Turbine AI

What can Virtual Cells do for you today?

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

Nov 11 • 

Kris Szalay

4

2

October 2025

The Patient Prediction Puzzle

on why solving patients need more than patients

Oct 16 • 

Kris Szalay

July 2025

June 2025

IC50 is a deep rabbit hole

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

Jun 30 • 

Kris Szalay

7

May 2025

April 2025

Pretraining virtual cells is useless

the way we do it now

Apr 16 • 

Kris Szalay

3

January 2025

How to make data points worthwhile?

Over the years as we worked with more and more clients, we encountered training data in all shapes and sizes.

Jan 11 • 

Kris Szalay

1

October 2024

In defense of RNASeq

We only use DNA and RNA for defining a cell (whether it’s a patient cell, PDX or cell line).

Oct 24, 2024 • 

Kris Szalay

2

So how do you benchmark biology?

This is a human-readable summary of the EFFECT paper.

Oct 7, 2024 • 

Kris Szalay

1

September 2024

Do cell foundation models work?

Biology is hard, and it’s very easy to accidentally produce misleading results.

Sep 23, 2024 • 

Kris Szalay

1