DeepRank
DE
Deep learning framework for data mining protein-protein interactions using CNN
Updated 5 months ago
60 8
Get started
493 commits | Last commit ≈ 1 month ago
Ctrl K
DeepRank GNN
DeepRank-GNN is the graph neural network of our DeepRank package. DeepRank GNN allows to train graph neural networks to classify protein-protein interface
37
mentions
2
contributors
What DeepRank GNN can do for you
- Creates graphs on protein-protein interface
- Train graph neural network on protein-protein interface
Gaining structural insights into the protein-protein interactome is essential to understand biological phenomena and extract knowledge for rational drug design or protein engineering. We have previously developed DeepRank, a deep-learning framework to facilitate pattern learning from protein-protein interfaces using Convolutional Neural Network (CNN) approaches. However, CNN is not rotation invariant and data augmentation is required to desensitize the network to the input data orientation which dramatically impairs the computation performance. Representing protein-protein complexes as atomic- or residue-scale rotation invariant graphs instead enables using graph neural networks (GNN) approaches, bypassing those limitations.
We have developed DeepRank-GNN, a framework that converts protein-protein interfaces from PDB 3D coordinates files into graphs that are further provided to a pre-defined or user-defined GNN architecture to learn problem-specific interaction patterns. DeepRank-GNN is designed to be highly modularizable, easily customized, and is wrapped into a user-friendly python3 package. Here, we showcase DeepRank-GNN’s performance for scoring docking models using a dedicated graph interaction neural network (GINet). We show that this graph-based model performs better than DeepRank, DOVE and HADDOCK scores and competes with iScore on the CAPRI score set. We show a significant gain in speed and storage requirement using DeepRank-GNN as compared to DeepRank.
Participating organisations
Reference papers
Mentions
Flavour your linked data with garlic
Author(s): Carlos Martinez-Ortiz
Published in 2018
Journal articles
26- 1.EGGNet, a Generalizable Geometric Deep Learning Framework for Protein Complex Pose ScoringAuthor(s): Zichen Wang, Ryan Brand, Jared Adolf-Bryfogle, Jasleen Grewal, Yanjun Qi, Steven A. Combs, Nataliya Golovach, Rebecca Alford, Huzefa Rangwala, Peter M. ClarkPublished in 202410.1021/acsomega.3c04889
- 2.Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody–Antigen InteractionsAuthor(s): Doo Nam Kim, Andrew D. McNaughton, Neeraj KumarPublished in 202410.3390/bioengineering11020185
- 3.Prop3D: A flexible, Python-based platform for machine learning with protein structural properties and biophysical dataAuthor(s): Eli J. Draizen, John Readey, Cameron Mura, Philip E. BournePublished in 202410.1186/s12859-023-05586-5
- 4.SurfPro-NN: A 3D point cloud neural network for the scoring of protein–protein docking models based on surfaces features and protein language modelsAuthor(s): Qianli Yang, Xiaocheng Jin, Haixia Zhou, Junjie Ying, JiaJun Zou, Yiyang Liao, Xiaoli Lu, Shengxiang Ge, Hai Yu, Xiaoping MinPublished in 202410.1016/j.compbiolchem.2024.108067
- 5.Leveraging machine learning models for peptide–protein interaction predictionAuthor(s): Yin, Song, Mi, Xuenan, Shukla, DiwakarPublished in 202410.1039/d3cb00208j
- 6.Computational Approaches to Predict Protein–Protein Interactions in Crowded Cellular EnvironmentsAuthor(s): Greta Grassmann, Mattia Miotto, Fausta Desantis, Lorenzo Di Rienzo, Gian Gaetano Tartaglia, Annalisa Pastore, Giancarlo Ruocco, Michele Monti, Edoardo MilanettiPublished in 202410.1021/acs.chemrev.3c00550
- 7.DeepRank-GNN-esm: A Graph Neural Network for Scoring Protein-Protein Models using Protein Language ModelAuthor(s): X Xu, A M J J BonvinPublished in 202410.1093/bioadv/vbad191
