Janani Durairaj (Jay)
@ninjani.bsky.social
Computational biologist @biozentrum.bsky.social. Likes protein structures.
https://ninjani.github.io/
https://ninjani.github.io/
Pinned
Fresh from bioRxiv our latest work introducing The Embedded Alphabet (TEA), a powerful new representation for protein sequences obtained by discretising ESM2 embeddings into 20 characters.
Pre-print: www.biorxiv.org/content/10.1...
🧵👇(1/n)
Pre-print: www.biorxiv.org/content/10.1...
🧵👇(1/n)
Rewriting protein alphabets with language models
Detecting remote homology with speed and sensitivity is crucial for tasks like function annotation and structure prediction. We introduce a novel approach using contrastive learning to convert protein...
www.biorxiv.org
Been excited about this one for a while! What would you do with a new alphabet and the wealth of protein sequence bioinformatics at your disposal? We're also around at #EMBOComp3D Heidelberg and MLSB Copenhagen this week to discuss
Reposted by Janani Durairaj (Jay)
My time in @martinsteinegger.bsky.social's group is ending, but I’m staying in Korea to build a lab at Sungkyunkwan University School of Medicine. If you or someone you know is interested in molecular machine learning and open-source bioinformatics, please reach out. I am hiring!
mirdita.org
mirdita.org
Mirdita Lab - Laboratory for Computational Biology & Molecular Machine Learning
Mirdita Lab builds scalable bioinformatics methods.
mirdita.org
January 20, 2026 at 11:07 AM
My time in @martinsteinegger.bsky.social's group is ending, but I’m staying in Korea to build a lab at Sungkyunkwan University School of Medicine. If you or someone you know is interested in molecular machine learning and open-source bioinformatics, please reach out. I am hiring!
mirdita.org
mirdita.org
Reposted by Janani Durairaj (Jay)
Reposted by Janani Durairaj (Jay)
I'm really excited to break up the holiday relaxation time with a new preprint that benchmarks AlphaFold3 (AF3)/“co-folding” methods with 2 new stringent performance tests.
Thread below - but first some links:
A longer take:
fraserlab.com/2025/12/29/k...
Preprint:
www.biorxiv.org/content/10.6...
Thread below - but first some links:
A longer take:
fraserlab.com/2025/12/29/k...
Preprint:
www.biorxiv.org/content/10.6...
Know when to co-fold'em
This is the official web page for the James Fraser Lab at UCSF.
fraserlab.com
December 29, 2025 at 10:25 PM
I'm really excited to break up the holiday relaxation time with a new preprint that benchmarks AlphaFold3 (AF3)/“co-folding” methods with 2 new stringent performance tests.
Thread below - but first some links:
A longer take:
fraserlab.com/2025/12/29/k...
Preprint:
www.biorxiv.org/content/10.6...
Thread below - but first some links:
A longer take:
fraserlab.com/2025/12/29/k...
Preprint:
www.biorxiv.org/content/10.6...
Reposted by Janani Durairaj (Jay)
🚀 New paper in @natmethods.nature.com!
We present OpenStructure's powerful scoring capabilities, used to assess predictionsin CAMEO and CASP.
Read the full study here:
🔗 doi.org/10.1038/s415...
#StructuralBiology #Bioinformatics #OpenStructure #CASP #CAMEO #ProteinStructure
We present OpenStructure's powerful scoring capabilities, used to assess predictionsin CAMEO and CASP.
Read the full study here:
🔗 doi.org/10.1038/s415...
#StructuralBiology #Bioinformatics #OpenStructure #CASP #CAMEO #ProteinStructure
doi.org
December 23, 2025 at 3:18 PM
🚀 New paper in @natmethods.nature.com!
We present OpenStructure's powerful scoring capabilities, used to assess predictionsin CAMEO and CASP.
Read the full study here:
🔗 doi.org/10.1038/s415...
