A feature extraction framework for discovering pan-cancer driver genes based on multi-omics data.

The protein-protein interaction (PPI) networks can be regarded as powerful platforms to elucidate the principle and mechanism of cellular organization. Uncovering protein complexes from PPI networks will lead to a better understanding of the science of biological function in cellular systems. In recent decades, numerous computational algorithms have been developed to identify protein complexes. However, the majority of them primarily concern the topological structure of PPI networks and lack of the consideration for the native organized structure among protein complexes. The PPI networks generated by high-throughput technology include a fraction of false protein interactions which make it difficult to identify protein complexes efficiently. To tackle these challenges, we propose a novel semi-supervised protein complex detection model based on non-negative matrix tri-factorization, which not only considers topological structure of a PPI network but also makes full use of available high quality known protein pairs with must-link constraints. We propose non-overlapping (NSSNMTF) and overlapping (OSSNMTF) protein complex detection algorithms to identify the significant protein complexes with clear module structures from PPI networks. In addition, the proposed two protein complex detection algorithms outperform a diverse range of state-of-the-art protein complex identification algorithms on both synthetic networks and human related PPI networks.

Advances in proteomic technologies combined with sophisticated computing and modeling methods have generated an unprecedented amount of high-throughput data for system-scale analysis. As a result, the study of protein-protein interaction (PPI) networks has garnered much attention in recent years. One of the most fundamental problems in studying PPI networks is to understand how their architecture originated and evolved to their current state. By investigating how proteins of different ages are connected in the yeast PPI networks, one can deduce their expansion procedure in evolution and how the ancient primitive network expanded and evolved. Studies have shown that proteins are often connected to other proteins of a similar age, suggesting a high degree of age preference between interacting proteins. Though several theories have been proposed to explain this phenomenon, none of them considered protein-clusters as a contributing factor. Here we first investigate the age-dependency of the proteins from the perspective of network motifs. Our analysis confirms that proteins of the same age groups tend to form interacting network motifs; furthermore, those proteins within motifs tend to be within protein complexes and the interactions among them largely contribute to the observed age preference in the yeast PPI networks. In light of these results, we describe a new modeling approach, based on "network motifs", whereby topologically connected protein clusters in the network are treated as single evolutionary units. Instead of modeling single proteins, our approach models the connections and evolutionary relationships of multiple related protein clusters or "network motifs" that are collectively integrated into an existing PPI network. Through simulation studies, we found that the "network motif" modeling approach can capture yeast PPI network properties better than if individual proteins were considered to be the simplest evolutionary units. Our approach provides a fresh perspective on modeling the evolution of yeast PPI networks, specifically that PPI networks may have a much higher age-dependency of interaction density than had been previously envisioned.

BackgroundAccurate determination of protein complexes has become a key task of system biology for revealing cellular organization and function. Up to now, the protein complex prediction methods are mostly focused on static protein protein interaction (PPI) networks. However, cellular systems are highly dynamic and responsive to cues from the environment. The shift from static PPI networks to dynamic PPI networks is essential to accurately predict protein complex.ResultsThe gene expression data contains crucial dynamic information of proteins and PPIs, along with high-throughput experimental PPI data, are valuable for protein complex prediction. Firstly, we exploit gene expression data to calculate the active time point and the active probability of each protein and PPI. The dynamic active information is integrated into high-throughput PPI data to construct dynamic PPI networks. Secondly, a novel method for predicting protein complexes from the dynamic PPI networks is proposed based on core-attachment structural feature. Our method can effectively exploit not only the dynamic active information but also the topology structure information based on the dynamic PPI networks.ConclusionsWe construct four dynamic PPI networks, and accurately predict many well-characterized protein complexes. The experimental results show that (i) the dynamic active information significantly improves the performance of protein complex prediction; (ii) our method can effectively make good use of both the dynamic active information and the topology structure information of dynamic PPI networks to achieve state-of-the-art protein complex prediction capabilities.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1101-y) contains supplementary material, which is available to authorized users.

