> ML_LITERATURE // JUMPER-2021-HIGHLY-ACCURATE-PROTEIN-STRUCTURE-PREDICTION-ALPHAFOLD_v1.0
Highly accurate protein structure prediction with AlphaFold (AlphaFold 2)
John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Alex Potapenko, Alex Bridgland, Clemens Meyer, Simon A. A. Kohl, Anna J. Ballard, Andrew Cowie, Bernardino Romera-Paredes, Stanislav Nikolov, Rishub Jain, Jonas Adler, Trevor Back, Stig Petersen, David Reiman, Ellen Clancy, Michal Zielinski, Martin Steinegger, Michalina Pacholska, Tamas Berghammer, Sebastian Bodenstein, David Silver, Oriol Vinyals, Andrew W. Senior, Koray Kavukcuoglu, Pushmeet Kohli, Demis Hassabis · Nature (2021)
Principal Contribution
Designed the Evoformer architecture and invariant point attention (IPA) to predict 3D atomic coordinates directly from primary amino acid sequences and evolutionary multiple sequence alignments (MSAs) with sub-Angstrom precision.
Operational Relevance
Serves as qualified reference for deploying task-structural-biology in production.
Assumptions
- Spatial feature coherence and data manifold structure adhere to continuous representation hypotheses
Limitations
- Computational complexity scales with spatial resolution and parameter capacity