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

Stronger findings for metabolomics through Bayesian modeling of multiple peaks and compound correlations

Research output: Contribution to journalJournal articleResearchpeer-review

  1. scVAE: variational auto-encoders for single-cell gene expression data

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. AA9int: SNP interaction pattern search using non-hierarchical additive model set

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Modeling tissue contamination to improve molecular identification of the primary tumor site of metastases

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Integrative analysis of histone ChIP-seq and transcription data using Bayesian mixture models

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. Multivariate multi-way analysis of multi-source data

    Research output: Contribution to journalJournal articleResearchpeer-review

  1. Ceramides and phospholipids are downregulated with liraglutide treatment: results from the LiraFlame randomized controlled trial

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Changes in the lipidome in type 1 diabetes following low carbohydrate diet: Post-hoc analysis of a randomized crossover trial

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Gut microbiota profile and selected plasma metabolites in type 1 diabetes without and with stratification by albuminuria

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Characterization of plasma lipidomics in adolescent subjects with increased risk for type 1 diabetes in the DiPiS cohort

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. Circulating Metabolites and Lipids Are Associated to Diabetic Retinopathy in Individuals With Type 1 Diabetes

    Research output: Contribution to journalJournal articleResearchpeer-review

View graph of relations

Motivation: Data analysis for metabolomics suffers from uncertainty because of the noisy measurement technology and the small sample size of experiments. Noise and the small sample size lead to a high probability of false findings. Further, individual compounds have natural variation between samples, which in many cases renders them unreliable as biomarkers. However, the levels of similar compounds are typically highly correlated, which is a phenomenon that we model in this work. Results: We propose a hierarchical Bayesian model for inferring differences between groups of samples more accurately in metabolomic studies, where the observed compounds are collinear. We discover that the method decreases the error of weak and non-existent covariate effects, and thereby reduces false-positive findings. To achieve this, the method makes use of the mass spectral peak data by clustering similar peaks into latent compounds, and by further clustering latent compounds into groups that respond in a coherent way to the experimental covariates.We demonstrate the method with three simulated studies and validate it with a metabolomic benchmark dataset.

Original languageEnglish
JournalBioinformatics
Volume30
Issue number17
ISSN1367-4803
DOIs
Publication statusPublished - 1 Sep 2014

ID: 61172853