Biological functions of a cell are typically carried out through protein complexes. The detection of protein complexes is therefore of great significance for understanding the cellular organizations and protein functions. In the past decades, many computational methods have been proposed to detect protein complexes. However, most of the existing methods just search the local topological information to mine dense subgraphs as protein complexes, ignoring the global topological information. To tackle this issue, we propose the DPCMNE method to detect protein complexes via multi-level network embedding. It can preserve both the local and global topological information of biological networks. First, DPCMNE employs a hierarchical compressing strategy to recursively compress the input protein-protein interaction (PPI) network into multi-level smaller PPI networks. Then, a network embedding method is applied on these smaller PPI networks to learn protein embeddings of different levels of granularity. The embeddings learned from all the compressed PPI networks are concatenated to represent the final protein embeddings of the original input PPI network. Finally, a core-attachment based strategy is adopted to detect protein complexes in the weighted PPI network constructed by the pairwise similarity of protein embeddings. To assess the efficiency of our proposed method, DPCMNE is compared with other eight clustering algorithms on two yeast datasets. The experimental results show that the performance of DPCMNE outperforms those state-of-the-art complex detection methods in terms of F1 and F1+Acc. Furthermore, the results of functional enrichment analysis indicate that protein complexes detected by DPCMNE are more biologically significant in terms of P-score.

A network of modular protein complexes inside a cell coordinates many biological processes and is known as protein-protein interaction (PPI) network. A PPI network can be modeled as a graph, in which edges represent interactions among proteins, and sub graphs represent protein complexes. Previous methods for protein complex mining from PPI network mainly focused on few topological features like density and degree statistics based on the assumption that proteins inside a complex are highly interactive with each other and thus form dense subgraphs. While this assumption is true for some complexes, it doesn’t hold for many others. The important biological information within the protein amino acid sequences, which estimates the interacting property among two proteins for performing a specific biological function is not considered in most of the previous studies. There is a need for algorithms that consider both topological and biological features for correctly identifying protein complexes having varying topological structures and biological patterns inside a PPI network. In this paper, we present an algorithm for detecting protein complexes from interaction graphs. By using graph topological patterns and biological properties as features, we model each complex sub graph by decision tree learners. We use a training set of known complexes to construct decision trees in depth first and BEST FIRST manner using divide and conquer strategy. Splitting criterion, such as information and Gini gain are used in tree expansion process. Training set is divided into subsets and each subset is represented as a branch of tree. Pruning techniques are used to reduce the size of tree. We applied our method to protein interaction data in yeast on two benchmark data sets, i.e., MIPS and CYC2008. According to our results, decision trees achieved a considerable improvement over clique-based algorithms in terms of its ability to recover known complexes by using integrated biological and topological properties.

Identifying functional modules in protein-protein interaction (PPI) networks elucidates cellular organization and mechanism. Various methods have been proposed to identify the functional modules in PPI networks, but most of these methods do not consider the noisy links in PPI networks. They achieve a competitive performance on the PPI networks without noisy links, but the performance of these methods considerably deteriorates in the noisy PPI networks. Furthermore, the noisy links are inevitable in the PPI networks. In this paper, we propose a novel link-driven label propagation algorithm (LLPA) to identify functional modules in PPI networks. The LLPA first find link clusters in PPI networks, and then the functional modules are identified from the link clusters. Two strategies aimed to ensure the robustness of LLPA are proposed. One strategy involves the proposed LLPA updating the link labels in accordance with the designed weight of the link, which can reduce the incidence of noisy links. The other strategy involves the filtration of some noisy labels from the link clusters to further reduce the influence of noisy links. The performance evaluation on three real PPI networks shows that LLPA outperforms other eight state-of-the-art detection algorithms in terms of accuracy and robustness.

Protein complexes play a critical role in many biological processes. Identifying the component proteins in a protein complex is an important step in understanding the complex as well as the related biological activities. This paper addresses the problem of predicting protein complexes from the protein-protein interaction (PPI) network of one species using a computational approach. Most of the previous methods rely on the assumption that proteins within the same complex would have relatively more interactions. This translates into dense subgraphs in the PPI network. However, the existing software tools have limited success. Recently, Gavin et al. (2006) provided a detailed study on the organization of protein complexes and suggested that a complex consists of two parts: a core and an attachment. Based on this core-attachment concept, we developed a novel approach to identify complexes from the PPI network by identifying their cores and attachments separately. We evaluated the effectiveness of our proposed approach using three different datasets and compared the quality of our predicted complexes with three existing tools. The evaluation results show that we can predict many more complexes and with higher accuracy than these tools with an improvement of over 30%. To verify the cores we identified in each complex, we compared our cores with the mediators produced by Andreopoulos et al. (2007), which were claimed to be the cores, based on the benchmark result produced by Gavin et al. (2006). We found that the cores we produced are of much higher quality ranging from 10- to 30-fold more correctly predicted cores and with better accuracy. (http://alse.cs.hku.hk/complexes/).

