Chaitanya K. Joshi
@chaitjo.bsky.social
PhD student at University of Cambridge. Intern at FAIR, Meta & Prescient Design, Genentech. Deep Learning for Biomolecule Design.
https://chaitjo.com
https://chaitjo.com
Pinned
Chaitanya K. Joshi
@chaitjo.bsky.social
· Mar 10
Introducing All-atom Diffusion Transformers
— towards Foundation Models for generative chemistry, from my internship with the FAIR Chemistry team
There are a couple ML ideas which I think are new and exciting in here 👇
— towards Foundation Models for generative chemistry, from my internship with the FAIR Chemistry team
There are a couple ML ideas which I think are new and exciting in here 👇
Why do 'frontier' labs train the best models?
I think its because training deep learning models is less like science/engineering, and more like cooking. It takes some time to develop the intuitions around learning dynamics of big models.
I think its because training deep learning models is less like science/engineering, and more like cooking. It takes some time to develop the intuitions around learning dynamics of big models.
October 18, 2025 at 5:30 AM
Why do 'frontier' labs train the best models?
I think its because training deep learning models is less like science/engineering, and more like cooking. It takes some time to develop the intuitions around learning dynamics of big models.
I think its because training deep learning models is less like science/engineering, and more like cooking. It takes some time to develop the intuitions around learning dynamics of big models.
Reposted by Chaitanya K. Joshi
The results are in: top codes in Stanford #RNA 3D Folding @kaggle.com competition are competitive with CASP16-leading humans Vfold, beat AlphaFold 3. Top team’s trick was template-based modeling, not #DeepLearning. Congrats: john, odat, Eigen, + all 1706 participants! www.kaggle.com/competitions...
September 24, 2025 at 4:21 PM
The results are in: top codes in Stanford #RNA 3D Folding @kaggle.com competition are competitive with CASP16-leading humans Vfold, beat AlphaFold 3. Top team’s trick was template-based modeling, not #DeepLearning. Congrats: john, odat, Eigen, + all 1706 participants! www.kaggle.com/competitions...
Reposted by Chaitanya K. Joshi
🚨To accommodate the addition of EuroMLSB, we have extended the submission deadline to October 1, 2025 11:59pm AoE.
Find information on paper guidelines at mlsb.io. Submissions will be made through CMT.
Find information on paper guidelines at mlsb.io. Submissions will be made through CMT.
📢The submission portal for MLSB 2025 is live! Submissions are due September 26, 2025 11:59 pm AoE. cmt3.research.microsoft.com/MLSB2025
September 17, 2025 at 2:59 PM
🚨To accommodate the addition of EuroMLSB, we have extended the submission deadline to October 1, 2025 11:59pm AoE.
Find information on paper guidelines at mlsb.io. Submissions will be made through CMT.
Find information on paper guidelines at mlsb.io. Submissions will be made through CMT.
Reposted by Chaitanya K. Joshi
Genome language models can generate new, high-fitness bacteriophages!
@samuelhking.bsky.social @claudiadriscoll.bsky.social
@david-li.bsky.social @danguo.bsky.social @adititm.bsky.social Garyk Brixi @maxewilkinson.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.1...
@samuelhking.bsky.social @claudiadriscoll.bsky.social
@david-li.bsky.social @danguo.bsky.social @adititm.bsky.social Garyk Brixi @maxewilkinson.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.1...
September 17, 2025 at 9:15 PM
Genome language models can generate new, high-fitness bacteriophages!
@samuelhking.bsky.social @claudiadriscoll.bsky.social
@david-li.bsky.social @danguo.bsky.social @adititm.bsky.social Garyk Brixi @maxewilkinson.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.1...
@samuelhking.bsky.social @claudiadriscoll.bsky.social
@david-li.bsky.social @danguo.bsky.social @adititm.bsky.social Garyk Brixi @maxewilkinson.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.1...
Reposted by Chaitanya K. Joshi
Many of the most complex and useful functions in biology emerge at the scale of whole genomes.
Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵
Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵
September 17, 2025 at 3:03 PM
Many of the most complex and useful functions in biology emerge at the scale of whole genomes.
Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵
Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵
Reposted by Chaitanya K. Joshi
very cool work and a milestone in synthetic biology. how impressive are the new phage genomes?
with generative bioML, i'm always looking at how similar the generated sequences are to known sequences. let's take a look
with generative bioML, i'm always looking at how similar the generated sequences are to known sequences. let's take a look
Many of the most complex and useful functions in biology emerge at the scale of whole genomes.
Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵
Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵
September 18, 2025 at 3:30 AM
very cool work and a milestone in synthetic biology. how impressive are the new phage genomes?
with generative bioML, i'm always looking at how similar the generated sequences are to known sequences. let's take a look
with generative bioML, i'm always looking at how similar the generated sequences are to known sequences. let's take a look
Reposted by Chaitanya K. Joshi
You asked and we listened... @workshopmlsb.bsky.social is excited to be expanding to Copenhagen, DK at @euripsconf.bsky.social 🎉
Two workshops (San Diego & Copenhagen) will run concurrently to support broader attendance. You can indicate your location preference(s) in the submission portal💫
Two workshops (San Diego & Copenhagen) will run concurrently to support broader attendance. You can indicate your location preference(s) in the submission portal💫
September 12, 2025 at 12:43 PM
You asked and we listened... @workshopmlsb.bsky.social is excited to be expanding to Copenhagen, DK at @euripsconf.bsky.social 🎉
Two workshops (San Diego & Copenhagen) will run concurrently to support broader attendance. You can indicate your location preference(s) in the submission portal💫
Two workshops (San Diego & Copenhagen) will run concurrently to support broader attendance. You can indicate your location preference(s) in the submission portal💫
The 3D structure of biomolecules are nature's 'thinking tokens' enroute to the output that we actually truly want to understand: Function.
(Slide from Denny Zhou's Stanford talk on LLM Reasoning)
(Slide from Denny Zhou's Stanford talk on LLM Reasoning)
September 5, 2025 at 4:01 AM
The 3D structure of biomolecules are nature's 'thinking tokens' enroute to the output that we actually truly want to understand: Function.
(Slide from Denny Zhou's Stanford talk on LLM Reasoning)
(Slide from Denny Zhou's Stanford talk on LLM Reasoning)
Reposted by Chaitanya K. Joshi
We have restarted our global Nucleic Acid Strcuture webinar series to bring the expiremental and computational communities together to discuss new developments in the field. Join us this Thursday for the next webinar. Sign up to our mailing list here: groups.google.com/g/casp-rna-sig
September 2, 2025 at 5:50 PM
We have restarted our global Nucleic Acid Strcuture webinar series to bring the expiremental and computational communities together to discuss new developments in the field. Join us this Thursday for the next webinar. Sign up to our mailing list here: groups.google.com/g/casp-rna-sig
Scaling laws for BioML and wet lab data will eventually work out in the right setting! After all, language data for LLMs was acquired by the largest wet lab experiment ever conducted: Human civilisation 🤯
August 31, 2025 at 5:31 AM
Scaling laws for BioML and wet lab data will eventually work out in the right setting! After all, language data for LLMs was acquired by the largest wet lab experiment ever conducted: Human civilisation 🤯
Reposted by Chaitanya K. Joshi
(1/7)
Training biomolecular foundation models shouldn't be so hard. And open-source structure prediction is important. So today we're releasing two software packages: AtomWorks and RosettaFold3 (RF3)
[https://www.biorxiv.org/content/10.1101/2025.08.14.670328v2](www.biorxiv.org/content/10.1...)
Training biomolecular foundation models shouldn't be so hard. And open-source structure prediction is important. So today we're releasing two software packages: AtomWorks and RosettaFold3 (RF3)
[https://www.biorxiv.org/content/10.1101/2025.08.14.670328v2](www.biorxiv.org/content/10.1...)
Accelerating Biomolecular Modeling with AtomWorks and RF3
Deep learning methods trained on protein structure databases have revolutionized biomolecular structure prediction, but developing and training new models remains a considerable challenge. To facilita...
www.biorxiv.org
August 15, 2025 at 5:17 PM
(1/7)
Training biomolecular foundation models shouldn't be so hard. And open-source structure prediction is important. So today we're releasing two software packages: AtomWorks and RosettaFold3 (RF3)
[https://www.biorxiv.org/content/10.1101/2025.08.14.670328v2](www.biorxiv.org/content/10.1...)
Training biomolecular foundation models shouldn't be so hard. And open-source structure prediction is important. So today we're releasing two software packages: AtomWorks and RosettaFold3 (RF3)
[https://www.biorxiv.org/content/10.1101/2025.08.14.670328v2](www.biorxiv.org/content/10.1...)
📢 Submissions for MLSB 2025 are officially open! We invite researchers to submit their work on the intersection of AI and structural biology.
🗓️ Deadline: September 26, 2025 🔗 More info: cmt3.research.microsoft.com/MLSB2025
🗓️ Deadline: September 26, 2025 🔗 More info: cmt3.research.microsoft.com/MLSB2025
MLSB 2025 Workshop
Workshop on Machine Learning in Structural Biology co-located with NeurIPS 2025
www.mlsb.io
August 15, 2025 at 6:10 PM
📢 Submissions for MLSB 2025 are officially open! We invite researchers to submit their work on the intersection of AI and structural biology.
