Discovery of multi-dimensional modules by integrative analysis of cancer genomic data

By Shihua Zhang, Chun-Chi Liu, Wenyuan Li, Hui Shen, Peter W. Laird, X. Zhou. Nucleic Acids Research, 2012

330 citations recorded by the source corpus.

Recent technology has made it possible to simultaneously perform multi-platform genomic profiling (e.g. DNA methylation (DM) and gene expression (GE)) of biological samples, resulting in so-called ‘multi-dimensional genomic data’. Such data provide unique opportunities to study the coordination between regulatory mechanisms on multiple levels. However, integrative analysis of multi-dimensional genomics data for the discovery of combinatorial patterns is currently lacking. Here, we adopt a joint matrix factorization technique to address this challenge. This method projects multiple types of genomic data onto a common coordinate system, in which heterogeneous variables weighted highly in the same projected direction form a multi-dimensional module (md-module). Genomic variables in such modules are characterized by significant correlations and likely functional associations. We applied this method to the DM, GE, and microRNA expression data of 385 ovarian cancer samples from the The Cancer Genome Atlas project. These md-modules revealed perturbed pathways that would have been overlooked with only a single type of data, uncovered associations between different layers of cellular activities and allowed the identification of clinically distinct patient subgroups. Our study provides an useful protocol for uncovering hidden patterns and their biological implications in multi-dimensional ‘omic’ data.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/6eb20b15fc964069104aaeb4c68a71005d540fa3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Data Fusion by Matrix Factorization (2013, methodology): “Zhang et al. (2012) (Zhang et al., 2012) proposed a joint matrix factorization to decompose a number of data matrices Ri into a common basis matrix W and di↵erent coe cient matrices Hi, such that Ri ⇡WHi by minimizing P i ||Ri WHi||.”
RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach (2016, methodology): “In addition, iDeep also performes better than other matrix factorization-based methods NMF [30], SNMF [31] and QNO [32], which achieves the average AUC of 0.83 ± 0.10, 0.71 ± 0.14, 0.79 ± 0.12 on 31 experiments, respectively.”
Multi-omic and multi-view clustering algorithms: review and cancer benchmark (2018, background): “Overall, rMKL-LPP outperformed all methods except MCCA and multiNMF with respect to both survival and clinical enrichment.”
Multi-omics Data Integration, Interpretation, and Its Application (2020, methodology): “57 Another extension of NMF, joint NMF (jNMF), 58 allows identification of homogeneity in data sets while integration.”
Integrative Data Analysis of Multi-Platform Cancer Data with a Multimodal Deep Learning Approach (2015, methodology): “A practical learning algorithm, called contrastive divergence (CD), is applied to infer the parameters of our multimodal DBN model in an unsupervised manner.”
Machine Learning and Integrative Analysis of Biomedical Big Data (2019, methodology): “Unlike PCA in which decomposition matrices have both positive and negative values, the resulting matrices from NMF only have positive values; thus, original data is represented only by additive combinations of latent variables. t-distributed stochastic neighbor embedding (t-SNE) [37] is an FE algori”
More Is Better: Recent Progress in Multi-Omics Data Integration Methods (2017, background): “Zhang et al. proposed NMF framework for multi-omics data integration (Zhang et al., 2011, 2012).”
Integration strategies of multi-omics data for machine learning analysis (2021, methodology): “Among those methods, extensions of the widely used Non-negative Matrix Factorization (NMF) [131] have been developed including joint NMF [132] and integrative NMF [133,134].”
A review on machine learning principles for multi-view biological data integration (2016, methodology): “Similar to iCluster [77], MultiNMF [113] and EquiNMF [114] allow all views to share a unique coefficient matrix for collective clustering, while Joint-NMF [115] restricts all”