#StructuralBiology #Bioinformatics #OpenStructure #CASP #CAMEO #ProteinStructure
We present OpenStructure's powerful scoring capabilities, used to assess predictionsin CAMEO and CASP.
Read the full study here:
🔗 doi.org/10.1038/s415...
#StructuralBiology #Bioinformatics #OpenStructure #CASP #CAMEO #ProteinStructure
Been excited about this one for a while! What would you do with a new alphabet and the wealth of protein sequence bioinformatics at your disposal? We're also around at #EMBOComp3D Heidelberg and MLSB Copenhagen this week to discuss
Fresh from bioRxiv our latest work introducing The Embedded Alphabet (TEA), a powerful new representation for protein sequences obtained by discretising ESM2 embeddings into 20 characters.
Pre-print: www.biorxiv.org/content/10.1...
🧵👇(1/n)
Pre-print: www.biorxiv.org/content/10.1...
🧵👇(1/n)
Rewriting protein alphabets with language models
Detecting remote homology with speed and sensitivity is crucial for tasks like function annotation and structure prediction. We introduce a novel approach using contrastive learning to convert protein...
www.biorxiv.org
December 1, 2025 at 10:58 AM
Been excited about this one for a while! What would you do with a new alphabet and the wealth of protein sequence bioinformatics at your disposal? We're also around at #EMBOComp3D Heidelberg and MLSB Copenhagen this week to discuss
Reposted by Janani Durairaj (Jay)
OpenFold3-preview (OF3p) is out: a sneak peek of our AF3-based structure prediction model. Our aim for OF3 is full AF3-parity for every modality. We now believe we have a clear path towards this goal and are releasing OF3p to enable building in the OF3 ecosystem. More👇
October 28, 2025 at 6:30 PM
OpenFold3-preview (OF3p) is out: a sneak peek of our AF3-based structure prediction model. Our aim for OF3 is full AF3-parity for every modality. We now believe we have a clear path towards this goal and are releasing OF3p to enable building in the OF3 ecosystem. More👇
Reposted by Janani Durairaj (Jay)
This October I’m drawing one molecule a day inspired by proteins in pdb @rcsbpdb.bsky.social
Day 2/31
Prompt WEAVE
N-terminal domain of a Fibrion - a building block of silk fiber produced by silkworms.
Pdb: 3UA0
Next prompt is CROWN and I would love your suggestions!
Day 2/31
Prompt WEAVE
N-terminal domain of a Fibrion - a building block of silk fiber produced by silkworms.
Pdb: 3UA0
Next prompt is CROWN and I would love your suggestions!
October 3, 2025 at 3:29 AM
This October I’m drawing one molecule a day inspired by proteins in pdb @rcsbpdb.bsky.social
Day 2/31
Prompt WEAVE
N-terminal domain of a Fibrion - a building block of silk fiber produced by silkworms.
Pdb: 3UA0
Next prompt is CROWN and I would love your suggestions!
Day 2/31
Prompt WEAVE
N-terminal domain of a Fibrion - a building block of silk fiber produced by silkworms.
Pdb: 3UA0
Next prompt is CROWN and I would love your suggestions!
Reposted by Janani Durairaj (Jay)
Viral AlphaFold Database (VAD) is live in Science Advances
~27,000 predicted viral protein monomers & homodimers
Conserved folds across bacteria, archaea & eukaryotic viruses
New toxin–antitoxin system KreTA uncovered
Vast “functional darkness” remains uncharted
www.science.org/doi/10.1126/...
~27,000 predicted viral protein monomers & homodimers
Conserved folds across bacteria, archaea & eukaryotic viruses
New toxin–antitoxin system KreTA uncovered
Vast “functional darkness” remains uncharted
www.science.org/doi/10.1126/...
