Bence Szalai
@benceszalai.bsky.social
Computational systems biology - research team lead at Turbine. Previously post-doc at RWTH Aachen and Semmelweis.
Pinned
Bence Szalai
@benceszalai.bsky.social
· Apr 25
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
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
Reposted by Bence Szalai
In October 2024, I twote that "something is deeply wrong" with what we now call virtual cell models. A lot has happened since then. How am I updating? New blog post: ekernf01.github.io/virtual-cell...
A recap of virtual cell releases circa June 2025
In October 2024, I twote that “something is deeply wrong” with what we now call virtual cell models. A lot has happened since then: modelers are advancing new architectures and mining new sources of i...
ekernf01.github.io
July 27, 2025 at 11:48 PM
In October 2024, I twote that "something is deeply wrong" with what we now call virtual cell models. A lot has happened since then. How am I updating? New blog post: ekernf01.github.io/virtual-cell...
Reposted by Bence Szalai
Our paper benchmarking foundation models for perturbation effect prediction is finally published 🎉🥳🎉
www.nature.com/articles/s41...
We show that none of the available* models outperform simple linear baselines. Since the original preprint, we added more methods, metrics, and prettier figures!
🧵
www.nature.com/articles/s41...
We show that none of the available* models outperform simple linear baselines. Since the original preprint, we added more methods, metrics, and prettier figures!
🧵
August 4, 2025 at 1:52 PM
Our paper benchmarking foundation models for perturbation effect prediction is finally published 🎉🥳🎉
www.nature.com/articles/s41...
We show that none of the available* models outperform simple linear baselines. Since the original preprint, we added more methods, metrics, and prettier figures!
🧵
www.nature.com/articles/s41...
We show that none of the available* models outperform simple linear baselines. Since the original preprint, we added more methods, metrics, and prettier figures!
🧵
Our tool, RIDDEN (Receptor actIvity Data Driven inferENce) for predicting #receptor activity from #transcriptomics data is published in
PLOS Computational Biology journals.plos.org/ploscompbiol... 1/n
PLOS Computational Biology journals.plos.org/ploscompbiol... 1/n
July 15, 2025 at 10:25 PM
Our tool, RIDDEN (Receptor actIvity Data Driven inferENce) for predicting #receptor activity from #transcriptomics data is published in
PLOS Computational Biology journals.plos.org/ploscompbiol... 1/n
PLOS Computational Biology journals.plos.org/ploscompbiol... 1/n
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
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
April 25, 2025 at 9:49 PM
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
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
Reposted by Bence Szalai
We have an opening for a PhD/Postdoc in Spatial Omics for Cardiology in Heidelberg 🫀 #job #academicjob #phd #postdoc #cadiology 👇
jobrxiv.org/job/heidelbe...
jobrxiv.org/job/heidelbe...
PhD/Postdoc in Spatial Omics for Cardiology
Post a job in 3min, or find thousands of job offers like this one at jobRxiv!
jobrxiv.org
April 22, 2025 at 10:28 AM
We have an opening for a PhD/Postdoc in Spatial Omics for Cardiology in Heidelberg 🫀 #job #academicjob #phd #postdoc #cadiology 👇
jobrxiv.org/job/heidelbe...
jobrxiv.org/job/heidelbe...
Reposted by Bence Szalai
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...
#virtualcells #foundationalmodels #compbio
blog.turbine.ai/p/pretrainin...
Pretraining virtual cells is useless
the way we do it now
blog.turbine.ai
April 16, 2025 at 5:03 PM
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...
#virtualcells #foundationalmodels #compbio
blog.turbine.ai/p/pretrainin...
easter holiday is coming: 2 revised versions submitted today
holiday season is coming: 2 papers submitted today
April 3, 2025 at 10:48 PM
easter holiday is coming: 2 revised versions submitted today
Reposted by Bence Szalai
You’ve probably heard about how AI/LLMs can solve Math Olympiad problems ( deepmind.google/discover/blo... ).
So naturally, some people put it to the test — hours after the 2025 US Math Olympiad problems were released.
The result: They all sucked!
So naturally, some people put it to the test — hours after the 2025 US Math Olympiad problems were released.
The result: They all sucked!
March 31, 2025 at 8:33 PM
You’ve probably heard about how AI/LLMs can solve Math Olympiad problems ( deepmind.google/discover/blo... ).
So naturally, some people put it to the test — hours after the 2025 US Math Olympiad problems were released.
The result: They all sucked!
So naturally, some people put it to the test — hours after the 2025 US Math Olympiad problems were released.
The result: They all sucked!
Reposted by Bence Szalai
Does @iscb.bsky.social have a statement on this? We need to be there to support bioinformatics researchers.
Detained in an ICE camp over a customs form technicality and facing deportation to Russia where she will be persecuted for vocal opposition to the invasion of Ukraine. She does bioinformatics
More here, for those asking
March 30, 2025 at 6:23 PM
Does @iscb.bsky.social have a statement on this? We need to be there to support bioinformatics researchers.
based on some recent papers / presentations, the hill(s) I'll die on:
1) Raw IC50 values != good metrics for comparing cancer drug sensitivity
2) Raw TPMs / counts are meaningless for comparing gene expression similarity
3) Diverging color palettes need a meaningful midpoint.
1) Raw IC50 values != good metrics for comparing cancer drug sensitivity
2) Raw TPMs / counts are meaningless for comparing gene expression similarity
3) Diverging color palettes need a meaningful midpoint.
