Biclustering of gene expression data by non-smooth non-negative matrix factorization

Carmona-Sáez, Pedro; Pascual-Marqui, Roberto D.; Tirado, Francisco; Carazo, José Marı́a; Pascual-Montano, Alberto

doi:10.1186/1471-2105-7-78

Cited by 167 publications

(71 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Characterization of identified clusters in terms of NP profile was based on the most strongly loading NP tests [17]. For characterization of identified clusters in terms of demographic, clinical, and neurobiological characteristics, we analyzed age, sex, education, disease duration reported by the patient, MMSE, APOE ε4 genotype, CSF biomarkers, MRI atrophy, and WMH measurements using χ 2 , t tests, or Kruskal-Wallis tests, where appropriate.…”

Section: Methodsmentioning

confidence: 99%

Cognitive subtypes of probable Alzheimer's disease robustly identified in four cohorts

Scheltens

Tijms

Koene

et al. 2017

Alzheimer's & Dementia

View full text Add to dashboard Cite

Introduction Patients with Alzheimer’s disease (AD) show heterogeneity in profile of cognitive impairment. We aimed to identify cognitive subtypes in four large AD cohorts using a data-driven clustering approach. Methods We included probable AD dementia patients from the Amsterdam Dementia Cohort (n = 496), Alzheimer’s Disease Neuroimaging Initiative (n = 376), German Dementia Competence Network (n = 521), and University of California, San Francisco (n = 589). Neuropsychological data were clustered using nonnegative matrix factorization. We explored clinical and neurobiological characteristics of identified clusters. Results In each cohort, a two-clusters solution best fitted the data (cophenetic correlation >0.9): one cluster was memory-impaired and the other relatively memory spared. Pooled analyses showed that the memory-spared clusters (29%–52% of patients) were younger, more often apolipoprotein E (APOE) ε4 negative, and had more severe posterior atrophy compared with the memory-impaired clusters (all P < .05). Conclusions We could identify two robust cognitive clusters in four independent large cohorts with distinct clinical characteristics.

show abstract

Section: Methodsmentioning

confidence: 99%

Cognitive subtypes of probable Alzheimer's disease robustly identified in four cohorts

Scheltens

Tijms

Koene

et al. 2017

Alzheimer's & Dementia

View full text Add to dashboard Cite

show abstract

“…Gao and Church introduced sparse NMF (sNMF), which penalized solutions based on the number of non-zero components in A and P , to address this issue [14]. Carmona-Saez et al applied a similar approach in non-smooth NMF (nsNMF) through introduction of a smoothness matrix into the factorization [31]. …”

Section: Review Of Matrix Factorization Methodsmentioning

confidence: 99%

“…The implementations used included the stats package (for SVD), the fastICA package based on the fastICA algorithm [40], the NMF package [34], and the coGAPS package [11]. The algorithms applied were SVD, ICA, the Brunet et al NMF algorithm [13], nsNMF [31], and coGAPS. The coGAPS analysis was equivalent to the original analysis performed with BD [10], as coGAPS was created using this as a test data set.…”

Section: Comparisons Of Matrix Factorization Methodsmentioning

confidence: 99%

Matrix factorization for transcriptional regulatory network inference

Ochs

Fertig

2012

2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)

View full text Add to dashboard Cite

Inference of Transcriptional Regulatory Networks (TRNs) provides insight into the mechanisms driving biological systems, especially mammalian development and disease. Many techniques have been developed for TRN estimation from indirect biochemical measurements. Although successful when initially tested in model organisms, these regulatory models often fail when applied to data from multicellular organisms where multiple regulation and gene reuse increase dramatically. Non-negative matrix factorization techniques were initially introduced to find non-orthogonal patterns in data, making them ideal techniques for inference in cases of multiple regulation. We review these techniques and their application to TRN analysis.

show abstract

“…Bimax was shown to have the best performance compared to five other prominent biclustering algorithms. Alternatively, Kluger et al [21] proposed the Spectral method using the singular value decomposition (SVD) approach, and Carmona-Saez et al [22] proposed the nsNMF (non-smooth non-negative matrix factorization) method for biclustering of gene expression data. Neither method requires specifying the number of biclusters, but rather requires pre-specifying the rank of factors to represent the data matrix.…”

Section: Introductionmentioning

confidence: 99%

Identification of Bicluster Regions in a Binary Matrix and Its Applications

Chen

Zou²,

Tien³

et al. 2013

PLoS ONE

View full text Add to dashboard Cite

Biclustering has emerged as an important approach to the analysis of large-scale datasets. A biclustering technique identifies a subset of rows that exhibit similar patterns on a subset of columns in a data matrix. Many biclustering methods have been proposed, and most, if not all, algorithms are developed to detect regions of “coherence” patterns. These methods perform unsatisfactorily if the purpose is to identify biclusters of a constant level. This paper presents a two-step biclustering method to identify constant level biclusters for binary or quantitative data. This algorithm identifies the maximal dimensional submatrix such that the proportion of non-signals is less than a pre-specified tolerance δ. The proposed method has much higher sensitivity and slightly lower specificity than several prominent biclustering methods from the analysis of two synthetic datasets. It was further compared with the Bimax method for two real datasets. The proposed method was shown to perform the most robust in terms of sensitivity, number of biclusters and number of serotype-specific biclusters identified. However, dichotomization using different signal level thresholds usually leads to different sets of biclusters; this also occurs in the present analysis.

show abstract

Biclustering of gene expression data by non-smooth non-negative matrix factorization

Cited by 167 publications

References 42 publications

Cognitive subtypes of probable Alzheimer's disease robustly identified in four cohorts

Cognitive subtypes of probable Alzheimer's disease robustly identified in four cohorts

Matrix factorization for transcriptional regulatory network inference

Identification of Bicluster Regions in a Binary Matrix and Its Applications

Contact Info

Product

Resources

About