The Viral AlphaFold Database of monomers and homodimers reveals conserved protein folds in viruses of bacteria, archaea, and eukaryotes
VAD is a Viral AlphaFold Database of protein monomers and homodimers from viruses infecting hosts across the tree of life.
www.science.org
October 2, 2025 at 8:48 AM
Viral AlphaFold Database (VAD) is live in Science Advances
~27,000 predicted viral protein monomers & homodimers
Conserved folds across bacteria, archaea & eukaryotic viruses
New toxin–antitoxin system KreTA uncovered
Vast “functional darkness” remains uncharted
www.science.org/doi/10.1126/...
~27,000 predicted viral protein monomers & homodimers
Conserved folds across bacteria, archaea & eukaryotic viruses
New toxin–antitoxin system KreTA uncovered
Vast “functional darkness” remains uncharted
www.science.org/doi/10.1126/...
Reposted by Janani Durairaj (Jay)
Océane Follonier @oceanef.bsky.social for
“From bytes to binders: design, score and optimize” #bc2basel #posterprize
“From bytes to binders: design, score and optimize” #bc2basel #posterprize
September 10, 2025 at 2:54 PM
Océane Follonier @oceanef.bsky.social for
“From bytes to binders: design, score and optimize” #bc2basel #posterprize
“From bytes to binders: design, score and optimize” #bc2basel #posterprize
Reposted by Janani Durairaj (Jay)
Critical benchmarking of structure prediction methods has been crucial for measuring progress and detecting breakthroughs. But how will the future look like? Join the discussion at our workshop in Basel on September 8 - just before the [BC]2 conference.
@sib.swiss @biozentrum.unibas.ch
⬇️⬇️⬇️
@sib.swiss @biozentrum.unibas.ch
⬇️⬇️⬇️
🔬 Workshop: Future of Structure Prediction Benchmarking
📅 Sept 8, 2025 | Basel
💡 Talks + breakout sessions on #CASP #CAPRI #CAMEO & benchmarking for drug discovery
🎟️ Free registration (limited spots): lu.ma/ws9nu1xf
Join us to explore how benchmarking can drive breakthroughs in structure prediction.
📅 Sept 8, 2025 | Basel
💡 Talks + breakout sessions on #CASP #CAPRI #CAMEO & benchmarking for drug discovery
🎟️ Free registration (limited spots): lu.ma/ws9nu1xf
Join us to explore how benchmarking can drive breakthroughs in structure prediction.
The future of structure prediction benchmarking: measuring progress and breakthroughs · Luma
Benchmarking has been a key driver of progress in protein structure prediction methods. As the field continues to evolve, several key questions prevail:
How…
lu.ma
August 27, 2025 at 5:32 PM
Critical benchmarking of structure prediction methods has been crucial for measuring progress and detecting breakthroughs. But how will the future look like? Join the discussion at our workshop in Basel on September 8 - just before the [BC]2 conference.
@sib.swiss @biozentrum.unibas.ch
⬇️⬇️⬇️
@sib.swiss @biozentrum.unibas.ch
⬇️⬇️⬇️
Reposted by Janani Durairaj (Jay)
Exciting to see our protein binder design pipeline BindCraft published in its final form in @Nature ! This has been an amazing collaborative effort with Lennart, Christian, @sokrypton.org, Bruno and many other amazing lab members and collaborators.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
August 27, 2025 at 4:14 PM
Exciting to see our protein binder design pipeline BindCraft published in its final form in @Nature ! This has been an amazing collaborative effort with Lennart, Christian, @sokrypton.org, Bruno and many other amazing lab members and collaborators.
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Still some spots left, join us in Basel on Sep 8 (before [BC]2) to discuss structure prediction benchmarking and more!
🔬 Workshop: Future of Structure Prediction Benchmarking
📅 Sept 8, 2025 | Basel
💡 Talks + breakout sessions on #CASP #CAPRI #CAMEO & benchmarking for drug discovery
🎟️ Free registration (limited spots): lu.ma/ws9nu1xf
Join us to explore how benchmarking can drive breakthroughs in structure prediction.
