Russell Rockne

Read the latest articles in the Cancer Research special series, Driving Cancer Discoveries with Computational Research, Data Science, and Machine Learning/AI: buff.ly/EjkhVK5

I’m going to halve my publication output. You should consider slow science, too If we don’t slow down, the research enterprise is going to crash, argues Adrian Barnett.

"I think the current publication system is a runaway train that is headed for disaster. Without adequate scrutiny, the overall quality of research seems to be degrading."

go.nature.com/4b8r0Zq

Brain food on our brain drainage system to help keep you healthy, with @jonykipnis.bsky.social
erictopol.substack.com/p/how-our-br...

Mathematics is hard for mathematicians to understand too At a recent conference on mathematics in the age of automated proofs, mathematician and Fields Medalist Akshay Venkatesh presented “How do we talk to our students about AI?'' He quoted an email he'd r...

Is the point of mathematical research to know *what* is true or to know *why* it's true? Emily Riehl lays out a strong argument - and what it has to do with AI - along great advice for the field in @science.org
www.science.org/doi/10.1126/...

@dfrankhouser.bsky.social

Finally, someone has solved a real problem with AI! No more having to take a paper in the format for a journal that rejected you, and reformat it for a new journal. Well done!! formatmypaper.com

Agitator?! 🤣 is there a bone to pick with someone or some field?

A+ level UK tour Paul!

A real challenge for science. Some good suggestions here but no silver bullet answer

Slide designs that present themselves: The assertion–evidence template Your slides are not your talk.

A simple design framework that will massively improve your slides and your public speaking
clauswilke.substack.com/p/slides-tha...

No way! I just may

Physicists disagree wildly on what quantum mechanics says about reality, Nature survey shows Nature - First major attempt to chart researchers’ views finds interpretations in conflict.

Quantum mechanics is one of the most successful theories in science — and makes much of modern life possible

go.nature.com/4mjXRg3

Abstract submission is now open for #MathOnco25! So please go ahead and submit asap to have a chance of getting one of our travel awards: mathematical-oncology.org/mathonco25

I called this back in February 🤞

Cool, congrats Paul!!

A packed opening plenary from one of the @smbmathbiology.bsky.social Canadian giants! Mark Lewis “One equation helps solve three paradoxes in the spatial ecology of predators and prey” Mark also wins the prestigious Akira Okubo Prize!! #SMB2025

Next up is former student & friend @stroblmar.bsky.social presenting new work with @cancerconnector.bsky.social on “Bridging the gap: What preclinical experiments can teach us about cancer drug scheduling” #MathOnco #SMB2025

State-Transition Analysis of Time-Sequential Gene Expression Identifies Critical Points That Predict Development of Acute Myeloid Leukemia - PubMed Temporal dynamics of gene expression inform cellular and molecular perturbations associated with disease development and evolution. Given the complexity of high-dimensional temporal genomic data, an a...

Very nice study. We also find that gene expression changes in cancer well before cancer cells are detectable. A response to oncogenic events.

pubmed.ncbi.nlm.nih.gov/32414754/

pmc.ncbi.nlm.nih.gov/articles/PMC...

The Future of Mathematical Oncology in the Age of AI mathematical-oncology.org

Over a month ago a bunch of #MathOnco and #AIOnco researchers got together in Syracuse to discuss how #AI may and may not change the field. Here are some thoughts in a collective effort led by @rrockne.bsky.social:

What’s it like to work with an AI team of virtual scientists? Emerging ‘co-scientist’ systems use teams of chatbots to mimic the deliberations of a research group. Do they really help?

Emerging ‘co-scientist’ systems use teams of chatbots to mimic the deliberations of a research group. Do they really help?

https://go.nature.com/4l3Lzbz

Nice paper congrats!! 🎉🎉

Disappointing that Hopkins response to the situation is mass layoffs. Wish they would invest and sustain and lead.

Attending a conference entitled, The Future of Cancer Research: Unleashing the Power of Machine Learning, taking place in the historic city of Syracuse. Organized by @cityofhope.bsky.social @sergiobranciamore.bsky.social, Andrei Rodin, Konstancja Urbaniak and @rrockne.bsky.social

Zero-shot evaluation reveals limitations of single-cell foundation models - Genome Biology Foundation models such as scGPT and Geneformer have not been rigorously evaluated in a setting where they are used without any further training (i.e., zero-shot). Understanding the performance of mode...

genomebiology.biomedcentral.com/articles/10....

Quite an indictment of some of the current single cell "virtual cell" foundation models. Even for the relatively mundane applications, cell labeling, batch correction etc, they are poor compared to much simpler & cheaper methods.

Learning Dynamics with Neural Networks mathematical-oncology.org

What is the difference between PINNs, Universal PINNs, Neural Differential Equations (DEs) and Universal DEs?

Don’t miss this blog post that I wrote with a bunch of amazing colleagues from a #MechanisticLearning workshop in Canada

mathematical-oncology.org/blog/learnin...

@ocbe.bsky.social