2023
DOI: 10.1002/prot.26542
|View full text |Cite
|
Sign up to set email alerts
|

Combining pairwise structural similarity and deep learning interface contact prediction to estimate protein complex model accuracy in CASP15

Abstract: Estimating the accuracy of quaternary structural models of protein complexes and assemblies (EMA) is important for predicting quaternary structures and applying them to studying protein function and interaction. The pairwise similarity between structural models is proven useful for estimating the quality of protein tertiary structural models, but it has been rarely applied to predicting the quality of quaternary structural models. Moreover, the pairwise similarity approach often fails when many structural mode… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
10
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(10 citation statements)
references
References 54 publications
0
10
0
Order By: Relevance
“…DeepUMQA3 uses the average of the lDDT of all residues (global lDDT) as the overall fold accuracy, and GraphGPSM directly predicts the TM‐score of the overall complex. The comprehensive performance of GraphGPSM and DeepUMQA3 ranked seventh and ninth among the 23 participating methods, respectively, and MULTICOM_qa 42 ranked first. In this section, TM‐score and global lDDT are used to measure the global accuracy evaluation performance of DeepUMQA3 and GraphGPSM.…”
Section: Resultsmentioning
confidence: 99%
“…DeepUMQA3 uses the average of the lDDT of all residues (global lDDT) as the overall fold accuracy, and GraphGPSM directly predicts the TM‐score of the overall complex. The comprehensive performance of GraphGPSM and DeepUMQA3 ranked seventh and ninth among the 23 participating methods, respectively, and MULTICOM_qa 42 ranked first. In this section, TM‐score and global lDDT are used to measure the global accuracy evaluation performance of DeepUMQA3 and GraphGPSM.…”
Section: Resultsmentioning
confidence: 99%
“… a The methods of ModFOLDdock series refer to Edmunds et al (2023) , the method of VoroIF refer to Olechnovič and Venclovas (2023) , the method of MULTICOM_deep refer to Roy et al (2023) , and the other methods refer to the abstract of CASP15 ( https://predictioncenter.org/casp15/doc/CASP15_Abstracts.pdf ). b Pearson and Spearman indicated the correlation between the accuracy of predicted interface residues and the real lDDT/CAD of interface residues.…”
Section: Resultsmentioning
confidence: 99%
“… a The methods of ModFOLDdock series refer to Edmunds et al (2023) , the method of VoroIF refer to Olechnovič and Venclovas (2023) , the method of MULTICOM_deep refer to Roy et al (2023) , and the other methods refer to the abstract of CASP15 ( https://predictioncenter.org/casp15/doc/CASP15_Abstracts.pdf ). …”
Section: Resultsmentioning
confidence: 99%
“…Hence, during the model selection, we relied mostly on the consistency of models with experimental data rather than on predicted ipTM scores. This strategy was based on the previous observations that the predicted contact scores often fail to identify the true models, 99 and experimental verification is usually required to validate and justify the physiological relevance of AF2-predicted conformations of membrane proteins. 100 We found that the V3 version produced better models for TPOR complexes (Figure S13A), but not for other receptors where the results with V2 and V3 versions were rather similar.…”
Section: Modeling Of Signaling Complexes With Alpha-fold-multimer (Afm)mentioning
confidence: 99%