High dimensionality reduction by matrix factorization for systems pharmacology

Abstract The extraction of predictive features from the complex high-dimensional multi-omic data is necessary for decoding and overcoming the therapeutic responses in systems pharmacology. Developing computational methods to reduce high-dimensional space of features in in vitro, in vivo and clinical...

Full description

Saved in:
Bibliographic Details
Published in:Briefings in bioinformatics 2022-01, Vol.23 (1)
Main Authors: Mehrpooya, Adel, Saberi-Movahed, Farid, Azizizadeh, Najmeh, Rezaei-Ravari, Mohammad, Saberi-Movahed, Farshad, Eftekhari, Mahdi, Tavassoly, Iman
Format: Article
Language:English
Subjects:
Algorithms
Computer applications
Drug resistance
Encyclopedias
Enzyme inhibitors
Factorization
Feature extraction
Feature selection
Gene expression
Humans
In vivo methods and tests
Kinases
Mathematical analysis
Neoplasms - drug therapy
Neoplasms - genetics
Network Pharmacology
Pharmacology
Phenotypes
Problem Solving Protocol
Protein-tyrosine kinase
Reduction
Tyrosine
Citations: Items that this one cites
Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract The extraction of predictive features from the complex high-dimensional multi-omic data is necessary for decoding and overcoming the therapeutic responses in systems pharmacology. Developing computational methods to reduce high-dimensional space of features in in vitro, in vivo and clinical data is essential to discover the evolution and mechanisms of the drug responses and drug resistance. In this paper, we have utilized the matrix factorization (MF) as a modality for high dimensionality reduction in systems pharmacology. In this respect, we have proposed three novel feature selection methods using the mathematical conception of a basis for features. We have applied these techniques as well as three other MF methods to analyze eight different gene expression datasets to investigate and compare their performance for feature selection. Our results show that these methods are capable of reducing the feature spaces and find predictive features in terms of phenotype determination. The three proposed techniques outperform the other methods used and can extract a 2-gene signature predictive of a tyrosine kinase inhibitor treatment response in the Cancer Cell Line Encyclopedia.
ISSN:1467-5463
1477-4054
DOI:10.1093/bib/bbab410