Pau Badia i Mompel
@paubadiam.bsky.social
Postdoctoral researcher at @anshulkundaje.bsky.social Machine learning #ML, gene regulatory networks #GRN, single cell and spatial #omics.
Previously at @saezlab.bsky.social
Core developer of https://decoupler.readthedocs.io/ at @scverse.bsky.social
Previously at @saezlab.bsky.social
Core developer of https://decoupler.readthedocs.io/ at @scverse.bsky.social
Pinned
Pau Badia i Mompel
@paubadiam.bsky.social
· Dec 23
We present Gene Regulatory nETwork Analsyis (GRETA), a framework to infer, compare and evaluate gene regulatory networks #GRNs. With it, we have benchmarked multimodal and unimodal GRN inference methods. Check the results here 👇
Paper: doi.org/10.1101/2024.12.20.629764
Code: github.com/saezlab/greta
Paper: doi.org/10.1101/2024.12.20.629764
Code: github.com/saezlab/greta
The final chapter of my PhD thesis is now out! 🎉 We compared the latest gene regulatory network (#GRN) inference methods for #single-cell multimodal datasets and evaluated their performance across various tasks. Hard to believe this journey started in March 2021 and has finally reached this point 😅🥳
scverse conference 2025 done ✅ Really engaging week at Stanford with scPerturb-seq work, agentic models in biology, and strong interest in scaling software to millions of cells. Organizing alongside the rest of the @scverse.bsky.social team was a blast! Hope attendees found it productive 😄
November 21, 2025 at 5:37 PM
scverse conference 2025 done ✅ Really engaging week at Stanford with scPerturb-seq work, agentic models in biology, and strong interest in scaling software to millions of cells. Organizing alongside the rest of the @scverse.bsky.social team was a blast! Hope attendees found it productive 😄
Reposted by Pau Badia i Mompel
A highlight of my summer was this collab w/
@twangmdphd.bsky.social ! CRISPR base editors are driving several clinical trials, but it's hard to quantify off-target edits and their effects. Tong developed a sequencing assay to identify off-targets *in primary cells* 🧬🖥️🧪 #genomics #chromatin #CRISPR
@twangmdphd.bsky.social ! CRISPR base editors are driving several clinical trials, but it's hard to quantify off-target edits and their effects. Tong developed a sequencing assay to identify off-targets *in primary cells* 🧬🖥️🧪 #genomics #chromatin #CRISPR
1/ Happy to share our preprint from the Greenleaf Lab: beCasKAS, our method to directly detect CRISPR base editor off-targets in primary cells. We additionally show how non-coding edits can be triaged for epigenetic dysregulation using deep learning.
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
November 7, 2025 at 6:38 PM
A highlight of my summer was this collab w/
@twangmdphd.bsky.social ! CRISPR base editors are driving several clinical trials, but it's hard to quantify off-target edits and their effects. Tong developed a sequencing assay to identify off-targets *in primary cells* 🧬🖥️🧪 #genomics #chromatin #CRISPR
@twangmdphd.bsky.social ! CRISPR base editors are driving several clinical trials, but it's hard to quantify off-target edits and their effects. Tong developed a sequencing assay to identify off-targets *in primary cells* 🧬🖥️🧪 #genomics #chromatin #CRISPR
Can't make it to Stanford? We've just opened remote attendance for scverse Conference 2025! Join us online Nov 17-18 via Zoom 👇
We're pleased to announce that we are now offering online attendance via Zoom.
Remote attendance is available for 30 USD, and you can secure your spot by registering at www.eventbrite.com/e/scverse-co....
We hope to see you online at the conference!
Remote attendance is available for 30 USD, and you can secure your spot by registering at www.eventbrite.com/e/scverse-co....
We hope to see you online at the conference!
