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...
cen.acs.org/pharmaceutic...
AI-macrocycle design program licensed by Vilya builds on RoseTTAFold 2 and RFdiffusion
AI-macrocycle design program licensed by Vilya builds on RoseTTAFold 2 and RFdiffusion
Details of RFpeptides released
AI-macrocycle design program licensed by Vilya builds on RoseTTAFold 2 and RFdiffusion
cen.acs.org
December 2, 2024 at 5:33 AM
cen.acs.org/pharmaceutic...
AI-macrocycle design program licensed by Vilya builds on RoseTTAFold 2 and RFdiffusion
AI-macrocycle design program licensed by Vilya builds on RoseTTAFold 2 and RFdiffusion
O Nobel de química de 2024 foi pra design computacional de proteínas e a predição de novas proteínas com o RosettaFold e o AlphaFold! Mas porque isso é importante? Vem no fio que eu explico 🧵1/15
October 9, 2024 at 3:55 PM
O Nobel de química de 2024 foi pra design computacional de proteínas e a predição de novas proteínas com o RosettaFold e o AlphaFold! Mas porque isso é importante? Vem no fio que eu explico 🧵1/15
RoseTTAFold All-Atom "a deep network capable of modeling full biological assemblies containing proteins, nucleic acids, small molecules, metals, and covalent modifications given the sequences of the polymers and the atomic bonded geometry of the small molecules..."
doi.org/10.1101/2023...
doi.org/10.1101/2023...
October 10, 2023 at 5:08 AM
RoseTTAFold All-Atom "a deep network capable of modeling full biological assemblies containing proteins, nucleic acids, small molecules, metals, and covalent modifications given the sequences of the polymers and the atomic bonded geometry of the small molecules..."
doi.org/10.1101/2023...
doi.org/10.1101/2023...
ProteinGenerator simultaneously generates protein sequences and structures using sequence space diffusion go.nature.com/4gGcus0
rdcu.be/eBetI
rdcu.be/eBetI
Multistate and functional protein design using RoseTTAFold sequence space diffusion - Nature Biotechnology
ProteinGenerator simultaneously generates protein sequences and structures using sequence space diffusion.
go.nature.com
August 19, 2025 at 1:17 AM
ProteinGenerator simultaneously generates protein sequences and structures using sequence space diffusion go.nature.com/4gGcus0
rdcu.be/eBetI
rdcu.be/eBetI
Today's discussion with Rohith Krishna about RosettaFold All-atom!
www.youtube.com/watch?v=LAQ4...
www.youtube.com/watch?v=LAQ4...
November 21, 2023 at 12:01 AM
Today's discussion with Rohith Krishna about RosettaFold All-atom!
www.youtube.com/watch?v=LAQ4...
www.youtube.com/watch?v=LAQ4...
@nikomccarty.bsky.social , not recently active on #Bluesky, on the use of RosettaFold/biophysics in-silico modelling to design a "random walker" protein that is 10,000 times more efficient than naturally occurring equivalent ones.
October 6, 2025 at 9:32 AM
@nikomccarty.bsky.social , not recently active on #Bluesky, on the use of RosettaFold/biophysics in-silico modelling to design a "random walker" protein that is 10,000 times more efficient than naturally occurring equivalent ones.
“Structure prediction of protein-ligand complexes from sequence information with Umol” 🧪🧶🧬
Outperforms RosettaFold-AA on held-out data and makes code available - no data vs AlphaFold-latest
www.biorxiv.org/content/10.1...
github.com/patrickbryan...
Outperforms RosettaFold-AA on held-out data and makes code available - no data vs AlphaFold-latest
www.biorxiv.org/content/10.1...
github.com/patrickbryan...
November 6, 2023 at 6:17 AM
“Structure prediction of protein-ligand complexes from sequence information with Umol” 🧪🧶🧬
Outperforms RosettaFold-AA on held-out data and makes code available - no data vs AlphaFold-latest
www.biorxiv.org/content/10.1...
github.com/patrickbryan...
Outperforms RosettaFold-AA on held-out data and makes code available - no data vs AlphaFold-latest
www.biorxiv.org/content/10.1...
github.com/patrickbryan...
