Protein-protein Interaction Graph Research Articles

PPICT: an integrated deep neural network for predicting inter-protein PTM cross-talk.

Post-translational modifications (PTMs) fine-tune various signaling pathways not only by the modification of a single residue, but also by the interplay of different modifications on residue pairs within or between proteins, defined as PTM cross-talk. As a challenging question, less attention has been given to PTM dynamics underlying cross-talk residue pairs and structural information underlying protein-protein interaction (PPI) graph, limiting the progress in this PTM functional research. Here we propose a novel integrated deep neural network PPICT (Predictor for PTM Inter-protein Cross-Talk), which predicts PTM cross-talk by combining protein sequence-structure-dynamics information and structural information for PPI graph. We find that cross-talk events preferentially occur among residues with high co-evolution and high potential in allosteric regulation. To make full use of the complex associations between protein evolutionary and biophysical features, and protein pair features, a heterogeneous feature combination net is introduced in the final prediction of PPICT. The comprehensive test results show that the proposed PPICT method significantly improves the prediction performance with an AUC value of 0.869, outperforming the existing state-of-the-art methods. Additionally, the PPICT method can capture the potential PTM cross-talks involved in the functional regulatory PTMs on modifying enzymes and their catalyzed PTM substrates. Therefore, PPICT represents an effective tool for identifying PTM cross-talk between proteins at the proteome level and highlights the hints for cross-talk between different signal pathways introduced by PTMs.

Graph analysis and clustering of proteins linked with COVID-19

A remarkable number of scientific initiatives are in practice to encounter the new coronavirus epidemic (COVID-19). One of the biggest challenges faced by the COVID-19 researchers in the therapeutic field is the knowledge about the biological functions in disease-human interacting proteins. The detection of COVID-19 protein complexes, a group of proteins that possess the same biological functions, helps in better understanding of the biological processes in our body. The main contribution of this work is to cluster proteins that perform the same biological functions to increase the knowledge about the COVID-19 disease-human interacting proteins. The authors investigated proteins linked with COVID-19 disease by creating a disease-human protein-protein interaction graph. Topological means of graph analysis and graph clustering have been employed to group proteins that possess the same biological functions. These clusters will be the protein complexes that work together to carry out a specific biological function in a human cell. Moreover, through the cluster analysis, we can uncover previously unknown COVID-19 disease-human protein links that are beneficial for promising knowledge discovery. Also, the authors evaluated how the Markov Cluster algorithm, a graph-based algorithm finds interesting patterns of similar features from COVID-19 disease-human protein-protein interaction graph. The Markov Cluster algorithm results in six statistically significant protein clusters, including cluster (A): keratinization (3.50E-71), (B): regulation of cellular process (6.62E-05), (C): regulation of cell cycle (1.31E-27), (D): mitotic cell cycle (1.66E-06), (E): regulation of phosphoprotein phosphatase activity (1.15E-09), and (G): G2/M transition of mitotic cell cycle (3.03E-07).

DeepGCNs: Making GCNs Go as Deep as CNNs.

Convolutional neural networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, activity understanding, to name just a few. One key enabling factor for their great performance has been the ability to train very deep networks. Despite their huge success in many tasks, CNNs do not work well with non-euclidean data, which is prevalent in many real-world applications. Graph Convolutional Networks (GCNs) offer an alternative that allows for non-Eucledian data input to a neural network. While GCNs already achieve encouraging results, they are currently limited to architectures with a relatively small number of layers, primarily due to vanishing gradients during training. This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs. We show the benefit of using deep GCNs (with as many as 112 layers) experimentally across various datasets and tasks. Specifically, we achieve very promising performance in part segmentation and semantic segmentation on point clouds and in node classification of protein functions across biological protein-protein interaction (PPI) graphs. We believe that the insights in this work will open avenues for future research on GCNs and their application to further tasks not explored in this paper. The source code for this work is available at https://github.com/lightaime/deep_gcns_torch and https://github.com/lightaime/deep_gcns for PyTorch and TensorFlow implementations respectively.