Scverse Conference 2025
From the foundational open-source software in the life sciences — to its large community coming together
www.eventbrite.com
November 6, 2025 at 4:24 AM
Can't make it to Stanford? We've just opened remote attendance for scverse Conference 2025! Join us online Nov 17-18 via Zoom 👇
Reposted by Pau Badia i Mompel
Nature suggests you use their "Manuscript Adviser" bot to get advice before submitting
I uploaded the classic Watson & Crick paper about DNA structure, and the Adviser had this to say about one of the greatest paper endings of the century:
I uploaded the classic Watson & Crick paper about DNA structure, and the Adviser had this to say about one of the greatest paper endings of the century:
November 3, 2025 at 1:55 PM
Nature suggests you use their "Manuscript Adviser" bot to get advice before submitting
I uploaded the classic Watson & Crick paper about DNA structure, and the Adviser had this to say about one of the greatest paper endings of the century:
I uploaded the classic Watson & Crick paper about DNA structure, and the Adviser had this to say about one of the greatest paper endings of the century:
Reposted by Pau Badia i Mompel
How do we know whether our AI solutions are up to our standards, for instance in clinical recommendations? We try to contribute to the answer by our recent study on *Benchmarking large language models for personalized, biomarker-based health intervention recommendations* rdcu.be/eMVeL
Benchmarking large language models for personalized, biomarker-based health intervention recommendations
npj Digital Medicine - Benchmarking large language models for personalized, biomarker-based health intervention recommendations
rdcu.be
October 27, 2025 at 3:14 PM
How do we know whether our AI solutions are up to our standards, for instance in clinical recommendations? We try to contribute to the answer by our recent study on *Benchmarking large language models for personalized, biomarker-based health intervention recommendations* rdcu.be/eMVeL
Reposted by Pau Badia i Mompel
Arc is looking for an outstanding early-career scientist to be our next Science Fellow. This program provides resources and freedom for those looking to transition into a principal investigator role immediately after doctoral training. Apply here: arcinstitute.org/programs/sea...
October 13, 2025 at 7:36 PM
Arc is looking for an outstanding early-career scientist to be our next Science Fellow. This program provides resources and freedom for those looking to transition into a principal investigator role immediately after doctoral training. Apply here: arcinstitute.org/programs/sea...
Reposted by Pau Badia i Mompel
Which mutations rewire function of regulatory DNA?
Excited to share SEAM: Systematic Explanation of Attribtuion-based Mechanisms. SEAM is an explainable AI method that dissects cis-regulatory mechanisms learned by seq2fun genomic deep learning models.
Led by @EESetiz
1/N 🧵👇
Excited to share SEAM: Systematic Explanation of Attribtuion-based Mechanisms. SEAM is an explainable AI method that dissects cis-regulatory mechanisms learned by seq2fun genomic deep learning models.
Led by @EESetiz
1/N 🧵👇
October 9, 2025 at 12:03 PM
Which mutations rewire function of regulatory DNA?
Excited to share SEAM: Systematic Explanation of Attribtuion-based Mechanisms. SEAM is an explainable AI method that dissects cis-regulatory mechanisms learned by seq2fun genomic deep learning models.
Led by @EESetiz
1/N 🧵👇
Excited to share SEAM: Systematic Explanation of Attribtuion-based Mechanisms. SEAM is an explainable AI method that dissects cis-regulatory mechanisms learned by seq2fun genomic deep learning models.
Led by @EESetiz
1/N 🧵👇
Reposted by Pau Badia i Mompel
🌟 Thank You to Our Gold Sponsor: Stellaromics! 🌟
We're proud to recognize Stellaromics as a Gold Sponsor of scverse conference 2025! 🥇
@stellaromics.bsky.social
#scverse2025 #SpatialBiology #3DSpatial #ComputationalBiology #SingleCell #Stellaromics #SpatialOmics #Bioinformatics
We're proud to recognize Stellaromics as a Gold Sponsor of scverse conference 2025! 🥇
@stellaromics.bsky.social
#scverse2025 #SpatialBiology #3DSpatial #ComputationalBiology #SingleCell #Stellaromics #SpatialOmics #Bioinformatics
October 9, 2025 at 3:25 PM
🌟 Thank You to Our Gold Sponsor: Stellaromics! 🌟
We're proud to recognize Stellaromics as a Gold Sponsor of scverse conference 2025! 🥇
@stellaromics.bsky.social
#scverse2025 #SpatialBiology #3DSpatial #ComputationalBiology #SingleCell #Stellaromics #SpatialOmics #Bioinformatics
We're proud to recognize Stellaromics as a Gold Sponsor of scverse conference 2025! 🥇
@stellaromics.bsky.social
#scverse2025 #SpatialBiology #3DSpatial #ComputationalBiology #SingleCell #Stellaromics #SpatialOmics #Bioinformatics
Reposted by Pau Badia i Mompel
Now that I'm settled in at @umasschan.bsky.social, I'm hiring at all levels: grad students, post-docs, and software engineers/bioinformaticians!
The goal of my lab is to understand the regulatory role of every nucleotide in our genomes and how this changes across every cell in our bodies.
