A two-layer integration framework for protein complex detection

Protein complexes carry out nearly all signaling and functional processes within cells. The study of protein complexes is an effective strategy to analyze cellular functions and biological processes. With the increasing availability of proteomics data, various computational methods have recently been developed to predict protein complexes. However, different computational methods are based on their own assumptions and designed to work on different data sources, and various biological screening methods have their unique experiment conditions, and are often different in scale and noise level. Therefore, a single computational method on a specific data source is generally not able to generate comprehensive and reliable prediction results. In this paper, we develop a novel Two-layer INtegrative Complex Detection (TINCD) model to detect protein complexes, leveraging the information from both clustering results and raw data sources. In particular, we first integrate various clustering results to construct consensus matrices for proteins to measure their overall co-complex propensity. Second, we combine these consensus matrices with the co-complex score matrix derived from Tandem Affinity Purification/Mass Spectrometry (TAP) data and obtain an integrated co-complex similarity network via an unsupervised metric fusion method. Finally, a novel graph regularized doubly stochastic matrix decomposition model is proposed to detect overlapping protein complexes from the integrated similarity network. Extensive experimental results demonstrate that TINCD performs much better than 21 state-of-the-art complex detection techniques, including ensemble clustering and data integration techniques.

• Publication year

  2016

• Venue

  BMC Bioinformatics

• Publication date

  2016-02-24

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1186/s12859-016-0939-3PMID 26911324PMCID 4765032
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Integrating experimental and literature protein-protein interaction data for protein complex prediction

  2015cited by this paper
• Use of targeted SNP selection for an improved anchoring of the melon (Cucumis melo L.) scaffold genome assembly

  2015cited by this paper
• Detecting Protein Complexes from Signed Protein-Protein Interaction Networks

  2015cited by this paper
• From proteomes to complexomes in the era of systems biology

  2014cited by this paper
• Detecting temporal protein complexes from dynamic protein-protein interaction networks

  2014cited by this paper
• Similarity network fusion for aggregating data types on a genomic scale

  2014influential reference
• Network inference from AP-MS data: computational challenges and solutions

  2014cited by this paper
• The binary protein-protein interaction landscape of Escherichia coli

  2014cited by this paper
• Protein Complex Detection via Weighted Ensemble Clustering Based on Bayesian Nonnegative Matrix Factorization

  2013cited by this paper
• Integrative approaches for finding modular structure in biological networks

  2013cited by this paper
• Identifying protein complexes from heterogeneous biological data

  2013influential reference
• Discovery of Protein Complexes with Core-Attachment Structures from Tandem Affinity Purification (TAP) Data

  2012cited by this paper
• Clustering by Low-Rank Doubly Stochastic Matrix Decomposition

  2012cited by this paper
• Towards the identification of protein complexes and functional modules by integrating PPI network and gene expression data

  2012cited by this paper
• Consensus clustering in complex networks

  2012cited by this paper
• Exploring Overlapping Functional Units with Various Structure in Protein Interaction Networks

  2012cited by this paper
• Predicting protein complexes via the integration of multiple biological information

  2012cited by this paper
• Detecting overlapping protein complexes in protein-protein interaction networks

  2012influential reference
• Graph Regularized Nonnegative Matrix Factorization for Data Representation

  2011cited by this paper
• Multifunctional proteins revealed by overlapping clustering in protein interaction network

  2011cited by this paper
• Construction of co-complex score matrix for protein complex prediction from AP-MS data

  2011cited by this paper
• A comparison of the functional modules identified from time course and static PPI network data

  2011cited by this paper
• A Fast Hierarchical Clustering Algorithm for Functional Modules Discovery in Protein Interaction Networks

  2011cited by this paper
• Modularity of Escherichia coli sRNA regulation revealed by sRNA-target and protein network analysis

  2010cited by this paper
• SPICi: a fast clustering algorithm for large biological networks

  2010cited by this paper
• Computational approaches for detecting protein complexes from protein interaction networks: a survey

  2010cited by this paper
• Recent advances in clustering methods for protein interaction networks

  2010cited by this paper
• Integrating diverse biological and computational sources for reliable protein-protein interactions

  2010cited by this paper
• Extensive analysis of D-J-C arrangements allows the identification of different mechanisms enhancing the diversity in sheep T cell receptor β-chain repertoire

  2010cited by this paper
• How and when should interactome-derived clusters be used to predict functional modules and protein function?

