What is it about?
We have applied "Tensor decomposition based unsupervised feature extraction" to protein-protein interaction represented as matrix/tensor. Using identified genes, we proposed gene-centric for drug repositioning that do not specify any genes and drugs
Featured Image
Photo by National Cancer Institute on Unsplash
Why is it important?
Usually, protein protein interaction is represented as networks and is analyzed using network based technique. However, we represent protein-protein interaction as matrix/tensor, to which tensor decomposition is applied. This approach enables us to identify gene sets, which cannot be identified by network based analyses.
Perspectives
In the previous study, I have integrated gene expression and PPI. I expected that only PPI is not useful for drug repositioning, but it was. So I decided to investigate the efficiency of the usage of PPI without any additional information. Then, I found that only PPI is useful for the drug repositioning.
Professor Y-h. Taguchi
Chuo Daigaku
Read the Original
This page is a summary of: Novel artificial intelligence-based identification of drug-gene-disease interaction using protein-protein interaction, BMC Bioinformatics, December 2024, Springer Science + Business Media,
DOI: 10.1186/s12859-024-06009-9.
You can read the full text:
Contributors
The following have contributed to this page
