Artificial neural networks (ANNs) have been utilized for classification and prediction task with remarkable accuracy. However, its implications for unsupervised data mining using molecular data is under-explored. We found that embedding can extract biologically relevant information from The Cancer Genome Atlas (TCGA) gene expression dataset by learning a vector representation through gene co-occurrence. Ground truth relationship, such as cancer types of the input sample and semantic meaning of genes, were showed to retain in the resulting entity matrices. We also demonstrated the interpretability and usage of these matrices in shortlisting candidates from a long gene list as in the case of immunotherapy response. 73 related genes are singled out while the relatedness of 55 genes with immune checkpoint proteins (PD-1, PD-L1, and CTLA-4) are supported by literature. 16 novel genes (ACAP1, C11orf45, CD79B, CFP, CLIC2, CMPK2, CXCR2P1, CYTIP, FER, MCTO1, MMP25, RASGEF1B, SLFN12, TBC1D10C, TRAF3IP3, TTC39B) related to immune checkpoint proteins were identified. Thus, this method is feasible to mine big volume of biological data, and embedding would be a valuable tool to discover novel knowledge from omics data. The resulting embedding matrices mined from TCGA gene expression data are interactively explorable online (http://bit.ly/tcga-embedding-cancer) and could serve as an informative reference for gene relatedness in the context of cancer and is readily applicable to biomarker discovery of any molecular targeted therapy.
Lung cancer has the highest incidence and mortality rate worldwide among all malignancy-associated mortalities, of which non-small cell lung cancer accounts for 80% of all cases. Resistance against epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKIs) develops following 8–12 months of disease progression, and is a critical issue. HCC827 cell lines with resistance to EGFR-TKIs were successfully screened. The half maximal inhibitory concentration values were 1,000-fold higher than the values for the parental HCC827 cell line, thereby demonstrating cross-resistance against the same family of TKIs. The expression of B-cell lymphoma 2 (Bcl2) was markedly increased in the resistant clones, as well as in the patient biopsies. The phosphatase and tensin homolog phosphoinositide 3-kinase signaling axis is a potential mechanism for acquiring resistance, and therefore targeting Bcl2 may be a useful strategy for further investigations.
Running Title: infer related genes with embeddingAbstract Artificial neural networks (ANNs) have been utilized for classification and prediction task with remarkable accuracy. However, its implications for unsupervised data mining using molecular data is under-explored. We adopted a method of unsupervised ANN, namely word embedding, to extract biologically relevant information from TCGA gene expression dataset. Ground truth relationship, such as cancer types of the input sample and semantic meaning of genes, were showed to retain in the resulting entity matrices. We also demonstrated the interpretability and usage of these matrices in shortlisting candidates from a long gene list. This method is feasible to mine big volume of biological data, and would be a valuable tool to discover novel knowledge from omics data. The resulting embedding matrices mined from TCGA gene expression data are interactively explorable online (http://bit.ly/tcga-embeddingcancer) and could serve as an informative reference.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.