A novel point mutation in exon 20 of EGFR showed sensitivity to erlotinib

Feature set optimization in biomarker discovery from genome-scale data

MOTIVATION

Omics technologies have the potential to facilitate the discovery of new biomarkers. However, only few omics-derived biomarkers have been successfully translated into clinical applications to date. Feature selection is a crucial step in this process that identifies small sets of features with high predictive power. Models consisting of a limited number of features are not only more robust in analytical terms, but also ensure cost effectiveness and clinical translatability of new biomarker panels. Here we introduce GARBO, a novel multi-island adaptive genetic algorithm to simultaneously optimize accuracy and set size in omics-driven biomarker discovery problems.

RESULTS

Compared to existing methods, GARBO enables the identification of biomarker sets that best optimize the trade-off between classification accuracy and number of biomarkers. We tested GARBO and six alternative selection methods with two high relevant topics in precision medicine: cancer patient stratification and drug sensitivity prediction. We found multivariate biomarker models from different omics data types such as mRNA, miRNA, copy number variation, mutation and DNA methylation. The top performing models were evaluated by using two different strategies: the Pareto-based selection, and the weighted sum between accuracy and set size (w = 0.5). Pareto-based preferences show the ability of the proposed algorithm to search minimal subsets of relevant features that can be used to model accurate random forest-based classification systems. Moreover, GARBO systematically identified, on larger omics data types, such as gene expression and DNA methylation, biomarker panels exhibiting higher classification accuracy or employing a number of features much lower than those discovered with other methods. These results were confirmed on independent datasets.

AVAILABILITY AND IMPLEMENTATION

github.com/Greco-Lab/GARBO.

CONTACT

dario.greco@tuni.fi.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Clinicopathological features of Chinese lung cancer patients with epidermal growth factor receptor mutation

BACKGROUND

Epidermal growth factor receptor (EGFR) gene was the major causative gene of lung cancer and also the specific treatment target. It is necessary to analyze the genotype and phenotype characters of patients.

METHODS

We investigated 1,034 lung cancer patients in this study. The collected clinicopathological parameters included gender, age at diagnosis, smoking status, pathological TNM stage, tumor morphology and location, visceral pleural invasion as well as histological type.

RESULTS

Almost 50% participants had EGFR mutations. L858R in exon 21 was the most common type. Concomitant mutation, 19 del and L858R, were detected in 20 patients. Compared to patients with exon 19 del or L858R mutations solely, they were inclined to have small size adenocarcinomas which occurred in bilateral and invaded the visceral pleura. The tyrosine kinases inhibitors (TKIs)-resistant mutation, insertions in exon 20, was detected in 11 patients.

CONCLUSIONS

The summarized clinicopathological features will help clinicians to implement the feasible treatment plan.

Epidermal growth factor receptor exon 20 mutation in lung cancer: types, incidence, clinical features and impact on treatment

BACKGROUND

There are limited data available on the treatment and outcome of epidermal growth factor receptor (EGFR) exon 20-mutated lung cancer patients. Hence, we planned an analysis of the demographic details, clinical profile and survival of lung cancer patients with exon 20 mutations. We compared our results to patients with EGFR tyrosine kinase inhibitor (TKI)-sensitizing activating and EGFR/anaplastic lymphoma kinase (ALK)-negative mutations.

METHODS

This was a retrospective analysis of lung cancer patients who were treated at our center between January 2010 and August 2014. We reviewed the results of EGFR mutation testing by real-time polymerase chain reaction and Sanger sequencing. We also reviewed the data relating to baseline demographics, clinical profile, patient treatment and outcome measures in terms of response and overall survival (OS).

RESULTS

A total of 580 patients fulfilled the selection criteria. In all, 227 (39.1%) patients had EGFR TKI-sensitizing activating mutations, 20 (3.4%) patients had exon 20 insertion mutations and 333 patients were EGFR/ALK mutation negative (57.5%). The median OS was 5 months (95% confidence interval [CI] 0.17-9.8 months) in exon 20 insertion mutations, 16.1 months (95% CI 12.8-19.5 months) in EGFR TKI-sensitizing activating mutations and 10 months (95% CI 7.9-12.1 months) in EGFR/ALK mutation-negative patients. The median OS was significantly better for the EGFR TKI-sensitizing activating mutation group (P=0.000, log-rank test) and for the EGFR/ALK-negative group (P=0.037, log-rank test) compared to the exon 20-mutated group.

CONCLUSION

Exon 20 mutation results in a poorer OS prognosis compared to EGFR- and ALK-negative patients and patients harboring EGFR TKI-sensitizing activating mutations. The incidence of de novo exon 20 insertions was 3.4%. Different types of exon mutations seem to have different outcomes.

EGFR mutations as a prognostic and predictive marker in non-small-cell lung cancer

Non-small-cell lung cancer (NSCLC) has entered the age of individual treatment, and increasing point mutations of specific oncogenes and rearrangement of some chromosomes are biomarkers used to predict the therapeutic effect of targeted therapy. At present, there is a consensus among clinicians that epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs) have shown favorable efficacy in NSCLC patients with EGFR mutation, and some relevant research has suggested that the presence of EGFR mutations is a favorable prognostic marker. However, the association of EGFR mutation status with the responsiveness to conventional chemotherapy agents and survival in NSCLC patients is still unclear. This review provides an overview of and assesses the role of EGFR as a prognostic marker for postoperative patients and as a predictive marker for response to cytotoxic chemotherapy. In addition, we review the comparison of response to chemotherapy between EGFR mutations in exon 19 and in exon 21 and the predictive role of p.T790M mutation.