Ekin Deniz Aksu
@ekindea.bsky.social
Scientist and medical doctor. Biology AI/ML methods, gene regulation, DNA sequence models, single cells. Doing a PhD in computational biology at @molgen.mpg.de.
Pinned
Ekin Deniz Aksu
@ekindea.bsky.social
· Jul 15
Context-aware sequence-to-function model of human gene regulation - Nature Communications
This study introduces Corgi and Corgi+ , biology-inspired deep neural network models of regulatory DNA sequences that can generalize to unseen cell types. They accurately impute epigenomic d...
www.nature.com
I'm excited to share that Corgi is out in
@natcomms.nature.com!
We refine context-aware sequence-to-function models by using FiLM to condition the model on trans-regulator expression levels. This way Corgi can generalize to unseen cell types.
www.nature.com/articles/s41...
🧵Thread 1/n
@natcomms.nature.com!
We refine context-aware sequence-to-function models by using FiLM to condition the model on trans-regulator expression levels. This way Corgi can generalize to unseen cell types.
www.nature.com/articles/s41...
🧵Thread 1/n
Reposted by Ekin Deniz Aksu
Cerberus: bidirectional state space blocks improve accuracy and efficiency of regulatory sequence models https://www.biorxiv.org/content/10.64898/2026.10.02.756377v1
October 9, 2026 at 2:33 PM
Cerberus: bidirectional state space blocks improve accuracy and efficiency of regulatory sequence models https://www.biorxiv.org/content/10.64898/2026.10.02.756377v1
Reposted by Ekin Deniz Aksu
I recently posted the first output of our partnership with Zack Smith's lab, here I post it again this time with the other 2 manuscripts that were generated from this partnership thanks to the fantastic postdoc Yusuke Kijima:
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
Epigenetic regulators partition the genome by evolutionary and developmental constraint
Many epigenetic regulators play essential roles in animal development, but precisely how they function across different cell types without clear sequence preferences remains a foundational challenge. ...
www.biorxiv.org
October 9, 2026 at 3:00 PM
I recently posted the first output of our partnership with Zack Smith's lab, here I post it again this time with the other 2 manuscripts that were generated from this partnership thanks to the fantastic postdoc Yusuke Kijima:
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
Reposted by Ekin Deniz Aksu
In our Nature paper, we introduce the first superhuman Stratego AI, which we built using general techniques that we developed for RL & test-time compute under imperfect information. www.nature.com/articles/s41...
Scalable decision-making for games of imperfect information - Nature
Ataraxos, an AI for the board wargame Stratego, establishes a design pattern for reinforcement learning and search that is effective under large amounts of hidden information, a longstanding desiderat...
www.nature.com
September 30, 2026 at 7:05 PM
In our Nature paper, we introduce the first superhuman Stratego AI, which we built using general techniques that we developed for RL & test-time compute under imperfect information. www.nature.com/articles/s41...
Reposted by Ekin Deniz Aksu
Our #genome still holds many mysteries… Want to help figuring out what is actually translated into proteins and how it is regulated? Our research network #ORFeus is looking for motivated #PhD students to join projects across Europe.
Deadline is soon (Oct 22), have a look!
www.orfeus-dn.eu/apply/
Deadline is soon (Oct 22), have a look!
www.orfeus-dn.eu/apply/
Apply to ORFeus — 15 fully funded PhD positions
15 fully funded PhD positions across Europe, starting 2027. Applications open 1 October and close 22 October 2026. Rank up to three projects.
www.orfeus-dn.eu
September 30, 2026 at 6:50 AM
Our #genome still holds many mysteries… Want to help figuring out what is actually translated into proteins and how it is regulated? Our research network #ORFeus is looking for motivated #PhD students to join projects across Europe.
Deadline is soon (Oct 22), have a look!
www.orfeus-dn.eu/apply/
Deadline is soon (Oct 22), have a look!
www.orfeus-dn.eu/apply/
Reposted by Ekin Deniz Aksu
Excited to show deepSCENIC to the world! GRNs meet sequence-to-function models: explicit TF-region and region-gene links, with the power of enhancer DL models, predicting RNA & ATAC at single-cell resolution.
