Ruslan Rust

Asst Professor @USC with interest in the brain, BBB, stem cells, AI + what can go wrong after stroke & AD. Alum @ETH_en. Fixing science @ResearchHub

[Anshul Kundaje @anshulkundaje]

Very excited to see cell state conditioned sequence-to-omics models going mainstream. And as always @adamgayoso @Avsecz & the DeepMind genomics team have crushed it. 1/

[Yuanhao Qu @YuanhaoQ]

One of the biggest challenges we’re tackling at Phylo is aligning LLMs with the standards of science that requires grounding claims with evidence and acknowledging uncertainties.

In our latest research, we identified a steering vector for LLM that substantially reduces hallucination/overclaim behaviors in our evaluations.

[Renaissance Philanthropy @RenPhilanthropy]

We saw more outstanding projects than one challenge could support – the top proposals have already been through a rigorous review and are ready to fund, so we're now working to bring in additional funders to back them.

Congratulations to all recipients – meet them here: https://t.co/w5kqN4aQOd

Interested in funding similar projects? Get in touch at [email protected].

[Ruslan Rust @rust_ruslan]

@RetractionWatch thank you for highlighting our work 🙏

[Ruslan Rust @rust_ruslan]

Generating interesting scientific ideas using knowledge graphs and LLMs: Evaluations with 100 research group leaders | PNAS https://t.co/vJgOSF4g16

[Ruslan Rust @rust_ruslan]

Great article by @andcyang lab in @CellCellPress showing that the blood-brain barrier selectively delivers plasma proteins to distinct brain cell types.

Increasing liver-derived APOA1 improved synaptic and behavioral outcomes in an Alzheimer’s mouse model.

[Ruslan Rust @rust_ruslan]

@ResearchHubF @blockchain Great news! 👏

[ResearchHub Foundation @ResearchHubF]

ResearchCoin ($RSC) is now live on @blockchain.

More ways to get RSC means more people funding science.

Put your RSC into ResearchHub Endowments and it continuously funds scientific research.

[Blockchain @blockchain]

What if scientific research could move better and faster?

Enter @ResearchHub. A market for the best science.

$RSC rewards the work that advances science — funding it, reviewing it, replicating it, discussing it.

Now available in your Blockchain Trading Account.

[Ruslan Rust @rust_ruslan]

@Aging_Scientist @AnthropicAI Doing it right now! For reducing the refusals you'd need to go through this application: https://t.co/nGQkoCVgyM

[Ruslan Rust @rust_ruslan]

Really proud that our lab is now officially part of @AnthropicAI "AI for Science" program!

With credits provided by Anthropic, we can now massively scale up our computational work.

We will use them for many exciting projects, including foundation models for stroke multi-omics that feed into a closed-loop drug discovery approach in human tissue, and much much more. 🧑‍💻🧬🧠

[Ruslan Rust @rust_ruslan]

@thepaulthomson Open AI reviewer (great name?) for every paper on PubMed/preprint servers. Free for everyone, so any reader can see how well the evidence supports each claim.

[David Lang @davidtlang]

BIG NEWS!

For the past few years, we've given scientists budgets so they can fund their peers with small, fast grants. Today, we're going bigger.

We're opening up a call to find and fund emerging "field builders"—people with the ambition and curiosity to kickstart a new field of science and technology. You'll get a budget of $70,000 to regrant (up to $10,000) out to projects and ideas and join a community of explorers.

Do you have an idea for a new field of science that *should* exist? Please apply!

[Ruslan Rust @rust_ruslan]

@askalphaxiv I wonder how the model token distribution would be for academic research around the globe @ResearchHub

[Keck School of Medicine of USC @KECKSchool_USC]

Can stem cells treat a heart attack? A $6.9 million @CIRMnews grant will fund Chuck Murry, MD, PhD, at @USCStemCell at Keck School of Medicine of @USC to prepare a stem cell-derived heart therapy for a trial targeted for late 2027.

https://t.co/o3PjO6HfjX

[Nature Methods @naturemethods]

A benchmark study analyzes the performance of deep learning tools for de novo sequencing of peptides from mass spectra.

https://t.co/fpCbpzy8Cs

[Ruslan Rust @rust_ruslan]

Check our work featured by @NewsfromScience 👇

[News from Science @NewsfromScience]

For clinical trials of tests and treatments, accuracy can be a matter of life or death; these studies directly inform medical practice, after all.

A new tool may help make sure the studies are sound: #AI.

In a test of whether 15 LLMs could identify methodological errors deliberately inserted into clinical research papers, one spotted nearly all the planted errors, and even the worst LLM performer found about half. Human reviewers found only one-quarter.

Learn more: https://t.co/OwnbzZzhy7

[Ash Paul @pash22]

AI beats scientists at finding errors in clinical research papers: New findings by @dominikus_brian et al demonstrate AI’s aptitude for identifying technical flaws in studies where medical decisions are on the line via @JeffreyBrainard
https://t.co/oBOaagNhAN

[antisense. @razoralign]

Human Development Multiomic Atlas: Multiomics and deep learning dissect regulatory syntax in human development https://t.co/EudjtUGs0n

[Hao Yin @HaoYin20]

Appreciate the coverage of Science News @NewsfromScience for our preprints on the capacity of LLMs to detect methodological errors in clinical trials 😆

https://t.co/O8pKt4gDXi

This great project led by Dr. Ruslan Rust @rust_ruslan now has its 2nd version, which tests over 58 🤠 randomized clinical trials published in 2026

Large language models detect methodological errors that human peer review misses in clinical trials

https://t.co/q8BdkHNKtt