PRODIGY-crystal: a web-tool for classification of biological interfaces in protein complexes

Jiménez‐García, Brian; Elez, Katarina; Koukos, Panagiotis I.; Bonvin, Alexandre M. J. J.; Vangone, Anna

doi:10.1093/bioinformatics/btz437

Cited by 31 publications

(45 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Distinguishing crystal interfaces from biological ones, when no additional information is available, is still challenging. Several computational approaches have been proposed to distinguish such interfaces, among which PISA 28 and PRODIGY-crystal 29,24 show the highest prediction performances. PISA is based on six physicochemical properties: Free energy of formation, solvation energy gain, interface area, hydrogen bonds, salt-bridge across the interface, and hydrophobic specificity.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

DeepRank: A deep learning framework for data mining 3D protein-protein interfaces

Renaud

Geng

Georgievska

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Three-dimensional (3D) structures of protein complexes provide fundamental information to decipher biological processes at the molecular scale. The vast amount of experimentally and computationally resolved protein-protein interfaces (PPIs) offers the possibility of training deep learning models to aid the predictions of their biological relevance.We present here DeepRank, a general, configurable deep learning framework for data mining PPIs using 3D convolutional neural networks (CNNs). DeepRank maps features of PPIs onto 3D grids and trains a user-specified CNN on these 3D grids. DeepRank allows for efficient training of 3D CNNs with data sets containing millions of PPIs and supports both classification and regression.We demonstrate the performance of DeepRank on two distinct challenges: The classification of biological versus crystallographic PPIs, and the ranking of docking models. For both problems DeepRank is competitive or outperforms state-of-the-art methods, demonstrating the versatility of the framework for research in structural biology.

show abstract

Section: Resultsmentioning

confidence: 99%

“…PRODIGY-crystal is a random forest classifier based on structural properties of interfacial residues and their contacts. 29…”

Section: Resultsmentioning

confidence: 99%

DeepRank: A deep learning framework for data mining 3D protein-protein interfaces

Renaud

Geng

Georgievska

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Various machine learning algorithms were trained on the Many [27] dataset using the 22 best features, attaining an accuracy of 92% with a random forest classifier in a 10-fold cross validation, compared to 88% obtained by EPPIC. The methodology was recently implemented in the user-friendly webserver PRODIGY-CRYSTAL [37].…”

Section: Prodigy-crystal (2018 2019)mentioning

confidence: 99%

“…When no prediction is made in highly uncertain cases, the accuracy increases by 1-2%, but the recall (see Equation (4)) drops, especially for the biological dimers. PIACO Covariation signal, number of core residues, amino acid compositions of the interface and of core residues, amino acid pair frequency, local density index, residue propensity score and gap volume index -> RF DC [16] https://github.com/yfukasawa/piaco [33] PISA Binding energy and entropy of dissociation Ponstingl et al [19] https://www.ebi.ac.uk/msd-srv/prot_int http://www.ccp4.ac.uk/pisa [17,18,20] PITA Interface area and atom-pair frequencies Ponstingl et al [19,23] https://www.ebi.ac.uk/thornton-srv/databases/pita [19,23] PRODIGY-CRYSTAL Number of residue contacts grouped by their character, number of residue contacts per amino acid and link density -> RF Many [27] https://haddock.science.uu.nl/services/PRODIGY-CRYSTAL [36,37] RPAIAnalyst Co-evolutionary and conservation scores, residue pair frequency, Voronoi cell volume, secondary structure, core-rim, B-factor and hot spots -> RF DC [16] http://liulab.hzau.edu.cn/RPAIAnalyst [38] Luo et al Core-surface and core-interface scores, residue propensity, core area, non-polar area and fully buried atoms fractions, gap volume and local density indices, number of hot spots, interface area ratio, amino acid and secondary structure compositions and propensities of interface residues, core residues and hot spots -> RF DC [16] http://cic.scu.edu.cn/bioinformatics/bio-cry.zip [40] NOXclass Interface area, ratio of interface area to protein surface area and amino acid composition of the interface -> SVM Zhu et al [22] http://noxclass.bioinf.mpiinf.mpg.de [22] PreBI and COMP Interface area and shape, hydrophobicity andelectrostatic potential 2.3.9. Valdar and Thornton (2001) Valdar and Thornton [43] were among the first to investigate the role of size and conservation in classifying interfaces.…”

Section: Dimovo (2008)mentioning

confidence: 99%

Biological vs. Crystallographic Protein Interfaces: An Overview of Computational Approaches for Their Classification

Elez

Bonvin

Vangone³

2020

Crystals

Self Cite

View full text Add to dashboard Cite

Complexes between proteins are at the basis of almost every process in cells. Their study, from a structural perspective, has a pivotal role in understanding biological functions and, importantly, in drug development. X-ray crystallography represents the broadest source for the experimental structural characterization of protein-protein complexes. Correctly identifying the biologically relevant interface from the crystallographic ones is, however, not trivial and can be prone to errors. Over the past two decades, computational methodologies have been developed to study the differences of those interfaces and automatically classify them as biological or crystallographic. Overall, protein-protein interfaces show differences in terms of composition, energetics and evolutionary conservation between biological and crystallographic ones. Based on those observations, a number of computational methods have been developed for this classification problem, which can be grouped into three main categories: Energy-, empirical knowledge- and machine learning-based approaches. In this review, we give a comprehensive overview of the training datasets and methods so far implemented, providing useful links and a brief description of each method.

show abstract

“…Finally, to ensure that the oligomer structures we took into account are quaternary structures biologically speaking, we used EPPIC, a protein-protein interface classifier (Capitani et al, 2016), and PRODIGY, a classifier of biological interfaces in protein complexes (Elez et al, 2018;Jiménez-García et al, 2019) to distinguish between crystallographic and biological assemblies.…”

Section: Algorithmmentioning

confidence: 99%

Getting to know each other: PPIMem, a novel approach for predicting transmembrane protein-protein complexes

Khazen

Gyulkhandanian

Issa

et al. 2019

Preprint

View full text Add to dashboard Cite

Membrane proteins account for about one-third of the proteomes of organisms and include structural proteins, channels, and receptors. The mutual interactions they establish in the membrane play crucial roles in organisms, as they are behind many processes such as cell signaling and protein function. Because of their number and diversity, these proteins and their macromolecular complexes, along with their physical interfaces represent potential pharmacological targets par excellence for a variety of diseases, with very important implications for the design and discovery of new drugs or peptides modulating or inhibiting the interaction. Yet, structural data coming from experiments is very scarce for this family of proteins. To overcome this problem, we propose a computational approach for the prediction of alpha transmembrane protein multimeric higher-order structures through data mining, sequence analysis, motif search, extraction, identification and characterization of the amino acid residues at the interface of the complexes. This method leads us to the formulation of binding sites used to scan protein sequence datasets for generating new potential interacting protein couples. Our template motif-based approach using experimental recognition sites leads us to predict new binding sites and to thousands of new binary complexes between membrane proteins when allowing amino acid mutations to take place. We generate an online database of the annotated predicted interactions.

show abstract

PRODIGY-crystal: a web-tool for classification of biological interfaces in protein complexes

Cited by 31 publications

References 13 publications

DeepRank: A deep learning framework for data mining 3D protein-protein interfaces

DeepRank: A deep learning framework for data mining 3D protein-protein interfaces

Biological vs. Crystallographic Protein Interfaces: An Overview of Computational Approaches for Their Classification

Getting to know each other: PPIMem, a novel approach for predicting transmembrane protein-protein complexes

Contact Info

Product

Resources

About