Log inSign up
user avatar
Olaf Ronneberger
@ORonneberger
Research scientist at @DeepMind, London, and adjunct professor for computer science at University of Freiburg, Germany.
London, England
Joined November 2018
117
Following
3,369
Followers
  • Pinned
    user avatar
    Olaf Ronneberger
    @ORonneberger
    Oct 9, 2024
    Woohoo! We got the Nobel Price for Alphafold!
    user avatar
    The Nobel Prize
    @NobelPrize
    Oct 9, 2024
    BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Chemistry with one half to David Baker “for computational protein design” and the other half jointly to Demis Hassabis and John M. Jumper “for protein structure prediction.”
    Image
    67K
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Jun 19, 2021
    Happy to announce that we will provide open source code for AlphaFold2!
    user avatar
    Demis Hassabis
    @demishassabis
    Jun 18, 2021
    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!
    Image
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Jun 29, 2021
    Proteins are not static bricks! Feasibility study to infer a continuous distribution of all states using an end-to-end model from Cryo-EM images to atom coordinates: arxiv.org/abs/2106.14108. @danrsm, @GarneloMarta, @MichaelZielins, @JonasAAdler, @arkitus, @CarlDoersch, @pushmeet
    Image
    00:00
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Dec 9, 2020
    Wow, I just realised that the U-net paper now has over 20k citations (according to google scholar). Throughout 2020 these were more than 1 citation per hour. A big thank you to all of you for making it so popular!
    Image
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Dec 17, 2018
    The newest research with my colleagues at University of Freiburg published in Nature Methods today nature.com/articles/s4159…: An ImageJ/@FijiSc plugin for U-net training and application in 2D and 3D. Read the open access full text here: rdcu.be/bdHaX
    Image
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Nov 6, 2018
    As of today the U-net arxiv.org/abs/1505.04597 is the most-cited paper in the 21 years history of the #miccai conference (3201 citations according to google scholar scholar.google.co.uk/scholar?hl=en&…). It just overtook the Frangi-filter from 1998 (scholar.google.co.uk/scholar?hl=en&…).
    arXiv logo
    arxiv.org
    U-Net: Convolutional Networks for Biomedical Image Segmentation
    There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the...
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Nov 28, 2018
    Looking forward to the Medical Imaging meets NeurIPS Workshop next week Saturday (Dec, 8th). At 9:45am I'll present our work on radiotherapy planning (arxiv.org/abs/1809.04430), triaging eye diseases (nature.com/articles/s4159…) and the probabilistic u-net (arxiv.org/abs/1806.05034)
    Image
    00:00
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Jul 15, 2021
    Replying to @demishassabis and @Nature
    AlphaFold paper in Nature with over 60 pages of Supplements to explain every tiny detail and the full source code on github are out!
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Jul 15, 2021
    AlphaFold paper in Nature with over 60 pages of Supplements to explain every tiny detail and the full source code on github are out!
    user avatar
    Demis Hassabis
    @demishassabis
    Jul 15, 2021
    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
    Image
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Nov 30, 2020
    Incredibly honoured to be a part of the AlphaFold team!
    user avatar
    Google DeepMind
    @GoogleDeepMind
    Nov 30, 2020
    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)
    Image
    GIF
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Dec 7, 2020
    If you need a U-net, take this! Fantastic work from a great group. Congratulations!
    user avatar
    Klaus Maier-Hein
    @maierhein
    Dec 7, 2020
    Nature Methods paper out on nnU-Net: self-configuring image segmentation for diverse tasks as an out-of-the-box tool. I was actually dreaming of this during my own PhD. Only missing pieces in 2007: DL, data... & the courage to actually try it;) @mic_dkfz rdcu.be/cbOJJ
    Image
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Jul 14, 2020
    (1/2) Our new paper "Contrastive Training for Improved Out-of-Distribution Detection" arxiv.org/abs/2007.05566 with @jimwinkens, @BunelR, @abzz4ssj, Robert Stanforth, @vivnat, @joe_ledsam, @patmacwilliams, @pushmeet, @alan_karthi, @saakohl, @TaylanCemgilML, @arkitus
    Image
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    Nov 2, 2021
    The source code for AlphaFold-Multimer (see biorxiv.org/content/10.110…) is now available on github github.com/deepmind/alpha…. Happy folding!
    user avatar
    Google DeepMind
    @GoogleDeepMind
    Nov 2, 2021
    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
    Image
    Image
    biorxiv.org
    Protein complex prediction with AlphaFold-Multimer
    While the vast majority of well-structured single protein chains can now be predicted to high accuracy due to the recent AlphaFold [[1][1]] model, the prediction of multi-chain protein complexes...
  • user avatar
    Olaf Ronneberger
    @ORonneberger
    May 31, 2019
    Our newest paper: A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities.
    user avatar
    Simon Kohl
    @saakohl
    May 31, 2019
    Medical images can exhibit ambiguities on multiple scales & locations often varying independently. We propose a hierarchical generative model to capture such variations in segmentations & show much improved sample fidelity and fit with the GT distribution: arxiv.org/abs/1905.13077