Protein complex identification based on weighted PPI network with multi-source information

Yu, Yang; Zheng, Zeyu

doi:10.1016/j.jtbi.2019.06.005

Cited by 3 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PPI network represents large-scale biological processes, which are fundamental to understanding cellular organizations (Yu, Zheng, 2019). A total of 34 common targets, which were associated with both anti-IBD activity and TXYF components, were imported into the STRING database for the construction of the PPI network.…”

Section: Ppi Network Analysismentioning

confidence: 99%

A Network Pharmacological Approach to Explore the Mechanisms of TongXieYaoFang in Inflammatory Bowel Disease

You

et al. 2022

Braz. J. Pharm. Sci.

View full text Add to dashboard Cite

Inflammatory bowel disease (IBD) is a chronic inflammatory disorder of the intestine, demonstrating an increasing incidence every year. TongXieYaoFang (TXYF) has been used widely in China as a complementary therapy to relieve the symptoms of IBD for hundreds of years. In the present research, a network pharmacology-based approach was used to systematically explore the intrinsic mechanisms of TXYF in IBD at the molecular level. Network pharmacology-based methods, which mainly included database mining, screening of bioactive compounds, target prediction, collection of IBD-related targets, gene enrichment analysis, network construction, and molecular docking, were employed in the present study. Network analysis revealed a total of 108 potential targets derived from 22 component compounds of TXYF, among which 34 targets were common with the IBD-related targets. In the protein-protein interaction (PPI) network, 10 key targets were identified. The gene enrichment analysis suggested that anti-inflammatory processes, such as NF-kappa B signaling pathway and Toll-like receptor signaling pathway, could be the core processes involved in the action of TXYF in IBD. Molecular docking results revealed that three compounds present in TXYF exhibited strong binding affinity for PTGS2. The present study provides novel insights into the molecular mechanisms and network approaches of TXYF action in IBD from a systemic perspective. The potential targets and pathways identified in the present study would assist in further research on the clinical application of TXYF in IBD therapy.

show abstract

Section: Ppi Network Analysismentioning

confidence: 99%

A Network Pharmacological Approach to Explore the Mechanisms of TongXieYaoFang in Inflammatory Bowel Disease

You

et al. 2022

Braz. J. Pharm. Sci.

View full text Add to dashboard Cite

show abstract

“…Ref. [4] defines a new condition for clustering proteins in density, diameter and cosine similarity by selecting specific nodes as key nodes. These conventional clustering‐based methods for protein complexes have high requirements for the sample characteristics, which are not conducive to large‐scale detection.…”

Section: Introductionmentioning

confidence: 99%

Constructing a PPI Network Based on Deep Transfer Learning for Protein Complex Detection

Yuan

Deng

2021

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

In the detection of protein complexes, the completeness of a protein–protein interaction (PPI) network is crucial. Complete PPI networks, however, are not available for most species because experimentally identified PPIs are usually very limited. This paper proposes a deep learning based PPI predictor to construct a complete PPI network, from which protein complexes are detected using a spectral clustering method. For this purpose, the unknown PPIs are estimated by using a deep PPI predictor consisting of a semi‐supervised SVM classifier and a deep feature extractor of the convolutional neural network (CNN). Meanwhile, the similarities of gene ontology (GO) annotations contribute to protein interactions, and the differences of subcellular localizations contribute to negative interactions. Considering that, we pretrain the deep CNN feature extractor in a class of deep GO annotation and subcellular localization predictors using datasets from the type species, then transfer it to the PPI prediction model for fine‐tuning. In this way, we have a deep PPI detector enhanced with transfer learning of GO annotation and subcellular localization prediction. Experimental results on benchmark datasets show that the proposed method outperforms the state‐of‐the‐art methods. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

Deep Transfer Learning Based PPI Prediction for Protein Complex Detection

Yuan

Deng

2021

2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

Protein complex identification based on weighted PPI network with multi-source information

Cited by 3 publications

References 41 publications

A Network Pharmacological Approach to Explore the Mechanisms of TongXieYaoFang in Inflammatory Bowel Disease

A Network Pharmacological Approach to Explore the Mechanisms of TongXieYaoFang in Inflammatory Bowel Disease

Constructing a PPI Network Based on Deep Transfer Learning for Protein Complex Detection

Deep Transfer Learning Based PPI Prediction for Protein Complex Detection

Contact Info

Product

Resources

About