Signal flow direction is one of the most important features of the protein-protein interactions in signaling networks. However, almost all the outcomes of current high-throughout techniques for protein-protein interactions mapping are usually supposed to be non-directional. Based on the pairwise interaction domains, here we defined a novel parameter protein interaction directional score and then used it to predict the direction of signal flow between proteins in proteome-wide signaling networks. Using 5-fold cross-validation, our approach obtained a satisfied performance with the accuracy 89.79%, coverage 48.08%, and error ratio 16.91%. As an application, we established an integrated human directional protein interaction network, including 2,237 proteins and 5,530 interactions, and inferred a large amount of novel signaling pathways. Directional protein interaction network was strongly supported by the known signaling pathways literature (with the 87.5% accuracy) and further analyses on the biological annotation, subcellular localization, and network topology property. Thus, this study provided an effective method to define the upstream/downstream relations of interacting protein pairs and a powerful tool to unravel the unknown signaling pathways.

Protein complexes are aggregates of protein molecules that play important roles in biological processes. Detecting protein complexes from protein-protein interaction (PPI) networks is one of the most challenging problems in computational biology, and many computational methods have been developed to solve this problem. Generally, these methods yield high false positive rates. In this article, a semantic similarity measure between proteins, based on Gene Ontology (GO) structure, is applied to weigh PPI networks. Consequently, one of the well-known methods, COACH, has been improved to be compatible with weighted PPI networks for protein complex detection. The new method, WCOACH, is compared to the COACH, ClusterOne, IPCA, CORE, OH-PIN, HC-PIN and MCODE methods on several PPI networks such as DIP, Krogan, Gavin 2002 and MIPS. WCOACH can be applied as a fast and high-performance algorithm to predict protein complexes in weighted PPI networks. All data and programs are freely available at http://bioinformatics.aut.ac.ir/wcoach.

Protein complex detection is an important issue in the field of system biology, which is crucial to understanding the cellular organization and inferring protein functions. In recent years, various computational methods have been proposed to detect protein complexes from protein-protein interaction (PPI) networks. Unfortunately, most of these methods only use the local information of PPI networks and treat protein complexes as dense subgraphs, ignoring the global topology information of PPI networks. To address these limitations, we propose a new method, named OPCMTS, to detect overlapping protein complexes by simultaneously considering the local topological information and global topological information of PPI network. First, a local similarity matrix is constructed via calculating the Jaccard coefficients between proteins in the original PPI network. Then, we adopt a hierarchical compressing strategy to get multiple levels of gradually compressed smaller networks from the original PPI network and apply a network embedding model to learn protein embeddings from the compressed networks at multiple levels. The protein embeddings from these networks are concatenated and a dimensionality reduction strategy is adopted to remove the redundancy of the concatenated embeddings to generate the final embeddings. Further, a global similarity matrix is constructed by calculating the cosine similarity of the final embeddings. Finally, a core-attachment strategy is used to detect overlapping protein complexes based on the local and global similarity matrices. The experimental results prove that the proposed OPCMTS method outperforms other five state-of-the-art methods in terms of F-measure on two yeast datasets.

BackgroundUnderstanding protein complexes is important for understanding the science of cellular organization and function. Many computational methods have been developed to identify protein complexes from experimentally obtained protein-protein interaction (PPI) networks. However, interaction information obtained experimentally can be unreliable and incomplete. Reconstructing these PPI networks with PPI evidences from other sources can improve protein complex identification.ResultsWe combined PPI information from 6 different sources and obtained a reconstructed PPI network for yeast through machine learning. Some popular protein complex identification methods were then applied to detect yeast protein complexes using the new PPI networks. Our evaluation indicates that protein complex identification algorithms using the reconstructed PPI network significantly outperform ones on experimentally verified PPI networks.ConclusionsWe conclude that incorporating PPI information from other sources can improve the effectiveness of protein complex identification.

