Subclass Mapping: Identifying Common Subtypes in Independent Disease Data Sets

By Yujin Hoshida, Jean-Philippe Brunet, Pablo Tamayo, Todd R. Golub, Jill P. Mesirov. PLoS ONE, 2007

552 citations recorded by the source corpus.

Whole genome expression profiles are widely used to discover molecular subtypes of diseases. A remaining challenge is to identify the correspondence or commonality of subtypes found in multiple, independent data sets generated on various platforms. While model-based supervised learning is often used to make these connections, the models can be biased to the training data set and thus miss inherent, relevant substructure in the test data. Here we describe an unsupervised subclass mapping method (SubMap), which reveals common subtypes between independent data sets. The subtypes within a data set can be determined by unsupervised clustering or given by predetermined phenotypes before applying SubMap. We define a measure of correspondence for subtypes and evaluate its significance building on our previous work on gene set enrichment analysis. The strength of the SubMap method is that it does not impose the structure of one data set upon another, but rather uses a bi-directional approach to highlight the common substructures in both. We show how this method can reveal the correspondence between several cancer-related data sets. Notably, it identifies common subtypes of breast cancer associated with estrogen receptor status, and a subgroup of lymphoma patients who share similar survival patterns, thus improving the accuracy of a clinical outcome predictor.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/3d3609aa1c279a27b657509813c7a140ecdf44d0

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

Multi-stage differentiation defines melanoma subtypes with differential vulnerability to drug-induced iron-dependent oxidative stress (2018, methodology): “We applied the SubMap subtype comparison tool (Hoshida et al., 2007) between the two datasets and found our identified clusters (C1–C4) show informative mapping relationships for all cohorts identified by Hoek et al. (2006), with C4 mapped to cohort A, C3 to both cohorts A and B, and C2–C1 to…”
Supervised, Unsupervised, and Semi-Supervised Feature Selection: A Review on Gene Selection (2016, unknown): “For example , Nie et al. [53] and Xiang et al. [54] implemented a robust feature selection with L 2;1 -norms, Du et al. [55] applied L 2 -norm penalty with augmented data technique, and Liang et al. [56] Better computational complexity than wrapper & Higher performance accuracy than filter & Less pr”
FABIA: factor analysis for bicluster acquisition (2010, methodology): “We consider three gene expression datasets that have been provided by the Broad Institute and were previously analyzed by Hoshida et al. (2007). They first clustered the samples using additional datasets and then confirmed the clusters by gene set enrichment analysis.”
Integrative Transcriptome Analysis Reveals Common Molecular Subclasses of Human Hepatocellular Carcinoma (2009, methodology): “were defined by subclass mapping (SubMap) method (12) based on”
Rank–rank hypergeometric overlap: identification of statistically significant overlap between gene-expression signatures (2010, methodology): “Alternatively, approaches such as subclass mapping allow the comparison of clusters of genes that have similar expression patterns within subsets of samples in different profiling experiments (5).”
Clustering Longitudinal Clinical Marker Trajectories from Electronic Health Data: Applications to Phenotyping and Endotype Discovery (2015, background): “2011; Kohane 2011), and allow medical scientists to view related diseases through a more fine-grained lens that can lead to insights that connect their causes and developmental pathways (Hoshida et al. 2007).”