Identification of Potential Links in Biomedical Networks

A special issue of Genes (ISSN 2073-4425). This special issue belongs to the section "Technologies and Resources for Genetics".

Deadline for manuscript submissions: closed (25 August 2022) | Viewed by 8393

Special Issue Editors

Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, China
Interests: bioinformatics; data mining; machine learning; kernel method; fuzzy systems; sparse representation; neural networks
Special Issues, Collections and Topics in MDPI journals
Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 610054, China
Interests: bioinformatics; parallel computing; deep learning; protein classification; genome assembly
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Predicting the potential associations in the biomedical bipartite network can provide useful insights for the diagnosis and treatment of complex diseases and the discovery of new drug targets. In particular, the analysis of biomedical networks can provide useful insights for the diagnosis and prognosis of complex diseases. An important subset of biomedical networks is the bipartite network, which includes two different types of nodes, so that each edge connects a node in one type to a node in the other type. In the biomedical dichotomous network, one type of node is usually composed of molecular components, such as genes, microRNA, or proteins, and the other type of node is usually composed of various indicators of human diseases, such as symptoms and adverse drug reactions. Identifying links in biomedical bidirectional networks through in vivo or biochemical experimental methods can be very expensive. The computational prediction of potential associations in the biomedical bipartite network can effectively guide in vivo verification and significantly reduce the cost of disease diagnosis and drug discovery. Therefore, many efforts have been devoted to the development of computational methods for predicting potential connections in biomedical bipartite networks. For example, computational predictions of interactions between drugs/compounds and targets have been widely used to supplement wet laboratory experiments for drug discovery and drug relocation. In order to study the correlation between the genetic complexity of complex diseases and the phenotype of discrete diseases, many network-based computational methods have been developed to identify the association between genes and diseases.

This Special Issue is about solving potential link (association) prediction in biomedical networks. Areas to be covered in this Special Issue may include but are not limited to:

  • Gene–disease network
  • Drug–disease network
  • Drug–target network
  • Drug–side effect network
  • Drug–drug network
  • Protein–protein interaction network
  • circRNA–disease network
  • microRNA–disease network
  • lncRNA–disease network
  • lncRNA–protein interaction network

Dr. Yijie Ding
Prof. Dr. Quan Zou
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Genes is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

 

Keywords

  • network analysis
  • data mining 
  • machine learning 
  • deep learning 
  • biomedical network 
  • link prediction of network

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

20 pages, 3078 KiB  
Article
Using Sequence Similarity Based on CKSNP Features and a Graph Neural Network Model to Identify miRNA–Disease Associations
Genes 2022, 13(10), 1759; https://doi.org/10.3390/genes13101759 - 28 Sep 2022
Cited by 3 | Viewed by 1402
Abstract
Among many machine learning models for analyzing the relationship between miRNAs and diseases, the prediction results are optimized by establishing different machine learning models, and less attention is paid to the feature information contained in the miRNA sequence itself. This study focused on [...] Read more.
Among many machine learning models for analyzing the relationship between miRNAs and diseases, the prediction results are optimized by establishing different machine learning models, and less attention is paid to the feature information contained in the miRNA sequence itself. This study focused on the impact of the different feature information of miRNA sequences on the relationship between miRNA and disease. It was found that when the graph neural network used was the same and the miRNA features based on the K-spacer nucleic acid pair composition (CKSNAP) feature were adopted, a better graph neural network prediction model of miRNA–disease relationship could be built (AUC = 93.71%), which was 0.15% greater than the best model in the literature based on the same benchmark dataset. The optimized model was also used to predict miRNAs related to lung tumors, esophageal tumors, and kidney tumors, and 47, 47, and 37 of the top 50 miRNAs related to three diseases predicted separately by the model were consistent with descriptions in the wet experiment validation database (dbDEMC). Full article
(This article belongs to the Special Issue Identification of Potential Links in Biomedical Networks)
Show Figures

