Multi-Data Aspects of Protein Similarity with a Learning Technique to Identify Drug-Disease Associations
Drug repositioning has been proposed to develop drugs for diseases. However, the similarity in a single aspect may not be sufficient to reveal hidden information. Therefore, we established protein–protein similarity vectors (PPSVs) based on potential similarities in various types of biological infor...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/7/2914 |
_version_ | 1797540141157318656 |
---|---|
author | Satanat Kitsiranuwat Apichat Suratanee Kitiporn Plaimas |
author_facet | Satanat Kitsiranuwat Apichat Suratanee Kitiporn Plaimas |
author_sort | Satanat Kitsiranuwat |
collection | DOAJ |
description | Drug repositioning has been proposed to develop drugs for diseases. However, the similarity in a single aspect may not be sufficient to reveal hidden information. Therefore, we established protein–protein similarity vectors (PPSVs) based on potential similarities in various types of biological information associated with proteins, including their network topology, proteomic data, functional analysis, and druggable property. Based on the proposed PPSVs, a separate drug–disease matrix was constructed for individual to prevent characteristics from being obscured between diseases. The classification technique was employed for prediction. The results showed that more than half of the tested disease models exhibited high performance, with overall F1 scores of more than 80%. Furthermore, comparing all diseases using traditional methods in one run, we obtained an (area under the curve) AUC of 98.9%. All candidate drugs were then tested in clinical trials (<i>p</i>-value < 2.2 × 10<sup>−16</sup>) and were known drugs based on their functions (<i>p</i>-value < 0.05). An analysis revealed that, in the functional aspect, the confidence value of an interaction in the protein–protein interaction network and the functional pathway score were the best descriptors for prediction. Based on the learning processes of PPSVs with an isolated disease, the classifier exhibited high performance in predicting and identifying new potential drugs for that disease. |
first_indexed | 2024-03-10T12:55:49Z |
format | Article |
id | doaj.art-1efbf5a2c10c4b338b1c5886dd8b80ad |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T12:55:49Z |
publishDate | 2021-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-1efbf5a2c10c4b338b1c5886dd8b80ad2023-11-21T11:53:44ZengMDPI AGApplied Sciences2076-34172021-03-01117291410.3390/app11072914Multi-Data Aspects of Protein Similarity with a Learning Technique to Identify Drug-Disease AssociationsSatanat Kitsiranuwat0Apichat Suratanee1Kitiporn Plaimas2Program in Bioinformatics and Computational Biology, Graduate School, Chulalongkorn University, Bangkok 10330, ThailandDepartment of Mathematics, Faculty of Applied Science, King Mongkut’s University of Technology North Bangkok, Bangkok 10800, ThailandProgram in Bioinformatics and Computational Biology, Graduate School, Chulalongkorn University, Bangkok 10330, ThailandDrug repositioning has been proposed to develop drugs for diseases. However, the similarity in a single aspect may not be sufficient to reveal hidden information. Therefore, we established protein–protein similarity vectors (PPSVs) based on potential similarities in various types of biological information associated with proteins, including their network topology, proteomic data, functional analysis, and druggable property. Based on the proposed PPSVs, a separate drug–disease matrix was constructed for individual to prevent characteristics from being obscured between diseases. The classification technique was employed for prediction. The results showed that more than half of the tested disease models exhibited high performance, with overall F1 scores of more than 80%. Furthermore, comparing all diseases using traditional methods in one run, we obtained an (area under the curve) AUC of 98.9%. All candidate drugs were then tested in clinical trials (<i>p</i>-value < 2.2 × 10<sup>−16</sup>) and were known drugs based on their functions (<i>p</i>-value < 0.05). An analysis revealed that, in the functional aspect, the confidence value of an interaction in the protein–protein interaction network and the functional pathway score were the best descriptors for prediction. Based on the learning processes of PPSVs with an isolated disease, the classifier exhibited high performance in predicting and identifying new potential drugs for that disease.https://www.mdpi.com/2076-3417/11/7/2914biological networkdrug repositioningdrug repurposingprotein’s interaction networkmachine learning |
spellingShingle | Satanat Kitsiranuwat Apichat Suratanee Kitiporn Plaimas Multi-Data Aspects of Protein Similarity with a Learning Technique to Identify Drug-Disease Associations Applied Sciences biological network drug repositioning drug repurposing protein’s interaction network machine learning |
title | Multi-Data Aspects of Protein Similarity with a Learning Technique to Identify Drug-Disease Associations |
title_full | Multi-Data Aspects of Protein Similarity with a Learning Technique to Identify Drug-Disease Associations |
title_fullStr | Multi-Data Aspects of Protein Similarity with a Learning Technique to Identify Drug-Disease Associations |
title_full_unstemmed | Multi-Data Aspects of Protein Similarity with a Learning Technique to Identify Drug-Disease Associations |
title_short | Multi-Data Aspects of Protein Similarity with a Learning Technique to Identify Drug-Disease Associations |
title_sort | multi data aspects of protein similarity with a learning technique to identify drug disease associations |
topic | biological network drug repositioning drug repurposing protein’s interaction network machine learning |
url | https://www.mdpi.com/2076-3417/11/7/2914 |
work_keys_str_mv | AT satanatkitsiranuwat multidataaspectsofproteinsimilaritywithalearningtechniquetoidentifydrugdiseaseassociations AT apichatsuratanee multidataaspectsofproteinsimilaritywithalearningtechniquetoidentifydrugdiseaseassociations AT kitipornplaimas multidataaspectsofproteinsimilaritywithalearningtechniquetoidentifydrugdiseaseassociations |