Classification of Cancer Types Using Graph Convolutional Neural Networks.

Cancer has been a leading cause of death in the United States with significant health care costs. Accurate prediction of cancers at an early stage and understanding the genomic mechanisms that drive cancer development are vital to the improvement of treatment outcomes and survival rates, thus resulting in significant social and economic impacts. Attempts have been made to classify cancer types with machine learning techniques during the past two decades and deep learning approaches more recently. In this paper, we established four models with graph convolutional neural network (GCNN) that use unstructured gene expressions as inputs to classify different tumor and non-tumor samples into their designated 33 cancer types or as normal. Four GCNN models based on a co-expression graph, co-expression+singleton graph, protein-protein interaction (PPI) graph, and PPI+singleton graph have been designed and implemented. They were trained and tested on combined 10,340 cancer samples and 731 normal tissue samples from The Cancer Genome Atlas (TCGA) dataset. The established GCNN models achieved excellent prediction accuracies (89.9-94.7%) among 34 classes (33 cancer types and a normal group). In silico gene-perturbation experiments were performed on four models based on co-expression graph, co-expression+singleton, PPI graph, and PPI+singleton graphs. The co-expression GCNN model was further interpreted to identify a total of 428 markers genes that drive the classification of 33 cancer types and normal. The concordance of differential expressions of these markers between the represented cancer type and others are confirmed. Successful classification of cancer types and a normal group regardless of normal tissues' origin suggested that the identified markers are cancer-specific rather than tissue-specific. Novel GCNN models have been established to predict cancer types or normal tissue based on gene expression profiles. We demonstrated the results from the TCGA dataset that these models can produce accurate classification (above 94%), using cancer-specific markers genes. The models and the source codes are publicly available and can be readily adapted to the diagnosis of cancer and other diseases by the data-driven modeling research community.

Large-scale identification of human protein function using topological features of interaction network.

The annotation of protein function is a vital step to elucidate the essence of life at a molecular level, and it is also meritorious in biomedical and pharmaceutical industry. Developments of sequencing technology result in constant expansion of the gap between the number of the known sequences and their functions. Therefore, it is indispensable to develop a computational method for the annotation of protein function. Herein, a novel method is proposed to identify protein function based on the weighted human protein-protein interaction network and graph theory. The network topology features with local and global information are presented to characterise proteins. The minimum redundancy maximum relevance algorithm is used to select 227 optimized feature subsets and support vector machine technique is utilized to build the prediction models. The performance of current method is assessed through 10-fold cross-validation test, and the range of accuracies is from 67.63% to 100%. Comparing with other annotation methods, the proposed way possesses a 50% improvement in the predictive accuracy. Generally, such network topology features provide insights into the relationship between protein functions and network architectures. The source code of Matlab is freely available on request from the authors.

SCODE: A Cytoscape app for supervised complex detection in protein-protein interaction graphs

Protein complexes are groups of interacting proteins unified by a common biological function. Identifying complexes amid a network of thousands of interacting proteins poses a difficult computational challenge. Traditional approaches to this problem rely on clique-like topography in order to identify complexes. Supervised learning is an alternative approach that leverages real-valued data in order to extract the features of protein complexes and identify candidates that do not conform to traditional, dense clique structures. SCODE (Supervised Complex Detection), an application for the Cytoscape App Store, implements a supervised learning algorithm for the detection of protein complexes in protein-protein interaction networks.

Predicting overlapping protein complexes from weighted protein interaction graphs by gradually expanding dense neighborhoods.

