PPubMed26 Jun 2023Cited 9×

<i> AlphaFold </i> and the future of structural biology 1 <i> AlphaFold </i> and the future of structural biology

Randy J. Read, Edward N. Baker, Charles S. Bond, Elspeth F. Garman, Mark J. van Raaij

Abstract

This editorial acknowledges the transformative impact of new machine-learning methods, such as the use of AlphaFold, but also makes the case for the continuing need for experimental structural biology.

§ The Valyu brief

The paper, in five minutes

Read from the full text via Valyu Contents

AlphaFold revolutionizes protein prediction but experimental structural biology remains essential for validation and discovery.

What’s new

i.Highlights AlphaFold’s transformative impact on structural biology
ii.Emphasizes the ongoing necessity of experimental techniques
iii.Identifies strengths and weaknesses of current machine‑learning predictions
iv.Shows examples of integrating AlphaFold with cryo‑EM and crystallography

How they did it

The authors reviewed recent literature and developments in protein structure prediction, summarizing advances like AlphaFold and related tools. They compared computational models to experimental data and discussed practical implications for the field.

What they found

AlphaFold models achieved backbone accuracy competitive with experimental structures at CASP14
AlphaFold Database now contains ~200 million protein structures covering most of UniProt
Experimental structures generally outperform AlphaFold models in diffraction data and docking benchmarks

Caveats

✕Predictions lack physics‑based insight, missing alternative conformations and ligand effects
✕Domain orientation errors are common in multi‑domain proteins
✕Side‑chain and local accuracy are lower than experimental structures
✕Experimental methods still needed for cofactors, post‑translational modifications, and stoichiometry

§ The Valyu brief

Reading the full paper and taking notes. This takes a few seconds…

§ Ask this paper

Ask a question about this paper

Valyu reads the full text and answers from what the paper actually says.

§ Related work in other archives

Similar papers in all four archives

The same idea searched in arXiv, PubMed, bioRxiv and chemRxiv at once, so a method can lead you to where it is being applied.

AarXiv4 found

PPubMed4 found

BbioRxiv4 found

CchemRxiv4 found

Searching the other archives…