Applying and improving AlphaFold at CASP14

By John M. Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko and 23 more. 2021

354 citations recorded by the source corpus.

We describe the operation and improvement of AlphaFold, the system that was entered by the team AlphaFold2 to the “human” category in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The AlphaFold system entered in CASP14 is entirely different to the one entered in CASP13. It used a novel end‐to‐end deep neural network trained to produce protein structures from amino acid sequence, multiple sequence alignments, and homologous proteins. In the assessors' ranking by summed z scores (>2.0), AlphaFold scored 244.0 compared to 90.8 by the next best group. The predictions made by AlphaFold had a median domain GDT_TS of 92.4; this is the first time that this level of average accuracy has been achieved during CASP, especially on the more difficult Free Modeling targets, and represents a significant improvement in the state of the art in protein structure prediction. We reported how AlphaFold was run as a human team during CASP14 and improved such that it now achieves an equivalent level of performance without intervention, opening the door to highly accurate large‐scale structure prediction.

Subfields: Environmental Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Sampling alternative conformational states of transporters and receptors with AlphaFold2 (2022, methodology): “A performance breakthrough was unveiled during CASP14 by AlphaFold2 (AF2) ( Jumper et al., 2021a ; Tunyasuvunakool et al., 2021 ; Pereira et al., 2021 ), which achieved remarkably accurate de novo structure prediction.”
Multi-State Modeling of G-protein Coupled Receptors at Experimental Accuracy (2021, background): “duced by AF2 during CASP14 (14th critical assessment of protein structure prediction) typically varied little, although different models for one target could match multiple conformational states accurately.(7,8)”
Computational approaches streamlining drug discovery (2023, background): “To expand the range of structure-based docking applicability to those targets lacking high-resolution structures, it is also tempting to use AI-derived AlphaFold2 (refs.”
AlphaFold Models of Small Proteins Rival the Accuracy of Solution NMR Structures (2022, methodology): “One caveat of this study is the fact that the AlphaFold2 AI is trained on X-ray crystal structures available in the PDB through April 2018 (Jumper et al., 2021a).”
The Statistical Trends of Protein Evolution: A Lesson from AlphaFold Database (2022, background): “In CASP14, the structures predicted by AlphaFold 2 were vastly more accurate than other competing methods (20).”
New prediction categories in CASP15 (2023, methodology): “…ideas and techniques with the protein prediction community, where deep learning methods recently made a significant impact on the modeling accuracy, 11,12 increase visibility of the field, and use CASP's standardized platform for managing predictions and evaluating and comparing different…”