On Predicting lung cancer subtypes using ‘omic’ data from tumor and tumor-adjacent histologically-normal tissue

Abstract

BackgroundAdenocarcinoma (ADC) and squamous cell carcinoma (SCC) are the most prevalent histological types among lung cancers. Distinguishing between these subtypes is critically important because they have different implications for prognosis and treatment. Normally, histopathological analyses are used to distinguish between the two, where the tissue samples are collected based on small endoscopic samples or needle aspirations. However, the lack of cell architecture in these small tissue samples hampers the process of distinguishing between the two subtypes.Molecular profiling can also be used to discriminate between the two lung cancer subtypes, on condition that the biopsy is composed of at least 50 % of tumor cells. However, for some cases, the tissue composition of a biopsy might be a mix of tumor and tumor-adjacent histologically normal tissue (TAHN). When this happens, a new biopsy is required, with associated cost, risks and discomfort to the patient. To avoid this problem, we hypothesize that a computational method can distinguish between lung cancer subtypes given tumor and TAHN tissue.MethodsUsing publicly available datasets for gene expression and DNA methylation, we applied four classification tasks, depending on the possible combinations of tumor and TAHN tissue. First, we used a feature selector (ReliefF/Limma) to select relevant variables, which were then used to build a simple naïve Bayes classification model. Then, we evaluated the classification performance of our models by measuring the area under the receiver operating characteristic curve (AUC). Finally, we analyzed the relevance of the selected genes using hierarchical clustering and IPA® software for gene functional analysis.ResultsAll Bayesian models achieved high classification performance (AUC > 0.94), which were confirmed by hierarchical cluster analysis. From the genes selected, 25 (93 %) were found to be related to cancer (19 were associated with ADC or SCC), confirming the biological relevance of our method.ConclusionsThe results from this study confirm that computational methods using tumor and TAHN tissue can serve as a prognostic tool for lung cancer subtype classification. Our study complements results from other studies where TAHN tissue has been used as prognostic tool for prostate cancer. The clinical implications of this finding could greatly benefit lung cancer patients.Electronic supplementary materialThe online version of this article (doi:10.1186/s12885-016-2223-3) contains supplementary material, which is available to authorized users.

Genome-Wide Plasma Cell-Free DNA Methylation Profiling Identifies Potential Biomarkers for Lung Cancer

“…We found 330 DMRs located in promoter regions (Figure 2(d)), including 33 hypermethylated regions and 297 hypomethylated regions (Table S3). Some genes with hypermethylated promoters have been reported in lung cancer, such as GAS7 [24], AQP10 [25], HLF [26], and HOPX [27].…”

Endometrial Cancer-Adjacent Tissues Express Higher Levels of Cancer-Promoting Genes than the Matched Tumors

“…As shown in breast and lung cancers, molecular changes in TA may relate to cancer subtype [ 7 , 8 ]. Molecular signatures of the extratumoral microenvironment predicted clinical outcome, e.g., in head and neck, breast, and hepatocellular cancers [ 9 , 10 , 11 ].…”

A Survey of Machine Learning Approaches Applied to Gene Expression Analysis for Cancer Prediction

“…This study failed to achieve the desired results (Table 1). Naïve Bayes and two feature selection methods (Reli-efF/Limma) were applied to classify different lung cancer subtypes [34]. This study used the gene expression dataset GDS3257, and DNA methylation data from TCGA.…”

“…This study is limited as it lacked evaluation of the model performance with prospective data. Pineda et al used gene expression (TCGA and GEO) and DNA methylation data (TCGA) to develop a classifier that effectively discriminated lung adenocarcinoma from lung squamous cell carcinoma cases[61].The dataset for both lung cancer subtypes were collected from[62][63][64]. They applied a feature selector (ReliefF/Limma) to select Four machine learning techniques were applied to four different sources of gene expression data for predicting lung cancer[33].…”