Molecular profiling of thyroid cancer subtypes using large-scale text mining

Abstract

BackgroundThyroid cancer is the most common endocrine tumor with a steady increase in incidence. It is classified into multiple histopathological subtypes with potentially distinct molecular mechanisms. Identifying the most relevant genes and biological pathways reported in the thyroid cancer literature is vital for understanding of the disease and developing targeted therapeutics.ResultsWe developed a large-scale text mining system to generate a molecular profiling of thyroid cancer subtypes. The system first uses a subtype classification method for the thyroid cancer literature, which employs a scoring scheme to assign different subtypes to articles. We evaluated the classification method on a gold standard derived from the PubMed Supplementary Concept annotations, achieving a micro-average F1-score of 85.9% for primary subtypes. We then used the subtype classification results to extract genes and pathways associated with different thyroid cancer subtypes and successfully unveiled important genes and pathways, including some instances that are missing from current manually annotated databases or most recent review articles.ConclusionsIdentification of key genes and pathways plays a central role in understanding the molecular biology of thyroid cancer. An integration of subtype context can allow prioritized screening for diagnostic biomarkers and novel molecular targeted therapeutics. Source code used for this study is made freely available online at https://github.com/chengkun-wu/GenesThyCan.

Integrative enrichment analysis: a new computational method to detect dysregulated pathways in heterogeneous samples

“…Therefore, the expression variance focused by IEA is actually full of biological meaning, and will help IEA to detect new dysregulated pathways, e.g., subtype-relevant pathways. In addition, the complex diseases concerned in IEA-specific datasets actually already have reports about the existence of subtypes on genetic level, such as dilated cardiomyopathy [ 46 ], renal cancer [ 47 ], prostate cancer [ 48 ], colorectal cancer [ 49 ], and thyroid cancer [ 50 ]. Every method, or every method category, can actually capture particular dysregulated pathways.…”

InCoB2014: mining biological data from genomics for transforming industry and health

“…With pandemic viral infections spreading rapidly by jet travel, understanding cross-species transmissibility of vectors is addressed by Tan and co-workers [ 28 ] for influenza A, using a random forest approach. In the quest for diagnostic biomarkers and therapeutic targets, Nenadic and co-workers [ 29 ] have developed a novel text-mining approach to successfully identify novel genes and pathways for thyroid cancer subtypes. While gene-based cancer biomarkers are typically sets of hundreds or thousands of genes, Olsen et al [ 30 ] have analysed public proteogenomic data to zoom in on just 32 tumor antigenic proteins as biomarkers for invasive ductal carcinomas.…”

Constructing a molecular interaction network for thyroid cancer via large-scale text mining of gene and pathway events

“…More potential targeted drugs are under investigation or being tested in clinical trials [ 33 ]. We have used text mining to construct a molecular profiling (related genes and pathways) of thyroid cancer, classified by commonly seen subtypes [ 34 ]. This has provided a systematic basis for the molecular understanding of thyroid cancer.…”