Test on existence of histology subtype-specific prognostic signatures among early stage lung adenocarcinoma and squamous cell carcinoma patients using a Cox-model based filter

Risk Stratification for Breast Cancer Patient by Simultaneous Learning of Molecular Subtype and Survival Outcome Using Genetic Algorithm-Based Gene Set Selection

Simple Summary

Patient stratification is clinically important because it allows us to understand the characteristics and establish treatment strategies for a group. Transcriptomic data play an important role in determining molecular subtypes and predicting survival. In the case of breast cancer, although the order of prognosis according to molecular subtypes is well known, there is heterogeneity even within a subtype. Therefore, patient stratification considering both molecular subtypes and survival outcomes is required. In this study, a methodology to handle this problem is presented. A genetic algorithm is used to select a set of genes, and a risk score is assigned to each patient using their expression level. According to the risk score, patients are ordered and stratified considering molecular subtypes and survival outcomes. Consequently, informative genes for patient stratification with respect to both aspects could be nominated, and the usefulness of the risk score was shown through comparison with other indicators.

Abstract

Patient stratification is a clinically important task because it allows us to establish and develop efficient treatment strategies for particular groups of patients. Molecular subtypes have been successfully defined using transcriptomic profiles, and they are used effectively in clinical practice, e.g., PAM50 subtypes of breast cancer. Survival prediction contributed to understanding diseases and also identifying genes related to prognosis. It is desirable to stratify patients considering these two aspects simultaneously. However, there are no methods for patient stratification that consider molecular subtypes and survival outcomes at once. Here, we propose a methodology to deal with the problem. A genetic algorithm is used to select a gene set from transcriptome data, and their expression quantities are utilized to assign a risk score to each patient. The patients are ordered and stratified according to the score. A gene set was selected by our method on a breast cancer cohort (TCGA-BRCA), and we examined its clinical utility using an independent cohort (SCAN-B). In this experiment, our method was successful in stratifying patients with respect to both molecular subtype and survival outcome. We demonstrated that the orders of patients were consistent across repeated experiments, and prognostic genes were successfully nominated. Additionally, it was observed that the risk score can be used to evaluate the molecular aggressiveness of individual patients.

Clinical and Prognostic Significance of CD117 in Non-Small Cell Lung Cancer: A Systemic Meta-Analysis

The aim of this study was to assess the relationship of cluster of differentiation 117 (CD117) expression with the clinicopathological characteristics and the prognosis in patients with non-small cell lung cancer (NSCLC). No meta-analysis concerning the correlation of CD117 expression with clinical and prognostic values of the patients with NSCLC is reported. A systematic literature search was conducted to achieve eligible studies. The combined odds ratios (ORs) or hazard ratios (HRs: multivariate Cox analysis) with their 95% confidence intervals (CIs) were calculated in this analysis. Final 17 eligible studies with 4,893 NSCLC patients using immunohistochemical detection were included in this meta-analysis. CD117 expression was not correlated with gender (male vs. female), clinical stage (stages 3-4 vs. stages 1-2), tumor grade (grade 3 vs. grades 1-2), T-stage (T-stages 3-4 vs. T-stages 0-2), distal metastasis, and disease-free survival (DFS) of NSCLC (all p values >0.05). CD117 expression was associated with lymph node metastasis (positive vs. negative: OR = 0.74, 95% CI = 0.56-0.97, p = 0.03), histological type (adenocarcinoma (AC) versus squamous cell carcinoma (SCC): OR = 1.74, 95% CI = 1.26-2.39, p = 0.001), and a worse overall survival (OS) (HR = 1.89, 95% CI = 1.22-2.92, p = 0.004). The expression of CD117 was significantly higher in AC than in SCC. CD117 may be an independent prognostic indicator for worse OS in NSCLC.

Radiomics-Based Features for Prediction of Histological Subtypes in Central Lung Cancer

Objectives

To evaluate the effectiveness of radiomic features on classifying histological subtypes of central lung cancer in contrast-enhanced CT (CECT) images.

Materials and Methods

A total of 200 patients with radiologically defined central lung cancer were recruited. All patients underwent dual-phase chest CECT, and the histological subtypes (adenocarcinoma (ADC), squamous cell carcinoma (SCC), small cell lung cancer (SCLC)) were confirmed by histopathological samples. 107 features were used in five machine learning classifiers to perform the predictive analysis among three subtypes. Models were trained and validated in two conditions: using radiomic features alone, and combining clinical features with radiomic features. The performance of the classification models was evaluated by the area under the receiver operating characteristic curve (AUC).

Results

The highest AUCs in classifying ADC vs. SCC, ADC vs. SCLC, and SCC vs. SCLC were 0.879, 0.836, 0.783, respectively by using only radiomic features in a feedforward neural network.

Conclusion

Our study indicates that radiomic features based on the CECT images might be a promising tool for noninvasive prediction of histological subtypes in central lung cancer and the neural network classifier might be well-suited to this task.

