Hybrid Models Identified a 12-Gene Signature for Lung Cancer Prognosis and Chemoresponse Prediction

Abstract

BackgroundLung cancer remains the leading cause of cancer-related deaths worldwide. The recurrence rate ranges from 35–50% among early stage non-small cell lung cancer patients. To date, there is no fully-validated and clinically applied prognostic gene signature for personalized treatment.Methodology/Principal FindingsFrom genome-wide mRNA expression profiles generated on 256 lung adenocarcinoma patients, a 12-gene signature was identified using combinatorial gene selection methods, and a risk score algorithm was developed with Naïve Bayes. The 12-gene model generates significant patient stratification in the training cohort HLM & UM (n = 256; log-rank P = 6.96e-7) and two independent validation sets, MSK (n = 104; log-rank P = 9.88e-4) and DFCI (n = 82; log-rank P = 2.57e-4), using Kaplan-Meier analyses. This gene signature also stratifies stage I and IB lung adenocarcinoma patients into two distinct survival groups (log-rank P<0.04). The 12-gene risk score is more significant (hazard ratio = 4.19, 95% CI: [2.08, 8.46]) than other commonly used clinical factors except tumor stage (III vs. I) in multivariate Cox analyses. The 12-gene model is more accurate than previously published lung cancer gene signatures on the same datasets. Furthermore, this signature accurately predicts chemoresistance/chemosensitivity to Cisplatin, Carboplatin, Paclitaxel, Etoposide, Erlotinib, and Gefitinib in NCI-60 cancer cell lines (P<0.017). The identified 12 genes exhibit curated interactions with major lung cancer signaling hallmarks in functional pathway analysis. The expression patterns of the signature genes have been confirmed in RT-PCR analyses of independent tumor samples.Conclusions/SignificanceThe results demonstrate the clinical utility of the identified gene signature in prognostic categorization. With this 12-gene risk score algorithm, early stage patients at high risk for tumor recurrence could be identified for adjuvant chemotherapy; whereas stage I and II patients at low risk could be spared the toxic side effects of chemotherapeutic drugs.

Identification of a 12-Gene Signature for Lung Cancer Prognosis through Machine Learning

“…Three statistical methods were used in our study: two for selecting significant genes and one for validation of our signature, following the methodology used in [5].…”

“…In order to accomplish this classification, researchers have sought to identity gene signatures that can accurately predict lung cancer patients' risk status (high or low) and which clearly differentiate the high-and low-risk groups [5][6][7][8]. This classification process can be accomplished with the application of gene expression profiling or machine learning algorithms [5][6][7][8][9][10][11][12].…”

“…This classification process can be accomplished with the application of gene expression profiling or machine learning algorithms [5][6][7][8][9][10][11][12].…”

“…In [5], the gene datasets previously published in [7] were assessed with SAM Statistics and unequal variance t-tests. The genes selected by both tests were ranked by the Relief algorithm, which ranked the genes according to their prognostic accuracy and then executed a forward selection process where the top genes were added one at a time to the final gene signature until the next gene to be added did not increase classification accuracy.…”

“…We also added the constraint that our signature must have better classification accuracy than the signature reported in [5].…”