AlphaFold at CASP13

By Mohammed Alquraishi. 2019

287 citations recorded by the source corpus.

Computational prediction of protein structure from sequence is broadly viewed as a foundational problem of biochemistry and one of the most difficult challenges in bioinformatics. Once every two years the Critical Assessment of protein Structure Prediction (CASP) experiments are held to assess the state of the art in the field in a blind fashion, by presenting predictor groups with protein sequences whose structures have been solved but have not yet been made publicly available. The first CASP was organized in 1994, and the latest, CASP13, took place last December, when for the first time the industrial laboratory DeepMind entered the competition. DeepMind's entry, AlphaFold, placed first in the Free Modeling (FM) category, which assesses methods on their ability to predict novel protein folds (the Zhang group placed first in the Template-Based Modeling (TBM) category, which assess methods on predicting proteins whose folds are related to ones already in the Protein Data Bank.) DeepMind's success generated significant public interest. Their approach builds on two ideas developed in the academic community during the preceding decade: (i) the use of co-evolutionary analysis to map residue co-variation in protein sequence to physical contact in protein structure, and (ii) the application of deep neural networks to robustly identify patterns in protein sequence and co-evolutionary couplings and convert them into contact maps. In this Letter, we contextualize the significance of DeepMind's entry within the broader history of CASP, relate AlphaFold's methodological advances to prior work, and speculate on the future of this important problem.

Subfields: Materials Chemistry, Molecular Biology

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

Citations in the corpus

A Survey of Embodied AI: From Simulators to Research Tasks (2021, background): “Modern techniques in machine learning, computer vision, natural language processing and robotics have achieved great successes in their respective fields, and the resulting applications have enhanced many aspects of technology and human life in general [3, 4, 5].”
A further leap of improvement in tertiary structure prediction in CASP13 prompts new routes for future assessments (2019, background): “Although there is no yet any official publication on A7D, the interested reader is referred to a recent article by AlQuraishi 17 presenting some aspects of A7D's methods as well as other interesting considerations.”
Deep Learning in Protein Structural Modeling and Design (2020, background): “Figure from AlQuraishi (2019).101 like the RaptorX-Contact group, emphasized that the accuracy of predictions relied heavily on learned distance distributions and co-evolutionary data.”
Assessing the accuracy of contact predictions in CASP13 (2019, background): “F -score has a drawback that it has a narrower (compared to the precision) scale on a short list of L/5 contacts, with the highest F -score of 0.54 in CASP13.”
Relative Positional Encoding for Transformers with Linear Complexity (2021, unknown): “…et al., 2017) is a new kind of neural network that quickly became state-of-the-art in many application domains, including the processing of natural language (He et al., 2020), images (Dosovitskiy et al., 2020), audio (Huang et al., 2018; Pham et al., 2020) or bioinformatics (AlQuraishi, 2019) sion.”
Systematic evaluation of computational tools to predict the effects of mutations on protein stability in the absence of experimental structures (2022, background): “In homology modelling, it is well-established that there is a correlation between template identity level and the reliability and quality of models generated [61], despite recent advances in the field pushing the boundaries of both de novo [72] and template-free modelling [73].”
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks (2021, background): “…achieved state-of-the-art performance in various applications and tasks, ranging from conventional research topics such as computer vision [24, 22] and natural language processing [13, 16] to distant fields such as games [44, 6], computational advertising [57, 54], and structural biology [1, 14].”
Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions (2022, background): “For instance, trRosetta [51] can predict the distance between two amino acids and the orientation formed by their atom planes, and Alphafold [52] can even directly predict the 3D structure of target proteins with high precision.”
The Application of Deep Learning in Cancer Prognosis Prediction (2020, methodology): “In recent years, deep learning has been applied to biomedical research to annotate pathogenicity of genetic variants [51,52], show state-of-the-art performance in the task of genomic variant calling [53] and improve protein folding prediction [54,55].”
Model-Based Reinforcement Learning with Value-Targeted Regression (2020, background): “Copyright 2020 by the author(s). mains, such as games, robotics and science, has witnessed phenomenal empirical advances during the last few years (e.g., Mnih et al. 2015; Silver et al. 2017; AlQuraishi 2019; Arulkumaran et al. 2019).”