March 30, 2025 at 8:44 PM
based on some recent papers / presentations, the hill(s) I'll die on:
1) Raw IC50 values != good metrics for comparing cancer drug sensitivity
2) Raw TPMs / counts are meaningless for comparing gene expression similarity
3) Diverging color palettes need a meaningful midpoint.
1) Raw IC50 values != good metrics for comparing cancer drug sensitivity
2) Raw TPMs / counts are meaningless for comparing gene expression similarity
3) Diverging color palettes need a meaningful midpoint.
Reposted by Bence Szalai
Post-doc opening to join our lab @ebi.embl.org to develop&apply #bioinformatics and #machine-learning methods to study intra-/extra cellular networks to extract disease mechanisms from #single-cell and #spatial multiomic data - please share 🙏 : embl.wd103.myworkdayjobs.com/EMBL/job/Hin...
Postdoctoral fellow - Saez-Rodriguez Group
Your group Saez-Rodriguez Research Group Your supervisor Julio Saez-Rodriguez Your role As a postdoctoral fellow in the Saez Rodriguez group, you will develop and apply computational methods and tools...
embl.wd103.myworkdayjobs.com
February 11, 2025 at 10:17 AM
Post-doc opening to join our lab @ebi.embl.org to develop&apply #bioinformatics and #machine-learning methods to study intra-/extra cellular networks to extract disease mechanisms from #single-cell and #spatial multiomic data - please share 🙏 : embl.wd103.myworkdayjobs.com/EMBL/job/Hin...
Reposted by Bence Szalai
We will be hosting the International Conference on Systems Biology (ICSB) in Dublin this year – 5-9th October icsb2025.com/registration/ #ICSB2025
January 29, 2025 at 4:50 PM
We will be hosting the International Conference on Systems Biology (ICSB) in Dublin this year – 5-9th October icsb2025.com/registration/ #ICSB2025
Reposted by Bence Szalai
It's been over 24 hours since #AdventOfCode 2024 ended!
This AoC season:
- 273,313 users collected at least one star
- 3,654,949 stars were collected
Since 2015:
- 779 users have all 500 stars
- 1,077,226 users collected at least one star
- 23,170,305 were collected
This AoC season:
- 273,313 users collected at least one star
- 3,654,949 stars were collected
Since 2015:
- 779 users have all 500 stars
- 1,077,226 users collected at least one star
- 23,170,305 were collected
December 26, 2024 at 10:21 PM
It's been over 24 hours since #AdventOfCode 2024 ended!
This AoC season:
- 273,313 users collected at least one star
- 3,654,949 stars were collected
Since 2015:
- 779 users have all 500 stars
- 1,077,226 users collected at least one star
- 23,170,305 were collected
This AoC season:
- 273,313 users collected at least one star
- 3,654,949 stars were collected
Since 2015:
- 779 users have all 500 stars
- 1,077,226 users collected at least one star
- 23,170,305 were collected
holiday season is coming: 2 papers submitted today
December 10, 2024 at 10:55 PM
holiday season is coming: 2 papers submitted today
[first 🦋] Receptors are essential for cell-cell communication, yet most comp CCC tools focus on ligand/receptor expression, not receptor activity. To address this, we developed RIDDEN, a model that infers activity for 229 receptors from transcriptomics data. 1/n www.biorxiv.org/content/10.1...
December 9, 2024 at 9:39 PM
[first 🦋] Receptors are essential for cell-cell communication, yet most comp CCC tools focus on ligand/receptor expression, not receptor activity. To address this, we developed RIDDEN, a model that infers activity for 229 receptors from transcriptomics data. 1/n www.biorxiv.org/content/10.1...
I just completed "Historian Hysteria" - Day 1 - Advent of Code 2024 #AdventOfCode adventofcode.com/2024/day/1
December 1, 2024 at 2:48 PM
I just completed "Historian Hysteria" - Day 1 - Advent of Code 2024 #AdventOfCode adventofcode.com/2024/day/1
Reposted by Bence Szalai
We have created a starterpack to make it easier to follow current members and alumni from our lab, check it out 👇 (DM us if we forgot about you)
Also juliosaezrod.bsky.social has recently joined Bluesky
go.bsky.app/5ZtPHPz
Also juliosaezrod.bsky.social has recently joined Bluesky
go.bsky.app/5ZtPHPz
November 20, 2024 at 1:10 PM
We have created a starterpack to make it easier to follow current members and alumni from our lab, check it out 👇 (DM us if we forgot about you)
Also juliosaezrod.bsky.social has recently joined Bluesky
go.bsky.app/5ZtPHPz
Also juliosaezrod.bsky.social has recently joined Bluesky
go.bsky.app/5ZtPHPz
Reposted by Bence Szalai
Hi 🦋 This is the saezlab (saezlab.org) bluesky account. We integrate #omics data with mechanistic molecular knowledge into statistical and machine learning #ML methods, and we share our tools as free #opensource packages (github.com/saezlab/) #systemsbiology #biology #compbio
Saez-Rodriguez GroupSaez-Rodriguez Group – Systems Biomedicine
saezlab.org
November 11, 2024 at 9:04 AM
Hi 🦋 This is the saezlab (saezlab.org) bluesky account. We integrate #omics data with mechanistic molecular knowledge into statistical and machine learning #ML methods, and we share our tools as free #opensource packages (github.com/saezlab/) #systemsbiology #biology #compbio