Sign in

johnboom.bsky.social

@johnboom.bsky.social
34 followers 86 following 0 posts

MD/PhD Student @Columbia. I develop AI tools to engineer biology and medicine.

PostsRepliesMedia
Reposted by @johnboom.bsky.social
Kyle Swanson, MD, FAANS, FCNS @kiswanson.medsky.network · 16/08/2025
Reading our medical school newsletter has become more depressing of late. As in the past, the articles highlight groundbreaking research done at Wisconsin, but now they have statements like “next steps…are on hold due to budget cuts at the National Institute of Health.
The ending to a news article from the University of Wisconsin school of medicine alumni magazine:

“Across the collaborating universities, tofacitinib quickly rendered the mice seizure-free. They stayed seizure-free for at least two months after the last dose. The mice also regained working memory.
Next steps toward testing the drug in humans are on hold due to budget cuts at the National Institutes of Health.”
1299
Reposted by @johnboom.bsky.social
NPR @npr.org · 03/08/2025
When public media disappears, so do the stories that bring us together. With federal funding eliminated, millions may lose their last trusted source of news and connection. If that matters to you, now’s the time to act. Donate: n.pr/458sOhq
460147465703
Reposted by @johnboom.bsky.social
Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 25/07/2025
In 1965, Margaret Dayhoff published the Atlas of Protein Sequence and Structure, which collated the 65 proteins whose amino acid sequences were then known. Inspired by that Atlas, today we are releasing the Dayhoff Atlas of protein sequence data and protein language models.
36628
Reposted by @johnboom.bsky.social
Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 25/07/2025
There's a lot more in the preprint! www.biorxiv.org/content/10.1...
biorxiv.org
The Dayhoff Atlas: scaling sequence diversity for improved protein generation
Modern biology is powered by the organization of biological information, a framework pioneered in 1965 by Margaret Dayhoff's Atlas of Protein Sequence and Structure. Databases descended from this comm...
182
Reposted by @johnboom.bsky.social
Pascal Notin @pascalnotin.bsky.social · 18/06/2025
🚨 New paper 🚨 RNA modeling just got its own Gym! 🏋️ Introducing RNAGym, large-scale benchmarks for RNA fitness and structure prediction. 🧵 1/9
14016
Reposted by @johnboom.bsky.social
BeccaCass @beccacass.bsky.social · 14/06/2025
183101232385
Reposted by @johnboom.bsky.social
Prof Jeffrey S Morris @jsm2334.bsky.social · 02/06/2025
Article in JAMA talking about the potential impact of the proposed focus on biomedical research funding based on current actions. jamanetwork.com/journals/jam...
jamanetwork.com
Cutting the NIH—The $8 Trillion Health Care Catastrophe
This JAMA Forum discusses the recent budget cuts to National Institutes of Health (NIH), the effects of these cuts on scientific research and health of individuals in the US, and the prospects for cha...
38748
Reposted by @johnboom.bsky.social
Your Local Epidemiologist @ylepidemiologist.bsky.social · 21/05/2025
1/ Yesterday, the FDA Commissioner, Marty Makary, and his new advisor, Vinay Prasad, unveiled a major shift in U.S. Covid-19 vaccine policy. Their bottom line: Going forward, #Covid-19vaccines will only be recommended for people over 65 or with at least one chronic condition. 🧵
95126
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 14/05/2025
So this is MAHA??? www.washingtonpost.com/climate-envi...
41829296
Reposted by @johnboom.bsky.social
Chaitanya K. Joshi @chaitjo.bsky.social · 05/05/2025
Equivariance is dead - long live equivariance? Scaling pure Transformers is the future of molecular generative models? I think its a lot more nuanced -- I tried to give some perspectives in my spotlight talk at #ICLR2025 AI4Mat Workshop last week Full video here: youtu.be/NiY4NLzemnU?...
youtu.be
All-atom Diffusion Transformers - Chaitanya K. Joshi - ICLR 2025 AI4Mat Spotlight
YouTube video by Chaitanya K. Joshi
192
Reposted by @johnboom.bsky.social
Randall Munroe @xkcd.com · 25/04/2025
PhD Timeline xkcd.com/3081
5865977420435
Reposted by @johnboom.bsky.social
C.H. Romatowski @chromatowski.bsky.social · 21/04/2025
This is incredibly cool: if you search for a condition that’s affected your family, the site returns stats on how much NIH has done for that disease, *and* a contact form for reaching out to tell your Members of Congress why you want to see them defend NIH. Pass it on!