GEE-TGDR: A Longitudinal Feature Selection Algorithm and Its Application to lncRNA Expression Profiles for Psoriasis Patients Treated with Immune Therapies

With the fast evolution of high-throughput technology, longitudinal gene expression experiments have become affordable and increasingly common in biomedical fields. Generalized estimating equation (GEE) approach is a widely used statistical method for the analysis of longitudinal data. Feature selection is imperative in longitudinal omics data analysis. Among a variety of existing feature selection methods, an embedded method-threshold gradient descent regularization (TGDR)-stands out due to its excellent characteristics. An alignment of GEE with TGDR is a promising area for the purpose of identifying relevant markers that can explain the dynamic changes of outcomes across time. We proposed a new novel feature selection algorithm for longitudinal outcomes-GEE-TGDR. In the GEE-TGDR method, the corresponding quasilikelihood function of a GEE model is the objective function to be optimized, and the optimization and feature selection are accomplished by the TGDR method. Long noncoding RNAs (lncRNAs) are posttranscriptional and epigenetic regulators and have lower expression levels and are more tissue-specific compared with protein-coding genes. So far, the implication of lncRNAs in psoriasis remains largely unexplored and poorly understood even though some evidence in the literature supports that lncRNAs and psoriasis are highly associated. In this study, we applied the GEE-TGDR method to a lncRNA expression dataset that examined the response of psoriasis patients to immune treatments. As a result, a list including 10 relevant lncRNAs was identified with a predictive accuracy of 70% that is superior to the accuracies achieved by two competitive methods and meaningful biological interpretation. A widespread application of the GEE-TGDR method in omics longitudinal data analysis is anticipated.

Identification of long non-coding RNA signatures for squamous cell carcinomas and adenocarcinomas

Studies have demonstrated that both squamous cell carcinomas (SCCs) and adenocarcinomas (ACs) possess some common molecular characteristics. Evidence has accumulated to support the theory that long non-coding RNAs (lncRNAs) serve as novel biomarkers and therapeutic targets in complex diseases such as cancer.

In this study, we aimed to identify pan lncRNA signatures that are common to squamous cell carcinomas or adenocarcinomas with different tissues of origin. With the aid of elastic-net regularized regression models, a 35-lncRNA pan discriminative signature and an 11-lncRNA pan prognostic signature were identified for squamous cell carcinomas, whereas a 6-lncRNA pan discriminative signature and a 5-lncRNA pan prognostic signature were identified for adenocarcinomas. Among them, many well-known cancer relevant genes such as MALAT1 and PVT1 were included.

The identified pan lncRNA lists can help experimental biologists generate research hypotheses and adopt existing treatments for less prevalent cancers. Therefore, these signatures warrant further investigation.

The cox-filter method identifies respective subtype-specific lncRNA prognostic signatures for two human cancers

BACKGROUND

The most common histological subtypes of esophageal cancer are squamous cell carcinoma (ESCC) and adenocarcinoma (EAC). It has been demonstrated that non-marginal differences in gene expression and somatic alternation exist between these two subtypes; consequently, biomarkers that have prognostic values for them are expected to be distinct. In contrast, laryngeal squamous cell cancer (LSCC) has a better prognosis than hypopharyngeal squamous cell carcinoma (HSCC). Likewise, subtype-specific prognostic signatures may exist for LSCC and HSCC. Long non-coding RNAs (lncRNAs) hold promise for identifying prognostic signatures for a variety of cancers including esophageal cancer and head and neck squamous cell carcinoma (HNSCC).

METHODS

In this study, we applied a novel feature selection method capable of identifying specific prognostic signatures uniquely for each subtype - the Cox-filter method - to The Cancer Genome Atlas esophageal cancer and HSNCC RNA-Seq data, with the objectives of constructing subtype-specific prognostic lncRNA expression signatures for esophageal cancer and HNSCC.

RESULTS

By incorporating biological relevancy information, the lncRNA lists identified by the Cox-filter method were further refined. The resulting signatures include genes that are highly related to cancer, such as H19 and NEAT1, which possess perfect prognostic values for esophageal cancer and HNSCC, respectively.

CONCLUSIONS

The Cox-filter method is indeed a handy tool to identify subtype-specific prognostic lncRNA signatures. We anticipate the method will gain wider applications.

Radiomics for Classification of Lung Cancer Histological Subtypes Based on Nonenhanced Computed Tomography

OBJECTIVES

To evaluate the performance of using radiomics method to classify lung cancer histological subtypes based on nonenhanced computed tomography images.

