In silico prediction of blood cholesterol levels from genotype data

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 R language. 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 patients cholesterol levels retrieved from literature. Prediction performance has been assessed taking in 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.

[1]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[2]  Yared Paalvast,et al.  Evaluating computational models of cholesterol metabolism. , 2015, Biochimica et biophysica acta.

[3]  Hadley Wickham,et al.  ggplot2 - Elegant Graphics for Data Analysis (2nd Edition) , 2017 .

[4]  Andrew White,et al.  The Limitations of Model-Based Experimental Design and Parameter Estimation in Sloppy Systems , 2016, PLoS Comput. Biol..

[5]  Karline Soetaert,et al.  Solving Differential Equations in R: Package deSolve , 2010 .

[6]  Ben van Ommen,et al.  A physiologically based in silico kinetic model predicting plasma cholesterol concentrations in humans[S] , 2012, Journal of Lipid Research.

[7]  Marco S. Nobile,et al.  Computational Strategies for a System-Level Understanding of Metabolism , 2014, Metabolites.

[8]  Matthew K Ito,et al.  The Agenda for Familial Hypercholesterolemia: A Scientific Statement From the American Heart Association. , 2015, Circulation.

[9]  Ben van Ommen,et al.  Systematic construction of a conceptual minimal model of plasma cholesterol levels based on knockout mouse phenotypes. , 2010, Biochimica et biophysica acta.

[10]  Hongwei Yu,et al.  Spectrum of Delta(7)-dehydrocholesterol reductase mutations in patients with the Smith-Lemli-Opitz (RSH) syndrome. , 2000, Human molecular genetics.

[11]  Mathilde Varret,et al.  Description of a Large Family with Autosomal Dominant Hypercholesterolemia Associated with the APOE p.Leu167del Mutation , 2013, Human mutation.

[12]  M. Shapiro,et al.  Rare Genetic Disorders Altering Lipoproteins , 2015 .

[13]  Raquel S. Sevilla,et al.  Exome-wide association study of plasma lipids in >300,000 individuals , 2017, Nature Genetics.

[14]  Celeste Eng,et al.  Human cholesterol 7alpha-hydroxylase (CYP7A1) deficiency has a hypercholesterolemic phenotype. , 2002, The Journal of clinical investigation.