4613403
Reposted by @johnboom.bsky.social
Kristen Panthagani, MD, PhD @kmpanthagani.bsky.social · 14/04/2025
A look back at what vaccines have done.
14623
Reposted by @johnboom.bsky.social
Eoin Higgins @eoinhiggins.bsky.social · 15/04/2025
MIT following Harvard's lead here
571328406677
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 13/04/2025
p-Tau217 is a breakthrough blood test that can predict and may help prevent Alzheimer's disease. erictopol.substack.com/p/the-breakt... Here's the rundown on it. Free, open-access.
erictopol.substack.com
The Breakthrough Blood Test for Alzheimer's Disease
The p-Tau217 Biomarker for Prediction and Prevention
20509165
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 09/04/2025
A high polygenic risk score (PRS) for screening prostate cancer was superior to a PSA test or MRI for detecting clinically significant disease (Gleason ≥7). A big step forward for supporting utility of PRS @nejm.org www.nejm.org/doi/full/10....
nejm.org
Assessment of a Polygenic Risk Score in Screening for Prostate Cancer | NEJM
The incidence of prostate cancer is increasing. Screening with an assay of prostate-specific antigen (PSA) has a high rate for false positive results. Genomewide association studies have identified...
217144
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 09/04/2025
When biomedical science and global health face existential threat, by @daltmann.bsky.social @angierasmussen.bsky.social @natrevimmunol.bsky.social www.nature.com/articles/s41... "The attack on some of us is an attack on all of us, and we must stand together."
4372127
Reposted by @johnboom.bsky.social
Randall Munroe @xkcd.com · 08/04/2025
Tariffs xkcd.com/3073
256311988706
Reposted by @johnboom.bsky.social
Fenit Nirappil @fenitn.bsky.social · 07/04/2025
Hours after posting in support of measles vaccines, RFK Jr. praised two doctors who have criticized vaccines and tout alternative treatments. One called the outbreak “God’s version of measles immunization.” The other was disciplined by medical regulators in 2003
915158
Reposted by @johnboom.bsky.social
ACLU @aclu.org · 02/04/2025
BREAKING: We're suing the National Institutes of Health over their politically-motivated purge of research grants. This is an unlawful attack on scientific progress that puts lives at risk.
126139962994
Reposted by @johnboom.bsky.social
Hank Green @hankgreen.bsky.social · 02/04/2025
Cory Booker just gave the longest speech in the history of Congress and concluded by apologizing to everyone who had to stay up all night keeping the chamber open and operating.
496489493897
Reposted by @johnboom.bsky.social
Ben Stiller @benstiller.redhour.com · 01/04/2025
Thank you Senator Cory Booker. This guy truly cares about the people he represents.
739585897246
Reposted by @johnboom.bsky.social
Pam Herd @pamherd.bsky.social · 30/03/2025
Trump has cut the NIH budget by more than half in defiance of Congressionally mandated appropriations for the agency. No comparison historically, not even the Great Recession. This is clearly not legal and Congress needs to address it.
Graph from the Washington Post showing declines in spending at NIH. New grants cut from 1 billion to around 400 million. Overall grants down from 4.5 billion to 2.4 billion.
