iiinova — where your digital self keeps evolving

Kris Szalay @kristofszalay.com · 11/11/2025

We did some tests to see what's possible with #virtualcells today with all the headlines. Turns out what's available for #training is what really matters, not the assay. Like #AGI to #AI, what we have today is narrow #virtual #cells. But there is a path to generality. blog.turbine.ai/p/what-can-v...

blog.turbine.ai

What can Virtual Cells do for you today?

and what they can't - because the bottleneck is not computing power

000

Kris Szalay @kristofszalay.com · 16/10/2025

There such a big disconnect between how #pharma insiders view the value of #AI and what's in the news. It's because retrospective #clinical #data prediction is very different than for a new #drug. blog.turbine.ai/p/the-patient-puzzle Thanks to #MSK and #Champions for supporting us in this effort!

blog.turbine.ai

The Patient Puzzle

on why solving patients need more than patients

000

Kris Szalay @kristofszalay.com · 30/06/2025

The reason doing #ML in #biology is much harder than doing ML on text is that "ground truth" is very different. In the post below I'll show you the first 5 things we check when curating one single data point to teach the right idea to the #AI. #compbio #virtualcell blog.turbine.ai/p/ic50-is-a-...

blog.turbine.ai

IC50 is a deep rabbit hole

On harmonizing data, because ground truth in biology is unlike text

000

Kris Szalay @kristofszalay.com · 22/05/2025

Why can #AI work in #biology? It's not about hidden shortcuts to do raw physics. I think it's because we are learning how evolution was shaping us over all this time to survive. blog.turbine.ai/p/why-can-we... So maybe we should move on from individual proteins to learning relations of processes.

blog.turbine.ai

Why can we predict biology?

and what are we really predicting?

000

Reposted by Kris Szalay

Bence Szalai @benceszalai.bsky.social · 25/04/2025

Single-cell foundation models, trained on large-scale scRNA-seq datasets, are increasingly used for post-perturbation RNA-seq prediction. But how do they actually perform? Our new paper from @turbine-ai.bsky.social is now out in BMC Genomics. bmcgenomics.biomedcentral.com/articles/10.... 1/5

121

Kris Szalay @kristofszalay.com · 16/04/2025

Turns out the way we usually pre-train foundational cell models adds very little information to the system - definitely not enough to make drug effect predictions work. Not what I've expected. #virtualcells #foundationalmodels #compbio blog.turbine.ai/p/pretrainin...

blog.turbine.ai

Pretraining virtual cells is useless

the way we do it now

022

Reposted by Kris Szalay

Andreas Bender @andreasbender.bsky.social · 20/02/2025

The 'Google Co-Scientist' claims to be 'Accelerating scientific breakthroughs with an AI co-scientist' But does it? A closer look at its scientific validation as currently reported Please share and let me know if you have any comments, cheers! Andreas www.drugdiscovery.net/2025/02/20/t...

2186