Check out the examples in the paper or try it on your own data: github.com/aertslab/Dee...
Check out the examples in the paper or try it on your own data: github.com/aertslab/Dee...
September 22, 2026 at 6:13 PM
Excited to show deepSCENIC to the world! GRNs meet sequence-to-function models: explicit TF-region and region-gene links, with the power of enhancer DL models, predicting RNA & ATAC at single-cell resolution.
Check out the examples in the paper or try it on your own data: github.com/aertslab/Dee...
Check out the examples in the paper or try it on your own data: github.com/aertslab/Dee...
Reposted by Ekin Deniz Aksu
Want an efficient way to delete cis-regulatory elements in stem cells? 🧬
Our lab just published a methods paper in JoVE's collection on 2D/3D Stem Cell-Based Models of Early Mammalian Development.
shorturl.at/QB1xo
Thank you @ancheldjs.bsky.social for the invitation to contribute!
Our lab just published a methods paper in JoVE's collection on 2D/3D Stem Cell-Based Models of Early Mammalian Development.
shorturl.at/QB1xo
Thank you @ancheldjs.bsky.social for the invitation to contribute!
September 22, 2026 at 6:56 AM
Want an efficient way to delete cis-regulatory elements in stem cells? 🧬
Our lab just published a methods paper in JoVE's collection on 2D/3D Stem Cell-Based Models of Early Mammalian Development.
shorturl.at/QB1xo
Thank you @ancheldjs.bsky.social for the invitation to contribute!
Our lab just published a methods paper in JoVE's collection on 2D/3D Stem Cell-Based Models of Early Mammalian Development.
shorturl.at/QB1xo
Thank you @ancheldjs.bsky.social for the invitation to contribute!
Reposted by Ekin Deniz Aksu
Academia has seen inflation in the past 30 years but it is now entering Republic of Weimar territory, with value of knowledge moving from "paper to land".
In all this, Open hardware is an act of armed resistance to Technofeudalism.
giorgio.gilest.ro/the-weimar-o...
In all this, Open hardware is an act of armed resistance to Technofeudalism.
giorgio.gilest.ro/the-weimar-o...
The Weimar of knowledge – la bottega
giorgio.gilest.ro
September 20, 2026 at 10:37 AM
Academia has seen inflation in the past 30 years but it is now entering Republic of Weimar territory, with value of knowledge moving from "paper to land".
In all this, Open hardware is an act of armed resistance to Technofeudalism.
giorgio.gilest.ro/the-weimar-o...
In all this, Open hardware is an act of armed resistance to Technofeudalism.
giorgio.gilest.ro/the-weimar-o...
Reposted by Ekin Deniz Aksu
I resigned from ExxonMobil today. I spent the last three years doing fossil fuel extraction research at both BP and ExxonMobil. Neither company is acting responsibly. They are racing to maximize extraction while the window to act closes, and gambling with our lives. More below.
September 12, 2026 at 1:14 PM
I resigned from ExxonMobil today. I spent the last three years doing fossil fuel extraction research at both BP and ExxonMobil. Neither company is acting responsibly. They are racing to maximize extraction while the window to act closes, and gambling with our lives. More below.
Reposted by Ekin Deniz Aksu
In 2023, @nature.com published 'Papers and patents are becoming less disruptive over time', receiving world-wide media attention. Our Matters Arising, published after a 32 month delay (more on that soon), shows that the reported decline can largely be attributed to dataset artefacts. 🧵
August 13, 2026 at 10:19 AM
In 2023, @nature.com published 'Papers and patents are becoming less disruptive over time', receiving world-wide media attention. Our Matters Arising, published after a 32 month delay (more on that soon), shows that the reported decline can largely be attributed to dataset artefacts. 🧵
Reposted by Ekin Deniz Aksu
"Here we describe a systematic effort (‘Codebook’) to determine the sequence specificity of 332 putative and poorly characterized human TFs."
www.nature.com/articles/s41...
www.nature.com/articles/s41...