🗓️ Deadline: September 26, 2025 🔗 More info: cmt3.research.microsoft.com/MLSB2025
🗓️ Deadline: September 26, 2025 🔗 More info: cmt3.research.microsoft.com/MLSB2025
RosettaFold 3 is here! 🧬🚀
AtomWorks (the foundational data pipeline powering it) is perhaps the really most exciting part of this release!
Congratulations @simonmathis.bsky.social and team!!! ❤️
bioRxiv preprint: www.biorxiv.org/content/10.1...
AtomWorks (the foundational data pipeline powering it) is perhaps the really most exciting part of this release!
Congratulations @simonmathis.bsky.social and team!!! ❤️
bioRxiv preprint: www.biorxiv.org/content/10.1...
August 15, 2025 at 1:26 PM
RosettaFold 3 is here! 🧬🚀
AtomWorks (the foundational data pipeline powering it) is perhaps the really most exciting part of this release!
Congratulations @simonmathis.bsky.social and team!!! ❤️
bioRxiv preprint: www.biorxiv.org/content/10.1...
AtomWorks (the foundational data pipeline powering it) is perhaps the really most exciting part of this release!
Congratulations @simonmathis.bsky.social and team!!! ❤️
bioRxiv preprint: www.biorxiv.org/content/10.1...
Really insightful post and responses - this is why I keep coming back to science social media!
We’re getting more and more papers on de novo protein design, but I still don’t really know what it means
What’s your definition of de novo design?
What’s your definition of de novo design?
August 1, 2025 at 7:53 AM
Really insightful post and responses - this is why I keep coming back to science social media!
🧬 Protein designers: we keep saying we're getting really good at making static, rock-like proteins...
Introducing Dynamic MPNN - our first step towards truly multi-state and 'programmable' protein design! Great collaboration led by Alex Abrudan and Sebastian Pujalte!
Introducing Dynamic MPNN - our first step towards truly multi-state and 'programmable' protein design! Great collaboration led by Alex Abrudan and Sebastian Pujalte!
July 31, 2025 at 6:11 PM
🧬 Protein designers: we keep saying we're getting really good at making static, rock-like proteins...
Introducing Dynamic MPNN - our first step towards truly multi-state and 'programmable' protein design! Great collaboration led by Alex Abrudan and Sebastian Pujalte!
Introducing Dynamic MPNN - our first step towards truly multi-state and 'programmable' protein design! Great collaboration led by Alex Abrudan and Sebastian Pujalte!
Reposted by Chaitanya K. Joshi
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 Chaitanya K. Joshi
Coming up this weekend, Eternacon will feature presentations about fellow #citsci platform @zooniverse.bsky.social and how participants of both Zooniverse and Eterna have created #machinelearning tools for projects. @noirlabastro.bsky.social
Register for free at eternagame.org/eternacon/2025
Register for free at eternagame.org/eternacon/2025
July 23, 2025 at 8:16 PM
Coming up this weekend, Eternacon will feature presentations about fellow #citsci platform @zooniverse.bsky.social and how participants of both Zooniverse and Eterna have created #machinelearning tools for projects. @noirlabastro.bsky.social
Register for free at eternagame.org/eternacon/2025
Register for free at eternagame.org/eternacon/2025
Reposted by Chaitanya K. Joshi
Are we hitting a wall with scaling molecular foundation models?
Some thoughts on what I think is one of the most interesting open Qs atm: chaitjo.substack.com/p/transfer-l...
Some thoughts on what I think is one of the most interesting open Qs atm: chaitjo.substack.com/p/transfer-l...
Towards transfer learning in molecular foundation models
Are multi-modal molecular foundation models learning transferable representations across biology and chemistry?
chaitjo.substack.com
July 16, 2025 at 10:25 AM
Are we hitting a wall with scaling molecular foundation models?
Some thoughts on what I think is one of the most interesting open Qs atm: chaitjo.substack.com/p/transfer-l...
Some thoughts on what I think is one of the most interesting open Qs atm: chaitjo.substack.com/p/transfer-l...
Reposted by Chaitanya K. Joshi
How does a cell know when it’s been damaged? A molecular alarm, set off by mutated RNA and colliding ribosomes, signals danger. @dsamorod.bsky.social reports: www.quantamagazine.org/rna-is-the-c...
