Sebastian Bodenstein (@sebbodenstein) 's Twitter Profile
Sebastian Bodenstein

@sebbodenstein

Research Engineer @DeepMind, working on proteins. Ex-physicist.

ID: 2804894554

linkhttp://www.sebastianbodenstein.com calendar_today04-10-2014 13:03:02

149 Tweet

558 Followers

361 Following

Feryal (@feryalmp) 's Twitter Profile Photo

Today Gheorghe Comanici & I taught the RL tutorial at EEML summer school! Here is the tutorial we prepared to teach value based methods. Tabular agents are in python & function approximation agents are in JAX using Acme (best viewed in Colab). github.com/eemlcommunity/…

Today Gheorghe Comanici &amp; I taught the RL tutorial at <a href="/EEMLcommunity/">EEML</a> summer school! Here is the tutorial we prepared to teach value based methods. Tabular agents are in python &amp; function approximation agents are in JAX using Acme (best viewed in Colab).
github.com/eemlcommunity/…
Women in Statistics and Data Science (@womeninstat) 's Twitter Profile Photo

So yesterday I asked you all what you wanted to hear about from me this week, and one answer stood out from all the others: the SINGULAR VALUE DECOMPOSITION (SVD). x.com/genomixgmailco… 1/

Alexia Jolicoeur-Martineau (@jm_alexia) 's Twitter Profile Photo

Just released a new blog post on the recent approach that will likely supersede GANs in the soon future: Score Matching with Langevin Sampling by @YSongStanford. I explain how the approach works and its pros and cons. ajolicoeur.wordpress.com/the-new-conten…

Sebastian Bodenstein (@sebbodenstein) 's Twitter Profile Photo

Some personal news: I'm moving to London next week to join the DeepMind Science team! Super excited to tackle major scientific challenges with machine learning, and also to work with some incredible new colleagues. If in London, don't be shy to say hi 😉

Sundar Pichai (@sundarpichai) 's Twitter Profile Photo

.@DeepMind's incredible AI-powered protein folding breakthrough will help us better understand one of life’s fundamental building blocks + enable researchers to tackle new and hard problems, from fighting diseases to environmental sustainability. deepmind.com/blog/article/a…

Wessel (@ikwess) 's Twitter Profile Photo

Cambridge MLG is launching a blog, featuring a first two-part post about what keeps a Bayesian awake at night by Richard E. Turner and me. 🧵 mlg-blog.com

Demis Hassabis (@demishassabis) 's Twitter Profile Photo

Brief update on some exciting progress on #AlphaFold! We’ve been heads down working flat out on our full methods paper (currently under review) with accompanying open source code and on providing broad free access to AlphaFold for the scientific community. More very soon!

Brief update on some exciting progress on #AlphaFold! We’ve been heads down working flat out on our full methods paper (currently under review) with accompanying open source code and on providing broad free access to AlphaFold for the scientific community. More very soon!
EMBL-EBI (@emblebi) 's Twitter Profile Photo

How can #AI help us speed up scientific discovery? We’ve teamed up with @DeepMind to make #AlphaFold protein structure predictions freely and openly available to the scientific community. ebi.ac.uk/about/news/pre… #FAIRdata #structuralbiology #opendata

Tim Green (@tfgg2) 's Twitter Profile Photo

Also, we've got a Colab for running AlphaFold using our validated genetic search up at: colab.research.google.com/github/deepmin… Have fun! Let me know if you have any issues. #alphafold

Sebastian Bodenstein (@sebbodenstein) 's Twitter Profile Photo

An amazing contribution to human knowledge, 350,000 protein structure predictions from AlphaFold 2 including for every protein in a human body.

Google DeepMind (@googledeepmind) 's Twitter Profile Photo

The #AlphaFold source code has been updated and now accounts for multi-chain protein complexes - providing a significant improvement in accuracy for predicting protein interactions: dpmd.ai/af-multimer-os Generate predictions from your browser via: dpmd.ai/alphafold-colab

The #AlphaFold source code has been updated and now accounts for multi-chain protein complexes - providing a significant improvement in accuracy for predicting protein interactions: dpmd.ai/af-multimer-os

Generate predictions from your browser via: dpmd.ai/alphafold-colab
Tim Green (@tfgg2) 's Twitter Profile Photo

We have updated the AlphaFold-Multimer paper and code with a new set of protein complex models trained with an improved loss. These models reduce the number of steric clashes and improve accuracy. Code: dpmd.ai/af-multimer-os Paper: dpmd.ai/alphafold-mult…

We have updated the AlphaFold-Multimer paper and code with a new set of protein complex models trained with an improved loss. These models reduce the number of steric clashes and improve accuracy.

Code: dpmd.ai/af-multimer-os
Paper: dpmd.ai/alphafold-mult…