Lung cancer is one of the leading causes of death worldwide. There are three major types of lung cancers, non-small cell lung cancer (NSCLC), small cell lung cancer (SCLC) and carcinoid. NSCLC is further classified into lung adenocarcinoma (LADC), squamous cell lung cancer (SQCLC) as well as large cell lung cancer. Many previous studies demonstrated that DNA methylation has emerged as potential lung cancer-specific biomarkers. However, whether there exists a set of DNA methylation markers simultaneously distinguishing such three types of lung cancers remains elusive. In the present study, ROC (Receiving Operating Curve), RFs (Random Forests) and mRMR (Maximum Relevancy and Minimum Redundancy) were proposed to capture the unbiased, informative as well as compact molecular signatures followed by machine learning methods to classify LADC, SQCLC and SCLC. As a result, a panel of 16 DNA methylation markers exhibits an ideal classification power with an accuracy of 86.54%, 84.6% and a recall 84.37%, 85.5% in the leave-one-out cross-validation (LOOCV) and independent data set test experiments, respectively. Besides, comparison results indicate that ensemble-based feature selection methods outperform individual ones when combined with the incremental feature selection (IFS) strategy in terms of the informative and compact property of features. Taken together, results obtained suggest the effectiveness of the ensemble-based feature selection approach and the possible existence of a common panel of DNA methylation markers among such three types of lung cancer tissue, which would facilitate clinical diagnosis and treatment.

The high frequency of epidermal growth factor receptor (EGFR) mutations in tyrosine kinase inhibitor-responsive non-small-cell lung cancer (NSCLC) cases is now well established, highlighting the predictive value of activating EGFR mutations in guiding the clinical use of EGFR-targeted therapies. However, specimen source and methods for EGFR mutation analysis are limited by tissue availability and technical feasibility in clinical application. Therefore, the current study is designed to establish a blood-based approach for the assessment of EGFR mutations in NSCLC patients, in particular the advanced stage, and to test its clinical application. Plasma samples were obtained from the enrolled 134 NSCLC patients. The detection rate of the EGFR exon19 deletions and exon21 L858R was 49.3% (66/134) by the blood-based, mutant-enriched polymerase chain reaction. In the paired tumor and plasma samples, the detected mutant types of each pair respectively by direct sequencing and mutant-enriched polymerase chain reaction were concordant in 17 of 18 (94.4%). In the patients treated with gefitinib as a second-line therapy, those with plasma EGFR mutation have a prolonged median progression-free survival compared with those with EGFR wild type (7.609 vs. 2.877 months, p 5 0.002). On comparing the efficacy of gefitinib with that of docetaxel, it was found that the median progression-free survival was significantly longer for patients treated with gefitinib than those with docetaxel in those harboring plasma EGFR mutation (7.609 vs. 3.192 months, p 5 0.006). These results suggest that the blood-based EGFR mutations test has the ability to provide a reliable guidance for clinical decision making for the treatment of the advanced NSCLC patients. ' 2009 UICC Key words: epidermal growth factor receptor; mutation; mutantenriched PCR assay; plasma; lung cancer Receptor tyrosine kinases play a key role in lung cancer tumorigenesis and progression. 1 Progress has been made in the treatment of advanced non-small-cell lung cancer (NSCLC) using smallmolecule tyrosine kinase inhibitors (TKIs) gefitinib and erlotinib, targeting epidermal growth factor receptor (EGFR). 2,3 EGFR kinase domain mutations, in particular exon19 deletions and exon21 (L858R), have been identified to be predictors of response to gefitinib/erlotinib. 4,5 These two mutations account for up to 90% of all EGFR mutations. Given the current knowledge in the field, two important issues have to be considered in the use of EGFR TKIs for NSCLC patients. One issue is the need to evaluate the application of TKIs as a first-line therapy for the patients with advanced NSCLC with EGFR activating mutations. Most recently, a Phase III, randomized, first-line study of gefitinib vs. carboplatin/paclitaxel was conducted in Asia with advanced NSCLC (IRE-SSA TM Pan ASia Study-IPASS) in which never or light ex-smokers with World Health Organization (WHO) performance status (PS) 0-2, adenocarcinoma histology and Stage IIIB/IV NSCLC were randomized to gefitinib (n 5 609) or carboplatin area...

No abstract

To understand the molecular mechanism of tumorigenesis of pulmonary lymphoepithelioma-like carcinoma and explore potential therapeutic strategies, we investigated the genomic profiles and PD-L1 expression of 29 Chinese pulmonary lymphoepithelioma-like carcinoma patients at various stages. We performed capture-based targeted sequencing on tissue samples collected from 27 patients with sufficient samples using a panel consisting of 520 cancer-related genes, spanning 1.64 Mb of the human genome. We identified 184 somatic mutations in 109 genes from 26 patients. One patient had no mutations detected by this panel. Copy number variations were detected in 52% (14/27) of the patients, with a majority having advancedstage disease (10/14). Except for the detection of ERBB2 amplification and KRAS mutation in two patients, no other classic lung cancer driver mutations were detected. Interestingly, 78% (21/27) of the patients had mutations in epigenetic regulators. Of the 184 mutations identified, 51 occurred in 29 epigenetics-related genes. Furthermore, we performed PD-L1 immunohistochemistry staining using the Dako 22C3 assay and demonstrated that 69% (20/29) of the cohort had positive PD-L1 expression, of which three patients received and benefited from a PD-1 inhibitor. In conclusion, we elucidated a distinct genomic landscape associated with pulmonary lymphoepithelioma-like carcinoma with no classic lung cancer driver mutation but an enrichment of mutations in epigenetic regulators. The detection of high PD-L1 expression and lack of any canonical druggable driver mutations raises the potential of checkpoint immunotherapy for pulmonary lymphoepithelioma-like carcinoma.