Proteins are vital biological molecules driving many fundamental cellular processes. They rarely act alone, but form interacting groups called protein complexes. The study of protein complexes is a key goal in systems biology. Recently, large protein-protein interaction (PPI) datasets have been published and a plethora of computational methods that provide new ideas for the prediction of protein complexes have been implemented. However, most of the methods suffer from two major limitations: First, they do not account for proteins participating in multiple functions and second, they are unable to handle weighted PPI graphs. Moreover, the problem remains open as existing algorithms and tools are insufficient in terms of predictive metrics. In the present paper, we propose gradually expanding neighborhoods with adjustment (GENA), a new algorithm that gradually expands neighborhoods in a graph starting from highly informative "seed" nodes. GENA considers proteins as multifunctional molecules allowing them to participate in more than one protein complex. In addition, GENA accepts weighted PPI graphs by using a weighted evaluation function for each cluster. In experiments with datasets from Saccharomyces cerevisiae and human, GENA outperformed Markov clustering, restricted neighborhood search and clustering with overlapping neighborhood expansion, three state-of-the-art methods for computationally predicting protein complexes. Seven PPI networks and seven evaluation datasets were used in total. GENA outperformed existing methods in 16 out of 18 experiments achieving an average improvement of 5.5% when the maximum matching ratio metric was used. Our method was able to discover functionally homogeneous protein clusters and uncover important network modules in a Parkinson expression dataset. When used on the human networks, around 47% of the detected clusters were enriched in gene ontology (GO) terms with depth higher than five in the GO hierarchy. In the present manuscript, we introduce a new method for the computational prediction of protein complexes by making the realistic assumption that proteins participate in multiple protein complexes and cellular functions. Our method can detect accurate and functionally homogeneous clusters.

Predicting protein complexes from weighted protein-protein interaction graphs with a novel unsupervised methodology: Evolutionary enhanced Markov clustering.

Proteins are considered to be the most important individual components of biological systems and they combine to form physical protein complexes which are responsible for certain molecular functions. Despite the large availability of protein-protein interaction (PPI) information, not much information is available about protein complexes. Experimental methods are limited in terms of time, efficiency, cost and performance constraints. Existing computational methods have provided encouraging preliminary results, but they phase certain disadvantages as they require parameter tuning, some of them cannot handle weighted PPI data and others do not allow a protein to participate in more than one protein complex. In the present paper, we propose a new fully unsupervised methodology for predicting protein complexes from weighted PPI graphs. The proposed methodology is called evolutionary enhanced Markov clustering (EE-MC) and it is a hybrid combination of an adaptive evolutionary algorithm and a state-of-the-art clustering algorithm named enhanced Markov clustering. EE-MC was compared with state-of-the-art methodologies when applied to datasets from the human and the yeast Saccharomyces cerevisiae organisms. Using public available datasets, EE-MC outperformed existing methodologies (in some datasets the separation metric was increased by 10-20%). Moreover, when applied to new human datasets its performance was encouraging in the prediction of protein complexes which consist of proteins with high functional similarity. In specific, 5737 protein complexes were predicted and 72.58% of them are enriched for at least one gene ontology (GO) function term. EE-MC is by design able to overcome intrinsic limitations of existing methodologies such as their inability to handle weighted PPI networks, their constraint to assign every protein in exactly one cluster and the difficulties they face concerning the parameter tuning. This fact was experimentally validated and moreover, new potentially true human protein complexes were suggested as candidates for further validation using experimental techniques.

Identifying Protein Complexes by Reducing Noise in Interaction Networks

Identifying protein complexes in protein-protein interaction (PPI) networks is a fundamental problem in computational biology. High-throughput experimental techniques have generated large, experimentally detected PPI datasets. These interactions represent a rich source of data that can be used to detect protein complexes; however, such interactions contain much noise. Therefore, these interactions should be validated before they could be applied to detect protein complexes. We propose an efficient measure to estimate PPI reliability (PPIR) and reduce noise level in two different yeast PPI networks. PPIRU, which is a new protein complex clustering algorithm based on PPIR, is introduced. Experiments demonstrated that interactome graph weighting methods incorporating PPIR clearly improve the results of several clustering algorithms. PPIR also outperforms other PPI graph weighting schemes in most cases. We compare PPIRU with several efficient, existing clustering algorithms and reveal that the accuracy values of PPIRU clusters are much higher than those of other algorithms.

