The breakthrough in protein structure prediction

Lupas, Andrei N.; Pereira, Joana; Alva, Vikram; Merino, Felipe; Coles, Murray; Hartmann, M.D.

doi:10.1042/bcj20200963

Cited by 45 publications

(35 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Two years later (CASP14), further improvements were achieved by all of the participants (Kryshtafovych, Schwede et al, 2021;Pearce & Zhang, 2021). However, the accuracy of the models generated by the new version of AlphaFold (version 2.0; hereafter named AlphaFold; Jumper et al, 2021) was superior compared with those obtained by other participants (Lupas et al, 2021;Pereira et al, 2021). The availability of structural templates yielded AlphaFold models with incredibly high accuracy for the so-called 'easy' targets.…”

Section: Introductionmentioning

confidence: 96%

The X-ray crystallography phase problem solved thanks to AlphaFold and RoseTTAFold models: a case-study report

Barbarin-Bocahu¹,

Graille²

2022

Acta Crystallogr D Struct Biol

View full text Add to dashboard Cite

The breakthrough recently made in protein structure prediction by deep-learning programs such as AlphaFold and RoseTTAFold will certainly revolutionize biology over the coming decades. The scientific community is only starting to appreciate the various applications, benefits and limitations of these protein models. Yet, after the first thrills due to this revolution, it is important to evaluate the impact of the proposed models and their overall quality to avoid the misinterpretation or overinterpretation of these models by biologists. One of the first applications of these models is in solving the `phase problem' encountered in X-ray crystallography in calculating electron-density maps from diffraction data. Indeed, the most frequently used technique to derive electron-density maps is molecular replacement. As this technique relies on knowledge of the structure of a protein that shares strong structural similarity with the studied protein, the availability of high-accuracy models is then definitely critical for successful structure solution. After the collection of a 2.45 Å resolution data set, we struggled for two years in trying to solve the crystal structure of a protein involved in the nonsense-mediated mRNA decay pathway, an mRNA quality-control pathway dedicated to the elimination of eukaryotic mRNAs harboring premature stop codons. We used different methods (isomorphous replacement, anomalous diffraction and molecular replacement) to determine this structure, but all failed until we straightforwardly succeeded thanks to both AlphaFold and RoseTTAFold models. Here, we describe how these new models helped us to solve this structure and conclude that in our case the AlphaFold model largely outcompetes the other models. We also discuss the importance of search-model generation for successful molecular replacement.

show abstract

Section: Introductionmentioning

confidence: 96%

The X-ray crystallography phase problem solved thanks to AlphaFold and RoseTTAFold models: a case-study report

Barbarin-Bocahu¹,

Graille²

2022

Acta Crystallogr D Struct Biol

View full text Add to dashboard Cite

show abstract

“…AlphaFold2 is a major advance in protein structure prediction, 1 particularly for single-fold proteins. 2 Nevertheless, it is based more on pattern recognition than biophysical principles. 4 38 Thus, it is not surprising that its predictions often fail for proteins whose properties are not fully apparent from solved protein structures, such as IDPs.…”

Section: Discussionmentioning

confidence: 99%

“…AlphaFold2 has revolutionized protein structure prediction by using sequence information to rapidly model protein folds with atomic‐level accuracy 1,2 . Its predictions are generated by a deep neural network that identifies features of both multiple sequence alignments (MSAs) and experimentally determined protein structures.…”

Section: Introductionmentioning

confidence: 99%

AlphaFold2 fails to predict protein fold switching

Chakravarty

Porter

2022

Protein Science

View full text Add to dashboard Cite

AlphaFold2 has revolutionized protein structure prediction by leveraging sequence information to rapidly model protein folds with atomic-level accuracy. Nevertheless, previous work has shown that these predictions tend to be inaccurate for structurally heterogeneous proteins. To systematically assess factors that contribute to this inaccuracy, we tested AlphaFold2's performance on 98-fold-switching proteins, which assume at least two distinct-yet-stable secondary and tertiary structures. Topological similarities were quantified between five predicted and two experimentally determined structures of each fold-switching protein. Overall, 94% of AlphaFold2 predictions captured one experimentally determined conformation but not the other. Despite these biased results, AlphaFold2's estimated confidences were moderate-to-high for 74% of fold-switching residues, a result that contrasts with overall low confidences for intrinsically disordered proteins, which are also structurally heterogeneous. To investigate factors contributing to this disparity, we quantified sequence variation within the multiple sequence alignments used to generate AlphaFold2's predictions of fold-switching and intrinsically disordered proteins. Unlike intrinsically disordered regions, whose sequence alignments show low conservation, fold-switching regions had conservation rates statistically similar to canonical single-fold proteins. Furthermore, intrinsically disordered regions had systematically lower prediction confidences than either foldswitching or single-fold proteins, regardless of sequence conservation. AlphaFold2's high prediction confidences for fold switchers indicate that it uses sophisticated pattern recognition to search for one most probable conformer rather than protein biophysics to model a protein's structural ensemble. Thus, it is not surprising that its predictions often fail for proteins whose properties are not fully apparent from solved protein structures. Our results emphasize the need to look at protein structure as an ensemble and suggest that systematic examination of fold-switching sequences may reveal propensities for multiple stable secondary and tertiary structures.

show abstract

“…Many proteins do not work in isolation but as part of protein complexes; what matters is not the shape of 1 protein but of the protein complex. 5 Also, proteins are not static; how the structure of different proteins changes as they function requires elucidation. Many diseases (eg, Alzheimer disease) are characterized by proteins that misfold and clump together into pathogenic fibrils; the breakthrough does not currently shed much light on such protein misfolding.…”

Section: Limitationsmentioning

confidence: 99%

Breakthrough Discovery in Protein Structure Prediction and the Promise of New Treatments

Komaroff

2021

JAMA

View full text Add to dashboard Cite

the use of artificial intelligence (AI) led to a breakthrough in an intense, 60-year-long race to solve the protein folding problem. Experts all agreed it was too soon to assess the implications of the breakthrough, but then divided into 2 camps. Some experts greeted the news cautiously, emphasizing what the advance had not yet achieved. Other scientists-including some who lost the race-called it "totally transformative," 1,2 "revolutionary," 3 and of equivalent importance to the Human Genome Project. 3 Most agreed that the discovery was a landmark in biomedical science, with great potential to advance medical practice.

show abstract

The breakthrough in protein structure prediction

Cited by 45 publications

References 28 publications

The X-ray crystallography phase problem solved thanks to AlphaFold and RoseTTAFold models: a case-study report

The X-ray crystallography phase problem solved thanks to AlphaFold and RoseTTAFold models: a case-study report

AlphaFold2 fails to predict protein fold switching

Breakthrough Discovery in Protein Structure Prediction and the Promise of New Treatments

Contact Info

Product

Resources

About