Postdoc @Princeton | PhD @Cornell | @okstate alum | Interested in studying mechanisms of membrane trafficking using cryo-EM
Princeton, NJ
Joined October 2018
- Tweets352
- Following527
- Followers409
- Likes865
Pinned Tweet
I'm so excited to finally share the results of my PhD work! Check out this thread for all of the highlights!
Ric1-Rgp1-Rab6 has been the most difficult #cryoEM project I've worked on so far, but I'm so happy with how it came together and what we learned about Rab6 activation!
We are excited to share a new preprint from the lab! Rab6 is a central regulator of the Golgi, important for trafficking and autophagy. @FeathersRyan used #cryoEM to determine the structural basis of the Rab6 activation process. (1/9)
Ryan Feathers retweeted
My little Blender plugin I started 4.5 years ago is literally the face of an entire Biotech industry / research sector 🥹
#b3d #GeometryNodes #MolecularNodes
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org
Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
Ryan Feathers retweeted
Our first protein 🥩 design paper! 🤠
Check out Minkyu's tour de force on T-REX 🦖, an agentic protein design controller for de novo binder design!
TLDR we treat protein design as an online allocation problem over heterogeneous tools (Proteina-complexa, Boltzgen, Bindcraft, ✨ etc), use 🤖 agents to reason over what tools + settings to run, designed a granular classification system to manage the agents (e.g. Rescue🛟/Explore🔎/eXploit🚀), that is all orchestrated with a deterministic controller to efficiently brrr the GPUs. 💸
T-REX 🦖 is fully open source: github.com/ml-struct-bio/T-R…
Preprint: biorxiv.org/content/10.64898…
Please let us know if you have any feedback!
Ryan Feathers retweeted
Excited to share T-REX 🦖: Target-adaptive Rescue-Explore-eXploit, an agentic campaign controller for high-throughput de novo protein binder design!
T-REX treats protein design as an online agentic allocation problem to leverage diverse tools with efficient GPU usage 🧵
Ryan Feathers retweeted
Congratulations to Ellen Zhong, Princeton University, for receiving the 2026 K.H. Kuo Award for Outstanding Young Scientist in Structural Biology
bsc.org.cn/KuoSymposium/2026…
Ryan Feathers retweeted
Last week, MB&B hosted Dr. Ryan Feathers (Princeton) for a hands-on workshop on AI for cryo-EM—showcasing cryoDRGN to reveal molecular heterogeneity in challenging datasets.
Read more here: bit.ly/3QoEOqq
@FeathersRyan #CryoEM #StructuralBiology
Ryan Feathers retweeted
When asked to draw a scientist, school-age kids in the United States are increasingly sketching women, according to a study from 2018.
Read more on #WomenInScienceDay: scim.ag/48YwNzI
ALT A child drawing of a female scientist. The hedline is: What does a scientist look like? Children are drawing women more than ever before
Ryan Feathers retweeted
Had a fun convo with @agupta at NeurIPS about
AI and proteins!
During NeurIPS's 2025 conference, @agupta sat down with @ZhongingAlong, an assistant professor of computer science at Princeton, to discuss how machine learning is reshaping structural biology.
They explore how proteins aren’t static structures but dynamic molecular machines, and how techniques like cryo-electron microscopy combined with ML are revealing protein motion beyond traditional structure prediction.
00:11 — Introduction
00:55 — From Supercomputers to Cryo-EM
02:43 — The Rise of Cryo-EM
03:30 — Proteins as Dynamic Systems
04:30 — Inverse Problems in Biology
05:31 — Lessons from DeepMind, Industry and Academia
07:35 — Why Protein Dynamics Remain Unsolved
08:29 — Collaborating with Experimental Scientists
09:28 — What’s Overhyped and Underhyped in AI-Driven Biology
10:51 — The Future of AI-Driven Biology
Ryan Feathers retweeted
Congrats Mo Seyedsayamdost with Ellen Zhong of @PrincetonCS, new Eric and Wendy Schmidt Transformative Technology Fund awardees who are working on an algorithm to automate the process of determining small molecule structure from NMR spectral analysis: bit.ly/4j2yWgR
ALT Full-color image of Mo and Ellen standing in a hallway at Frick Chemistry Lab.
