Research
Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital
Published

Translating polygenic risk scores for clinical use by estimating the confidence bounds of risk prediction

Research output: Contribution to journalJournal articleResearchpeer-review

  1. Capsid-like particles decorated with the SARS-CoV-2 receptor-binding domain elicit strong virus neutralization activity

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Common variants in Alzheimer's disease and risk stratification by polygenic risk scores

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Risk variants and polygenic architecture of disruptive behavior disorders in the context of attention-deficit/hyperactivity disorder

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Ultraviolet radiation drives mutations in a subset of mucosal melanomas

    Research output: Contribution to journalJournal articleResearchpeer-review

  • Regeneron Genetics Center
View graph of relations

A promise of genomics in precision medicine is to provide individualized genetic risk predictions. Polygenic risk scores (PRS), computed by aggregating effects from many genomic variants, have been developed as a useful tool in complex disease research. However, the application of PRS as a tool for predicting an individual's disease susceptibility in a clinical setting is challenging because PRS typically provide a relative measure of risk evaluated at the level of a group of people but not at individual level. Here, we introduce a machine-learning technique, Mondrian Cross-Conformal Prediction (MCCP), to estimate the confidence bounds of PRS-to-disease-risk prediction. MCCP can report disease status conditional probability value for each individual and give a prediction at a desired error level. Moreover, with a user-defined prediction error rate, MCCP can estimate the proportion of sample (coverage) with a correct prediction.

Original languageEnglish
Article number5276
JournalNature Communications
Volume12
Issue number1
Pages (from-to)5276
DOIs
Publication statusPublished - 6 Sep 2021

    Research areas

  • Age Factors, Biological Specimen Banks, Breast Neoplasms/genetics, Coronary Artery Disease/genetics, Diabetes Mellitus, Type 2/genetics, Female, Genetic Predisposition to Disease/genetics, Humans, Inflammatory Bowel Diseases/genetics, Machine Learning, Male, Multifactorial Inheritance/genetics, Reproducibility of Results, Schizophrenia/genetics, Sweden, United Kingdom

ID: 67620766