An expanded codebook of human transcription factor DNA-binding specificity - Nature
Results from a panel of assays that analyse different aspects of DNA sequence specificity reveal more than 100 new motifs to aid the characterization of putative human transcription factors.
www.nature.com
August 5, 2026 at 6:55 PM
"Here we describe a systematic effort (‘Codebook’) to determine the sequence specificity of 332 putative and poorly characterized human TFs."
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Reposted by Ekin Deniz Aksu
In a new study in Nature Communications, Martin Vingron and @ekindea.bsky.social present "Corgi", an AI-based tool that allows researchers to predict how the genome behaves across different cell types.
Read more: www.molgen.mpg.de/news-2026-le...
Original publication: doi.org/10.1038/s414...
Read more: www.molgen.mpg.de/news-2026-le...
Original publication: doi.org/10.1038/s414...
July 21, 2026 at 3:51 PM
In a new study in Nature Communications, Martin Vingron and @ekindea.bsky.social present "Corgi", an AI-based tool that allows researchers to predict how the genome behaves across different cell types.
Read more: www.molgen.mpg.de/news-2026-le...
Original publication: doi.org/10.1038/s414...
Read more: www.molgen.mpg.de/news-2026-le...
Original publication: doi.org/10.1038/s414...
Reposted by Ekin Deniz Aksu
1/ I'm excited to share that we're launching NECB 2026, the inaugural New England Computational Biology Symposium. Oct 1-2 at Microsoft Research New England, Cambridge. Two days of keynotes,talks, and posters to bring our community together across institutions.Space is limited. newenglandcompbio.org
July 17, 2026 at 9:48 PM
1/ I'm excited to share that we're launching NECB 2026, the inaugural New England Computational Biology Symposium. Oct 1-2 at Microsoft Research New England, Cambridge. Two days of keynotes,talks, and posters to bring our community together across institutions.Space is limited. newenglandcompbio.org
I'm excited to share that Corgi is out in
@natcomms.nature.com!
We refine context-aware sequence-to-function models by using FiLM to condition the model on trans-regulator expression levels. This way Corgi can generalize to unseen cell types.
www.nature.com/articles/s41...
🧵Thread 1/n
@natcomms.nature.com!
We refine context-aware sequence-to-function models by using FiLM to condition the model on trans-regulator expression levels. This way Corgi can generalize to unseen cell types.
www.nature.com/articles/s41...
🧵Thread 1/n
Context-aware sequence-to-function model of human gene regulation - Nature Communications
This study introduces Corgi and Corgi+ , biology-inspired deep neural network models of regulatory DNA sequences that can generalize to unseen cell types. They accurately impute epigenomic d...
www.nature.com
July 15, 2026 at 9:21 AM
I'm excited to share that Corgi is out in
@natcomms.nature.com!
We refine context-aware sequence-to-function models by using FiLM to condition the model on trans-regulator expression levels. This way Corgi can generalize to unseen cell types.
www.nature.com/articles/s41...
🧵Thread 1/n
@natcomms.nature.com!
We refine context-aware sequence-to-function models by using FiLM to condition the model on trans-regulator expression levels. This way Corgi can generalize to unseen cell types.
www.nature.com/articles/s41...
🧵Thread 1/n
Reposted by Ekin Deniz Aksu
My first PhD paper is out in Nucleic Acids Research! We describe "Ab-trapping" - an antibody artifact that distorts assays relying on antibody diffusion (microscopy, CUT&Tag, CUT&RUN). The revisions made the story much stronger. Check it out!
doi.org/10.1093/nar/...
doi.org/10.1093/nar/...