My (I think funny) take on AlphaFold3 and equivariance:
There are many versions of AF3 which may be better at different tasks —
The one they publicly released is as diametrically opposite in terms of architecture (no equivariance, no frames, generative) to RosettaFold-AllAtom.
There are many versions of AF3 which may be better at different tasks —
The one they publicly released is as diametrically opposite in terms of architecture (no equivariance, no frames, generative) to RosettaFold-AllAtom.
December 12, 2024 at 3:48 AM
My (I think funny) take on AlphaFold3 and equivariance:
There are many versions of AF3 which may be better at different tasks —
The one they publicly released is as diametrically opposite in terms of architecture (no equivariance, no frames, generative) to RosettaFold-AllAtom.
There are many versions of AF3 which may be better at different tasks —
The one they publicly released is as diametrically opposite in terms of architecture (no equivariance, no frames, generative) to RosettaFold-AllAtom.
@uofwa.bsky.social researchers have lifted the lid on a tool for artificial intelligence–assisted macrocycle design licensed to Vilya, one of C&EN’s #10StartUpstoWatch for 2024: cen.acs.org/pharmaceutic... #AI #biopharma
Details of RFpeptides released
AI-macrocycle design program licensed by Vilya builds on RoseTTAFold 2 and RFdiffusion
cen.acs.org
December 1, 2024 at 7:23 PM
@uofwa.bsky.social researchers have lifted the lid on a tool for artificial intelligence–assisted macrocycle design licensed to Vilya, one of C&EN’s #10StartUpstoWatch for 2024: cen.acs.org/pharmaceutic... #AI #biopharma
AI models like AlphaFold and RoseTTAFold are transforming nephrology by predicting protein structures, aiding in disease insight. Retweet if amazed! PMID:41781721, Nat Rev Nephrol 2026, @NatRevNeph https://doi.org/10.1038/s41581-026-01060-6 #Medsky #Pharmsky #RNA #ASHG #ESHG 🧪
Bridging structure and function: artificial intelligence-based modelling of kidney proteins | Nature Reviews Nephrology
The ability to predict the three-dimensional structure of a protein from its amino acid sequence has potential to provide insights into its function, and in the context of disease, its pathogenic mechanisms and potential drug targets. Artificial intelligence (AI)-driven algorithms, particularly AlphaFold and RoseTTAFold, have revolutionized the field of protein modelling, enabling rapid, high-confidence predictions of protein structures. In nephrology, these advances have clarified the molecular architecture of key renal systems such as podocyte slit diaphragm complexes, the conformational states of membrane transporters and the structural basis of channelopathies that affect polycystin channels. These developments have also enabled low-resolution modelling of complex macromolecular structures, providing insights into structural changes that might underlie the pathogenesis of disease mutants, and enabled virtual screening of drugs and toxins. Although these AI models have yielded impor
doi.org
May 10, 2026 at 1:10 PM
Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom https://www.biorxiv.org/content/10.1101/2023.10.09.561603v1
Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom https://www.biorxiv.org/content/10.1101/2023.10.09.561603v1
Although AlphaFold2 (AF2) and RoseTTAFold (RF) have transformed structural biology by enabling high-
www.biorxiv.org
October 10, 2023 at 2:46 AM
Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom https://www.biorxiv.org/content/10.1101/2023.10.09.561603v1
“Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom” 🧶🧬
Includes non-protein molecules during prediction, such as nucleic acids, metals, glycans, etc, by appending atom types to the sequence, bonds to the distogram, and chirality to the structure
www.biorxiv.org/content/10.1...
Includes non-protein molecules during prediction, such as nucleic acids, metals, glycans, etc, by appending atom types to the sequence, bonds to the distogram, and chirality to the structure
www.biorxiv.org/content/10.1...
October 10, 2023 at 5:24 AM
“Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom” 🧶🧬
Includes non-protein molecules during prediction, such as nucleic acids, metals, glycans, etc, by appending atom types to the sequence, bonds to the distogram, and chirality to the structure
www.biorxiv.org/content/10.1...
Includes non-protein molecules during prediction, such as nucleic acids, metals, glycans, etc, by appending atom types to the sequence, bonds to the distogram, and chirality to the structure
www.biorxiv.org/content/10.1...