  2009cited by this paper
• A core-attachment based method to detect protein complexes in PPI networks

  2009cited by this paper
• RRW: repeated random walks on genome-scale protein networks for local cluster discovery

  2009cited by this paper
• Complex discovery from weighted PPI networks

  2009cited by this paper
• A novel approach to simulate gene-environment interactions in complex diseases

  2009cited by this paper
• Modifying the DPClus algorithm for identifying protein complexes based on new topological structures

  2008cited by this paper
• From pull-down data to protein interaction networks and complexes with biological relevance

  2008cited by this paper
• Nonnegative Matrix Factorization with Gaussian Process Priors

  2008cited by this paper
• Up-to-date catalogues of yeast protein complexes

  2008cited by this paper
• Bootstrapping the Interactome: Unsupervised Identification of Protein Complexes in Yeast

  2008cited by this paper
• Toward a Comprehensive Atlas of the Physical Interactome of Saccharomyces cerevisiae*S

  2007cited by this paper
• Identification of functional modules using network topology and high-throughput data

  2007cited by this paper
• Discovering protein complexes in dense reliable neighborhoods of protein interaction networks.

  2007cited by this paper
• An ensemble framework for clustering protein-protein interaction networks

  2007cited by this paper
• A high-accuracy consensus map of yeast protein complexes reveals modular nature of gene essentiality

  2007cited by this paper
• Identifying functional modules in the physical interactome of Saccharomyces cerevisiae

  2007cited by this paper
• Assessment of the relationship between pre-chip and post-chip quality measures for Affymetrix GeneChip expression data

  2006cited by this paper
• MIPS: analysis and annotation of proteins from whole genomes in 2005

  2006cited by this paper
• Proteome survey reveals modularity of the yeast cell machinery

  2006influential reference
• Evaluation of clustering algorithms for protein-protein interaction networks

  2006cited by this paper
• Global landscape of protein complexes in the yeast Saccharomyces cerevisiae

  2006cited by this paper
• Development and implementation of an algorithm for detection of protein complexes in large interaction networks

  2006cited by this paper
• CFinder: locating cliques and overlapping modules in biological networks

  2006influential reference
• MIPS: analysis and annotation of proteins from whole genomes in 2005

  2005cited by this paper
• On the Equivalence of Nonnegative Matrix Factorization and Spectral Clustering

  2005cited by this paper
• Protein complex prediction via cost-based clustering

  2004cited by this paper
• Onto-Tools: an ensemble of web-accessible, ontology-based tools for the functional design and interpretation of high-throughput gene expression experiments

  2004cited by this paper
• The Database of Interacting Proteins: 2004 update

  2004cited by this paper
• An automated method for finding molecular complexes in large protein interaction networks

  2003cited by this paper
• An efficient algorithm for large-scale detection of protein families.

  2002cited by this paper
• Functional organization of the yeast proteome by systematic analysis of protein complexes

  2002cited by this paper
• A comprehensive two-hybrid analysis to explore the yeast protein interactome

  2001cited by this paper
• DIP: The Database of Interacting Proteins: 2001 update

  2001cited by this paper
• SGD: Saccharomyces Genome Database

  1998cited by this paper
• Bioinformatics Advance Access published June 12, 2008 Ensemble Non-negative Matrix Factorization Methods for Clustering Protein-Protein Interactions

  year unknowncited by this paper

• A partially shared joint clustering framework for detecting protein complexes from multiple state-specific signed interaction networks

  2023cites this paper
• Protein‐protein interaction networks as miners of biological discovery

  2022cites this paper
• Efficient and accurate identification of protein complexes from protein-protein interaction networks based on the clustering coefficient

  2021cites this paper
• Community Detection in Protein-Protein Interaction Networks and Applications

  2021cites this paper
• idenPC-CAP: Identify protein complexes from weighted RNA-protein heterogeneous interaction networks using co-assemble partner relation

  2020cites this paper
• DPCT: A Dynamic Method for Detecting Protein Complexes From TAP-Aware Weighted PPI Network

  2020cites this paper
• A comprehensive review and evaluation of computational methods for identifying protein complexes from protein-protein interaction networks

  2019cites this paper
• Performance evaluation measures for protein complex prediction.

  2019cites this paper
• Integrating network topology, gene expression data and GO annotation information for protein complex prediction

  2019cites this paper
• Integrating data and knowledge to identify functional modules of genes: a multilayer approach

  2019cites this paper
• Detecting protein complexes based on a combination of topological and biological properties in protein-protein interaction network

  2019cites this paper
• Protein Complexes Detection Based on Semi-Supervised Network Embedding Model

  2019cites this paper
• The impact of protein interaction networks' characteristics on computational complex detection methods.

  2018cites this paper
• Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities

  2018cites this paper
• Improvement of cancer subtype prediction by incorporating transcriptome expression data and heterogeneous biological networks

  2018cites this paper
• K-means Clustering: An Efficient Algorithm for Protein Complex Detection

  2018cites this paper
• Detecting protein complexes based on a combination of topological and biological properties in protein-protein interaction network

  2017influential citation
• Global profiling of protein complexes: current approaches and their perspective in biomedical research

  2016cites this paper
• Constructing an integrated gene similarity network for the identification of disease genes

  2016cites this paper