Open AccessIn silico prediction of blood cholesterol levels from genotype data
Author(s) -
Francesco Reggiani,
Marco Carraro,
Anna Belligoli,
Marta Sanna,
Chiara Dal Prà,
Francesca Favaretto,
Carlo Ferrari,
Roberto Vettor,
Silvio C. E. Tosatto
Publication year - 2020
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0227191
Subject(s) - in silico , computer science , cholesterol , predictive modelling , genotype , bioinformatics , machine learning , artificial intelligence , data mining , computational biology , biology , medicine , genetics , gene
In this work we present a framework for blood cholesterol levels prediction from genotype data. The predictor is based on an algorithm for cholesterol metabolism simulation available in literature, implemented and optimized by our group in the R language. The main weakness of the former simulation algorithm was the need of experimental data to simulate mutations in genes altering the cholesterol metabolism. This caveat strongly limited the application of the model in the clinical practice. In this work we present how this limitation could be bypassed thanks to an optimization of model parameters based on patient cholesterol levels retrieved from literature. Prediction performance has been assessed taking into consideration several scoring indices currently used for performance evaluation of machine learning methods. Our assessment shows how the optimization phase improved model performance, compared to the original version available in literature.