📅 Sept 8, 2025 | Basel
💡 Talks + breakout sessions on #CASP #CAPRI #CAMEO & benchmarking for drug discovery
🎟️ Free registration (limited spots): lu.ma/ws9nu1xf
Join us to explore how benchmarking can drive breakthroughs in structure prediction.
The future of structure prediction benchmarking: measuring progress and breakthroughs · Luma
Benchmarking has been a key driver of progress in protein structure prediction methods. As the field continues to evolve, several key questions prevail:
How…
lu.ma
August 27, 2025 at 8:14 AM
Still some spots left, join us in Basel on Sep 8 (before [BC]2) to discuss structure prediction benchmarking and more!
Reposted by Janani Durairaj (Jay)
🔬 Workshop: Future of Structure Prediction Benchmarking
📅 Sept 8, 2025 | Basel
💡 Talks + breakout sessions on #CASP #CAPRI #CAMEO & benchmarking for drug discovery
🎟️ Free registration (limited spots): lu.ma/ws9nu1xf
Join us to explore how benchmarking can drive breakthroughs in structure prediction.
📅 Sept 8, 2025 | Basel
💡 Talks + breakout sessions on #CASP #CAPRI #CAMEO & benchmarking for drug discovery
🎟️ Free registration (limited spots): lu.ma/ws9nu1xf
Join us to explore how benchmarking can drive breakthroughs in structure prediction.
The future of structure prediction benchmarking: measuring progress and breakthroughs · Luma
Benchmarking has been a key driver of progress in protein structure prediction methods. As the field continues to evolve, several key questions prevail:
How…
lu.ma
August 27, 2025 at 7:59 AM
🔬 Workshop: Future of Structure Prediction Benchmarking
📅 Sept 8, 2025 | Basel
💡 Talks + breakout sessions on #CASP #CAPRI #CAMEO & benchmarking for drug discovery
🎟️ Free registration (limited spots): lu.ma/ws9nu1xf
Join us to explore how benchmarking can drive breakthroughs in structure prediction.
📅 Sept 8, 2025 | Basel
💡 Talks + breakout sessions on #CASP #CAPRI #CAMEO & benchmarking for drug discovery
🎟️ Free registration (limited spots): lu.ma/ws9nu1xf
Join us to explore how benchmarking can drive breakthroughs in structure prediction.
Reposted by Janani Durairaj (Jay)
Join us at #EMBOComp3D to explore cutting-edge breakthroughs in computational structural biology, AI, drug design, and innovative software! 💻
Find out about molecular modelling to systems-level analyses and evolution, and more.
Submit your abstract by 26 Aug ➡️ s.embl.org/csb25-01-bl
Find out about molecular modelling to systems-level analyses and evolution, and more.
Submit your abstract by 26 Aug ➡️ s.embl.org/csb25-01-bl
July 24, 2025 at 11:14 AM
Join us at #EMBOComp3D to explore cutting-edge breakthroughs in computational structural biology, AI, drug design, and innovative software! 💻
Find out about molecular modelling to systems-level analyses and evolution, and more.
Submit your abstract by 26 Aug ➡️ s.embl.org/csb25-01-bl
Find out about molecular modelling to systems-level analyses and evolution, and more.
Submit your abstract by 26 Aug ➡️ s.embl.org/csb25-01-bl
Reposted by Janani Durairaj (Jay)
CATH turns 30 years old this year!
We are organising a 1-day symposium on September 16th at UCL, highlighting recent AI-based developments to enhance protein family classifications, annotations and analyses.
www.eventbrite.co.uk/e/protein-an...
We are organising a 1-day symposium on September 16th at UCL, highlighting recent AI-based developments to enhance protein family classifications, annotations and analyses.
www.eventbrite.co.uk/e/protein-an...
