Valentine Svensson

The pharma industry from Paul Janssen to today: why drugs got harder to develop and what we can do about it Personal site for posts about my interests: the biotech industry, medicine, molecular biology, neuroscience, biorisk, science, consciousness, AI, innovation, decision making, philosophy, games, sci-fi...

The pharma industry from Paul Janssen to today: why drugs got harder to develop and what we can do about it - atelfo.github.io/2023/12/23/b...

Valentine Svensson
Negative binomial regression and inference using a pre-trained transformer
https://arxiv.org/abs/2508.04111

Negative binomial regression and inference using a pre-trained transformer Negative binomial regression is essential for analyzing over-dispersed count data in in comparative studies, but parameter estimation becomes computationally challenging in large screens requiring mil...

Negative binomial regression and inference using a pre-trained transformer - arxiv.org/abs/2508.04111

🎉 scverse conference 2025 Registration & Call for Abstracts NOW OPEN! 🎉
We're excited to announce that registration and the call for abstracts are officially open for the scverse Conference 2025!
Details in thread!
🧵 1/3

Overinterpreting underpowered multi-omics experiments Betaine, Exercise-in-a-pill, Geroprotection

Overinterpreting underpowered multi-omics experiments - thecodon.substack.com/p/falling-in...

(1) Fitting hierarchical models in genetics, (2) A Stan model that runs faster with 400,000 latent parameters, (3) Super-scalable penalized maximum likelihood inference for biome problems, (4) “In the end, I basically gave up working on biology bec... - statmodeling.stat.columbia.edu/2025/07/31/b...

Using hierarchical modeling to get more stable rankings of gene expression - statmodeling.stat.columbia.edu/2025/07/30/u...

Which Kind of Science Reform What hope is there for science reform, if we can't agree on what to reform? Right now, principles are more important than practices.

Which Kind of Science Reform - elevanth.org/blog/2025/07...

A bioinformatician, computer scientist, and geneticist lead bioinformatic tool development—which one is better? AbstractMotivation. The development of accurate bioinformatic software tools is crucial for the effective analysis of complex biological data. This study e

A bioinformatician, computer scientist, and geneticist lead bioinformatic tool development—which one is better? - academic.oup.com/bioinformati...

A recap of virtual cell releases circa June 2025 - ekernf01.github.io/virtual-cell...

This episode is so crazy. I feel like I barely understand this game suddenly hours in. Please check it out!

Optimizing murine sample sizes for RNA-seq studies revealed from large-scale comparative analysis Determining the appropriate sample size (N) for comparative biological experiments is critical for obtaining reliable results. In order to determine the N, the usual approach is to perform a power cal...

Optimizing murine sample sizes for RNA-seq studies revealed from large-scale comparative analysis - www.biorxiv.org/content/10.1...

Sequences and consequences | Philosophical Transactions of the Royal Society B: Biological Sciences The conversion of data into knowledge constitutes a great challenge for future biological research. The new science of Systems Biology claims to be able to solve the problem but I contend that this ap...

Sequences and consequences - royalsocietypublishing.org/doi/10.1098/...

H5AD files in GEO I’m working on a project where I want to use a lot of well-annotated scRNA-seq data.

H5AD files in GEO - www.nxn.se/p/h5ad-files...

IC50 is a deep rabbit hole On harmonizing data, because ground truth in biology is unlike text

IC50 is a deep rabbit hole - blog.turbine.ai/p/ic50-is-a-...

The elusive virtual cell Rosetta Stone or Moby Dick?

The elusive virtual cell - srikosuri.substack.com/p/the-elusiv...

The Elite Overproduction Hypothesis A repost from the Noahpinion archives, with a few updates.

The Elite Overproduction Hypothesis - www.noahpinion.blog/p/the-elite-...

Reading Neuromancer for the very first time in 2025 So many sci-fi movies, anime, and video games owe a massive debt of gratitude to William Gibson's seminal 1984 novel.

Reading Neuromancer for the very first time in 2025 - mbh4h.substack.com/p/neuromance...

The state of research on virtual cell modeling Measuring where we are on the emerging grand challenge

The state of research on virtual cell modeling - behindbioml.substack.com/p/the-state-...

Creating therapeutic abundance On limiting reagents in the medicine production function

Creating therapeutic abundance - blog.jck.bio/p/creating-t...

On Progress Studies A bird's view on a meeting of ornithologists

On Progress Studies - luispedro.substack.com/p/on-progress

The Truth is Out There, Part 2: The Power of Belief - www.filfre.net/2024/09/the-...

A pre-trained t-test transformer - www.nxn.se/p/a-pre-trai...

Slot machine strategy - www.nxn.se/p/slot-machi...

Drug Discovery may be in the Cold War Era - kyunghyuncho.me/drug-discove...

Soviet Anime? Plus: news.

Soviet Anime? - animationobsessive.substack.com/p/soviet-anime

What Are Virtual Cells? Learning "universal representations" of life's fundamental unit

What Are Virtual Cells? - centuryofbio.com/p/virtual-cell

SCVI with variational batch encoding - www.nxn.se/p/scvi-with-...

Atul Butte died yesterday.
The world lost a giant.
A big bear of a man.
With a huge smile.
With love for everyone.
With energy that could power a room.
I loved everything about Atul.
I loved how he was always happy.
I loved how excited he was about science and helping people.

Figma Slides is a Beautiful Disaster Some highlights and lowlights.

Figma Slides is a Beautiful Disaster - allenpike.com/2025/figma-s...