RNA Is the Cell’s Emergency Alert System | Quanta Magazine
How does a cell know when it’s been damaged? A molecular alarm, set off by mutated RNA and colliding ribosomes, signals danger.
www.quantamagazine.org
July 14, 2025 at 2:29 PM
How does a cell know when it’s been damaged? A molecular alarm, set off by mutated RNA and colliding ribosomes, signals danger. @dsamorod.bsky.social reports: www.quantamagazine.org/rna-is-the-c...
Reposted by Chaitanya K. Joshi
We are looking to recruit a tenure track group leader in the field of Chemical/Synthetic Biology (in the broadest sense) to lead a research program within the Division of Protein & Nucleic Acid Chemistry ( www.jobs.ac.uk/job/DNW809/r... ) at the MRC Laboratory of Molecular Biology (LMB).
Research Group Leader in Chemical/Synthetic Biology at MRC Laboratory of Molecular Biology
Start your UK & international job search for academic jobs, research jobs, science jobs and managerial jobs in leading universities and top...
www.jobs.ac.uk
July 14, 2025 at 12:10 PM
We are looking to recruit a tenure track group leader in the field of Chemical/Synthetic Biology (in the broadest sense) to lead a research program within the Division of Protein & Nucleic Acid Chemistry ( www.jobs.ac.uk/job/DNW809/r... ) at the MRC Laboratory of Molecular Biology (LMB).
Reposted by Chaitanya K. Joshi
Highly collaborative efforts that involved 6 lab members and the labs of @yiliangding.bsky.social and @rdaslab.bsky.social. We uncovered a telomerase dimer and its potential role in telomere maintenance.
Sebastian Balch, Zala Sekne & Elsa Franco-Echevarría in @kellythd-nguyen.bsky.social's group have confirmed the existence of dimeric telomerase and illustrated how it is key to telomere maintenance:
www2.mrc-lmb.cam.ac.uk/first-struct...
#LMBResearch @yiliangding.bsky.social @rdaslab.bsky.social 🧪
www2.mrc-lmb.cam.ac.uk/first-struct...
#LMBResearch @yiliangding.bsky.social @rdaslab.bsky.social 🧪
July 11, 2025 at 10:22 AM
Highly collaborative efforts that involved 6 lab members and the labs of @yiliangding.bsky.social and @rdaslab.bsky.social. We uncovered a telomerase dimer and its potential role in telomere maintenance.
Reposted by Chaitanya K. Joshi
Unfortunately, the MLSB Workshop @ NeurIPS (@workshopmlsb.bsky.social) was rejected this year.
Feedback from the deciding committee indicates it was a coin flip decision, with 283 proposals & a number related to “computational biology”
More on the future of MLSB soon…
Feedback from the deciding committee indicates it was a coin flip decision, with 283 proposals & a number related to “computational biology”
More on the future of MLSB soon…
July 7, 2025 at 2:21 PM
Unfortunately, the MLSB Workshop @ NeurIPS (@workshopmlsb.bsky.social) was rejected this year.
Feedback from the deciding committee indicates it was a coin flip decision, with 283 proposals & a number related to “computational biology”
More on the future of MLSB soon…
Feedback from the deciding committee indicates it was a coin flip decision, with 283 proposals & a number related to “computational biology”
More on the future of MLSB soon…
Needing a permanent doi was a forcing function to revisit this article on Transformers and Graph Neural Networks: arxiv.org/abs/2506.22084
This is (very) old news, so what's new?
This is (very) old news, so what's new?
June 30, 2025 at 9:22 AM
Needing a permanent doi was a forcing function to revisit this article on Transformers and Graph Neural Networks: arxiv.org/abs/2506.22084
This is (very) old news, so what's new?
This is (very) old news, so what's new?
This was posed by a VC (@dreidco.bsky.social ) on LinkedIn.
Just a thought: Maybe Boltz-2 is also a moment similar to GPT-3 where a sizeable part of the community moves on from academic publishing
and to the world of capabilities, tech reports, and shipping models
Just a thought: Maybe Boltz-2 is also a moment similar to GPT-3 where a sizeable part of the community moves on from academic publishing
and to the world of capabilities, tech reports, and shipping models
June 28, 2025 at 2:30 PM
This was posed by a VC (@dreidco.bsky.social ) on LinkedIn.
Just a thought: Maybe Boltz-2 is also a moment similar to GPT-3 where a sizeable part of the community moves on from academic publishing
and to the world of capabilities, tech reports, and shipping models
Just a thought: Maybe Boltz-2 is also a moment similar to GPT-3 where a sizeable part of the community moves on from academic publishing
and to the world of capabilities, tech reports, and shipping models