Protein Annotations in the age of AI
A not-for-profit symposium hosted at UCL - more details about speakers and venue below.
www.eventbrite.co.uk
August 22, 2025 at 10:45 AM
CATH turns 30 years old this year!
We are organising a 1-day symposium on September 16th at UCL, highlighting recent AI-based developments to enhance protein family classifications, annotations and analyses.
www.eventbrite.co.uk/e/protein-an...
We are organising a 1-day symposium on September 16th at UCL, highlighting recent AI-based developments to enhance protein family classifications, annotations and analyses.
www.eventbrite.co.uk/e/protein-an...
Reposted by Janani Durairaj (Jay)
AtomWorks is out! Building upon @biotite_python, we built a toolkit for all things biomolecules and trained RF3 with it. All open-source, test it via `pip install atomworks`!
AtomWorks: github.com/RosettaCommo...
RF3: github.com/RosettaCommo...
Paper: tinyurl.com/y2w4z65b
1/6
AtomWorks: github.com/RosettaCommo...
RF3: github.com/RosettaCommo...
Paper: tinyurl.com/y2w4z65b
1/6
August 15, 2025 at 5:44 PM
AtomWorks is out! Building upon @biotite_python, we built a toolkit for all things biomolecules and trained RF3 with it. All open-source, test it via `pip install atomworks`!
AtomWorks: github.com/RosettaCommo...
RF3: github.com/RosettaCommo...
Paper: tinyurl.com/y2w4z65b
1/6
AtomWorks: github.com/RosettaCommo...
RF3: github.com/RosettaCommo...
Paper: tinyurl.com/y2w4z65b
1/6
Reposted by Janani Durairaj (Jay)
Filtering out homologous structures from the PDB at 40% sequence identity is not enough to create a robust test set. Significant leakage persists at this level, and comparative modeling can still produce high quality models.
August 8, 2025 at 7:48 AM
Filtering out homologous structures from the PDB at 40% sequence identity is not enough to create a robust test set. Significant leakage persists at this level, and comparative modeling can still produce high quality models.
Reposted by Janani Durairaj (Jay)
Looking for a #fellowship for an independent #PhD at one of the best places for life sciences in the world?
The summer call at @biozentrum.unibas.ch @unibas.ch is open until October 12, 2025.
www.biozentrum.unibas.ch/phd/internat...
The summer call at @biozentrum.unibas.ch @unibas.ch is open until October 12, 2025.
www.biozentrum.unibas.ch/phd/internat...
Biozentrum PhD Fellowships
Share your passion for life sciences. If you are talented and highly motivated, want to broaden your horizons and are interested in a wide range of research topics, apply for one of the sought after B...
www.biozentrum.unibas.ch
August 7, 2025 at 4:17 AM
Looking for a #fellowship for an independent #PhD at one of the best places for life sciences in the world?
The summer call at @biozentrum.unibas.ch @unibas.ch is open until October 12, 2025.
www.biozentrum.unibas.ch/phd/internat...
The summer call at @biozentrum.unibas.ch @unibas.ch is open until October 12, 2025.
www.biozentrum.unibas.ch/phd/internat...
Reposted by Janani Durairaj (Jay)
Excited to share work with
Zhidian Zhang, @milot.bsky.social, @martinsteinegger.bsky.social, and @sokrypton.org
biorxiv.org/content/10.1...
TLDR: We introduce MSA Pairformer, a 111M parameter protein language model that challenges the scaling paradigm in self-supervised protein language modeling🧵
Zhidian Zhang, @milot.bsky.social, @martinsteinegger.bsky.social, and @sokrypton.org
biorxiv.org/content/10.1...
TLDR: We introduce MSA Pairformer, a 111M parameter protein language model that challenges the scaling paradigm in self-supervised protein language modeling🧵
Scaling down protein language modeling with MSA Pairformer
Recent efforts in protein language modeling have focused on scaling single-sequence models and their training data, requiring vast compute resources that limit accessibility. Although models that use ...
biorxiv.org
August 5, 2025 at 6:31 AM
Excited to share work with
Zhidian Zhang, @milot.bsky.social, @martinsteinegger.bsky.social, and @sokrypton.org
biorxiv.org/content/10.1...
