Pascal Sturmfels

PhD student at @uwcse + @UWproteindesign working on machine learning for protein design, protein language models, etc.

[Pascal Sturmfels @PascalSturmfels]

Even though I probably spent more time in the lab playing chess than doing research, for some reason they gave me a PhD 🥳🥳

[Yang Hsia @yhsia_ipd]

Today we celebrate @PascalSturmfels on a successful thesis defense!

Photo by @Hannahlhan

[Pascal Sturmfels @PascalSturmfels]

@brianltrippe @Stanford @StanfordData Congratulations and very well deserved 🔥

[Indrek Kalvet @ikalvet]

That's my designed protein on the cover of Science! Achievement unlocked!

[Science Magazine @ScienceMagazine]

Researchers in Science present a next-generation protein structure prediction and design tool, #RoseTTAFold All-Atom, that can accept a wide range of ligands and covalent amino acid modifications.

Learn more in this week's issue: https://t.co/PmmMUjxNaz

[Simon Duerr @simonduerr]

Specifying the input for cofolding models just got easier with my new gradio component "gradio_cofoldinginput".

Try it here to generate inputs for RoseTTAfold2 All Atom predictions including covalent modifications: https://t.co/YS3BzdE4Qt

[Hannah Han @Hannahlhan]

Super excited to share our paper “Design of amyloidogenic peptide traps” is out now! 🧠

https://t.co/Qmu9BpZiMA

Special thanks to @eaandrzejewska , Danny Sahtoe and David Baker

[Pascal Sturmfels @PascalSturmfels]

@naterbennett0 🔥

[Nate Bennett @naterbennett0]

We’re excited to share our preprint where we show, for the first time, the atomically accurate design of VHH antibodies!

[Yi-Lun Liao @yilunliao]

🧵(1/7) Excited to share that our work, EquiformerV2, has been accepted to #ICLR2024. EquiformerV2 is the state-of-the-art on large-scale atomistic benchmarks -- OC20, OC22, AdsorbML, and ODAC23.

Joint work with @bwood_m, @abhshkdz from @OpenCatalyst and @tesssmidt

Paper: https://t.co/Y5GAoXDMN2
Code: https://t.co/wrMqWXsi7g

[Nature Biotechnology @NatureBiotech]

AlphaFold2 and RoseTTAFold are limited to predicting the 3D structure of proteins. A new all-atom method models complete biomolecular assemblies, including proteins, nucleic acids, small molecules, metals, and covalent modifications. #NBThighlight https://t.co/a9relIlKLC

[Rohith Krishna @r_krishna3]

Our work on modeling and designing biomolecular assemblies is now in @ScienceMagazine.
https://t.co/J0xnuTGGgZ
RFAA Code: https://t.co/PkMLFH9iid
RFdiffusionAA Code: https://t.co/96Ul66ljJe

[Gabriele Corso @GabriCorso]

Excited to finally be able to share our ICLR work critically analyzing the capacity of deep learning docking methods to generalize and how to improve this (spoiler scaling, augmentation and RL)! With this, we release a new significantly improved version of DiffDock!

A thread! 🧵

[Kiera Sumida @KieraSumida]

Our paper using ProteinMPNN redesign for improved properties is up on JACS! Huge thanks to Reyes, @ikalvet, Sam, and many others for their work. Shout out to @JustasDauparas for developing such a groundbreaking (and versatile!) tool. @UWproteindesign

https://t.co/bLm0jFuOvF

[Samuel Stanton @samuel_stanton_]

looking for interns for two projects next summer, come work with me, @nc_frey and the rest of the @PrescientDesign team applying bleeding edge machine learning to fascinating biological data!

[Hannes Stark @HannesStaerk]

Monday 11am Reading group: RosettaFold all-atom!
https://t.co/Wh4UiZbbJE

Let us discuss with @r_krishna3 what protein design niceties we can achieve with this. And also the AlphaFold all-atom "glimpse" :)

Join on Zoom at 11am ET / 4pm UTC / 5pm CET:
https://t.co/R8d1EHxLCx

[Hannes Stark @HannesStaerk]

Soo, this is a big one :)
On Nov 20 we will have RosettaFold all-atom in the reading group with @r_krishna3!

Quite amazing protein design capabilities. But that is my naive evaluation - join us and let's discuss and hear your insights! Sign up here: https://t.co/R8d1EHxLCx

[Sanjay Srivatsan @SRsrivatsan]

Thrilled to announce the opening of the Srivatsan Lab (https://t.co/mUPc2wHm0X) at the @fredhutch. The lab will be building new sequencing technologies to understand how our cells and bodies form over the course of development.

[Woody Ahern @woodyahern]

RFdiffusionAA generating a small molecule binding protein against an experimental FXIa inhibitor (OQO), a ligand which is significantly different than any in its training dataset.

[Sergey Ovchinnikov @sokrypton]

RoseTTAFold updated to be All-Atom... biological assemblies containing proteins, nucleic acids, small molecules, metals, and covalent modifications ... and diffusion🤯https://t.co/36EtN0IzoL

[Mohammed AlQuraishi @MoAlQuraishi]

All-atom version of RoseTTAFold looks quite exciting! https://t.co/SdjFGeg666