Asst Prof @USC with interest in the brain, BBB, stem cells, AI what can go wrong after stroke & AD. Alum @ETH_en. Fixing science @ResearchHub
Joined June 2019
- Tweets 3,944
- Following 2,020
- Followers 3,095
- Likes 7,775
641 Photos and videos
I just funded: Development Of Broad-Spectrum Antiviral Inhibitors To Target Pathogens Of Pandemic Concern on ResearchHub! researchhub.com/proposal/323…
2
211
Very interesting! @EvidenceOpen might be worth to contact the journal and post a rebuttal to the paper in @NatureMedicine. Also shows how important a potential COI and public peer reviews are
Rigorous evaluation of medical AI is good for everyone, and we welcome it. Counter to a half-dozen independent studies from institutions such as the Mayo Clinic that were highly positive on OpenEvidence—a lone paper now purports to show that generalized AI beats specialized clinical AI (@UpToDate, @EvidenceOpen). The paper has a massive undisclosed conflict of interest and irredeemable methodological flaws.
Behind the scenes: The study authors run a competing in-house medical AI at their hospital, and asked OpenEvidence for an API to power it — including rights to build a "competing product" with OpenEvidence's own API. OpenEvidence declined. Then, this paper coincidentally appeared.
Point-by-point, looking closely at the datasets used in the study, the disingenuous and fatal flaws become immediately apparent 🧵.
1
1
5
677
Ruslan Rust retweeted
SenCat: Cataloging human cell senescence through multi-omic profiling of multiple senescent primary cell types
cell.com/molecular-cell/full…
5
12
791
Transcriptional analyses identify pericyte-centered signaling programs altered by sex and brain region in Alzheimer’s Disease
nature.com/articles/s42003-0…
2
5
14
823
Ruslan Rust retweeted
Jun 12
Only 48 hours after its publication, our new Emerald Bay dataset is the top trending biological dataset on @huggingface. Can't wait to see what people will do with it.
2
13
49
3,057
Ruslan Rust retweeted
1 modular R01 in 1995:
- Buy latest equipment
- 7 postdocs
- 3 grad students
- Lab manager
- 2 technicians
- Tenure
- Cover good % salary
1 modular R01 in 2026:
- 1 postdoc
- Consumables
$1M in 1995:
- Buy forever home
- Raise 3 kids
- Stay at home spouse
- Retire early
$1M in 2026:
5
23
152
25,844
Jun 13
Engineered Pericyte‐Targeted Extracellular Vesicles Protect Against Hypoperfusion‐Induced Cognitive Impairment and Vascular Demyelination - Shen - 2026 - Journal of Extracellular Vesicles - Wiley Online Library isevjournals.onlinelibrary.w…
6
10
586
Ruslan Rust retweeted
Jun 12
Hard to think of another chart in biology more misunderstood and misappropriated
6
12
156
33,762
Ruslan Rust retweeted
Jun 12
Medicine discovers the bitter lesson: frontier LLMs (here GPT 5.2, Opus 4.6, Gemini 3.1) outperform specialized "clinical AI" (e.g. OpenEvidence) in a blind test.
Even funnier that hospital IT are more likely to approve the *specialized* versions despite them being worse.
Jun 12
For medical information, general AI frontier models (Google, OpenAI, Anthropic) outperformed specialized @EvidenceOpen and @UpToDate as assessed by 12 US clinicians, randomized and blinded to which model and extensive testing/benchmarks. This was not anticipated. @NatureMedicine
nature.com/articles/s41591-0…
30
166
1,152
181,394
Ruslan Rust retweeted
New funding opportunity on @ResearchHub: 💰
$5K for complexity science applied to real-world health systems.
Agent-based models, network analysis, systems dynamics — if you're thinking beyond linear causality in public health, this one's for you.
Open to all career stages, internationally.
Apply here: researchhub.com/grant/32295
1
5
34
1,596
I read a lot of preprints and read them again in their peer-reviewed versions.
Most of the time, I sense little substantive difference in the major conclusions/claims.
Is it my subjective feeling?🤔 Am I such a sloppy reader that I ignore essential improvements?🤪
To work with @rust_ruslan & Claude, we will find quantitative evidence for the content evolution from preprints to peer-reviewed publications.
Take a look at our preregistered report on @ResearchHub
Tracking claim changes from preprint to publication across biomedical studies using large language models
researchhub.com/proposal/323…
Jun 12
Some scientists still don't trust preprints (crazy right?).
But how much do claims really change from preprint to published paper? We plan using LLMs @claudeai @AnthropicAI to track exactly that across every single biomedical study published in the last 7 years. Fun new project with @HaoYin20 🚀
Here our preregistration. We expect results in 1-3 weeks after funding completion: researchhub.com/proposal/323…
2
8
24
3,446
Jun 12
Some scientists still don't trust preprints (crazy right?).
But how much do claims really change from preprint to published paper? We plan using LLMs @claudeai @AnthropicAI to track exactly that across every single biomedical study published in the last 7 years. Fun new project with @HaoYin20 🚀
Here our preregistration. We expect results in 1-3 weeks after funding completion: researchhub.com/proposal/323…
2
4
19
4,658
Jun 12
Ok this is crazy, the project was fully funded within less than 5 minutes 😀 Might be the fastest turnaround from proposal to funding ever.
Thank you @dr_benrein @IliaRasskazov. We will start working tomorrow! 🙏
1
5
353
Jun 11
😅
Calling all researchers using Anthropic's AI model Claude: how are you using the new Claude Fable 5 model in your research?
We want to hear about the most impressive things it's built for your research projects or left you asking what the fuss is all about. Can it do things you couldn't do before? Let us know.
5
509
Jun 11
😅 that’s insane
Jun 10
I’ve officially resigned as Associate Editor for Frontiers in Systems Neuroscience (part of @FrontNeurosci). It used to be a reputable journal, but became a case study in how forced automation destroys academic integrity. 👇
3
1,130
Jun 11
A role for nucleolin in functional improvement in stroke: iScience cell.com/iscience/fulltext/S…
2
8
654
Ruslan Rust retweeted
Jun 10
Arguably the most boring step in genomics is the first one: normalization. Settled science. Scale log. Move on.
Except that here's been a huge blind spot in the field. And it matters for AIxBio. A 🧵about what I think may be one of the most important papers I've written. 1/
18
147
669
113,736
SIRT6 T294A
An evolutionary longevity variant
"SIRT6 C-terminal phosphorylation is strongly correlated with species maximum lifespan"
"C-terminal phosphorylation enhances the interaction of SIRT6 with PARP1 thereby conferring enhanced oxidative stress resistance"
DYRK/HIPK-dependent
MAPK/GSK3/CDK-independent
Whale!!🐳 I want to study whale arteriolar/capillary mural cells!😆
Vera Gorbunova lab bioRxiv 2026
biorxiv.org/content/10.64898…
1
8
24
1,211