"We show that, despite this compression factor, SSEs can be used as a highly effective tertiary structure comparison tool, with accuracy that approaches that of Foldseek, while offering a 200-fold speedup. "
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Compression of protein secondary structures enables ultra-fast and accurate structure searching
Protein structure prediction has undergone a revolution with the advent of AI- based algorithms, such as AlphaFold and RoseTTAFold. As a result, over 200 million predicted protein structures have been...
www.biorxiv.org
September 17, 2025 at 6:53 PM
"We show that, despite this compression factor, SSEs can be used as a highly effective tertiary structure comparison tool, with accuracy that approaches that of Foldseek, while offering a 200-fold speedup. "
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
This week's recap highlights protein design with RoseTTAFold, surveillance with wastewater sequencing, T2T human genomes, Vitessce for visualization of multimodal spatial single-cell data, and Taxometer for taxonomic classification of metagenomics contigs... blog.stephenturner.us/p/weekly-rec... 🧬🖥️
Weekly Recap (Oct 2024, part 4)
Protein design with RoseTTAFold, wastewater sequencing T2T human genomes, single-cell spatial transcriptomics, taxonomic classification, ...
blog.stephenturner.us
October 25, 2024 at 10:07 AM
This week's recap highlights protein design with RoseTTAFold, surveillance with wastewater sequencing, T2T human genomes, Vitessce for visualization of multimodal spatial single-cell data, and Taxometer for taxonomic classification of metagenomics contigs... blog.stephenturner.us/p/weekly-rec... 🧬🖥️
As someone who use to study proteins but stopped the year #AlphaFold and #RoseTTAfold hid the scene I wonder how studying proteins has changed since.
What is the impact on your work of having all those protein structures availible?
🧪 #Protein
What is the impact on your work of having all those protein structures availible?
🧪 #Protein
March 21, 2025 at 9:27 AM
As someone who use to study proteins but stopped the year #AlphaFold and #RoseTTAfold hid the scene I wonder how studying proteins has changed since.
What is the impact on your work of having all those protein structures availible?
🧪 #Protein
What is the impact on your work of having all those protein structures availible?
🧪 #Protein
"Cerebra: a computationally efficient framework for accurate protein structure prediction" presents a structure module without invariant point attention, used in almost all protein structure prediction networks so far (with the notable exception of RosettaFold)
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
February 8, 2024 at 5:55 AM
"Cerebra: a computationally efficient framework for accurate protein structure prediction" presents a structure module without invariant point attention, used in almost all protein structure prediction networks so far (with the notable exception of RosettaFold)
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
An incredibly comprehensive walkthrough of the protein folding NN RosettaFold-1. Exhaustively summarizes many components in RF1 & related NNs, such as how HMMs are used to make MSAs. Also great source for figs for PPTs.
alchemybio.substack.com/p/a-complete...
alchemybio.substack.com/p/a-complete...
A Complete Guide to Protein Folding Prediction with RoseTTAFold: Part I
A 3-hour breakdown of the three-track RoseTTAFold protein prediction model that leverages multi-modal deep learning architectures to transform single sequences into dynamic 3D structures.
alchemybio.substack.com
November 4, 2024 at 9:04 AM
An incredibly comprehensive walkthrough of the protein folding NN RosettaFold-1. Exhaustively summarizes many components in RF1 & related NNs, such as how HMMs are used to make MSAs. Also great source for figs for PPTs.
alchemybio.substack.com/p/a-complete...
alchemybio.substack.com/p/a-complete...
Quick scan only so far, but this looks like an important step in the evolution of AlphaFold and RosettaFold ML methods for predicting protein-small molecule complexes, and in designing proteins that bind specific small molecules.
Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom https://www.biorxiv.org/content/10.1101/2023.10.09.561603v1
Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom https://www.biorxiv.org/content/10.1101/2023.10.09.561603v1
Although AlphaFold2 (AF2) and RoseTTAFold (RF) have transformed structural biology by enabling high-
www.biorxiv.org
October 10, 2023 at 2:55 AM
Quick scan only so far, but this looks like an important step in the evolution of AlphaFold and RosettaFold ML methods for predicting protein-small molecule complexes, and in designing proteins that bind specific small molecules.
