Genetic analysis of coronary artery disease using tree-based automated machine learning informed by biology-based feature selection
Created by W.Langdon from
gp-bibliography.bib Revision:1.8081
- @Article{manduchi:2021:tcbb,
-
author = "Elisabetta Manduchi and Trang Le and Weixuan Fu and
Jason H Moore",
-
title = "Genetic analysis of coronary artery disease using
tree-based automated machine learning informed by
biology-based feature selection",
-
journal = "IEEE/ACM transactions on computational biology and
bioinformatics",
-
year = "2022",
-
volume = "19",
-
number = "3",
-
pages = "1379--1386",
-
month = jul # " 26",
-
keywords = "genetic algorithms, genetic programming, TPOT",
-
ISSN = "1557-9964",
-
DOI = "doi:10.1109/TCBB.2021.3099068",
-
abstract = "Machine Learning (ML) approaches are increasingly
being used in biomedical applications. Important
challenges of ML include choosing the right algorithm
and tuning the parameters for optimal performance.
Automated ML (AutoML) methods, such as Tree-based
Pipeline Optimization Tool (TPOT), have been developed
to take some of the guesswork out of ML thus making
this technology available to users from more diverse
backgrounds. The goals of this study were to assess
applicability of TPOT to genomics and to identify
combinations of single nucleotide polymorphisms (SNPs)
associated with coronary artery disease (CAD), with a
focus on genes with high likelihood of being good CAD
drug targets. We leveraged public functional genomic
resources to group SNPs into biologically meaningful
sets to be selected by TPOT. We applied this strategy
to data from the UK Biobank, detecting a strikingly
recurrent signal stemming from a group of 28 SNPs.
Importance analysis of these SNPs uncovered functional
relevance of the top SNPs to genes whose association
with CAD is supported in the literature and other
resources. Furthermore, we employed game-theory based
metrics to study SNP contributions to individual-level
TPOT predictions and discover distinct clusters of
well-predicted CAD cases. The latter indicates a
promising approach towards precision medicine.",
-
notes = "Also known as \cite{9495156}. PMID: 34310318",
- }
Genetic Programming entries for
Elisabetta Manduchi
Trang T Le
Weixuan Fu
Jason H Moore
Citations