diff mbox series

[bug#36799,10/11] gnu: Add r-mixomics.

Message ID 20190724182204.6818-11-zimon.toutoune@gmail.com
State Accepted
Headers show
Series Add r packages to process flow cytometry data | expand

Commit Message

zimoun July 24, 2019, 6:22 p.m. UTC
* gnu/packages/bioconductor.scm (r-mixomics): New variable.
 gnu/packages/bioconductor.scm | 54 +++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)
diff mbox series


diff --git a/gnu/packages/bioconductor.scm b/gnu/packages/bioconductor.scm
index dd6570ed17..64625aedd4 100644
--- a/gnu/packages/bioconductor.scm
+++ b/gnu/packages/bioconductor.scm
@@ -4959,3 +4959,57 @@  and to both short and long sequence reads.")
       "FlowSOM offers visualization options for cytometry data, by using Self-Organizing Map clustering and Minimal Spanning Trees.")
     (license license:gpl2+)))
+(define-public r-mixomics
+  (package
+    (name "r-mixomics")
+    (version "6.8.0")
+    (source
+      (origin
+        (method url-fetch)
+        (uri (bioconductor-uri "mixOmics" version))
+        (sha256
+          (base32
+            "1f08jx35amn3sfcmqb96mjxxsm6dnpzhff625z758x1992wj4zsk"))))
+    (properties `((upstream-name . "mixOmics")))
+    (build-system r-build-system)
+    (propagated-inputs
+      `(("r-corpcor" ,r-corpcor)
+        ("r-dplyr" ,r-dplyr)
+        ("r-ellipse" ,r-ellipse)
+        ("r-ggplot2" ,r-ggplot2)
+        ("r-gridextra" ,r-gridextra)
+        ("r-igraph" ,r-igraph)
+        ("r-lattice" ,r-lattice)
+        ("r-mass" ,r-mass)
+        ("r-matrixstats" ,r-matrixstats)
+        ("r-rarpack" ,r-rarpack)
+        ("r-rcolorbrewer" ,r-rcolorbrewer)
+        ("r-reshape2" ,r-reshape2)
+        ("r-tidyr" ,r-tidyr)))
+    (home-page "http://www.mixOmics.org")
+    (synopsis "Omics Data Integration Project")
+    (description
+      "Multivariate methods are well suited to large omics data sets where the
+number of variables (e.g.  genes, proteins, metabolites) is much larger than
+the number of samples (patients, cells, mice).  They have the appealing
+properties of reducing the dimension of the data by using instrumental
+variables (components), which are defined as combinations of all variables.
+Those components are then used to produce useful graphical outputs that enable
+better understanding of the relationships and correlation structures between
+the different data sets that are integrated.  mixOmics offers a wide range of
+multivariate methods for the exploration and integration of biological
+datasets with a particular focus on variable selection.  The package proposes
+several sparse multivariate models we have developed to identify the key
+variables that are highly correlated, and/or explain the biological outcome of
+interest.  The data that can be analysed with mixOmics may come from high
+throughput sequencing technologies, such as omics data (transcriptomics,
+metabolomics, proteomics, metagenomics etc) but also beyond the realm of
+omics (e.g.  spectral imaging).  The methods implemented in mixOmics can also
+handle missing values without having to delete entire rows with missing data.
+A non exhaustive list of methods include variants of generalised Canonical
+Correlation Analysis, sparse Partial Least Squares and sparse Discriminant
+Analysis.  Recently we implemented integrative methods to combine multiple
+data sets: N-integration with variants of Generalised Canonical Correlation
+Analysis and P-integration with variants of multi-group Partial Least
+    (license license:gpl2+)))