Rohith Krishna Profile
Rohith Krishna

@r_krishna3

Followers
719
Following
933
Media
16
Statuses
135

@UWproteindesign

Joined August 2013
Don't wanna be here? Send us removal request.
@r_krishna3
Rohith Krishna
7 months
RFdiffusion2 generates new enzyme structures just from the most basic descriptions of their geometry. See @woodyahern's thread to see the next generation of de novo enzyme design:
@woodyahern
Woody Ahern
7 months
New enzymes can unlock chemistry we never had access to before. Here, we introduce RFdiffusion2 (RFD2), a generative model that makes significant strides in de novo enzyme design. Preprint: https://t.co/cAWGkrSxBo Code: coming soon Animation credit: https://t.co/Th9ZjsYeX2 (1/n)
1
5
50
@andrew_favor
Andrew Favor
1 month
We are pleased to share our new preprint: “De novo design of RNA and nucleoprotein complexes”. This work extends the principles of de novo protein design to RNA and DNA, enabling the generative design of complex multi-polymer structures! (1/6) https://t.co/QPqpNZr0er
Tweet card summary image
biorxiv.org
Nucleic acids fold into sequence-dependent tertiary structures and carry out diverse biological functions, much like proteins. However, while considerable advances have been made in the de novo...
9
53
195
@r_krishna3
Rohith Krishna
1 month
Specifically binding phosphotyrosines in disordered peptides could have been the premise of a science fiction novel... until now. Read Magnus' thread
@kinasekid
Magnus Bauer
1 month
Phosphorylation on tyrosines control key pathways in immunity, cancer, and metabolism. For the first time, we can now design proteins that specifically recognize individual phosphotyrosines, even in disordered regions. (1/8) Preprint: https://t.co/iIucGbMSDp
2
1
21
@r_krishna3
Rohith Krishna
2 months
@butcher_jasper
Jasper Butcher
2 months
Very excited to share our paper "De novo Design of All-atom Biomolecular Interactions with RFdiffusion3", now on BioRXiv. https://t.co/ry7b17DHgy 1/n
0
0
2
@r_krishna3
Rohith Krishna
2 months
Privileged to work with @butcher_jasper @Raktim7879 @RafiBrent @lyjjj12138 @nscorley Paul Kim @JonathanFunk12 @SimMat20 @samansalike31 @ai_muraishi @HelenEisenach Tuscan Thompson and many others at the IPD and beyond!
1
0
2
@r_krishna3
Rohith Krishna
2 months
We asked ourselves what could we do if we worked cooperatively as a team to create a single model that could design any biomolecular interactions. Yesterday, we reported details of RFdiffusion3, the next step towards building functional proteins straight from the computer.
4
33
191
@butcher_jasper
Jasper Butcher
2 months
Very excited to share our paper "De novo Design of All-atom Biomolecular Interactions with RFdiffusion3", now on BioRXiv. https://t.co/ry7b17DHgy 1/n
5
90
410
@Raktim7879
Raktim Mitra
2 months
RFDiffusion3 generates all atom bound conformation, making it significant for flexible targets like DNA. An excellent teamwork to achieve something impossible by any one of us in just few months. @butcher_jasper @r_krishna3 https://t.co/i60oujJS1L
2
66
378
@r_krishna3
Rohith Krishna
2 months
@nvidia Full details on how to retrain RF3 from scratch coming soon 👀
0
1
7
@r_krishna3
Rohith Krishna
2 months
We built RF3 with @nvidia’s latest cuEquivariance accelerations, letting us iterate fast. Now we’re sharing the full stack: ModelForge — open-source infra for training biomolecular AI. Start your project here 👉
Tweet card summary image
github.com
Central repository for biomolecular foundation models with shared trainers and pipeline components - RosettaCommons/modelforge
4
42
167
@r_krishna3
Rohith Krishna
2 months
Excited for the next generation of enzyme design from minimal atomic motifs. Congrats @woodyahern, @json_yim and Doug Tischer!
@ikalvet
Indrek Kalvet
2 months
