Rapid protein-protein interaction network creation from multiple sequence alignments with Deep Learning

Bryant, Patrick; Noé, Frank

doi:10.1101/2023.04.15.536993

Cited by 6 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although AF2 has recently been used to discriminate interacting from non-interacting pairs with promising results, ,,, it is always worthy of pushing the system to the limits to better know its applicability range. Here, I propose to further test the AF2 prediction capability in extreme conditions.…”

Section: Resultsmentioning

confidence: 99%

“…The separation between scores of interacting and non-interacting pairs is measured by the AUC value obtained when using the scores to predict whether the proteins interact. Two prediction scores are considered: the AF2 ipTM score and the pDockQ score, recently introduced by Bryant et al., which is derived from the plDDT scores of interface residues. Statistical significance between AUC values is assessed using the nonparametric DeLong’s test implemented in the pROC package …”

Section: Methodsmentioning

confidence: 99%

“…Logically then, the capability of AlphaFold2 to predict whether proteins interact has recently been explored, by using the predicted quality of modeled interfaces as prediction criterion, with very encouraging discrimination capability. ,,− …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

AlphaFold2 Predicts Whether Proteins Interact Amidst Confounding Structural Compatibility

Martin

2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Predicting whether two proteins physically interact is one of the holy grails of computational biology, galvanized by rapid advancements in deep learning. AlphaFold2, although not developed with this goal, is promising in this respect. Here, I test the prediction capability of AlphaFold2 on a very challenging data set, where proteins are structurally compatible, even when they do not interact. AlphaFold2 achieves high discrimination between interacting and non-interacting proteins, and the cases of misclassifications can either be rescued by revisiting the input sequences or can suggest false positives and negatives in the data set. AlphaFold2 is thus not impaired by the compatibility between protein structures and has the potential to be applied on a large scale.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

AlphaFold2 Predicts Whether Proteins Interact Amidst Confounding Structural Compatibility

Martin

2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…In this study, four stat-of-art PPI prediction methods have been used as comparison objects to evaluate the performance of the model. Those methods are D-script [31], DeepTrio [32], PEPPI [22] and SpeedPPI [33].…”

Section: Resultsmentioning

confidence: 99%

SpatialPPI: three-dimensional space protein-protein interaction prediction with AlphaFold Multimer

Hu,

Ohue

2023

Preprint

View full text Add to dashboard Cite

The rapid advancement of protein sequencing technology has resulted in a gap between proteins with identified sequences and those with mapped structures. Although sequence-based predictions offer insights, they can be incomplete due to the absence of structural details. On the other hand, structure-based methods face challenges with newly sequenced proteins. AlphaFold emerges as a potential solution, especially in predicting protein-protein interactions. This research delves into using deep neural networks, specifically analyzing protein complex structures as predicted by AlphaFold Multimer. By transforming atomic coordinates and utilizing sophisticated image processing techniques, the study extracts vital 3D structural details from protein complexes. Recognizing the significance of evaluating residue distances in protein interactions, the study leverages image recognition approaches, notably integrating DenseNet and ResNet within 3D convolutional networks for protein 3D structure analysis. When benchmarked against leading protein-protein interaction prediction methods like SpeedPPI, D-script, DeepTrio, and PEPPI, our proposed method, named SpatialPPI, exhibits notable efficacy, emphasizing the promising role of 3D spatial processing in advancing the realm of structural biology.Abstract Figure

show abstract

“…These findings enhance our understanding of the molecular basis for 53BP1‐RIF1‐shieldin‐CST assembly (Fig 6E ) with putative structural information that shows remarkable agreement with experimental data and represent yet another validation of this approach to discover novel biologically relevant protein–protein interactions. The steady march of innovation in reducing the computational cost of protein structure prediction (Humphreys et al , 2021 ; Mirdita et al , 2022 ; preprint: Bryant & Noe, 2023 ) and in benchmarking scoring functions to detect accurate models (Bryant et al , 2022 ; Yin et al , 2022 ; preprint: Zhu et al , 2022 ) will increase the utility and accessibility of computational mining of the protein interactome.…”

Section: Discussionmentioning

confidence: 99%

An AlphaFold2 map of the 53BP1 pathway identifies a direct SHLD3–RIF1 interaction critical for shieldin activity

et al. 2023

View full text Add to dashboard Cite

53BP1 is a chromatin‐binding protein that promotes DNA double‐strand break repair through the recruitment of downstream effectors including RIF1, shieldin, and CST. The structural basis of the protein–protein interactions within the 53BP1‐RIF1‐shieldin‐CST pathway that are essential for its DNA repair activity is largely unknown. Here, we used AlphaFold2‐Multimer (AF2) to predict all possible pairwise combinations of proteins within this pathway and provide structural models of seven previously characterized interactions. This analysis also predicted an entirely novel binding interface between the HEAT‐repeat domain of RIF1 and the eIF4E‐like domain of SHLD3. Extensive interrogation of this interface through both in vitro pulldown analysis and cellular assays supports the AF2‐predicted model and demonstrates that RIF1‐SHLD3 binding is essential for shieldin recruitment to sites of DNA damage, and for its role in antibody class switch recombination and PARP inhibitor sensitivity. Direct physical interaction between RIF1 and SHLD3 is therefore essential for 53BP1‐RIF1‐shieldin‐CST pathway activity.

show abstract

Rapid protein-protein interaction network creation from multiple sequence alignments with Deep Learning

Cited by 6 publications

References 19 publications

AlphaFold2 Predicts Whether Proteins Interact Amidst Confounding Structural Compatibility

AlphaFold2 Predicts Whether Proteins Interact Amidst Confounding Structural Compatibility

SpatialPPI: three-dimensional space protein-protein interaction prediction with AlphaFold Multimer

An AlphaFold2 map of the 53BP1 pathway identifies a direct SHLD3–RIF1 interaction critical for shieldin activity

Contact Info

Product

Resources

About