The impact of <scp>AI</scp>‐based modeling on the accuracy of protein assembly prediction: Insights from <scp>CASP15</scp>

Ozden, Burcu; Kryshtafovych, Andriy; Karaca, Ezgi

doi:10.1002/prot.26598

Cited by 18 publications

(17 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The analysis was conducted in close collaboration with our colleagues at Critical Assessment of PRedicted Interactions (CAPRI 5 ). Two assessments were performed, one by CASP 11 and one by CAPRI, 30 providing two views. Here we summarize the main conclusions from the CASP15 assessment.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Critical assessment of methods of protein structure prediction (CASP)—Round XV

Kryshtafovych,

Schwede,

Topf

et al. 2023

Proteins

Self Cite

View full text Add to dashboard Cite

Computing protein structure from amino acid sequence information has been a long‐standing grand challenge. Critical assessment of structure prediction (CASP) conducts community experiments aimed at advancing solutions to this and related problems. Experiments are conducted every 2 years. The 2020 experiment (CASP14) saw major progress, with the second generation of deep learning methods delivering accuracy comparable with experiment for many single proteins. There is an expectation that these methods will have much wider application in computational structural biology. Here we summarize results from the most recent experiment, CASP15, in 2022, with an emphasis on new deep learning‐driven progress. Other papers in this special issue of proteins provide more detailed analysis. For single protein structures, the AlphaFold2 deep learning method is still superior to other approaches, but there are two points of note. First, although AlphaFold2 was the core of all the most successful methods, there was a wide variety of implementation and combination with other methods. Second, using the standard AlphaFold2 protocol and default parameters only produces the highest quality result for about two thirds of the targets, and more extensive sampling is required for the others. The major advance in this CASP is the enormous increase in the accuracy of computed protein complexes, achieved by the use of deep learning methods, although overall these do not fully match the performance for single proteins. Here too, AlphaFold2 based method perform best, and again more extensive sampling than the defaults is often required. Also of note are the encouraging early results on the use of deep learning to compute ensembles of macromolecular structures. Critically for the usability of computed structures, for both single proteins and protein complexes, deep learning derived estimates of both local and global accuracy are of high quality, however the estimates in interface regions are slightly less reliable. CASP15 also included computation of RNA structures for the first time. Here, the classical approaches produced better agreement with experiment than the new deep learning ones, and accuracy is limited. Also, for the first time, CASP included the computation of protein–ligand complexes, an area of special interest for drug design. Here too, classical methods were still superior to deep learning ones. Many new approaches were discussed at the CASP conference, and it is clear methods will continue to advance.

show abstract

Section: Resultsmentioning

confidence: 99%

“…% of CASP14 (blue) and CASP15 (red) protein assembly targets with high quality (>0.8) and low quality (<0.5) computed models as measured by the average contact precision (left) and recall (right) 11 . In CASP15 the fraction of high‐quality models increased from less than 10% to more than 60% by both measures.…”

Section: Resultsmentioning

confidence: 99%

Critical assessment of methods of protein structure prediction (CASP)—Round XV

Kryshtafovych,

Schwede,

Topf

et al. 2023

Proteins

Self Cite

View full text Add to dashboard Cite

show abstract

“…Predictors were asked to assess the models from the multimeric category in CASP15. 14 As described above, three distinct types of scores were requested: SCORE, QSCORE and Local for which predictions were returned by 24, 19, and 14 groups, respectively. To enable a fair comparison and avoid cherry picking of favorable targets, only groups that returned a sufficient amount of data points (80%) for at least 80% of the targets were considered for evaluation.…”

Section: Overview Of the Ema Experiments Performed In Casp15mentioning

confidence: 99%

“…Additionally to evaluating selfassessment in tertiary structure modeling, where we see excellent performance of participants, we processed protein complex models which we furthermore split into core, interface, and surface residues and observed differences in quality estimation accuracy according to residue location. CASP15 EMA participants were asked to process all models from the CASP15 multimeric prediction category 14 and to provide estimates of quaternary structure accuracy on a global level, as well as of local interfaces. We related the predictions to common reference values in the field and developed new ones where required.…”