Figure 1

20 pages, 23812 KiB  
Article
Network Pharmacology-Based Approach Combined with Bioinformatic Analytics to Elucidate the Potential of Curcumol against Hepatocellular Carcinoma
Genes 2022, 13(4), 653; https://doi.org/10.3390/genes13040653 - 07 Apr 2022
Cited by 8 | Viewed by 4048
Abstract
Purpose: Modern, open-source databases provide an unprecedented wealth of information to help drug development. By combining data available in these databases with the proper bioinformatical tools, we can elucidate the molecular targets of natural compounds. One such molecule is curcumol, a guaiane-type sesquiterpenoid [...] Read more.
Purpose: Modern, open-source databases provide an unprecedented wealth of information to help drug development. By combining data available in these databases with the proper bioinformatical tools, we can elucidate the molecular targets of natural compounds. One such molecule is curcumol, a guaiane-type sesquiterpenoid hemiketal isolated from Rhizoma Curcumae, which is used for a broad range of diseases in traditional Chinese and Indian medicine. It has been reported to exert anti-tumor activity, but the intrinsic molecular mechanism in hepatocellular carcinoma (HCC) is unclear. Therefore, the present study was designed to reveal the predictive targets and biological mechanisms of curcumol against HCC via a network pharmacology-based approach combined with bioinformatic analytics and to provide proof of concept for further similar investigations. Methods: Data available from open-source databases (Traditional Chinese Medicine Systems Pharmacology, Comparative Toxicogenomic Database, The Cancer Genome Atlas, the Human Protein Atlas project) was processed with the help of a variety of open-source tools (SwissADME, SwissTargetPrediction, JVenn, Gene Ontology, Kyoto Encyclopedia of Genes and Genomes, GeneMANIA, Cytoscape). Results: In the present study, the potential of curcumol against HCC was unraveled by network pharmacology-based elucidation. It suggests that curcumol shows exciting druggability with 44 potent homo sapiens biotargets against HCC. The GO terms and KEGG pathways enrichment analyses, curcumol-targets-pathways-HCC network, PPI network, and corresponding in-depth topological analyses, as well as survival analysis, molecular docking simulation indicate that the potential mechanism of curcumol against HCC is complicated, as it may act in various ways, mainly by inducing apoptosis and modulating the inflammatory response, increasing presentation of HCC-specific protein. Conclusion: The present study highlights the potential of curcumol against HCC, giving reference to further experimental study. It also presents a roadmap that can be followed to conduct in silico prescreening of other compounds of interest. Full article
(This article belongs to the Special Issue Identification of Potential Links in Biomedical Networks)
Show Figures

Figure 1

23 pages, 3473 KiB  
Article
SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model
Genes 2022, 13(4), 568; https://doi.org/10.3390/genes13040568 - 23 Mar 2022
Cited by 1 | Viewed by 1658
Abstract
A large number of inorganic and organic compounds are able to bind DNA and form complexes, among which drug-related molecules are important. Chromatin accessibility changes not only directly affect drug–DNA interactions, but they can promote or inhibit the expression of the critical genes [...] Read more.
A large number of inorganic and organic compounds are able to bind DNA and form complexes, among which drug-related molecules are important. Chromatin accessibility changes not only directly affect drug–DNA interactions, but they can promote or inhibit the expression of the critical genes associated with drug resistance by affecting the DNA binding capacity of TFs and transcriptional regulators. However, the biological experimental techniques for measuring it are expensive and time-consuming. In recent years, several kinds of computational methods have been proposed to identify accessible regions of the genome. Existing computational models mostly ignore the contextual information provided by the bases in gene sequences. To address these issues, we proposed a new solution called SemanticCAP. It introduces a gene language model that models the context of gene sequences and is thus able to provide an effective representation of a certain site in a gene sequence. Basically, we merged the features provided by the gene language model into our chromatin accessibility model. During the process, we designed methods called SFA and SFC to make feature fusion smoother. Compared to DeepSEA, gkm-SVM, and k-mer using public benchmarks, our model proved to have better performance, showing a 1.25% maximum improvement in auROC and a 2.41% maximum improvement in auPRC. Full article
(This article belongs to the Special Issue Identification of Potential Links in Biomedical Networks)
Show Figures

Figure 1

Back to TopTop