Reverse top-k search using random walk with restart

With the increasing popularity of social networks, large volumes of graph data are becoming available. Large graphs are also derived by structure extraction from relational, text, or scientific data (e.g., relational tuple networks, citation graphs, ontology networks, protein-protein interaction graphs). Node-to-node proximity is the key building block for many graph-based applications that search or analyze the data. Among various proximity measures, random walk with restart (RWR) is widely adopted because of its ability to consider the global structure of the whole network. Although RWR-based similarity search has been well studied before, there is no prior work on reverse top- k proximity search in graphs based on RWR. We discuss the applicability of this query and show that its direct evaluation using existing methods on RWR-based similarity search has very high computational and storage demands. To address this issue, we propose an indexing technique, paired with an on-line reverse top- k search algorithm. Our experiments show that our technique is efficient and has manageable storage requirements even when applied on very large graphs.

Noise reduction in protein-protein interaction graphs by the implementation of a novel weighting scheme

BackgroundRecent technological advances applied to biology such as yeast-two-hybrid, phage display and mass spectrometry have enabled us to create a detailed map of protein interaction networks. These interaction networks represent a rich, yet noisy, source of data that could be used to extract meaningful information, such as protein complexes. Several interaction network weighting schemes have been proposed so far in the literature in order to eliminate the noise inherent in interactome data. In this paper, we propose a novel weighting scheme and apply it to the S. cerevisiae interactome. Complex prediction rates are improved by up to 39%, depending on the clustering algorithm applied.ResultsWe adopt a two step procedure. During the first step, by applying both novel and well established protein-protein interaction (PPI) weighting methods, weights are introduced to the original interactome graph based on the confidence level that a given interaction is a true-positive one. The second step applies clustering using established algorithms in the field of graph theory, as well as two variations of Spectral clustering. The clustered interactome networks are also cross-validated against the confirmed protein complexes present in the MIPS database.ConclusionsThe results of our experimental work demonstrate that interactome graph weighting methods clearly improve the clustering results of several clustering algorithms. Moreover, our proposed weighting scheme outperforms other approaches of PPI graph weighting.

IDENTIFICATION OF FUNCTIONAL MODULES IN A PPI NETWORK BY BOUNDED DIAMETER CLUSTERING

Dense subgraphs of Protein-Protein Interaction (PPI) graphs are assumed to be potential functional modules and play an important role in inferring the functional behavior of proteins. Increasing amount of available PPI data implies a fast, accurate approach of biological complex identification. Therefore, there are different models and algorithms in identifying functional modules. This paper describes a new graph theoretic clustering algorithm that detects densely connected regions in a large PPI graph. The method is based on finding bounded diameter subgraphs around a seed node. The algorithm has the advantage of being very simple and efficient when compared with other graph clustering methods. This algorithm is tested on the yeast PPI graph and the results are compared with MCL, Core-Attachment, and MCODE algorithms.

An in silico method for detecting overlapping functional modules from composite biological networks

BackgroundThe ever-increasing flow of gene expression and protein-protein interaction (PPI) data has assisted in understanding the dynamics of the cell. The detection of functional modules is the first step in deciphering the apparent modularity of biological networks. However, most network-partitioning algorithms consider only the topological aspects and ignore the underlying functional relationships.ResultsIn the current study we integrate proteomics and microarray data of yeast, in the form of a weighted PPI graph. We partition the enriched PPI network with the novel DetMod algorithm and we identify 335 modules. One of the main advantages of DetMod is that it manages to capture the inter-module cross-talk by allowing a controlled degree of overlap among the detected modules. The obtained modules are densely connected in terms of protein interactions, while their members share up to a high degree similar biological process GO terms.Moreover, known protein complexes are largely incorporated in the assessed modules. Finally, we display the prevalence of our method against modules resulting from other computational approaches.ConclusionThe successful integration of heterogeneous data and the concept of the proposed algorithm provide confident functional modules. We also proved that our approach is superior to methods restricted to PPI data only.