Section: Introductionmentioning

confidence: 99%

Assessment of the assessment—All about complexes

Studer,

Tauriello,

Schwede

2023

Proteins

View full text Add to dashboard Cite

Predicting model quality is a fundamental component of any modeling procedure, and blind assessment of these methods constitutes a crucial aspect of the Critical Assessment of Protein Structure Prediction (CASP) experiment. Historically, the main focus was on assessing methods that predict global and per‐residue accuracies in tertiary structure models. This focus shifted with the community's increased efforts in modeling complexes and assemblies. We asked the community to process the models from the CASP15 assembly category and provide estimates of the accuracy of the predicted quaternary structure, both globally and at the local interface level. Besides identifying remarkable accuracy of modeling groups in assessing their own predictions, we set up a benchmarking pipeline to highlight different aspects of quaternary structure models and introduced a simple consensus EMA method as baseline. While participating methods showed commendable performance, the baseline was difficult to surpass. It is important to point out that prediction performance varies for the individual CASP targets, highlighting potential areas of improvement and challenges ahead.

show abstract

“…Recently, at CASP15, the accuracy of AF-M has been demonstrated in modeling the quaternary structure of proteins was demonstrated in comparison to bioinformatics methods used prior to AF software (Ozden et al, 2023). The human T1R2/T1R3 (hT1R2/T1R3) complex generated by AF-M contains an ionic bond between hT1R2 Arg217 and hT1R3 Glu217.…”

Section: Prediction Of the Structure Of The T1r2/t1r3 Complexmentioning

confidence: 99%

Novel Gurmarin-like Peptides fromGymnema sylvestreand their Interactions with the Sweet Taste Receptor T1R2/T1R3

Maaroufi

2023

Preprint

View full text Add to dashboard Cite

Gymnema sylvestre (GS) is a traditional medicinal plant known for its hypoglycemic and hypolipidemic effects. Gurmarin (hereafter Gur-1) is the only known peptide in GS. Gur-1 functions as a sweet taste suppressor in rodents but weakly in humans. Here, eight gurmarin-like peptides (Gur-2 to Gur-9) and their isoforms are reported in the GS transcriptome. The molecular mechanism of sweet taste suppression by Gur-1 is still largely unknown. Therefore, the complete architecture of human and mouse sweet taste receptor (STR) T1R2/T1R3 and its interaction with Gur-1 to Gur-9 were predicted by AlphaFold-Multimer (AF-M). Only Gur-1 and Gur-2 interact with T1R2 and T1R3 monomers and the T1R2/T1R3 heterodimer. AF-M predicted that Gur-1 binds to the intracellular domain (ICD) of the T1R2 monomer and to two binding sites in the cysteine rich domain (CRD) of the T1R3 monomer. In the T1R2/T1R3 heterodimer, Gur-1 binds to an additional site on the T1R2 subunit in addition to the ICD. The novel Gur-2 binds to two sites on the T1R2 monomer and one site on the T1R3 monomer, and as Gur-1 to two binding sites on the T1R2 subunit of the T1R2/T1R3 heterodimer. Furthermore, AF-M predicted that the Galpha-gustducin (a role in sweet taste transduction) interacts as Gur-1 with the ICD of the T1R2 subunit in the T1R2/T1R3 heterodimer, suggesting that Gur-1 may compete with Galpha-gustducin in the cell. These results highlight an unexpected diversity of gurmarin-like peptides in GS and provide the complete predicted architecture of the human and mouse sweet taste receptor with the putative binding sites of Gur-1, Gur-2 and Galpha-gustducin.

show abstract

The impact of AI‐based modeling on the accuracy of protein assembly prediction: Insights from CASP15

Cited by 18 publications

References 108 publications

Critical assessment of methods of protein structure prediction (CASP)—Round XV

Critical assessment of methods of protein structure prediction (CASP)—Round XV

Assessment of the assessment—All about complexes

Novel Gurmarin-like Peptides fromGymnema sylvestreand their Interactions with the Sweet Taste Receptor T1R2/T1R3

Contact Info

Product

Resources

About