Machine learning in protein structure prediction.

By Mohammed Alquraishi. 2021

152 citations recorded by the source corpus.

Prediction of protein structure from sequence has been intensely studied for many decades, owing to the problem's importance and its uniquely well-defined physical and computational bases. While progress has historically ebbed and flowed, the past two years saw dramatic advances driven by the increasing "neuralization" of structure prediction pipelines, whereby computations previously based on energy models and sampling procedures are replaced by neural networks. The extraction of physical contacts from the evolutionary record; the distillation of sequence-structure patterns from known structures; the incorporation of templates from homologs in the Protein Databank; and the refinement of coarsely predicted structures into finely resolved ones have all been reformulated using neural networks. Cumulatively, this transformation has resulted in algorithms that can now predict single protein domains with a median accuracy of 2.1 Å, setting the stage for a foundational reconfiguration of the role of biomolecular modeling within the life sciences.

Subfields: Computational Theory and Mathematics, 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 Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

Citations in the corpus

Biasing AlphaFold2 to predict GPCRs and kinases with user-defined functional or structural properties (2022, methodology): “Since the emergence of AF2, a number of deep learning-based methods have been developed with the same goal of predicting protein structures at experimental accuracy (AlQuraishi, 2021; Baek et al., 2021; Chowdhury et al., 2022; Lin et al., 2022).”
A structural biology community assessment of AlphaFold2 applications (2021, background): “These developments have been reviewed recently 9 and can be characterized by the increasing use of neural-network models in key aspects of the challenge of predicting protein structures from their primary sequence.”
Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies (2022, unknown): “Similar to the role played by alignments of evolutionarily related sequences for general protein structure prediction 33 , embeddings from AntiB-ERTy act as a contextual representation that places individual sequences within the broader antibody space.”
AlphaFold, Artificial Intelligence (AI), and Allostery (2022, background): “157 − 163 AlphaFold is not the first in being a machine-learning model.”
Single-sequence protein structure prediction using language models and deep learning (2022, background): “5).”
Modeling Alternate Conformations with Alphafold2 via Modification of the Multiple Sequence Alignment (2021, background): “29 Multiple groups have harnessed co-evolution of residues to generate distance restraints/matrices and 30 the subsequent construction of a three-dimensional protein structure.(1) The latest iteration, Alphafold2 31 (AF2), took a significant leap forward with the quality of the predicted structures ”
Using machine learning to study protein–protein interactions: From the uromodulin polymer to egg zona pellucida filaments (2021, background): “, 2021) to investigate whether the recent advances in the application of machine‐learning to protein structure prediction (AlQuraishi, 2021) can provide insights into these kinds of questions, using ZP module activation as an example of the complex conformational changes that can take place during t”