- 8.MGMT promoter methylation prediction based on multiparametric MRI via vision graph neural networkAuthor(s): Mingzhe Hu, Kailin Yang, Jing Wang, Richard L. J. Qiu, Justin Roper, Shannon Kahn, Hui-Kuo Shu, Xiaofeng YangPublished in 202410.1117/1.jmi.11.1.014503
- 9.ProInterVal: Validation of Protein–Protein Interfaces through Learned Interface RepresentationsAuthor(s): Damla Ovek, Ozlem Keskin, Attila GursoyPublished in 202410.1021/acs.jcim.3c01788
- 10.Ha-gnn: a novel graph neural network based on hyperbolic attentionAuthor(s): Hongbo Qu, Yu-Rong Song, Minglei Zhang, Guo-Ping Jiang, Ruqi Li, Bo SongPublished in 202410.1007/s00521-024-09689-9
- 11.Bi-directional prediction of hydrothermal carbonization characteristics of agroforestry and livestock wastes with variable components: Graph learning model-aided waste recycleAuthor(s): Zi-Kai Lin, Chao-Sheng Li, Rong-Rong Cai, Yan-Qiu LongPublished in 202410.1016/j.jclepro.2024.140894
- 12.Predicting Phase Stability at InterfacesAuthor(s): J. Pitfield, N. T. Taylor, S. P. HepplestonePublished in 202410.1103/physrevlett.132.066201
- 13.A modified GNN architecture with enhanced aggregator and Message Passing FunctionsAuthor(s): Debjit Sarkar, Sourodeep Roy, Samir Malakar, Ram SarkarPublished in 202310.1016/j.engappai.2023.106077
- 14.A network analysis-based framework to understand the representation dynamics of graph neural networksAuthor(s): Gianluca Bonifazi, Francesco Cauteruccio, Enrico Corradini, Michele Marchetti, Domenico Ursino, Luca VirgiliPublished in 202310.1007/s00521-023-09181-w
- 15.Evaluating protein binding interfaces with transformer networksAuthor(s): Vitalii Stebliankin, Azam Shirali, Prabin Baral, Jimeng Shi, Prem Chapagain, Kalai Mathee, Giri NarasimhanPublished in 202310.1038/s42256-023-00715-4
- 16.<scp>VoroIF‐GNN</scp>: Voronoi tessellation‐derived protein–protein interface assessment using a graph neural networkAuthor(s): Kliment Olechnovič, Česlovas VenclovasPublished in 202310.1002/prot.26554
- 17.Enhancing Dissolved Oxygen Concentrations Prediction in Water Bodies: A Temporal Transformer Approach with Multi-Site Meteorological Data Graph EmbeddingAuthor(s): Hongqing Wang, Lifu Zhang, Rong Wu, Hongying ZhaoPublished in 202310.3390/w15173029
- 18.G-RANK: an equivariant graph neural network for the scoring of protein–protein docking modelsAuthor(s): Ha Young Kim, Sungsik Kim, Woong-Yang Park, Dongsup KimPublished in 202310.1093/bioadv/vbad011
- 19.Recent Advances in Deep Learning for Protein-Protein Interaction Analysis: A Comprehensive ReviewAuthor(s): Minhyeok LeePublished in 202310.3390/molecules28135169
- 20.Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational IntelligenceAuthor(s): Uzair Aslam Bhatti, Hao Tang, Guilu Wu, Shah Marjan, Aamir HussainPublished in 202310.1155/2023/8342104
- 21.Open-Source Machine Learning in Computational ChemistryAuthor(s): Alexander Hagg, Karl N KirschnerPublished in 202310.1021/acs.jcim.3c00643
- 22.A Survey on Differential Privacy for Medical Data AnalysisAuthor(s): WeiKang Liu, Yanchun Zhang, Hong Yang, Qinxue MengPublished in 202310.1007/s40745-023-00475-3
- 23.A gated graph transformer for protein complex structure quality assessment and its performance in CASP15Author(s): Xiao Chen, Alex Morehead, Jian Liu, Jianlin ChengPublished in 202310.1093/bioinformatics/btad203
- 24.Discriminating physiological from non‐physiological interfaces in structures of protein complexes: A community‐wide studyAuthor(s): Hugo Schweke, Qifang Xu, Gerardo Tauriello, Lorenzo Pantolini, Torsten Schwede, Frédéric Cazals, Alix Lhéritier, Juan Fernandez-Recio, Luis Angel Rodríguez-Lumbreras, Ora Schueler-Furman, Julia K Varga, Brian Jiménez-García, Manon F Réau, Alexandre M J J Bonvin, Castrense Savojardo, Pier-Luigi Martelli, Rita Casadio, Jérôme Tubiana, Haim J Wolfson, Romina Oliva, Didier Barradas-Bautista, Tiziana Ricciardelli, Luigi Cavallo, Česlovas Venclovas, Kliment Olechnovič, Raphael Guerois, Jessica Andreani, Juliette Martin, Xiao Wang, Genki Terashi, Daipayan Sarkar, Charles Christoffer, Tunde Aderinwale, Jacob Verburgt, Daisuke Kihara, Anthony Marchand, Bruno E Correia, Rui Duan, Liming Qiu, Xianjin Xu, Shuang Zhang, Xiaoqin Zou, Sucharita Dey, Roland L Dunbrack, Emmanuel D Levy, Shoshana J WodakPublished in 202310.1002/pmic.202200323
