Protein complex detection algorithm based on multiple topological characteristics in PPI networks

Wang, Jie; Liang, Jiye; Zheng, Wei; Zhao, Xin; Mu, Junfang

doi:10.1016/j.ins.2019.03.015

Cited by 16 publications

(14 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, a greedy algorithm expands the seed node to make the sub-graphs obtain higher cohesiveness until no seed node forms a protein complex. Similar methods include SE-DMTG [ 9 ] and HGCA [ 10 ], based on point expansion methods to predict protein complexes from protein interaction networks. Xu et al proposed the CPredictor2.0 [ 11 ] algorithm, which first grouped proteins with similar functions, clustered each group using the Markov clustering algorithm, and merged overlapping protein complexes.…”

Section: Introductionmentioning

confidence: 99%

A supervised protein complex prediction method with network representation learning and gene ontology knowledge

et al. 2022

View full text Add to dashboard Cite

Background Protein complexes are essential for biologists to understand cell organization and function effectively. In recent years, predicting complexes from protein–protein interaction (PPI) networks through computational methods is one of the current research hotspots. Many methods for protein complex prediction have been proposed. However, how to use the information of known protein complexes is still a fundamental problem that needs to be solved urgently in predicting protein complexes. Results To solve these problems, we propose a supervised learning method based on network representation learning and gene ontology knowledge, which can fully use the information of known protein complexes to predict new protein complexes. This method first constructs a weighted PPI network based on gene ontology knowledge and topology information, reducing the network's noise problem. On this basis, the topological information of known protein complexes is extracted as features, and the supervised learning model SVCC is obtained according to the feature training. At the same time, the SVCC model is used to predict candidate protein complexes from the protein interaction network. Then, we use the network representation learning method to obtain the vector representation of the protein complex and train the random forest model. Finally, we use the random forest model to classify the candidate protein complexes to obtain the final predicted protein complexes. We evaluate the performance of the proposed method on two publicly PPI data sets. Conclusions Experimental results show that our method can effectively improve the performance of protein complex recognition compared with existing methods. In addition, we also analyze the biological significance of protein complexes predicted by our method and other methods. The results show that the protein complexes predicted by our method have high biological significance.

show abstract

Section: Introductionmentioning

confidence: 99%

A supervised protein complex prediction method with network representation learning and gene ontology knowledge

et al. 2022

View full text Add to dashboard Cite

show abstract

“…IG [ 16 ] designed a pairwise interaction detection method taking advantage of information gain, and then constructed an SNP interaction network, from which MCODE was applied to find modules that are regarded as high-order SNP interactions. Wang et al [ 17 ] proposed a heuristic module detection method for searching protein complexes based on multiple topological features, which evaluates the weight of a node through clustering coefficient and node degree.…”

Section: Introductionmentioning

confidence: 99%

MDSN: A Module Detection Method for Identifying High-Order Epistatic Interactions

Sun

Ren

et al. 2022

Genes

View full text Add to dashboard Cite

Epistatic interactions are referred to as SNPs (single nucleotide polymorphisms) that affect disease development and trait expression nonlinearly, and hence identifying epistatic interactions plays a great role in explaining the pathogenesis and genetic heterogeneity of complex diseases. Many methods have been proposed for epistasis detection; nevertheless, they mainly focus on low-order epistatic interactions, two-order or three-order for instance, and often ignore high-order interactions due to computational burden. In this paper, a module detection method called MDSN is proposed for identifying high-order epistatic interactions. First, an SNP network is constructed by a construction strategy of interaction complementary, which consists of low-order SNP interactions that can be obtained from fast computations. Then, a node evaluation measure that integrates multi-topological features is proposed to improve the node expansion algorithm, where the importance of a node is comprehensively evaluated by the topological characteristics of the neighborhood. Finally, modules are detected in the constructed SNP network, which have high-order epistatic interactions associated with the disease. The MDSN was compared with four state-of-the-art methods on simulation datasets and a real Age-related Macular Degeneration dataset. The results demonstrate that MDSN has higher performance on detecting high-order interactions.

show abstract

“…In recent years, protein complex prediction via computational approaches from PPI network has gained a lot of attention from bioinformatics researchers. The main line of the approaches for identifying protein complexes from PPI network is based on the observation of the inherent topological structures of protein complexes [4], [5]. Consequently, identifying protein complexes can be formulated as searching for subgraphs that are densely connected inside and well separated from the rest of the networks.…”

Section: Introductionmentioning

confidence: 99%

Using Alias Sampling Strategy Based on Network Embeddings to Detect Protein Complexes

2020

View full text Add to dashboard Cite

Detecting protein complexes from available protein-protein interaction (PPI) data will help to deeply understand the mechanism of the biological activities. In recent years, various computational methods have been developed for identifying protein complexes from PPI networks. Almost all the basic computational methods mainly depend on the association of topological analysis of PPI networks. However, most of them fail to satisfactorily capture the global and local topological structures of the PPI networks, as well as the diversity of connectivity patterns between individual nodes at the same time. To solve this problem, in this work we propose a node embedding based alias sampling extension method to detect protein complexes. More specifically, for a given set of seed nodes, it first uses the alias sampling strategy based on protein node embedding similarities to select potential addable nodes. Then it makes use of a new conductance measure, which could better quantify the likelihood of a subgraph being a protein complex, to decide whether to extend the current candidate subgraph in order to find protein complexes. Evaluated on six real yeast PPI networks, our method outperforms state-of-the-art methods in detecting protein complexes. Furthermore, the experimental results demonstrate the protein complexes predicted by our method have higher biological significance.

show abstract

Protein complex detection algorithm based on multiple topological characteristics in PPI networks

Cited by 16 publications

References 45 publications

A supervised protein complex prediction method with network representation learning and gene ontology knowledge

A supervised protein complex prediction method with network representation learning and gene ontology knowledge

MDSN: A Module Detection Method for Identifying High-Order Epistatic Interactions

Using Alias Sampling Strategy Based on Network Embeddings to Detect Protein Complexes

Contact Info

Product

Resources

About