Cargando…

Learning high-order interactions for polygenic risk prediction

Within the framework of precision medicine, the stratification of individual genetic susceptibility based on inherited DNA variation has paramount relevance. However, one of the most relevant pitfalls of traditional Polygenic Risk Scores (PRS) approaches is their inability to model complex high-orde...

Descripción completa

Detalles Bibliográficos
Autores principales: Massi, Michela C., Franco, Nicola R., Manzoni, Andrea, Paganoni, Anna Maria, Park, Hanla A., Hoffmeister, Michael, Brenner, Hermann, Chang-Claude, Jenny, Ieva, Francesca, Zunino, Paolo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9916647/
https://www.ncbi.nlm.nih.gov/pubmed/36763605
http://dx.doi.org/10.1371/journal.pone.0281618
_version_ 1784886177007927296
author Massi, Michela C.
Franco, Nicola R.
Manzoni, Andrea
Paganoni, Anna Maria
Park, Hanla A.
Hoffmeister, Michael
Brenner, Hermann
Chang-Claude, Jenny
Ieva, Francesca
Zunino, Paolo
author_facet Massi, Michela C.
Franco, Nicola R.
Manzoni, Andrea
Paganoni, Anna Maria
Park, Hanla A.
Hoffmeister, Michael
Brenner, Hermann
Chang-Claude, Jenny
Ieva, Francesca
Zunino, Paolo
author_sort Massi, Michela C.
collection PubMed
description Within the framework of precision medicine, the stratification of individual genetic susceptibility based on inherited DNA variation has paramount relevance. However, one of the most relevant pitfalls of traditional Polygenic Risk Scores (PRS) approaches is their inability to model complex high-order non-linear SNP-SNP interactions and their effect on the phenotype (e.g. epistasis). Indeed, they incur in a computational challenge as the number of possible interactions grows exponentially with the number of SNPs considered, affecting the statistical reliability of the model parameters as well. In this work, we address this issue by proposing a novel PRS approach, called High-order Interactions-aware Polygenic Risk Score (hiPRS), that incorporates high-order interactions in modeling polygenic risk. The latter combines an interaction search routine based on frequent itemsets mining and a novel interaction selection algorithm based on Mutual Information, to construct a simple and interpretable weighted model of user-specified dimensionality that can predict a given binary phenotype. Compared to traditional PRSs methods, hiPRS does not rely on GWAS summary statistics nor any external information. Moreover, hiPRS differs from Machine Learning-based approaches that can include complex interactions in that it provides a readable and interpretable model and it is able to control overfitting, even on small samples. In the present work we demonstrate through a comprehensive simulation study the superior performance of hiPRS w.r.t. state of the art methods, both in terms of scoring performance and interpretability of the resulting model. We also test hiPRS against small sample size, class imbalance and the presence of noise, showcasing its robustness to extreme experimental settings. Finally, we apply hiPRS to a case study on real data from DACHS cohort, defining an interaction-aware scoring model to predict mortality of stage II-III Colon-Rectal Cancer patients treated with oxaliplatin.
format Online
Article
Text
id pubmed-9916647
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-99166472023-02-11 Learning high-order interactions for polygenic risk prediction Massi, Michela C. Franco, Nicola R. Manzoni, Andrea Paganoni, Anna Maria Park, Hanla A. Hoffmeister, Michael Brenner, Hermann Chang-Claude, Jenny Ieva, Francesca Zunino, Paolo PLoS One Research Article Within the framework of precision medicine, the stratification of individual genetic susceptibility based on inherited DNA variation has paramount relevance. However, one of the most relevant pitfalls of traditional Polygenic Risk Scores (PRS) approaches is their inability to model complex high-order non-linear SNP-SNP interactions and their effect on the phenotype (e.g. epistasis). Indeed, they incur in a computational challenge as the number of possible interactions grows exponentially with the number of SNPs considered, affecting the statistical reliability of the model parameters as well. In this work, we address this issue by proposing a novel PRS approach, called High-order Interactions-aware Polygenic Risk Score (hiPRS), that incorporates high-order interactions in modeling polygenic risk. The latter combines an interaction search routine based on frequent itemsets mining and a novel interaction selection algorithm based on Mutual Information, to construct a simple and interpretable weighted model of user-specified dimensionality that can predict a given binary phenotype. Compared to traditional PRSs methods, hiPRS does not rely on GWAS summary statistics nor any external information. Moreover, hiPRS differs from Machine Learning-based approaches that can include complex interactions in that it provides a readable and interpretable model and it is able to control overfitting, even on small samples. In the present work we demonstrate through a comprehensive simulation study the superior performance of hiPRS w.r.t. state of the art methods, both in terms of scoring performance and interpretability of the resulting model. We also test hiPRS against small sample size, class imbalance and the presence of noise, showcasing its robustness to extreme experimental settings. Finally, we apply hiPRS to a case study on real data from DACHS cohort, defining an interaction-aware scoring model to predict mortality of stage II-III Colon-Rectal Cancer patients treated with oxaliplatin. Public Library of Science 2023-02-10 /pmc/articles/PMC9916647/ /pubmed/36763605 http://dx.doi.org/10.1371/journal.pone.0281618 Text en © 2023 Massi et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Massi, Michela C.
Franco, Nicola R.
Manzoni, Andrea
Paganoni, Anna Maria
Park, Hanla A.
Hoffmeister, Michael
Brenner, Hermann
Chang-Claude, Jenny
Ieva, Francesca
Zunino, Paolo
Learning high-order interactions for polygenic risk prediction
title Learning high-order interactions for polygenic risk prediction
title_full Learning high-order interactions for polygenic risk prediction
title_fullStr Learning high-order interactions for polygenic risk prediction
title_full_unstemmed Learning high-order interactions for polygenic risk prediction
title_short Learning high-order interactions for polygenic risk prediction
title_sort learning high-order interactions for polygenic risk prediction
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9916647/
https://www.ncbi.nlm.nih.gov/pubmed/36763605
http://dx.doi.org/10.1371/journal.pone.0281618
work_keys_str_mv AT massimichelac learninghighorderinteractionsforpolygenicriskprediction
AT franconicolar learninghighorderinteractionsforpolygenicriskprediction
AT manzoniandrea learninghighorderinteractionsforpolygenicriskprediction
AT paganoniannamaria learninghighorderinteractionsforpolygenicriskprediction
AT parkhanlaa learninghighorderinteractionsforpolygenicriskprediction
AT hoffmeistermichael learninghighorderinteractionsforpolygenicriskprediction
AT brennerhermann learninghighorderinteractionsforpolygenicriskprediction
AT changclaudejenny learninghighorderinteractionsforpolygenicriskprediction
AT ievafrancesca learninghighorderinteractionsforpolygenicriskprediction
AT zuninopaolo learninghighorderinteractionsforpolygenicriskprediction