Ryan Feathers retweeted
We’ll be presenting CryoBoltz ❄️⚡️ at #NeurIPS this week!
Check out the new experiments in our updated paper. We’re also releasing our code for the community to try out on their data 🚀
Paper: arxiv.org/abs/2506.04490
Code: github.com/ml-struct-bio/cry…
Excited to present CryoBoltz ❄️⚡, a multiscale guidance approach for steering AlphaFold3/Boltz-1 to sample structures that are consistent with experimental cryo-EM density maps. 🧵1/7
arxiv.org/abs/2506.04490
Joint work with @axlevy0 @GordonWetzstein & @ZhongingAlong!
Reviewed a nice #CryoET paper in journal club today and it got me wondering... @ScienceMagazine has a very clear policy on data and computational methods. Why isn't this policy upheld for the #CryoEM and #TeamTomo communities? #OpenSoftwareAcceleratesScience
Calling all #CryoEM aficionados and method developers! Come join the webinar happening soon to learn more about our new community data processing challenge! #CAHRA
If you're not on the multi-thousand-person cryo-EM listservs... we (EZ lab @PrincetonCS, @FlatironInst, #CCPEM) just announced a new #heterogeneity challenge for cryo-EM! #CAHRA2025
Webinar this Fri Nov 14 at 12p ET. Datasets and more info here: heterogeneity.notion.site/ch…
We've been preparing this challenge for over a year 🥵 (designing the heterogeneity, collecting data, validating results and metrics). Super excited to finally share it with the community!
There are three mystery❓❔❓ datasets! Some fun facts about each:
1) comp-het: an experimental dataset containing a mixture of mystery❔complexes
2) conf-het: we're asking folks to submit *atomic models* instead of density maps for the first time ❗️❕
3) pose-entanglement: a simple dataset to test how much the pose distribution influences conformation estimation 🐎
Huge shoutout to the members of my group driving this work @FeathersRyan and Robert Heeter, @sonyahans + @PilarCossio2's groups @FlatironInst, and Joel Greer from Tom Burnley's group at #CCPEM.
Calling both methods developers and users to participate! Check out our website for more details!
Ryan Feathers retweeted
If you're not on the multi-thousand-person cryo-EM listservs... we (EZ lab @PrincetonCS, @FlatironInst, #CCPEM) just announced a new #heterogeneity challenge for cryo-EM! #CAHRA2025
Webinar this Fri Nov 14 at 12p ET. Datasets and more info here: heterogeneity.notion.site/ch…
We've been preparing this challenge for over a year 🥵 (designing the heterogeneity, collecting data, validating results and metrics). Super excited to finally share it with the community!
There are three mystery❓❔❓ datasets! Some fun facts about each:
1) comp-het: an experimental dataset containing a mixture of mystery❔complexes
2) conf-het: we're asking folks to submit *atomic models* instead of density maps for the first time ❗️❕
3) pose-entanglement: a simple dataset to test how much the pose distribution influences conformation estimation 🐎
Huge shoutout to the members of my group driving this work @FeathersRyan and Robert Heeter, @sonyahans + @PilarCossio2's groups @FlatironInst, and Joel Greer from Tom Burnley's group at #CCPEM.
Calling both methods developers and users to participate! Check out our website for more details!
Ryan Feathers retweeted
Announcing cryo-EM heterogeneity challenge #2, now dubbed the 2025 Community-Wide Assessment of Cryo-EM Heterogeneous Reconstruction Algorithms (CAHRA)! Join us for a webinar next Friday (Nov 14th) to learn more. Datasets already posted here: heterogeneity.notion.site/ch…
Ryan Feathers retweeted
Congratulations to @tri_dao and @ZhongingAlong on being named AI2050 Early Career Fellows by @schmidtsciences!