- 25.MT$$^2$$AD: multi-layer temporal transaction anomaly detection in ethereum networks with GNNAuthor(s): Beibei Han, Yingmei Wei, Qingyong Wang, Francesco Maria De Collibus, Claudio J. TessonePublished in 202310.1007/s40747-023-01126-z
- 26.Deep Local Analysis evaluates protein docking conformations with locally oriented cubesAuthor(s): Yasser Mohseni Behbahani, Simon Crouzet, Elodie Laine, Alessandra CarbonePublished in 202210.1093/bioinformatics/btac551
Other
10- 1.ProAffinity-GNN: A Novel Approach to Structure-based Protein-Protein Binding Affinity Prediction via a Curated Dataset and Graph Neural NetworksAuthor(s): Zhiyuan Zhou, Yueming Yin, Hao Han, Yiping Jia, Jun Hong Koh, Adams Wai-Kin Kong, Yuguang MuPublished in 202410.1101/2024.03.14.584935
- 2.Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property predictionAuthor(s): Yang Yue, Shu Li, Yihua Cheng, Zexuan Zhu, Lie Wang, Tingjun Hou, Shan HePublished in 202410.1101/2024.03.14.585015
- 3.Building explainable graph neural network by sparse learning for the drug-protein binding predictionAuthor(s): Yang Wang, Zanyu Shi, Timothy Richardson, Kun Huang, Pathum Weerawarna, Yijie WangPublished in 202310.1101/2023.08.28.555203
- 4.DeepRank-GNN-esm: A Graph Neural Network for Scoring Protein-Protein Models using Protein Language ModelAuthor(s): Xiaotong Xu, Alexandre MJJ BonvinPublished in 202310.1101/2023.06.22.546080
- 5.Leveraging Graph Machine Learning for Moonlighting Protein Prediction: A Local PPI Network and Physiochemical Feature ApproachAuthor(s): Hongliang Zhou, Rik SarkarPublished in 202310.1101/2023.11.13.566879
- 6.ZEPPI: proteome-scale sequence-based evaluation of protein-protein interaction modelsAuthor(s): Barry Honig, Haiqing Zhao, Diana Murray, Donald PetreyPublished in 202310.21203/rs.3.rs-3289791/v1
- 7.Allocator is a graph neural network-based framework for mRNA subcellular localization predictionAuthor(s): Fuyi Li, Yue Bi, Xudong Guo, Xiaolan Tan, Cong Wang, Shirui PanPublished in 202310.1101/2023.12.14.571762
- 8.ProInterVal: Validation of Protein-Protein Interfaces through Learned Interface RepresentationsAuthor(s): Damla Ovek, Ozlem Keskin, Attila GursoyPublished in 202310.1101/2023.12.27.573460
- 9.EGGNet, a generalizable geometric deep learning framework for protein complex pose scoringAuthor(s): Zichen Wang, Ryan Brand, Jared Adolf-Bryfogle, Jasleen Grewal, Yanjun Qi, Steven A Combs, Nataliya Golovach, Rebecca Alford, Huzefa Rangwala, Peter M ClarkPublished in 202310.1101/2023.03.22.533800
- 10.A Gated Graph Transformer for Protein Complex Structure Quality Assessment and its Performance in CASP15Author(s): Xiao Chen, Alex Morehead, Jian Liu, Jianlin ChengPublished in 202210.1101/2022.05.19.492741
Contributors
Contact person
Nicolas Renaud
Netherlands eScience Center
MR
Manon Réau
Utrecht University
Nicolas Renaud
Netherlands eScience Center
Related projects
3D-Vac
Personalized cancer vaccine design through 3D modelling boosted geometric learning
Updated 2 weeks ago
In progress
DeepRank
Scoring 3D protein-protein interaction models using deep learning
Updated 13 months ago
Finished
Related software
iScore
IS
A framework and predictor based on support vector machine and random walk graph kernel for scoring protein-protein interfaces.
Updated 5 months ago
3 4
pdb2sql
PD
Fast and versatile Python package that leverages SQL queries to parse, manipulate and process biomolecular structure files. The structure files should be in the PDB format and are available on www.rcsb.org.
Updated 21 months ago
3 2