Mohammed AlQuraishi Connor W. Coley Thanks, our perspective (for the casp issue) can be found here arxiv.org/abs/2105.07407

Structural biology is evolving fast! With the big push coming from machine learning, what are the new challenges? If you’re interested, please consider participating in a small in-person gathering in the south of France this summer! conferences.cirm-math.fr/2700.html

The workshop aims at bringing together researchers from computational structural biology and several machine learning communities. As in-person space is limited, participation will have to be approved by the organizers (please answer the two pre-registration form questions).

The meeting cost is $200 ($100 students, $1000 industry) plus accommodation charges (€105 per day, including all meals). Accompanying persons are accepted. Paiement details are communicated after pre-registration validation.

Last year we presented #AlphaFold v2 which predicts 3D structures of proteins down to atomic accuracy. Today we’re proud to share the methods in nature w/open source code. Excited to see the research this enables. More very soon! bit.ly/alphafoldmetho… bit.ly/alphafoldgithub

Our work with @ilvailvail and Nikita Pavlichenko is published today! What a day for #AI and protein structure prediction :)

by popular demand, Sergey Ovchinnikov is going teach us how to use #RoseTTAFold and #AlphaFold2 on Wednesday, August 4th at 7pm EDT Sergey Ovchinnikov "ColabFold - Making protein folding accessible to all via Google Colab!" harvard.zoom.us/j/94214636314

Proud to share the first work of Dmitrii Zhemchuzhnikov with assitance from @ilvailvail on our vision of 6DCNNs, roto-translational convolutions, local SE(3) equivariance and a mix of protein representations! arxiv.org/abs/2107.12078 #6dcnn #equivariance

Protein language model embeddings for fast, accurate, alignment-free protein structure prediction biorxiv.org/cgi/content/sh… #biorxiv_bioinfo

After 2 weeks of working together intensively, we proudly present our assessment of using #alphafold2 from @DeepMind for peptide-protein docking: it works! biorxiv.org/content/10.110… 🧵

What are the ingredients for protein partner identification? Check out our preprint reporting on a molecular cross-docking-based approach for the ab initio reconstruction of protein-protein interaction networks! Alessandra Carbone Yasser MOHSENI LCQB biorxiv.org/content/10.110…

Our new paper on using AlphaFold2 with ClusPro for protein docking. #AlphaFold #alphafold2 #ClusPro biorxiv.org/content/10.110…

Thematic School 2021 : Graph as models in life sciences: #Machinelearning and integrative approaches 📍Online ⏰25th – 29th of October 2021 َ Sergei Grudinin Jean Louis Raisaro @cazencott

Now we have updated (and submitted9 our AF2 Fold and Dock manuscript. The major change is that we now also benchmark the capacity of AlphaFold2 to separate interacting from non-interacting proteins. biorxiv.org/content/10.110… #Alphafold2

PhD proposal to work on alternative splicing and protein design. Selected candidates will be funded for 4 years (pre-doc+PhD). Apply before March 24! ibio.sorbonne-universite.fr/wp-content/upl… ibio.sorbonne-universite.fr/2022-program/ i-Bio Sorbonne Université Sergei Grudinin

Very happy to expand our Deep Local Analysis series! Protein interfaces represented as many residue-centred locally oriented cubes. Step 1: what's in the cube? Step 2: what's the effect of mutating that residue? thanks to Yasser MOHSENI Alessandra Carbone for the great collaboration!

Protein sequences to motions, great PhD work by Valentin Lombard, with Sergei Grudinin! We investigated whether compact continuous representations of protein motions can be predicted directly from sequences, without relying on or sampling protein structures. biorxiv.org/content/10.110… 1/3

Come to my group!!! #PhDstudent wanted in an excellence research center in beautiful Barcelona!!!!

We engineered membrane protein bacteriorhodopsin to be soluble. It binds retinal and can photocycle! X-ray structure reveals conserved binding pocket with 0.8 Å all atom RMSD to WT BR. All this became possible due to hard work by Andrey Nikolaev and the team 🙏 #proteindesign

BAnG: Bidirectional Anchored Generation for Conditional RNA Design 1/ This study introduces RNA-BAnG, a deep learning model for designing RNA sequences that interact with specific proteins without requiring extensive experimental data or RNA structural information. 2/ The