231354548
Reposted by @johnboom.bsky.social
Jacek Debiec, MD, PhD, DPhil 🌎 🧠 @drjacekdebiec.bsky.social · 26/03/2025
"Grant termination letters went out last night to principal investigators of 29 awards made by the National Institute of Allergy and Infectious Diseases.., including 9 grants that were part of a program hoping to deliver antiviral drugs to prevent future pandemics." www.science.org/content/arti...
science.org
Saying ‘pandemic is over,’ NIH starts cutting COVID-19 research
Grant terminations halt research on improving vaccinations and preventing future pandemics
24021
Reposted by @johnboom.bsky.social
Gabriel Rocklin @grocklin.bsky.social · 26/03/2025
Small proteins can be more complex than they look! We know proteins fluctuate between different conformations- but by how much? How does it vary from protein to protein? Can highly stable domains have low stability segments? @ajrferrari.bsky.social experimentally tested >5,000 domains to find out!
48736
Reposted by @johnboom.bsky.social
Gina El Nesr @ginaelnesr.bsky.social · 20/03/2025
Protein function often depends on protein dynamics. To design proteins that function like natural ones, how do we predict their dynamics? @hkws.bsky.social and I are thrilled to share the first big, experimental datasets on protein dynamics and our new model: Dyna-1! 🧵
610538
Reposted by @johnboom.bsky.social
David A Knowles @davidaknowles.bsky.social · 11/03/2025
Wow. "NIH" canceled my co-mentored (with Dave Sulzer) PhD student's F31 funding. His work is on understanding the genetics and neuroscience of language learning disorders. F31 provides no indirect $ to Columbia, just pays his salary. Not that it should matter, but he's an American citizen. W.T.F.
21512215
Reposted by @johnboom.bsky.social
Prasad Jallepalli, MD, PhD @prasad.bsky.social · 11/03/2025
they’re treating medical research as some kind of favor to bestow, rather than what it is — arduous painstaking and unprofitable work done for all Americans this will slow Alzheimer’s and other brain research, not help it in net, patients will suffer
17835
Reposted by @johnboom.bsky.social
Sergey Ovchinnikov @sokrypton.org · 10/03/2025
First they came for Columbia...
0153
Reposted by @johnboom.bsky.social
Lindsay @schweetzy.bsky.social · 08/03/2025
I have a story very similar to Emily’s. I am the longest ever patient on a Cystic Fibrosis modulator drug, currently at 15 years. I went from annual hospitalizations and to no chronic cough anymore. I wrote my will at 22 and like Francis Collins mentioned yesterday, now I have a retirement plan.
1233
Reposted by @johnboom.bsky.social
Adam Rodman @adamrodmanmd.bsky.social · 07/03/2025
Medical education 🌶️🔥take: the threat of cognitive deskilling from genAI technologies is the #1 things medical educators need to be talking about right now.
2195
Reposted by @johnboom.bsky.social
Stand Up for Science! @standupforscience.net · 06/03/2025
WHERE WILL YOU BE TOMORROW?
Stand up for science flyer, happening on March 7th in DC & nationwide with more information at www.standupforscience2025.org
35792339
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 06/03/2025
In these unprecedented dark times for American life science and medical research (no less well beyond biomedicine), my coping mechanism is to laser focus on the unremitting and remarkable daily advances, and the fervent hope these will not be slowed or interrupted.
281280152
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 26/02/2025
The large clinical trial of a new Covid vaccine pill (not shot) was halted by RFK Jr www.aol.com/multimillion... The Covid nasal vaccines may be next up to be axed.
aol.com
Multimillion-dollar Biden-era COVID-19 vax project halted by Trump’s HHS
Department of Health and Human Services Secretary Robert F. Kennedy Jr. paused a $240 million contract to create a new coronavirus vaccine.
39246522866
Reposted by @johnboom.bsky.social
Science Magazine @science.org · 24/02/2025
“There’s going to be a missing age class of researchers that will reverberate for years.” scim.ag/3ERRLDo
scim.ag
U.S. early-career researchers struggling amid chaos
Uncertain funding, government firings, and distressed universities hit vulnerable groups especially hard
632326646
Reposted by @johnboom.bsky.social
Alisia Fadini @alisiafadini.bsky.social · 24/02/2025
Structural biology is in an era of dynamics & assemblies but turning raw experimental data into atomic models at scale remains challenging. @minhuanli.bsky.social and I present ROCKET🚀: an AlphaFold augmentation that integrates crystallographic and cryoEM/ET data with room for more! 1/14.