Proteiineja rakentava ESMFold perustuu kai kuitenkin aika pitkälti LLM-teknologiaan? Ja ainakin AlphaFold2 ja RosettaFold samaan transformer-ideaan kuin LLM-mallit, samoin kuin docking-mallit?
December 25, 2025 at 2:15 PM
Proteiineja rakentava ESMFold perustuu kai kuitenkin aika pitkälti LLM-teknologiaan? Ja ainakin AlphaFold2 ja RosettaFold samaan transformer-ideaan kuin LLM-mallit, samoin kuin docking-mallit?
Boltz-1x
Chai-1
Protenix
AF2
AF3
Unifold
CombFold
ESMFold
D-I-TASSER
RosettaFold All-Atom
IgDesign
RFantibody
BindCraft
RoseTTAFold2NA
AFCluster
AntiFold
HighFold
BioEmu
DiffAb
AbMPNN
RFDiffusion
HyperMPNN
AntiBERTy
AF-Traj
AbGPT
Chai-1
Protenix
AF2
AF3
Unifold
CombFold
ESMFold
D-I-TASSER
RosettaFold All-Atom
IgDesign
RFantibody
BindCraft
RoseTTAFold2NA
AFCluster
AntiFold
HighFold
BioEmu
DiffAb
AbMPNN
RFDiffusion
HyperMPNN
AntiBERTy
AF-Traj
AbGPT
a man with glasses is holding his head in front of a computer monitor
ALT: a man with glasses is holding his head in front of a computer monitor
media.tenor.com
June 5, 2025 at 12:36 PM
Boltz-1x
Chai-1
Protenix
AF2
AF3
Unifold
CombFold
ESMFold
D-I-TASSER
RosettaFold All-Atom
IgDesign
RFantibody
BindCraft
RoseTTAFold2NA
AFCluster
AntiFold
HighFold
BioEmu
DiffAb
AbMPNN
RFDiffusion
HyperMPNN
AntiBERTy
AF-Traj
AbGPT
Chai-1
Protenix
AF2
AF3
Unifold
CombFold
ESMFold
D-I-TASSER
RosettaFold All-Atom
IgDesign
RFantibody
BindCraft
RoseTTAFold2NA
AFCluster
AntiFold
HighFold
BioEmu
DiffAb
AbMPNN
RFDiffusion
HyperMPNN
AntiBERTy
AF-Traj
AbGPT
AlphaFold 2 and RoseTTAFold are really cool tools, that is, until you try to model transmembrane and membrane-associated proteins. Then their quality really takes a serious hit. 🧪🧬⚗️💻
October 16, 2024 at 7:43 PM
AlphaFold 2 and RoseTTAFold are really cool tools, that is, until you try to model transmembrane and membrane-associated proteins. Then their quality really takes a serious hit. 🧪🧬⚗️💻
('allegedly', because while the authors show evidence that RosettaFold fails when trying to model protein topologies that cannot be sampled by RFdiffusion, they do not show the inverse, so IMO it isn't conclusive evidence of RosettaFold being the root cause of the failure)
October 16, 2024 at 12:14 PM
('allegedly', because while the authors show evidence that RosettaFold fails when trying to model protein topologies that cannot be sampled by RFdiffusion, they do not show the inverse, so IMO it isn't conclusive evidence of RosettaFold being the root cause of the failure)
New in NCI DATA : Structural Biology AI Reference Collection 🧬
A curated, versioned set of reference databases supporting protein structure prediction at scale.
Built for tools like AlphaFold 3, AlphaFold 2 and RoseTTAFold, using updated data from UniProt and the Protein Data Bank
A curated, versioned set of reference databases supporting protein structure prediction at scale.
Built for tools like AlphaFold 3, AlphaFold 2 and RoseTTAFold, using updated data from UniProt and the Protein Data Bank
February 23, 2026 at 11:11 PM
New in NCI DATA : Structural Biology AI Reference Collection 🧬
A curated, versioned set of reference databases supporting protein structure prediction at scale.
Built for tools like AlphaFold 3, AlphaFold 2 and RoseTTAFold, using updated data from UniProt and the Protein Data Bank
A curated, versioned set of reference databases supporting protein structure prediction at scale.
Built for tools like AlphaFold 3, AlphaFold 2 and RoseTTAFold, using updated data from UniProt and the Protein Data Bank