A flexible R package for nonnegative matrix factorization
By Renaud Gaujoux, Cathal Seoighe. BMC Bioinformatics, 2010
1,375 citations recorded by the source corpus.
BackgroundNonnegative Matrix Factorization (NMF) is an unsupervised learning technique that has been applied successfully in several fields, including signal processing, face recognition and text mining. Recent applications of NMF in bioinformatics have demonstrated its ability to extract meaningful information from high-dimensional data such as gene expression microarrays. Developments in NMF theory and applications have resulted in a variety of algorithms and methods. However, most NMF implementations have been on commercial platforms, while those that are freely available typically require programming skills. This limits their use by the wider research community.ResultsOur objective is to provide the bioinformatics community with an open-source, easy-to-use and unified interface to standard NMF algorithms, as well as with a simple framework to help implement and test new NMF methods. For that purpose, we have developed a package for the R/BioConductor platform. The package ports public code to R, and is structured to enable users to easily modify and/or add algorithms. It includes a number of published NMF algorithms and initialization methods and facilitates the combination of these to produce new NMF strategies. Commonly used benchmark data and visualization methods are provided to help in the comparison and interpretation of the results.ConclusionsThe NMF package helps realize the potential of Nonnegative Matrix Factorization, especially in bioinformatics, providing easy access to methods that have already yielded new insights in many applications. Documentation, source code and sample data are available from CRAN.
Subfields: Computational Mathematics, Computer Vision and Pattern Recognition, Molecular Biology
View Paper: https://www.semanticscholar.org/paper/bf19714930d10b4263b8d0b6966702a4785f5fd0
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mathematics
In Computer Vision and Pattern Recognition
- Zuguang Gu
- D. Huebschmann
- Bernd Fischer
- Michael F. Lawrence
- Aviv Regev
- Michael R. Stratton
- Christopher Sander
- Edwin Cuppen
In Molecular Biology
- Hans Clevers
- Zuguang Gu
- Eric S. Lander
- Gad Getz
- Aviv Regev
- Toshiro Sato
- Matthew Meyerson
- Katherine A. Hoadley
Citations in the corpus
- Structural Remodeling of the Human Colonic Mesenchyme in Inflammatory Bowel Disease (2018, methodology): “Cell clustering Following module detection, a matrix comprising expression values for all genes assigned to modules was used as a basis for cell clustering by non-negative matrix factorisation using the R package ‘NMF’ (Gaujoux and Seoighe, 2010).”
- Integrative Analysis Identifies Four Molecular and Clinical Subsets in Uveal Melanoma. (2018, background): “10.0) NA https://www.bioconductor.org/packages/release/ bioc/html/methylumi.html MuTect Cibulskis et al., 2013 http://archive.broadinstitute.org/cancer/cga/mutect MuTect2 Van der Auwera et al., 2013 https://software.broadinstitute.org/gatk/ documentation/tooldocs/current/org_broadinstitute_ gatk_too”
- Integrated Genomic Characterization of Pancreatic Ductal Adenocarcinoma (2017, neutral): “Unsupervised Clustering and Differential Abundance for miRNAs and lncRNAs, for 76 High-Purity Tumors (A) Heatmap of row-scaled, log10-transformed normalized expression for miRNA 5p and 3p mature strands (miRs) that were abundant and also differentially abundant across three consensus clusters comput”
- Tissue-specific mutation accumulation in human adult stem cells during life (2016, positive): “To determine the replication bias of signatures, we determined whether the point mutations were located in an intermediate, early or late replicating region (as defined above) using GenomicRanges 37 and repeated the NMF on a 288 count matrix (96 trinucleotides × 3 replication timing regions).”
- Make Interactive Complex Heatmaps in R (2021, methodology): “There are also packages implemented with the grid graphics system such as the function pheatmap() from package pheatmap (Kolde 2019) and the function aheatmap() from package NMF (Gaujoux and Seoighe 2010).”
- An Integrated Metabolic Atlas of Clear Cell Renal Cell Carcinoma (2016, positive): “To evaluate whether ccRCC tumors could be partitioned into clusters with distinct metabolic phenotypes, we performed (A) Non-negative matrix factorization (NMF) clustering of metabolomics data.”
- Maftools: efficient and comprehensive analysis of somatic variants in cancer (2018, background): “W(96× r )andH( r × n ) — suchthat productofWandHsufficient-ly recomposes the original matrix M (Gaujoux and Seoighe 2010).”
- Integrative molecular and clinical modeling of clinical outcomes to PD-1 blockade in metastatic melanoma patients (2019, positive): “Mutational Signatures— De novo mutational signatures were generated in this cohort using an adaptation of NMF 70 using the Brunet update method 71 as previously described in detail 51 , using the R-packages SomaticSignatures 72 and NMF 73 .”
- Interrogation of the Microenvironmental Landscape in Brain Tumors Reveals Disease-Specific Alterations of Immune Cells (2020, methodology): “, 2016) was employed: (a) GSEA was performed using the MSigDB C7 collection as described above, (b) the leading edge genes of the significant gene sets were arranged into a genes by gene sets matrix with the shrunken fold changes as the entries, (c) this matrix was clustered using non-negative matri”