Sebastian Bodenstein

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

[Sebastian Bodenstein @sebbodenstein]

Very proud to have contributed to this incredible project and excited to see how it will be used! #AlphaFold

[Demis Hassabis @demishassabis]

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!

https://t.co/6uiV51Xly5
https://t.co/CLo7EKubBT

[NaN demeulemeester @snikolov]

we won the Nobel Prize for AlphaFold

can't believe it

[Sebastian Bodenstein @sebbodenstein]

@AlexLaterre @sarahookr Note that the the JAX graph does not allow for any conclusions to be drawn: JIT is not used and these are mostly tiny single ops completely dominated by Python/CPU overhead (different CPUs are used on the GPU/TPU machines). I've reported this issue to the authors.

[Tim Green @tfgg2]

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: https://t.co/LgqAo6GKzc
Paper: https://t.co/A3uTYVoTeq

[Google DeepMind @GoogleDeepMind]

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: https://t.co/4gyZ0loLrd

Generate predictions from your browser via: https://t.co/2Vd4itjElu

[Sebastian Bodenstein @sebbodenstein]

So excited for this! Visual Complex Analysis by Needham is one of my all-time favourite books.

[Steven Strogatz @stevenstrogatz]

I’ve started reading this marvelous new book by Tristan Needham. It’s passionate and filled with geometrical insight, just like his earlier masterpiece VISUAL COMPLEX ANALYSIS. https://t.co/eDuAhYYJSi

[Tim Green @tfgg2]

Also, we've got a Colab for running AlphaFold using our validated genetic search up at: https://t.co/W5uq8X5Vt9 Have fun! Let me know if you have any issues. #alphafold

[EMBL-EBI @emblebi]

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.

https://t.co/Lq2aUvjkQS

#FAIRdata #structuralbiology #opendata

[Sebastian Bodenstein @sebbodenstein]

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]

Today with @emblebi, we're launching the #AlphaFold Protein Structure Database, which offers the most complete and accurate picture of the human proteome, doubling humanity’s accumulated knowledge of high-accuracy human protein structures - for free: https://t.co/vtBGmTkKhy 1/

[Demis Hassabis @demishassabis]

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!

[Wessel @ikwess]

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

https://t.co/Gs8MhzAp6L

[Sebastian Bodenstein @sebbodenstein]

@wiebketous Wow, so jealous!!

[David Pfau @pfau]

If you follow me on Twitter, you probably know that I am pretty allergic to hype, especially around deep learning. So believe me when I say - this is a big f---ing deal.

https://t.co/GV7CDPQMlN

[Sundar Pichai @sundarpichai]

.@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.
https://t.co/kpr8EAx34h

[Sebastian Bodenstein @sebbodenstein]

Very proud of this work done by my new colleagues in the protein team. Its a truly incredible achievement!

[Google DeepMind @GoogleDeepMind]

In a major scientific breakthrough, the latest version of #AlphaFold has been recognised as a solution to one of biology's grand challenges - the “protein folding problem”. It was validated today at #CASP14, the biennial Critical Assessment of protein Structure Prediction (1/3)

[Sebastian Bodenstein @sebbodenstein]

@AmiraMorphism @Google Congratulations!! What amazing news ❤️

[Sebastian Bodenstein @sebbodenstein]

@Thom_Wolf @bhutanisanyam1 Reading MacKays book during my PhD inspired me to leave physics for machine learning 🤗

[zion | w.ai @benzion_b]

2015: the AI revolution is coming
2020:

@geoffreyhinton @SchmidhuberAI

[Sebastian Bodenstein @sebbodenstein]

@sharky6000 Even the thought of calling a Python-implemented non-trivial RL environment ~millions of times whilst I'm fighting with some obstreperous learning algorithm causes me deep psychic pain 😜

[Sebastian Bodenstein @sebbodenstein]

I started a blog! The first post explains AlphaZero, but also touches on human cognition, why Python is bad for ML, game theory and model-based reinforcement learning. Hope you enjoy! https://t.co/T4RdWcMlRw