Antibody-trapping presents a widespread pitfall for microscopy and genomics in the nucleus
Abstract. Chromatin has a complex 3D structure and diverse binding proteins that coordinate the genome’s most essential functions. Many microscopy and geno
doi.org
June 30, 2026 at 9:19 AM
My first PhD paper is out in Nucleic Acids Research! We describe "Ab-trapping" - an antibody artifact that distorts assays relying on antibody diffusion (microscopy, CUT&Tag, CUT&RUN). The revisions made the story much stronger. Check it out!
doi.org/10.1093/nar/...
doi.org/10.1093/nar/...
Reposted by Ekin Deniz Aksu
I have been thinking since yesterday about why I find the 1% thing so, so disturbing. It's a visceral reaction of 'just no', which goes beyond the general yuck towards the enshittification of/via AI. I have finally put my finger on it: it is the feeling you get when
June 26, 2026 at 4:21 PM
I have been thinking since yesterday about why I find the 1% thing so, so disturbing. It's a visceral reaction of 'just no', which goes beyond the general yuck towards the enshittification of/via AI. I have finally put my finger on it: it is the feeling you get when
Reposted by Ekin Deniz Aksu
(1/n) Very excited to share tri-lab collab (Mirny & Zechner) led by Harvey, Henrik & Jack:
Q: How do enhancers & promoters interact in space (contact vs. action-at-a-distance) and time (stable vs. transient)?
A: Transient E-P contact (~25-42 nm lasting ~10-20 sec):
www.biorxiv.org/content/10.6...
Q: How do enhancers & promoters interact in space (contact vs. action-at-a-distance) and time (stable vs. transient)?
A: Transient E-P contact (~25-42 nm lasting ~10-20 sec):
www.biorxiv.org/content/10.6...
June 22, 2026 at 3:32 PM
(1/n) Very excited to share tri-lab collab (Mirny & Zechner) led by Harvey, Henrik & Jack:
Q: How do enhancers & promoters interact in space (contact vs. action-at-a-distance) and time (stable vs. transient)?
A: Transient E-P contact (~25-42 nm lasting ~10-20 sec):
www.biorxiv.org/content/10.6...
Q: How do enhancers & promoters interact in space (contact vs. action-at-a-distance) and time (stable vs. transient)?
A: Transient E-P contact (~25-42 nm lasting ~10-20 sec):
www.biorxiv.org/content/10.6...
Reposted by Ekin Deniz Aksu
A new Science study shows that bumble bees can position a ball underneath a fake “flower” to reach a reward, suggesting they can exhibit spontaneous problem-solving and challenging the notion that such advanced cognitive abilities are exclusive to large-brained vertebrates. https://scim.ag/4vs08dC
June 14, 2026 at 8:17 PM
A new Science study shows that bumble bees can position a ball underneath a fake “flower” to reach a reward, suggesting they can exhibit spontaneous problem-solving and challenging the notion that such advanced cognitive abilities are exclusive to large-brained vertebrates. https://scim.ag/4vs08dC
Reposted by Ekin Deniz Aksu
Exciting breakthrough technology from the lab, now live in
@cellcellpress.bsky.social
! Instead of cutting the genome where proteins bind (e.g., Cut&Tag), D&D-seq scars the DNA with a deaminase, allowing single cell genome mapping of TFs and chromatin remodellers!
@cellcellpress.bsky.social
! Instead of cutting the genome where proteins bind (e.g., Cut&Tag), D&D-seq scars the DNA with a deaminase, allowing single cell genome mapping of TFs and chromatin remodellers!
June 4, 2026 at 3:50 PM
Exciting breakthrough technology from the lab, now live in
@cellcellpress.bsky.social
! Instead of cutting the genome where proteins bind (e.g., Cut&Tag), D&D-seq scars the DNA with a deaminase, allowing single cell genome mapping of TFs and chromatin remodellers!
@cellcellpress.bsky.social
! Instead of cutting the genome where proteins bind (e.g., Cut&Tag), D&D-seq scars the DNA with a deaminase, allowing single cell genome mapping of TFs and chromatin remodellers!
This is insane.
TL;DR: We've identified more than 100 cases of apparent manipulation in Thermo Fisher Scientific's antibody verification data.