The goal of my lab is to understand the regulatory role of every nucleotide in our genomes and how this changes across every cell in our bodies.
October 7, 2025 at 3:24 PM
Now that I'm settled in at @umasschan.bsky.social, I'm hiring at all levels: grad students, post-docs, and software engineers/bioinformaticians!
The goal of my lab is to understand the regulatory role of every nucleotide in our genomes and how this changes across every cell in our bodies.
The goal of my lab is to understand the regulatory role of every nucleotide in our genomes and how this changes across every cell in our bodies.
Reposted by Pau Badia i Mompel
I adored writing this piece. It brings together several of the things preoccupying me right now, like chromatin organization and gene regulation. There's so much more to be said on that. Also, these marine critters look gorgeous.
www.quantamagazine.org/loops-of-dna...
www.quantamagazine.org/loops-of-dna...
Loops of DNA Equipped Ancient Life To Become Complex | Quanta Magazine
New work shows that physical folding of the genome to control genes located far away may have been an early evolutionary development.
www.quantamagazine.org
October 8, 2025 at 2:21 PM
I adored writing this piece. It brings together several of the things preoccupying me right now, like chromatin organization and gene regulation. There's so much more to be said on that. Also, these marine critters look gorgeous.
www.quantamagazine.org/loops-of-dna...
www.quantamagazine.org/loops-of-dna...
Reposted by Pau Badia i Mompel
🧠 Arc Workshop at the upcoming scverse conference 2025 🧠
Processing and Modeling Large-Scale Single-Cell Perturbation Data with Machine Learning
🧵
@arcinstitute.org
#scverse2025 #PerturbSeq #MachineLearning #SingleCell #CRISPR #GenomicScreening #VirtualCells
Processing and Modeling Large-Scale Single-Cell Perturbation Data with Machine Learning
🧵
@arcinstitute.org
#scverse2025 #PerturbSeq #MachineLearning #SingleCell #CRISPR #GenomicScreening #VirtualCells
October 8, 2025 at 2:55 PM
🧠 Arc Workshop at the upcoming scverse conference 2025 🧠
Processing and Modeling Large-Scale Single-Cell Perturbation Data with Machine Learning
🧵
@arcinstitute.org
#scverse2025 #PerturbSeq #MachineLearning #SingleCell #CRISPR #GenomicScreening #VirtualCells
Processing and Modeling Large-Scale Single-Cell Perturbation Data with Machine Learning
🧵
@arcinstitute.org
#scverse2025 #PerturbSeq #MachineLearning #SingleCell #CRISPR #GenomicScreening #VirtualCells
Reposted by Pau Badia i Mompel
Jane Goodall has died at the age of 91.
In 2020, Goodall spoke with Science Editor-in-Chief H. Holden Thorp for a #ScienceEditorial reflecting on the 60th anniversary of her arrival in Gombe to study wild chimpanzees. Read more: https://scim.ag/472Chb8
In 2020, Goodall spoke with Science Editor-in-Chief H. Holden Thorp for a #ScienceEditorial reflecting on the 60th anniversary of her arrival in Gombe to study wild chimpanzees. Read more: https://scim.ag/472Chb8
October 1, 2025 at 7:13 PM
Jane Goodall has died at the age of 91.
In 2020, Goodall spoke with Science Editor-in-Chief H. Holden Thorp for a #ScienceEditorial reflecting on the 60th anniversary of her arrival in Gombe to study wild chimpanzees. Read more: https://scim.ag/472Chb8
In 2020, Goodall spoke with Science Editor-in-Chief H. Holden Thorp for a #ScienceEditorial reflecting on the 60th anniversary of her arrival in Gombe to study wild chimpanzees. Read more: https://scim.ag/472Chb8
Reposted by Pau Badia i Mompel
Introducing ParTIpy, a python package for Pareto Task Inference that scales to large-scale datasets, including single-cell and spatial transcriptomics.
🔗 Manuscript: www.biorxiv.org/content/10.1...
💻 Code: partipy.readthedocs.io
🔗 Manuscript: www.biorxiv.org/content/10.1...
💻 Code: partipy.readthedocs.io
September 15, 2025 at 8:40 AM
Introducing ParTIpy, a python package for Pareto Task Inference that scales to large-scale datasets, including single-cell and spatial transcriptomics.
🔗 Manuscript: www.biorxiv.org/content/10.1...
