Uncovering the complex genetic architecture of human plasma lipidome using machine learning methods

Genetic architecture of plasma lipidome provides insights into regulation of lipid metabolism and related diseases. We applied an unsupervised machine learning method, PGMRA, to discover phenotype-genotype many-to-many relations between genotype and plasma lipidome (phenotype) in order to identify t...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2023-02, Vol.13 (1), p.3078-3078, Article 3078
Main Authors: Lehtimäki, Miikael, Mishra, Binisha H., Del-Val, Coral, Lyytikäinen, Leo-Pekka, Kähönen, Mika, Cloninger, C. Robert, Raitakari, Olli T., Laaksonen, Reijo, Zwir, Igor, Lehtimäki, Terho, Mishra, Pashupati P.
Format: Article
Language:English
Subjects:
631/114
631/208
631/337
Genetic diversity
Genetic variance
Genotype
Genotype & phenotype
Genotypes
Humanities and Social Sciences
Humans
Learning algorithms
Lipid metabolism
Lipidomics
Machine Learning
Metabolism
multidisciplinary
Phenotype
Phenotypes
Plasma
Polymorphism, Single Nucleotide
Population studies
Precision medicine
Science
Science (multidisciplinary)
Single-nucleotide polymorphism
Statistical analysis
Unsupervised Machine Learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Genetic architecture of plasma lipidome provides insights into regulation of lipid metabolism and related diseases. We applied an unsupervised machine learning method, PGMRA, to discover phenotype-genotype many-to-many relations between genotype and plasma lipidome (phenotype) in order to identify the genetic architecture of plasma lipidome profiled from 1,426 Finnish individuals aged 30–45 years. PGMRA involves biclustering genotype and lipidome data independently followed by their inter-domain integration based on hypergeometric tests of the number of shared individuals. Pathway enrichment analysis was performed on the SNP sets to identify their associated biological processes. We identified 93 statistically significant (hypergeometric p -value 
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-023-30168-z