The AI2050 fellowships fund researchers working to solve hard problems in AI and improve technology for the benefit of humanity by 2050.
bit.ly/3WFG6Ny
ALT Tri Dao and Ellen Zhong
Ryan Feathers retweeted
new podcast filmed with someone who basically created a new subfield in bio-ml during her phd, and whose lab at Princeton continues to remain at the forefront of the field
out (hopefully) next weekend
to prepare, you should read the article below
A primer on ML in cryo-electron microscopy (cryo-EM)
owlposting.com/p/a-primer-on…
confused about cryo-EM???
i explain why people do it, how it works and some ML problems in the area via explanations of 3 @ZhongingAlong papers
7.9k words, 36 minutes reading time. ToC in thread❄️
Ryan Feathers retweeted
Congrats Scott for his discovery of ESCRTs.
The 2025 WLA Prize in Intelligent Science or Mathematics was awarded to Richard Schoen, honorary chair professor at Stanford University's School of Humanities and Sciences, CCTV reported today. The prize in Life Sciences or Medicine was awarded to Scott D. Emr, honorary professor of molecular biology and genetics at Cornell University, and Wesley I. Sundquist, distinguished professor and co-chair of the Department of Biochemistry at the University of Utah. @thewlaprize #2025WLAPIRIZE @Stanford @Cornell @CornellCALS @UUtah @UofUHealth
Ryan Feathers retweeted
CryoDRGN-AI ❄️🐉🤖 is now published in @naturemethods!!! So excited to see this out and a huge congrats to @axlevy0 and team!
CryoDRGN-AI extends cryoDRGN from requiring input, fixed camera poses, to end-to-end ab initio reconstruction of biomolecules and their conformational landscapes!
Since our preprint, we have added ab initio reconstruction of cryo-ET subtomograms (@rishwanth_raghu @FeathersRyan 🙌) and several additional examples reconstructing large, messy datasets and discovery of new structures!
You can find a recent SBGrid webinar I gave about cryoDRGN-ET and cryoDRGN-AI here: youtube.com/watch?v=P9c1dUO3…
Paper: nature.com/articles/s41592-0…
A few more thoughts ⬇️ (1/3)
We present DRGN-AI for fast, ab initio cryo-EM reconstruction!
* learns a neural field from unposed images,
* designed for single-shot reconstruction of unfiltered datasets,
* finds new states missed by prior approaches!
Teamwork led by @ZhongingAlong
drgnai.cs.princeton.edu/ 1/
Ryan Feathers retweeted
🎉New preprint!🎉 Extremely excited to share CryoBoltz❄️⚡️, led by superstar @rishwanth_raghu!
We develop a multiscale guidance recipe to steer structure prediction models (e.g. AlphaFold3 / Boltz-1) towards experimental cryo-EM density maps, including heterogeneous, low-resolution data!
CryoBoltz ❄️⚡️bridges protein structure prediction and cryo-EM structure determination. We believe this opens up exciting directions for data-guided structure prediction and atomic modeling of dynamic molecules.
Check out @rishwanth_raghu's thread below for more details! So fun to work with the dream team @rishwanth_raghu @axlevy0 and @GordonWetzstein on this paper.
Finally, this work was made possible by the openly available Boltz-1 repo and the AlphaFold3 release. Excited to see the continuing developments with Boltz-2 and beyond!
Excited to present CryoBoltz ❄️⚡, a multiscale guidance approach for steering AlphaFold3/Boltz-1 to sample structures that are consistent with experimental cryo-EM density maps. 🧵1/7
arxiv.org/abs/2506.04490
Joint work with @axlevy0 @GordonWetzstein & @ZhongingAlong!
Ryan Feathers retweeted
🚀 Exciting update on CryoBench! 🚀
We’ve refactored the metric (per-img-FSC) script to make it even easier to use and created a user manual on GitBook: CryoBench Manual: ez-lab.gitbook.io/cryobench
Big thanks to Michal Grzadkowski for the amazing refactor! 🙏
Ryan Feathers retweeted
🚨New paper at #NeurIPS2024! We present Hydra, a mixture of neural fields 🐉🐉🐉 for ab initio cryo-EM reconstruction of complex mixtures.
Hydra is our attempt at pushing the boundaries for even more extreme forms of heterogeneity in cryo-EM 🤯.
This was joint work with an awesome team, led by @axlevy0 @rishwanth_raghu & David Shustin.
Paper: hydra.cs.princeton.edu/
Poster session happening now! Come by 👋