💻 Code: partipy.readthedocs.io
🔗 Manuscript: www.biorxiv.org/content/10.1...
💻 Code: partipy.readthedocs.io
Reposted by Pau Badia i Mompel
My favorite part of last-year #scverse conference was to finally meet in-person many developers that I only knew from their GitHub username!
Submissions and travel grant applications close in 3 days. Find out more and apply at scverse.org/conference2025
@scverse.bsky.social
Submissions and travel grant applications close in 3 days. Find out more and apply at scverse.org/conference2025
@scverse.bsky.social
September 12, 2025 at 8:11 PM
My favorite part of last-year #scverse conference was to finally meet in-person many developers that I only knew from their GitHub username!
Submissions and travel grant applications close in 3 days. Find out more and apply at scverse.org/conference2025
@scverse.bsky.social
Submissions and travel grant applications close in 3 days. Find out more and apply at scverse.org/conference2025
@scverse.bsky.social
Reposted by Pau Badia i Mompel
A-tack-seq OR attack-seq?
Explain your answer.
Explain your answer.
September 11, 2025 at 7:06 PM
A-tack-seq OR attack-seq?
Explain your answer.
Explain your answer.
Been digging through GEO for multiome single-cell data, frustrating how much is unusable 🫠 (missing annotations, frag files, raw data). Uploading properly takes effort, but it makes your dataset so much more impactful... Props to (most of) the authors who fixed things when I reached out, though 👍
September 12, 2025 at 1:33 AM
Been digging through GEO for multiome single-cell data, frustrating how much is unusable 🫠 (missing annotations, frag files, raw data). Uploading properly takes effort, but it makes your dataset so much more impactful... Props to (most of) the authors who fixed things when I reached out, though 👍
Reposted by Pau Badia i Mompel
@niklaskemp.bsky.social will present our new CREsted framework at the next scverse community meeting!
CREsted allows you to train sequence-to-function models tailored to cell type-specific enhancers (including synthetic enhancer design) www.biorxiv.org/content/10.1... github.com/aertslab/cre...
CREsted allows you to train sequence-to-function models tailored to cell type-specific enhancers (including synthetic enhancer design) www.biorxiv.org/content/10.1... github.com/aertslab/cre...
We will have our next community meeting on Tuesday, 2025-09-16 at 18:00 CEST! Niklas Kempynck will be presenting on CREsted, a package for training enhancer models on scATAC-seq data.
(Zoom registration link and more information in thread!)
🧵
(Zoom registration link and more information in thread!)
🧵
September 11, 2025 at 2:34 PM
@niklaskemp.bsky.social will present our new CREsted framework at the next scverse community meeting!
CREsted allows you to train sequence-to-function models tailored to cell type-specific enhancers (including synthetic enhancer design) www.biorxiv.org/content/10.1... github.com/aertslab/cre...
CREsted allows you to train sequence-to-function models tailored to cell type-specific enhancers (including synthetic enhancer design) www.biorxiv.org/content/10.1... github.com/aertslab/cre...
Reposted by Pau Badia i Mompel
1/ First preprint from @jdemeul.bsky.social lab 🥳! We present our new multi-modal single-cell long-read method SPLONGGET (Single-cell Profiling of LONG-read Genome, Epigenome, and Transcriptome)! www.biorxiv.org/content/10.1...
September 10, 2025 at 3:48 PM
1/ First preprint from @jdemeul.bsky.social lab 🥳! We present our new multi-modal single-cell long-read method SPLONGGET (Single-cell Profiling of LONG-read Genome, Epigenome, and Transcriptome)! www.biorxiv.org/content/10.1...
Reposted by Pau Badia i Mompel
Join EMBL as a research group leader in AI in biology. EMBL AI is our new initiative aiming to exploit the full potential of ML/AI-based approaches to advance our understanding of the most complex system in the known universe - life on Earth.
embl.wd103.myworkdayjobs.com/en-US/EMBL/j...
(1/3)
embl.wd103.myworkdayjobs.com/en-US/EMBL/j...
(1/3)
September 9, 2025 at 10:07 AM
Join EMBL as a research group leader in AI in biology. EMBL AI is our new initiative aiming to exploit the full potential of ML/AI-based approaches to advance our understanding of the most complex system in the known universe - life on Earth.
embl.wd103.myworkdayjobs.com/en-US/EMBL/j...
(1/3)
embl.wd103.myworkdayjobs.com/en-US/EMBL/j...