PATIKAmad: Putting microarray data into pathway context

High-throughput experiments, most significantly DNA microarrays, provide us with system-scale profiles. Connecting these data with existing biological networks poses a formidable challenge to uncover facts about a cell's proteome. Studies and tools with this purpose are limited to networks with simple structure, such as protein-protein interaction graphs, or do not go much beyond than simply displaying values on the network. We have built a microarray data analysis tool, named PATIKAmad, which can be used to associate microarray data with the pathway models in mechanistic detail, and provides facilities for visualization, clustering, querying, and navigation of biological graphs related with loaded microarray experiments. PATIKAmad is freely available to noncommercial users as a new module of PATIKAweb at http://web.patika.org.

Growing functional modules from a seed protein via integration of protein interaction and gene expression data.

BackgroundNowadays modern biology aims at unravelling the strands of complex biological structures such as the protein-protein interaction (PPI) networks. A key concept in the organization of PPI networks is the existence of dense subnetworks (functional modules) in them. In recent approaches clustering algorithms were applied at these networks and the resulting subnetworks were evaluated by estimating the coverage of well-established protein complexes they contained. However, most of these algorithms elaborate on an unweighted graph structure which in turn fails to elevate those interactions that would contribute to the construction of biologically more valid and coherent functional modules.ResultsIn the current study, we present a method that corroborates the integration of protein interaction and microarray data via the discovery of biologically valid functional modules. Initially the gene expression information is overlaid as weights onto the PPI network and the enriched PPI graph allows us to exploit its topological aspects, while simultaneously highlights enhanced functional association in specific pairs of proteins. Then we present an algorithm that unveils the functional modules of the weighted graph by expanding a kernel protein set, which originates from a given 'seed' protein used as starting-point.ConclusionThe integrated data and the concept of our approach provide reliable functional modules. We give proofs based on yeast data that our method manages to give accurate results in terms both of structural coherency, as well as functional consistency.

A parallel edge-betweenness clustering tool for Protein-Protein Interaction networks

The increasing availability of protein-protein interaction graphs (PPI) requires new efficient tools capable of extracting valuable biological knowledge from these networks. Among the wide range of clustering algorithms, Girvan and Newman's edge betweenness algorithm showed remarkable performances in discovering clustering structures in several real-world networks. Unfortunately, their algorithm suffers from high computational cost and it is impractical for inputs of the size of large PPI networks. Here we report on a novel parallel implementation of Girvan and Newman's clustering algorithm that achieves almost linear speed-up for up to 32 processors. The tool is available in the public domain from the authors' website.

Identifying Regulatory Subnetworks for a Set of Genes

High throughput genomic/proteomic strategies, such as microarray studies, drug screens, and genetic screens, often produce a list of genes that are believed to be important for one or more reasons. Unfortunately it is often difficult to discern meaningful biological relationships from such lists. This study presents a new bioinformatic approach that can be used to identify regulatory subnetworks for lists of significant genes or proteins. We demonstrate the utility of this approach using an interaction network for yeast constructed from BIND, TRANSFAC, SCPD, and chromatin immunoprecipitation (ChIP)-Chip data bases and lists of genes from well known metabolic pathways or differential expression experiments. The approach accurately rediscovers known regulatory elements of the heat shock response as well as the gluconeogenesis, galactose, glycolysis, and glucose fermentation pathways in yeast. We also find evidence supporting a previous conjecture that approximately half of the enzymes in a metabolic pathway are transcriptionally co-regulated. Finally we demonstrate a previously unknown connection between GAL80 and the diauxic shift in yeast.

On the structure of protein-protein interaction networks.

We present a simple model for the underlying structure of protein-protein pairwise interaction graphs that is based on the way in which proteins attach to each other in experiments such as yeast two-hybrid assays. We show that data on the interactions of human proteins lend support to this model. The frequency of the number of connections per protein under this model does not follow a power law, in contrast to the reported behaviour of data from large-scale yeast two-hybrid screens of yeast protein-protein interactions. Sampling sub-graphs from the underlying graphs generated with our model, in a way analogous to the sampling performed in large-scale yeast two-hybrid searches, gives degree distributions that differ subtly from the power law and that fit the observed data better than the power law itself. Our results show that the observation of approximate power law behaviour in a sampled sub-graph does not imply that the underlying graph follows a power law.