In network and systems medicine, active module identification methods (AMIMs) are widely used for discovering candidate molecular disease mechanisms. To this end, AMIMs combine network analysis algorithms with molecular profiling data, most commonly, by projecting gene expression data onto generic protein-protein interaction (PPI) networks. Although active module identification has led to various novel insights into complex diseases, there is increasing awareness in the field that the combination of gene expression data and PPI network is problematic because up-to-date PPI networks have a very small diameter and are subject to both technical and literature bias. In this paper, we report the results of an extensive study where we analyzed for the first time whether widely used AMIMs really benefit from using PPI networks. Our results clearly show that, except for the recently proposed AMIM DOMINO, the tested AMIMs do not produce biologically more meaningful candidate disease modules on widely used PPI networks than on random networks with the same node degrees. AMIMs hence mainly learn from the node degrees and mostly fail to exploit the biological knowledge encoded in the edges of the PPI networks. This has far-reaching consequences for the field of active module identification. In particular, we suggest that novel algorithms are needed which overcome the degree bias of most existing AMIMs and/or work with customized, context-specific networks instead of generic PPI networks.

Protein–protein interaction (PPI) data derived from biological experiments include many false-positive interactions which are treated equally as other real physical interactions, thereby complicating the detection of real protein complexes from protein–protein interaction (PPI) networks. In this paper, a new weighting method, named as cwMINE (combined weight of module identification in networks), for detecting protein complexes efficiently in protein interaction networks is presented. cwMINE has a good combination between network topology and biological feature, which can solve false positives efficiently of PPI networks and make discovered protein complexes higher quality. In addition, a new expanding rule during the detection process, namely, expanding coefficient, is developed to filter edges with lower weights. The proposed method is compared with several state- of-the-art algorithms in three yeast PPI networks with two benchmark data sets. The experimental results show that the proposed method outperforms the other algorithms in most datasets in terms of the evaluation metrics. We further validate the effectiveness of our method on a human PPI network constructed from the HPRD dataset to identify important disease-related functional modules and provided valuable indications for disease treatment.

Graph clustering algorithms are widely used in the analysis of biological networks. Extracting functional modules in protein-protein interaction (PPI) networks is one such use. Most clustering algorithms whose focuses are on finding functional modules try either to find a clique like sub networks or to grow clusters starting from vertices with high degrees as seeds. These algorithms do not make any difference between a biological network and any other networks. In the current research, we present a new procedure to find functional modules in PPI networks. Our main idea is to model a biological concept and to use this concept for finding good functional modules in PPI networks. In order to evaluate the quality of the obtained clusters, we compared the results of our algorithm with those of some other widely used clustering algorithms on three high throughput PPI networks from Sacchromyces Cerevisiae, Homo sapiens and Caenorhabditis elegans as well as on some tissue specific networks. Gene Ontology (GO) analyses were used to compare the results of different algorithms. Each algorithm's result was then compared with GO-term derived functional modules. We also analyzed the effect of using tissue specific networks on the quality of the obtained clusters. The experimental results indicate that the new algorithm outperforms most of the others, and this improvement is more significant when tissue specific networks are used.

Protein-protein interaction (PPI) networks provide insights into understanding of biological processes, function and the underlying complex evolutionary mechanisms of the cell. Modeling PPI network is an important and fundamental problem in system biology, where it is still of major concern to find a better fitting model that requires less structural assumptions and is more robust against the large fraction of noisy PPIs. In this paper, we propose a new approach called t-logistic semantic embedding (t-LSE) to model PPI networks. t-LSE tries to adaptively learn a metric embedding under the simple geometric assumption of PPI networks, and a non-convex cost function was adopted to deal with the noise in PPI networks. The experimental results show the superiority of the fit of t-LSE over other network models to PPI data. Furthermore, the robust loss function adopted here leads to big improvements for dealing with the noise in PPI network. The proposed model could thus facilitate further graph-based studies of PPIs and may help infer the hidden underlying biological knowledge. The Matlab code implementing the proposed method is freely available from the web site: http://home.ustc.edu.cn/~yzh33108/PPIModel.htm.