TLDR: We introduce MSA Pairformer, a 111M parameter protein language model that challenges the scaling paradigm in self-supervised protein language modeling🧵
Zhidian Zhang, @milot.bsky.social, @martinsteinegger.bsky.social, and @sokrypton.org
biorxiv.org/content/10.1...
TLDR: We introduce MSA Pairformer, a 111M parameter protein language model that challenges the scaling paradigm in self-supervised protein language modeling🧵
Reposted by Janani Durairaj (Jay)
The big difference is in the pairing. The MMseqs2 server pairs sequences based on species, while our old HHblits MSAs were paired based on genome proximity (number of genes apart). Working w/ @milot.bsky.social and @martinsteinegger.bsky.social we implemented the proximity filtering in server (3/4)
August 5, 2025 at 7:39 AM
The big difference is in the pairing. The MMseqs2 server pairs sequences based on species, while our old HHblits MSAs were paired based on genome proximity (number of genes apart). Working w/ @milot.bsky.social and @martinsteinegger.bsky.social we implemented the proximity filtering in server (3/4)
Reposted by Janani Durairaj (Jay)
I am super excited to announce that I will be starting my lab at the Department of Pharmacology of the University of Zurich in Switzerland next year!
July 25, 2025 at 7:48 AM
I am super excited to announce that I will be starting my lab at the Department of Pharmacology of the University of Zurich in Switzerland next year!
Reposted by Janani Durairaj (Jay)
New Practical Cheminformatics Post
patwalters.github.io/Three-Papers...
patwalters.github.io/Three-Papers...
July 22, 2025 at 1:40 PM
New Practical Cheminformatics Post
patwalters.github.io/Three-Papers...
patwalters.github.io/Three-Papers...
Reposted by Janani Durairaj (Jay)
We will be hosting a mirror site of the CASP data and workflows at @sib.swiss. Operating a redundant site with independent funding is a good idea for important scientific infrastructure, independent from the current funding situation in the US.
July 5, 2025 at 1:48 AM
We will be hosting a mirror site of the CASP data and workflows at @sib.swiss. Operating a redundant site with independent funding is a good idea for important scientific infrastructure, independent from the current funding situation in the US.
Reposted by Janani Durairaj (Jay)
Hello everyone! I am pleased to share information on the first ever Computational Structural Virology Symposium, conducted August 4th on zoom and highlighting work in this emerging field. You can register for this event here: forms.gle/CNiqskMwQEuV.... Please re-post!
June 12, 2025 at 8:31 PM
Hello everyone! I am pleased to share information on the first ever Computational Structural Virology Symposium, conducted August 4th on zoom and highlighting work in this emerging field. You can register for this event here: forms.gle/CNiqskMwQEuV.... Please re-post!
Reposted by Janani Durairaj (Jay)
Read this intro thread 🧵. CAMEO is part of SWISS-MODEL: a protein structure homology-modelling suite of software tools and databases which is one of the 17 resources in our portfolio of leading open biodata resources.
@torstenschwede.bsky.social @xavier.robin.info
@torstenschwede.bsky.social @xavier.robin.info
Introducing CAMEO Structures & Complexes - automated weekly blind benchmarking of structure prediction servers. Now with heteromeric and protein-ligand complexes.
Join us and register your server now!
cameo3d.org
Join us and register your server now!
cameo3d.org
May 22, 2025 at 3:28 PM
Read this intro thread 🧵. CAMEO is part of SWISS-MODEL: a protein structure homology-modelling suite of software tools and databases which is one of the 17 resources in our portfolio of leading open biodata resources.
@torstenschwede.bsky.social @xavier.robin.info
@torstenschwede.bsky.social @xavier.robin.info