(1/3)
Reposted by Pau Badia i Mompel
Bro… please reinspect and change the acronym.
Pathway impact analysis (PIS) for robust and comprehensive interpretation of differentially expressed genes (DEGs) https://www.biorxiv.org/content/10.1101/2025.09.08.674792v1
September 8, 2025 at 5:03 PM
Bro… please reinspect and change the acronym.
Reposted by Pau Badia i Mompel
👋 Time to say goodbye to another one of our PhD students, @smuellerdott.bsky.social. She was working on the integration of phosphoproteomics and transcriptomics data and will now join the Computational Oncology Team at Merck. We wish her all the best for this new chapter! 🚀 ✨
September 1, 2025 at 5:35 AM
👋 Time to say goodbye to another one of our PhD students, @smuellerdott.bsky.social. She was working on the integration of phosphoproteomics and transcriptomics data and will now join the Computational Oncology Team at Merck. We wish her all the best for this new chapter! 🚀 ✨
Reposted by Pau Badia i Mompel
I've read the abstract 3 times and I still don't understand the phenomenon
www.nature.com/articles/s41...
www.nature.com/articles/s41...
One mother for two species via obligate cross-species cloning in ants - Nature
In a case of obligate cross-species cloning, female ants of Messor ibericus need to clone males of Messor structor to obtain sperm for producing the worker caste, resulting in males from the same moth...
www.nature.com
September 3, 2025 at 8:06 PM
I've read the abstract 3 times and I still don't understand the phenomenon
www.nature.com/articles/s41...
www.nature.com/articles/s41...
I always find it funny that we obsess over sample size, yet peer review relies on the arbitrary opinions of just 2/3 people. That would be fine if editors were truly engaged, but given the workload, they don’t have the time, or don’t care enough. Anyway, I’m just glad it finally got published! 👏
1/ Everything that could go wrong in paper publishing… did.
A story of patience, absurdity, and persistence 🌀 <1min
From Alfonso Valencia’s lab and a very stubborn PhD student (me).
A story of patience, absurdity, and persistence 🌀 <1min
From Alfonso Valencia’s lab and a very stubborn PhD student (me).
September 3, 2025 at 3:09 PM
I always find it funny that we obsess over sample size, yet peer review relies on the arbitrary opinions of just 2/3 people. That would be fine if editors were truly engaged, but given the workload, they don’t have the time, or don’t care enough. Anyway, I’m just glad it finally got published! 👏
Reposted by Pau Badia i Mompel
🚨 New in PNAS!
🧬 64% of disease co-occurrences can be explained by transcriptomic similarities.
Comorbidities aren’t random—they have a molecular basis.
Here’s how we found it 👇 (1/n)
🔗 doi.org/10.1073/pnas.2421060122
@alfonsovalencia.bsky.social
🧬 64% of disease co-occurrences can be explained by transcriptomic similarities.
Comorbidities aren’t random—they have a molecular basis.
Here’s how we found it 👇 (1/n)
🔗 doi.org/10.1073/pnas.2421060122
@alfonsovalencia.bsky.social
September 2, 2025 at 11:42 AM
🚨 New in PNAS!
🧬 64% of disease co-occurrences can be explained by transcriptomic similarities.
Comorbidities aren’t random—they have a molecular basis.
Here’s how we found it 👇 (1/n)
🔗 doi.org/10.1073/pnas.2421060122
@alfonsovalencia.bsky.social
🧬 64% of disease co-occurrences can be explained by transcriptomic similarities.
Comorbidities aren’t random—they have a molecular basis.
Here’s how we found it 👇 (1/n)
🔗 doi.org/10.1073/pnas.2421060122
@alfonsovalencia.bsky.social
Reposted by Pau Badia i Mompel
1/ Everything that could go wrong in paper publishing… did.
A story of patience, absurdity, and persistence 🌀 <1min
From Alfonso Valencia’s lab and a very stubborn PhD student (me).
A story of patience, absurdity, and persistence 🌀 <1min
From Alfonso Valencia’s lab and a very stubborn PhD student (me).
September 2, 2025 at 6:37 PM
1/ Everything that could go wrong in paper publishing… did.
A story of patience, absurdity, and persistence 🌀 <1min
From Alfonso Valencia’s lab and a very stubborn PhD student (me).
A story of patience, absurdity, and persistence 🌀 <1min
From Alfonso Valencia’s lab and a very stubborn PhD student (me).