neurodegeneration postdoc | prev: @umichmedicine (PhD) @oberlincollege (BA) | midwesterner on the west coast
Joined June 2018
- Tweets6.1K
- Following795
- Followers955
- Likes9.1K
Pinned Tweet
Super excited about my first, first-author being published the day after my defense! 🥳🥂✨
Keep an eye out for the second half of my PhD research, we're hard at work getting it wrapped up for submission 🙂
Congrats to @UMichCMB PhD student @synaptikate for her first author paper with @3268_AMP from @UMPhysiology published in @PLOSGenetics showing loss of FIC-1 dependent ampylation slows disease in a C.elegans model of polyglutamine toxicity doi.org/10.1371/journal.pgen…
stoked to be home after a 12 day freak hospitalization! gallstones, post-ERCP pancreatitis, renal failure, and a celiac artery occlusion all of the price of one admission!
in all seriousness I’m glad to have had no previous health issues & am expected to make a full recovery 🤞🏼
*desperately trying to awaken my 2014 macbook pro to dredge up my 20 page AP lit thesis paper on thematics of dementia and aging through the lens of King Lear*
Kate M. Van Pelt, PhD ✨ retweeted
Chemistry really is the final frontier. Or rather the first place where computationalists realize the universe is indeed not a computer.
Kate M. Van Pelt, PhD ✨ retweeted
Wherein a couple of tech bros get excited that Claude can propose exactly the same things that researchers did a few years ago
What is AI really capable of in bio?
To separate hype from reality, we spent 3 months working firsthand with @AnthropicAI's internal research model to see if it could create an experimental scorpion antivenom.
Introducing Citrini Therapeutics.
citriniresearch.com/p/citrin…
“we tried to use AI to do biology, & it was great at the all-computer part! unfortunately we were shocked and horrified to learn that experiments performed in a lab take time, even days or weeks! some are saying months! this sucks”
Where do you go next after reporting from the Strait of Hormuz? For the past three months, Citrini Research, an independent research firm, has been working with our team and an internal research model to see if they could use AI to create a new drug. What follows is an entertaining, candid, and humbling account of a group of motivated nonexperts (or “filthy casuals”, as Citrini would say) trying to tackle a real problem in human health with Claude.
We landed on scorpion neurotoxins, which kill over 3,000 people a year. Of the 211 designs we produced and tested, 17 met our criteria for a binder. None of the designs bound more than one toxin and none have been tested for neutralizing a toxin.
One of my favorite quotes from the piece is: “Our virtual biologist may have compressed a year's worth of work into a couple days, but biology works at the speed of life…Over two days, we watched Claude work through problems at a speed that was difficult to comprehend. For the next two months, we spent much of the time becoming familiar with laboratory turnaround times (This mostly involved sending memes in Slack).”
Kate M. Van Pelt, PhD ✨ retweeted
Anyone thinking that the labs are going to make serious, independent efforts in biotech is tech-brained and doesn't really understand the industry imo. Their supposed edge is in generating potential drug candidates, which is not and has never been the problem
Kate M. Van Pelt, PhD ✨ retweeted
We spent several months and hundreds of thousands of dollars trying to make a better antivenom. We didn't do it, but we had a lot of fun playing on the computer and ordering CROs around
checking my phone during a break at my job where i work as an actual molecular biologist in an actual lab studying the pathology of Alzheimer’s and other neurodegenerative diseases only to see another tech bio slop YC startup grift grace my timeline 😩😩😩
You can have Alzheimer's for 15 years and not know it.
We can finally slow it down. But only if we catch it early.
So we built the earliest test for it. Saccade (YC F26)
Readers added context they thought people might want to know
Under FDA rules (21 CFR 812.7), promotion of an investigational device as safe or effective is prohibited. This post violates FDA rules.
ecfr.gov/current/title-…
rebranding my skillset to better appease the new AI ruling class
Kate M. Van Pelt, PhD ✨ retweeted
Please stop calling the AI companies “labs”
They are not labs
They are venture-backed for-profit entities
Calling them “labs” really obscures what is happening
Kate M. Van Pelt, PhD ✨ retweeted
it’s hard to overstate the degree to which people (and people’s life’s work) are seen as mere grist for the mill of building better models to increment some fuck-ass benchmarks by these people, and it shows in the products
"Most teams in drug-discovery don’t receive target-organism verification until clinical trials."
I imagine if said teams were also trying to ID pesticides that kill worms vs drugs that treat diseases in human beings, they'd also get target-organism verification much quicker!
We built an 8000 sqft. high-throughput wet-lab in 30 days, to solve molecular discovery - starting with pesticides.
Most teams in drug-discovery don’t receive target-organism verification until clinical trials. Pesticides allow us to rapidly validate our model in the target organism directly. With the help of our high-throughput lab, we were able to generate compounds that killed a $13 billion pest, the Fall Armyworm.
We believe that the bitter lesson is coming for biology.
again, my issue w/ AI/bio is not that it’s impossible to revolutionize the field, but that I haven’t seen good evidence of AI companies doing this. spending tons of $ doesn’t guarantee a new cancer drug. we have no proof that the body can be modeled on a computer like a website
looking at open AI’s accomplishments in pure math and saying “naturally, we will next cure all human disease” makes you sound like you’re a moron with no appreciation for fields that require hands-on experimentation and validation with actual living things
