High‐accuracy protein structure prediction in CASP14

By Joana Pereira, Adam J. Simpkin, Marcus D. Hartmann, Daniel J. Rigden, Ronan M. Keegan, Andrei N. Lupas. 2021

276 citations recorded by the source corpus.

The application of state‐of‐the‐art deep‐learning approaches to the protein modeling problem has expanded the “high‐accuracy” category in CASP14 to encompass all targets. Building on the metrics used for high‐accuracy assessment in previous CASPs, we evaluated the performance of all groups that submitted models for at least 10 targets across all difficulty classes, and judged the usefulness of those produced by AlphaFold2 (AF2) as molecular replacement search models with AMPLE. Driven by the qualitative diversity of the targets submitted to CASP, we also introduce DipDiff as a new measure for the improvement in backbone geometry provided by a model versus available templates. Although a large leap in high‐accuracy is seen due to AF2, the second‐best method in CASP14 out‐performed the best in CASP13, illustrating the role of community‐based benchmarking in the development and evolution of the protein structure prediction field.

Subfields: Materials Chemistry, Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

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

In Materials Chemistry

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

Predicting multiple conformations via sequence clustering and AlphaFold2 (2023, positive): “AlphaFold2 (AF2) achieved breakthrough performance in the CASP14 competition 6 in part by advancing the state of the art for inferring patterns of interactions between related sequences in a multiple-sequence alignment (MSA), building on a long history of methods for inferring these patterns 7–10 ,…”
Assessment of three-dimensional RNA structure prediction in CASP15 (2023, positive): “Following the success of AI-based tools in protein structure prediction 13 and a surge of interest in RNA during the COVID pandemic, 14 the hope of the organizers and assessors was to generate motivation and attention from protein modeling groups to develop and evaluate methods for RNA.”
Sampling alternative conformational states of transporters and receptors with AlphaFold2 (2022, positive): “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.”
Critical Assessment of Methods of Protein Structure Prediction (CASP) – Round XIV (2021, methodology): “A total of 39 experimental groups from 15 countries provided targets for CASP14.”
AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models (2021, background): “In 2020, the organizers of the CASP14 benchmark recognized AlphaFold as a solution to the protein–structure–prediction problem (12).”
AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB (2022, background): “In 2020, the CASP14 benchmark has recognized AlphaFold2 as a solution to the protein–folding problem (Pereira et al., 2021).”
Topology Evaluation of Models for Difficult Targets in the 14th Round of the Critical Assessment of Protein Structure Prediction (CASP14) (2021, methodology): “The assessment category included 23 difficult EUs (FM class) and 15 borderline EUs (FM/TBM) that were also evaluated by the high accuracy modeling assessment 18 .”
DALI shines a light on remote homologs: One hundred discoveries (2022, background): “The predicted AlphaFold models are remarkably accurate, displaying low RMSD values and high Z-scores, and add to the record of successful predictions by AlphaFold (Jumper et al., 2021; Pereira et al., 2021) (Table 1).”
De novo protein design by inversion of the AlphaFold structure prediction network (2022, methodology): “Although the network was trained on MSAs containing co-evolutionary signals and templates as inputs, AF2 can accurately predict protein structures of de novo proteins from a single sequence alone (Pereira et al., 2021).”
Intrinsic protein disorder and conditional folding in AlphaFoldDB (2022, background): “2,3 This is leading to a paradigm shift for structural biology due to the sudden availability of orders of magnitude more protein structures.”