Amrit Singh1, Casey P Shannon1, Benoît Gautier2, Florian Rohart3, Michaël Vacher4, Scott J Tebbutt1, Kim-Anh Lê Cao5. 1. Prevention of Organ Failure (PROOF) Centre of Excellence, University of British Columbia, Vancouver, BC, Canada. 2. The University of Queensland Diamantina Institute, Translational Research Institute, Woolloongabba, Queensland, Australia. 3. Institute for Molecular Bioscience, The University of Queensland, St Lucia, Queensland, Australia. 4. Australian eHealth Research Centre, Commonwealth Scientific and Industrial Research Organisation, Brisbane, Queensland, Australia. 5. Melbourne Integrative Genomics, School of Mathematics and Statistics, The University of Melbourne, Melbourne, Australia.
Abstract
MOTIVATION: In the continuously expanding omics era, novel computational and statistical strategies are needed for data integration and identification of biomarkers and molecular signatures. We present Data Integration Analysis for Biomarker discovery using Latent cOmponents (DIABLO), a multi-omics integrative method that seeks for common information across different data types through the selection of a subset of molecular features, while discriminating between multiple phenotypic groups. RESULTS: Using simulations and benchmark multi-omics studies, we show that DIABLO identifies features with superior biological relevance compared with existing unsupervised integrative methods, while achieving predictive performance comparable to state-of-the-art supervised approaches. DIABLO is versatile, allowing for modular-based analyses and cross-over study designs. In two case studies, DIABLO identified both known and novel multi-omics biomarkers consisting of mRNAs, miRNAs, CpGs, proteins and metabolites. AVAILABILITY AND IMPLEMENTATION: DIABLO is implemented in the mixOmics R Bioconductor package with functions for parameters' choice and visualization to assist in the interpretation of the integrative analyses, along with tutorials on http://mixomics.org and in our Bioconductor vignette. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
MOTIVATION: In the continuously expanding omics era, novel computational and statistical strategies are needed for data integration and identification of biomarkers and molecular signatures. We present Data Integration Analysis for Biomarker discovery using Latent cOmponents (DIABLO), a multi-omics integrative method that seeks for common information across different data types through the selection of a subset of molecular features, while discriminating between multiple phenotypic groups. RESULTS: Using simulations and benchmark multi-omics studies, we show that DIABLO identifies features with superior biological relevance compared with existing unsupervised integrative methods, while achieving predictive performance comparable to state-of-the-art supervised approaches. DIABLO is versatile, allowing for modular-based analyses and cross-over study designs. In two case studies, DIABLO identified both known and novel multi-omics biomarkers consisting of mRNAs, miRNAs, CpGs, proteins and metabolites. AVAILABILITY AND IMPLEMENTATION:DIABLO is implemented in the mixOmics R Bioconductor package with functions for parameters' choice and visualization to assist in the interpretation of the integrative analyses, along with tutorials on http://mixomics.org and in our Bioconductor vignette. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Authors: Jun Zhu; Pavel Sova; Qiuwei Xu; Kenneth M Dombek; Ethan Y Xu; Heather Vu; Zhidong Tu; Rachel B Brem; Roger E Bumgarner; Eric E Schadt Journal: PLoS Biol Date: 2012-04-03 Impact factor: 8.029
Authors: Ada Hamosh; Alan F Scott; Joanna S Amberger; Carol A Bocchini; Victor A McKusick Journal: Nucleic Acids Res Date: 2005-01-01 Impact factor: 16.971
Authors: Nelly Amenyogbe; Pedro Dimitriu; Patricia Cho; Candice Ruck; Edgardo S Fortuno; Bing Cai; Ariane Alimenti; Hélène C F Côté; Evelyn J Maan; Amy L Slogrove; Monika Esser; Arnaud Marchant; Tessa Goetghebuer; Casey P Shannon; Scott J Tebbutt; Tobias R Kollmann; William W Mohn; Kinga K Smolen Journal: J Immunol Date: 2020-10-16 Impact factor: 5.422
Authors: Vincent van Unen; Mikhael D Manurung; Koen A Stam; Sanne E de Jong; Jelle J Goeman; Simon P Jochems; Thomas Höllt; Nicola Pezzotti; Yoanne D Mouwenda; Madeleine Eunice Betouke Ongwe; Freia-Raphaella Lorenz; Yvonne C M Kruize; Shohreh Azimi; Marion H König; Anna Vilanova; Elmar Eisemann; Boudewijn P F Lelieveldt; Meta Roestenberg; B Kim Lee Sim; Marcel J T Reinders; Rolf Fendel; Stephen L Hoffman; Peter G Kremsner; Frits Koning; Benjamin Mordmüller; Bertrand Lell; Maria Yazdanbakhsh Journal: Nat Immunol Date: 2021-04-22 Impact factor: 25.606
Authors: Heather E Ashwood; Christopher Ashwood; Anna P Schmidt; Rebekah L Gundry; Karin M Hoffmeister; Waseem Q Anani Journal: Blood Adv Date: 2021-03-09