A Topic Modeling Analysis of TCGA Breast and Lung Cancer Transcriptomic Data

SIMPLE SUMMARY: Topic modeling was introduced to classify texts of natural language by inferring their topic structure from the frequency of words. This paper assumes that analogously the cancer subtype identity, which is crucial for the correct diagnosis and treatment plan, can be extracted from gene expression patterns with similar techniques. Focusing on breast and lung cancer, we show that state-of-the-art topic modeling techniques can successfully classify known subtypes and identify cohorts of patients with different survival probabilities. The topic structure hidden in expression data can be looked at as a biologically relevant low-dimensional data representation that can be used to build efficient classifiers of expression patterns. ABSTRACT: Topic modeling is a widely used technique to extract relevant information from large arrays of data. The problem of finding a topic structure in a dataset was recently recognized to be analogous to the community detection problem in network theory. Leveraging on this analogy, a new class of topic modeling strategies has been introduced to overcome some of the limitations of classical methods. This paper applies these recent ideas to TCGA transcriptomic data on breast and lung cancer. The established cancer subtype organization is well reconstructed in the inferred latent topic structure. Moreover, we identify specific topics that are enriched in genes known to play a role in the corresponding disease and are strongly related to the survival probability of patients. Finally, we show that a simple neural network classifier operating in the low dimensional topic space is able to predict with high accuracy the cancer subtype of a test expression sample.