Lung adenocarcinoma and lung squamous cell carcinoma cancer classification, biomarker identification, and gene expression analysis using overlapping feature selection methods

Abstract

Lung cancer is one of the deadliest cancers in the world. Two of the most common subtypes, lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), have drastically different biological signatures, yet they are often treated similarly and classified together as non-small cell lung cancer (NSCLC). LUAD and LUSC biomarkers are scarce, and their distinct biological mechanisms have yet to be elucidated. To detect biologically relevant markers, many studies have attempted to improve traditional machine learning algorithms or develop novel algorithms for biomarker discovery. However, few have used overlapping machine learning or feature selection methods for cancer classification, biomarker identification, or gene expression analysis. This study proposes to use overlapping traditional feature selection or feature reduction techniques for cancer classification and biomarker discovery. The genes selected by the overlapping method were then verified using random forest. The classification statistics of the overlapping method were compared to those of the traditional feature selection methods. The identified biomarkers were validated in an external dataset using AUC and ROC analysis. Gene expression analysis was then performed to further investigate biological differences between LUAD and LUSC. Overall, our method achieved classification results comparable to, if not better than, the traditional algorithms. It also identified multiple known biomarkers, and five potentially novel biomarkers with high discriminating values between LUAD and LUSC. Many of the biomarkers also exhibit significant prognostic potential, particularly in LUAD. Our study also unraveled distinct biological pathways between LUAD and LUSC.

Analysis of Exosomal Cargo Provides Accurate Clinical, Histologic and Mutational Information in Non-Small Cell Lung Cancer

“…The present study confirmed three DEGs that were overexpressed in patients with LUAD compared with those with LUSC, and three DEGs that were downregulated in patients with LUAD compared with those with LUSC. However, there are currently limited available studies on effective molecular diagnostic markers of LUAD and LUSC [56,57]. For example, Luccheta et al used a robust statistical framework with the integration of diverse bioinformatics tools to analyze NGS data from more than 1000 patients from LUAD vs. LUSC [58].…”

Tumor Nonimmune-Microenvironment-Related Gene Expression Signature Predicts Brain Metastasis in Lung Adenocarcinoma Patients after Surgery: A Machine Learning Approach Using Gene Expression Profiling

“…AUC, accuracy, F1 score, precision, and recall were compared using four machine learning classifiers. Because all four machine learning classifiers have been used in many gene expression studies [93][94][95][96], it is difficult to know which classifier is suitable. Therefore, we used all four widely used machine learning classifiers.…”

Gangliosides as Biomarkers of Human Brain Diseases: Trends in Discovery and Characterization by High-Performance Mass Spectrometry

“…Almost 10% of the patients have brain metastases already at the time of LADC diagnosis, whereas up to 50% of patients will develop them during the course of the disease. LADC is the most widespread type of lung cancer (LC), accounting for about 30 percent of all LCs and half of all non-small cell LCs, the later form being the most common [ 209 ]. Typically, LADC grows in the outer region of the lungs, most often in the alveoli.…”