RFdiffusion2 is now live! https://t.co/H5bsYd0YuA You can now design proteins, and in particular enzymes from just partially defined amino acid side chains, and without defining their sequence position or order! Great job @r_krishna3 @woodyahern @dougtischer and everyone else!
0
2
18
@SimMat20
Simon Mathis
3 months
Great to finally have this available for people 🙌 Thank you to everyone involved, especially @nscorley & @r_krishna3! We'll be pushing a few smaller updates in the coming days to enhance usability for everyone (including some docs on what you can do with it) - so stay tuned (:
@DidiKieran
Kieran Didi
3 months
AtomWorks is out! Building upon @biotite_python, we built for a toolkit for all things biomolecules and trained RF3 with it. All open-source, test it via `pip install atomworks`! AtomWorks: https://t.co/cNl31hMzws RF3: https://t.co/CmIXV29FXA Paper: https://t.co/Cc3lB8BCmm 1/6
4
11
51
@r_krishna3
Rohith Krishna
3 months
Special shout out to Nate Corley, @SimMat20 and Frank DiMaio who led the charge!
0
0
5
@r_krishna3
Rohith Krishna
3 months
Today, we're releasing a software suite to train biomolecular neural networks called AtomWorks. We have already used it to train performant networks in our group -- we hope that others find it as useful as we do! Check it out at
Tweet card summary image
github.com
A generalized computational framework for biomolecular modeling. - RosettaCommons/atomworks
@DidiKieran
Kieran Didi
3 months
AtomWorks is out! Building upon @biotite_python, we built for a toolkit for all things biomolecules and trained RF3 with it. All open-source, test it via `pip install atomworks`! AtomWorks: https://t.co/cNl31hMzws RF3: https://t.co/CmIXV29FXA Paper: https://t.co/Cc3lB8BCmm 1/6
2
19
80
@r_krishna3
Rohith Krishna
5 months
Excited to see this out! congrats @DaveJuergens and team :)
@DaveJuergens
David Juergens
5 months
Late, but got it done. Inference and training code for CA RFDiffusion is available here: https://t.co/stvOqQs6zJ Please have fun. Getting this online was an adventure, to say the least.
0
0
6
@r_krishna3
Rohith Krishna
7 months
@woodyahern One of the best parts of science: working with insanely talented colleagues who constantly push the limits of what's possible. Big shoutout to @woodyahern and @json_yim for keeping the standard sky-high.
0
0
5
@json_yim
Jason Yim
7 months
RFdiffusion => generative binder design. RFdiffusion2 => generative enzyme design. It's rare to find scientists with deep knowledge in chemistry, machine learning, and software engineering like Woody. The complexity of enzymes matches the complexity of his skills. Check out RFD2
@woodyahern
Woody Ahern
7 months
New enzymes can unlock chemistry we never had access to before. Here, we introduce RFdiffusion2 (RFD2), a generative model that makes significant strides in de novo enzyme design. Preprint: https://t.co/cAWGkrSxBo Code: coming soon Animation credit: https://t.co/Th9ZjsYeX2 (1/n)
1
33
146
@r_krishna3
Rohith Krishna
8 months
Congrats Joe and team!
@_JosephWatson
Joseph Watson
8 months
I’m excited to share our significantly-updated preprint on de novo antibody design, where we now demonstrate the structurally accurate design of scFvs (in addition to VHHs) with RFdiffusion! https://t.co/WdYKu0s1Uc
0
0
5
@DaveJuergens
David Juergens
9 months
Anna and Sam figured out subtle geometric details of serine hydrolase active sites, and then figured out how make new proteins which fold up to reconstruct those active sites with sub-angstrom accuracy and catalyze ester hydrolysis. They are absolutely savage and inspiring.
@ScienceMagazine
Science Magazine
9 months
New research in Science represents a notable step forward in designing enzymes from scratch. With a new approach, researchers designed an enzyme that uses a covalent intermediate to catalyze a two-step reaction, analogous to what many proteases do when breaking apart proteins.
2
22
111