615568
Reposted by @johnboom.bsky.social
Randy Read 🇨🇦🇬🇧 @randyjread.bsky.social · 22/02/2025
Watch out for an upcoming bluetorial/tweetorial on this work from the amazing @alisiafadini.bsky.social! www.biorxiv.org/content/10.1...
biorxiv.org
AlphaFold as a Prior: Experimental Structure Determination Conditioned on a Pretrained Neural Network
Advances in machine learning have transformed structural biology, enabling swift and accurate prediction of protein structure from sequence. However, challenges persist in capturing sidechain packing,...
23214
Reposted by @johnboom.bsky.social
Diego del Alamo @delalamo.xyz · 19/02/2025
Not sure why Silicon Valley is so fixated on marketing AI to scientists as a tool for hypothesis generation? We have no problems generating hypotheses. We can crank out half-baked ideas just fine. You can help by pipetting, debugging unmaintained code, and troubleshooting weird unreported edge cases
Google AI co-scientist announcement saying: "We introduce AI co-scientist, a multi-agent AI system built with Gemini 2.0 as a virtual scientific collaborator to help scientists generate novel hypotheses and research proposals, and to accelerate the clock speed of scientific and biomedical discoveries."
128119
Reposted by @johnboom.bsky.social
Mohammed AlQuraishi @moalquraishi.bsky.social · 10/02/2025
It's long seemed that molecular biology is a natural home for ML interpretability research, given the maturity of human-constructed models of biological mechanisms—permitting direct comparison with their ML-derived counterparts—unlike vision and NLP. Our first foray below👇.
03815
Reposted by @johnboom.bsky.social
Diego del Alamo @delalamo.xyz · 10/02/2025
This might be the best paper on applying sparse autoencoders to protein language models. The authors identify how neural networks trained on amino acid sequences "discover" different features, some specific to individual protein families, other for substructures www.biorxiv.org/content/10.1...
A range of features identified from sparse autoencoders trained on different layers on ESM2-650M
24411
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 05/02/2025
The promise of a personalized (neoantigen) vaccine for treating cancer, as seen by immune response bolstering against renal cell carcinoma in a Phase 1 trial nature.com/articles/d41... nature.com/articles/s41...
nature.com
A neoantigen vaccine generates antitumour immunity in renal cell carcinoma - Nature
A phase I trial of a neoantigen-targeting personalized cancer vaccine led to durable and polyfunctional T cell responses and antitumour recognition, and was associated with no recurrence in patie...
732461
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 04/02/2025
New: The largest medical A.I. randomized controlled trial yet performed, enrolling >100,000 women undergoing mammography screening The use of AI led to 29% higher detection of cancer, no increase of false positives, and reduced workload compared with radiologists w/o AI thelancet.com/journals/lan...
thelancet.com
Screening performance and characteristics of breast cancer detected in the Mammography Screening with Artificial Intelligence trial (MASAI): a randomised, controlled, parallel-group, non-inferiority, ...
The findings suggest that AI contributes to the early detection of clinically relevant breast cancer and reduces screen-reading workload without increasing false positives.
381348346
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 03/02/2025
A new paper on microplastics accumulating in the brain was just published in Nature Medicine. I've reviewed the background and main findings in a new Ground Truths post erictopol.substack.com/p/the-microp...
19493180
Reposted by @johnboom.bsky.social
Nikki McCann Ramírez @nikkimcr.bsky.social · 29/01/2025
Brutal exchange between RFK Jr. and Sen. Bennet: Bennet: Did you say Lyme disease is a highly likely militarily engineered bioweapon? Kennedy: I probably did say that.
1683000709
Reposted by @johnboom.bsky.social
Eric Topol @erictopol.bsky.social · 20/01/2025
In a very large dataset of people with diabetes treated with GLP-1 drugs cf other medications, there were benefits seen for reduced clotting disorders, seizures, neurocognitive disorders (including Alzheimer's), by @zalaly.bsky.social and colleagues www.nature.com/articles/s41...
823556