watermark signal could be washed out while preserving the predicted structure.
We don’t think protein sequence watermarks buy much biosecurity.
owl retweeted
The position isn’t live yet but we need a GMP director for personalized scale RNA therapeutics manufacturing. If you’re in NC and have relevant industry experience, let’s talk!
owl retweeted
The OpenAI Foundation — the charity arm of the AI behemoth — has so far committed to giving away at least $25 billion. The foundation's life sciences lead speaks to Nature about its ambitions to cure disease.
go.nature.com/47pvvLZ
owl retweeted
Another great piece by @owl_posting.
Organoids can offer a lot, but there’s a lot of complexity to make them very useful. This comes from the complexity of Alzheimer’s itself, and the challenges with organoids themselves with the nuances of molecular biology.
Are organoids useful for Alzheimer’s research?
(3.8k words, 17 minutes reading time)
owlposting.com/p/are-organoi…
the final organoid essay; a case study into how useful organoids have been for one of the hardest-to-address diseases that exist today
also: i moved to san francisco!
owl retweeted
Great thoughts from @owl_posting on organoids as models for Alzehimers.
Raises the more important general point that "all models are wrong but some are useful" and more importantly some are useful in particular ways even as they are wrong in other ways. Often in drug discovery it's unclear if a model is useful. Ideally it would discriminate between successful and unsuccseful drug but you don't know that until years later, if ever. And then even in cases where we are pretty sure a model system is useful (maybe it's predicting downstream advancement well), you often aren't sure why.
With so many ways to be wrong, you can always take the negative view and point out what's almost certainly wrong, or you can try to find better things and see how they work out.
Are organoids useful for Alzheimer’s research?
(3.8k words, 17 minutes reading time)
owlposting.com/p/are-organoi…
the final organoid essay; a case study into how useful organoids have been for one of the hardest-to-address diseases that exist today
also: i moved to san francisco!
owl retweeted
Last year, one of the best essays on endometriosis from a biotech and discovery perspective was published by Abhishaike Mahajan, known for @owl_posting. We interviewed him to learn what his most interesting findings were when researching this condition.
How massively underfunded it is, considering its prognosis and DALYs (a standard measure used to calculate the total burden of disease and early death in a population), came to mind.
Read his full essay and interview here:
athenabio.org/collection/an-…
owl retweeted
Great series! Ended with a bang.
Are organoids useful for Alzheimer’s research?
(3.8k words, 17 minutes reading time)
owlposting.com/p/are-organoi…
the final organoid essay; a case study into how useful organoids have been for one of the hardest-to-address diseases that exist today
also: i moved to san francisco!
owl retweeted
science advances are typically preceded by measurement advances. the closer the lab model is to the underlying phenomenon the faster we typically progress. this is a good essay laying out that logic for organoids for alzheimers in particular but i think applies to many brain diseases
Are organoids useful for Alzheimer’s research?
(3.8k words, 17 minutes reading time)
owlposting.com/p/are-organoi…
the final organoid essay; a case study into how useful organoids have been for one of the hardest-to-address diseases that exist today
also: i moved to san francisco!
owl retweeted
Here's more on our initial strategy behind these grants, and other grants we're investigating in Public Data for Health, that may be of interest to researchers:
Our starting hypotheses for areas OpenAI Foundation support can be most useful are: connected data, scarce data, and direct data. Datasets we fund will usually have one or two of these properties, described in more detail in the next tweets, and in rare cases will share all three properties.
Across all datasets, we believe making data broadly accessible, while ensuring privacy whenever that relates to patient data, will become increasingly important. This will allow researchers to build on each other’s work, and scientific progress to emerge from unexpected places.
At the OpenAI Foundation, we believe breakthroughs against disease will come from pairing intelligence with more observations of the world – in other words, more data.
Today, we're announcing over $125M in grants, launching our second science program:
openaifoundation.org/news/pu…
