TABLE 2.
Low-level: Regression/Association-based unsupervised integration methods.
| Approach | Method | Macro category* | Author | Objective | Omics data** | Software*** |
|---|---|---|---|---|---|---|
| Sequential Analysis | • CNAMet | MS-SA | Louhimo and Hautaniemi, (2011) | Biomarker-prediction | CNV, DM, GE | • CNAmet (http://csbi.ltdk.helsinki.fi/CNAmet ) |
| • MEMo (Mutual Exclusivity Modules) | MS-SA | Ciriello et al. (2012) | Module-discovery | CNA, GE | • JAVA code (http://cbio.mskcc.org/memo) | |
| • iPAC (in-trans Process Associated and cis-Correlated) | MS-SA | Aure et al. (2013) | Biomarker-prediction | CNV, GE | • - | |
| CCA & CIA | • Sparse MCCA (Sparse Multiple Canonical Correlation Analysis) | DatE | Witten and Tibshirani, (2009) | Disease insight, Hotspot-detection | GE, CNV | • PMA (https://cran.r-project.org/web/packages/PMA/index.html) |
| • BCCA (Bayesian Canonical Correlation Analysis) | DatE | Klami et al. (2013) | Disease insight | Any Omics | • CCAGFA (https://cran.r-project.org/web/packages/CCAGFA/index.html) | |
| • MCIA (Multiple Co-Inertia Analysis) | DatE | Meng et al. (2014) | Disease-subtyping, Biomarker-prediction | GE, PE | • omicade4 (https://www.bioconductor.org/packages/release/bioc/html/omicade4.html) | |
| • ade4 (https://cran.r-project.org/web/packages/ade4/index.html) | ||||||
| • sMCIA (sparse Multiple Co-Inertia Analysis) | DatE | Min and Long, (2020) | Biomarker-prediction | Any Omics | • pmCIA (https://www.med.upenn.edu/long-lab/software.html) | |
| Factor Analysis | • Joint Bayesian Factor | DatE | Ray et al. (2014) | Biomarker-prediction | CNV, DM, GE | • Matlab code (https://sites.google.com/site/jointgenomics/) |
| • MOFA (Multi-Omics Factor Analysis) | DatE | Argelaguet et al. (2018) | Biomarker-prediction | Any Omics | • MOFAtools | |
| (https://github.com/bioFAM/MOFA) | ||||||
| • BayRel (Bayesian Relational learning) | DatE | Hajiramezanali et al. (2020) | Biomarker-prediction | Any Omics | • TensorFlow (https://github.com/ehsanhajiramezanali/BayReL) |
*Macro categories include (A) Multi-step and Sequential Analysis (MS-SA), (B) Data-ensemble (DatE), (C) Model-ensemble (ModE). ** CNV: copy number variation, DM: DNA methylation, GE: gene expression, PE: Protein expression. ***R packages, unless otherwise stated.