@sholtodavid.bsky.social @johanduchene.bsky.social
reeserichardson.blog/2026/05/28/h...
@sholtodavid.bsky.social @johanduchene.bsky.social
reeserichardson.blog/2026/05/28/h...
How much of Thermo Fisher’s antibody data has been manipulated?
We’ve documented more than 100 instances of apparent data manipulation in Thermo’s catalog
reeserichardson.blog
May 29, 2026 at 5:55 AM
This is insane.
Reposted by Ekin Deniz Aksu
TL;DR: We've identified more than 100 cases of apparent manipulation in Thermo Fisher Scientific's antibody verification data.
@sholtodavid.bsky.social @johanduchene.bsky.social
reeserichardson.blog/2026/05/28/h...
@sholtodavid.bsky.social @johanduchene.bsky.social
reeserichardson.blog/2026/05/28/h...
How much of Thermo Fisher’s antibody data has been manipulated?
We’ve documented more than 100 instances of apparent data manipulation in Thermo’s catalog
reeserichardson.blog
May 28, 2026 at 5:48 PM
TL;DR: We've identified more than 100 cases of apparent manipulation in Thermo Fisher Scientific's antibody verification data.
@sholtodavid.bsky.social @johanduchene.bsky.social
reeserichardson.blog/2026/05/28/h...
@sholtodavid.bsky.social @johanduchene.bsky.social
reeserichardson.blog/2026/05/28/h...
I'm very happy to say that my first first-author paper has been published in Bioinf. Advances! 1/2
academic.oup.com/bioinformati...
academic.oup.com/bioinformati...
May 23, 2026 at 11:43 AM
I'm very happy to say that my first first-author paper has been published in Bioinf. Advances! 1/2
academic.oup.com/bioinformati...
academic.oup.com/bioinformati...
Reposted by Ekin Deniz Aksu
🔬 Latest research in Bioinformatics Advances: "Modeling strategies for in vivo transcription factor binding predictions"
Read it here: https://doi.org/10.1093/bioadv/vbag123
Authors include: @ekindea.bsky.social
Read it here: https://doi.org/10.1093/bioadv/vbag123
Authors include: @ekindea.bsky.social
May 21, 2026 at 9:30 AM
🔬 Latest research in Bioinformatics Advances: "Modeling strategies for in vivo transcription factor binding predictions"
Read it here: https://doi.org/10.1093/bioadv/vbag123
Authors include: @ekindea.bsky.social
Read it here: https://doi.org/10.1093/bioadv/vbag123
Authors include: @ekindea.bsky.social
Reposted by Ekin Deniz Aksu
Very excited to share our newest findings! A very long team effort pursued by multiple team members -to frantically reproduce everything over and over-, we show mTOR-Polycomb synergy at promoters of developmental master regulator TFs in ESCs prior to their expression. www.biorxiv.org/content/10.6...
www.biorxiv.org
May 3, 2026 at 6:31 PM
Very excited to share our newest findings! A very long team effort pursued by multiple team members -to frantically reproduce everything over and over-, we show mTOR-Polycomb synergy at promoters of developmental master regulator TFs in ESCs prior to their expression. www.biorxiv.org/content/10.6...
Does this mean the end of the central dogma?
I am so excited to share our new findings with you! We provide the structural evidence for a direct protein-to-DNA information pathway, showing how a bacterial enzyme 'reads' its own structure to 'write' DNA. www.science.org/doi/10.1126/...
April 18, 2026 at 1:49 PM
Does this mean the end of the central dogma?
Reposted by Ekin Deniz Aksu
I am so excited to share our new findings with you! We provide the structural evidence for a direct protein-to-DNA information pathway, showing how a bacterial enzyme 'reads' its own structure to 'write' DNA. www.science.org/doi/10.1126/...
April 16, 2026 at 10:55 PM
I am so excited to share our new findings with you! We provide the structural evidence for a direct protein-to-DNA information pathway, showing how a bacterial enzyme 'reads' its own structure to 'write' DNA. www.science.org/doi/10.1126/...