Construction and contextualization approaches for protein-protein interaction networks

Badkas, Apurva; Landtsheer, Sébastien De; Sauter, Thomas

doi:10.1016/j.csbj.2022.06.040

Cited by 5 publications

(3 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned in Section 2 , independent data sources are commonly aggregated to address the issue of sparsity in the PPI network, and embedding methods are able to learn one singular vector to represent all the interaction data sources [61] , [64] , [65] . BIONIC [66] is the leading PPI network embedding method specifically designed for pathway prediction tasks.…”

Section: Network Embedding Methods Transform Ppi Networkmentioning

confidence: 99%

Heterogeneous network approaches to protein pathway prediction

Nayar,

Altman

2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Section: Network Embedding Methods Transform Ppi Networkmentioning

confidence: 99%

Heterogeneous network approaches to protein pathway prediction

Nayar,

Altman

2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

“…Currently, graph representation learning has gained wide application within the analysis of PPINs. Such methods take the entire network as input and learn to transform its topological structure into a vector representation (embeddings), which can be applied to tasks such as label prediction and edge prediction [12][13][14]. Meng et al [15] employed a hierarchical compression strategy to condense the inputted protein interaction network into a multi-layer PPI network, learning different granularity levels of protein embeddings through network embedding methods and constructing a weighted PPI network using the similarity of protein embeddings.…”

Section: Introductionmentioning

confidence: 99%

A Construction Method for a Dynamic Weighted Protein Network Using Multi-Level Embedding

Li,

Guo,

Zhang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The rapid development of high-throughput technology has generated a large amount of protein–protein interaction (PPI) data, which provide a large amount of data support for constructing dynamic protein–protein interaction networks (PPINs). Constructing dynamic PPINs and applying them to recognize protein complexes has become a hot research topic. Most existing methods for complex recognition cannot fully mine the information of PPINs. To address this problem, we propose a construction method of dynamic weighted protein network by multi-level embedding (DWPNMLE). It can reflect the protein network’s dynamics and the protein network’s higher-order proximity. Firstly, the protein active period is calculated to divide the protein subnetworks at different time points. Then, the connection probability is used for the proteins possessing the same time points to judge whether there is an interaction relationship between them. Then, the corresponding protein subnetworks (multiple adjacency matrices) are constructed. Secondly, the multiple feature matrices are constructed using one-hot coding with the gene ontology (GO) information. Next, the first embedding is performed using variational graph auto-encoders (VGAEs) to aggregate features efficiently, followed by the second embedding using deep attributed network embedding (DANE) to strengthen the node representations learned in the first embedding and to maintain the first-order and higher-order proximity of the original network; finally, we compute the cosine similarity to obtain the final dynamic weighted PPIN. To evaluate the effectiveness of DWPNMLE, we apply four classical protein-complex-recognition algorithms on the DWPNMLE and compare them with two other dynamic protein network construction methods. The experimental results demonstrate that DWPNMLE significantly enhances the accuracy of complex recognition with high robustness, and the algorithms’ efficiency is also within a reasonable range.

show abstract

“…In case of such differences, it is not clear if combining information from different sources offers improved outcomes, or if there is an advantage in analysing different topologies separately. Outcomes of network-based analyses are dependent on construction methods, which affect the size and topology of the constructed network [ 12 ]. Thus, one of the challenges is to identify DAPs while incorporating this uncertainty.…”

Section: Introductionmentioning

confidence: 99%

Expanding the Disease Network of Glioblastoma Multiforme via Topological Analysis

Badkas

Landtsheer

Sauter

2023

IJMS

Self Cite

View full text Add to dashboard Cite

Glioblastoma multiforme (GBM), a grade IV glioma, is a challenging disease for patients and clinicians, with an extremely poor prognosis. These tumours manifest a high molecular heterogeneity, with limited therapeutic options for patients. Since GBM is a rare disease, sufficient statistically strong evidence is often not available to explore the roles of lesser-known GBM proteins. We present a network-based approach using centrality measures to explore some key, topologically strategic proteins for the analysis of GBM. Since network-based analyses are sensitive to changes in network topology, we analysed nine different GBM networks, and show that small but well-curated networks consistently highlight a set of proteins, indicating their likely involvement in the disease. We propose 18 novel candidates which, based on differential expression, mutation analysis, and survival analysis, indicate that they may play a role in GBM progression. These should be investigated further for their functional roles in GBM, their clinical prognostic relevance, and their potential as therapeutic targets.

show abstract

Construction and contextualization approaches for protein-protein interaction networks

Cited by 5 publications

References 78 publications

Heterogeneous network approaches to protein pathway prediction

Heterogeneous network approaches to protein pathway prediction

A Construction Method for a Dynamic Weighted Protein Network Using Multi-Level Embedding

Expanding the Disease Network of Glioblastoma Multiforme via Topological Analysis

Contact Info

Product

Resources

About