MATERIALS AND METHODS

278 patients with pathologically confirmed lung cancer were collected, including 181 nonsmall cell lung cancer (NSCLC) and 97 small cell lung cancers (SCLC) patients. Among the NSCLC patients, 88 patients were adenocarcinomas (AD) and 93 patients were squamous cell carcinomas (SCC). In total, 1695 quantitative radiomic features (QRF) were calculated from the primary lung cancer tumor in each patient. To build radiomic classification model based on the extracted QRFs, several machine-learning algorithms were applied sequentially. First, unsupervised hierarchical clustering was used to exclude highly correlated QRFs; second, the minimum Redundancy Maximum Relevance feature selection algorithm was employed to select informative and nonredundant QRFs; finally, the Incremental Forward Search and Support Vector Machine classification algorithms were used to combine the selected QRFs and build the model. In our work, to study the phenotypic differences among lung cancer histological subtypes, four classification models were built. They were models of SCLC vs NSCLC, SCLC vs AD, SCLC vs SCC, and AD vs SCC. The performance of the classification models was evaluated by the area under the receiver operating characteristic curve (AUC) estimated by three-fold cross-validation.

RESULTS

The AUC (95% confidence interval) for the model of SCLC vs NSCLC was 0.741(0.678, 0.795). For the models of SCLC vs AD and SCLC vs SCC, the AUCs were 0.822(0.755, 0.875) and 0.665(0.583, 0.738), respectively. The AUC for the model of AD vs SCC was 0.655(0.570, 0.731). Several QRFs ("Law_15," "LoG_Uniformity," "GLCM_Contrast," and "Compactness Factor") that characterize tumor heterogeneity and shape were selected as the significant features to build the models.

CONCLUSION

Our results show that phenotypic differences exist among different lung cancer histological subtypes on nonenhanced computed tomography image.

Construction of subtype-specific prognostic gene signatures for early-stage non-small cell lung cancer using meta feature selection methods

Feature selection in the framework of meta-analyses (meta feature selection), combines meta-analysis with a feature selection process and thus allows meta-analysis feature selection across multiple datasets. In the present study, a meta feature selection procedure that fitted a multiple Cox regression model to estimate the effect size of a gene in individual studies and to identify the overall effect of the gene using a meta-analysis model was proposed. The method was used to identify prognostic gene signatures for lung adenocarcinoma and lung squamous cell carcinoma. Furthermore, redundant gene elimination (RGE) is of crucial importance during feature selection, and is also essential for a meta feature selection process. The current study demonstrated that the proposed meta feature selection procedure with RGE outperforms that without RGE in terms of predictive ability, model parsimony and biological interpretation.

Identification of monotonically differentially expressed genes for non-small cell lung cancer

Background

Monotonically expressed genes (MEGs) are genes whose expression values increase or decrease monotonically as a disease advances or time proceeds. Non-small cell lung cancer (NSCLC) is a multistage progression process resulting from genetic sequences mutations, the identification of MEGs for NSCLC is important.

Results

With the aid of a feature selection algorithm capable of identifying MEGs – the MFSelector method – two sets of potential MEGs were selected in this study: the MEGs across the different pathologic stages and the MEGs across the risk levels of death for the NSCLC patients at early stages. For the lung adenocarcinoma (AC) subtypes no statistically significant MEGs were identified across pathologic stages, however dozens of MEGs were identified across the risk levels of death. By contrast, for the squamous cell lung carcinoma (SCC) there were no statistically significant MEGs as either stage or risk level advanced.

Conclusions

The pathologic stage of non-small cell lung cancer patients at early stages has no prognostic value, making the identification of prognostic gene signatures for them more meaningful and highly desirable.

Radiomics for Classifying Histological Subtypes of Lung Cancer Based on Multiphasic Contrast-Enhanced Computed Tomography

OBJECTIVES

The aim of this study was to evaluate the performance of the radiomics method in classifying lung cancer histological subtypes based on multiphasic contrast-enhanced computed tomography (CT) images.

METHODS

A total of 229 patients with pathologically confirmed lung cancer were retrospectively recruited. All recruited patients underwent nonenhanced and dual-phase chest contrast-enhanced CT; 1160 quantitative radiomics features were calculated to build a radiomics classification model. The performance of the classification models was evaluated by the receiver operating characteristic curve.

RESULTS

The areas under the curve of radiomics models in classifying adenocarcinoma and squamous cell carcinoma, adenocarcinoma and small cell lung cancer, and squamous cell carcinoma and small cell lung cancer were 0.801, 0.857, and 0.657 (nonenhanced); 0.834, 0.855, and 0.619 (arterial phase); and 0.864, 0.864, and 0.664 (venous phase), respectively. Moreover, the application of contrast-enhanced CT may affect the selection of radiomics features.

CONCLUSIONS

Our study indicates that radiomics may be a promising tool for noninvasive predicting histological subtypes of lung cancer based on the multiphasic contrast-enhanced CT images.

FOXM1 is a novel predictor of recurrence in patients with oral squamous cell carcinoma associated with an increase in epithelial‑mesenchymal transition

Although forkhead box protein M1 (FOXM1) is markedly upregulated in human premalignant and oral squamous cell carcinoma (OSCC) tissues and cultured cells, the association of FOXM1 expression with OSCC prognosis is not well understood. The present study investigated the possible association of FOXM1 expression in patients with OSCC with their clinicopathological characteristics and clinical outcomes. The expression of FOXM1 protein in OSCC tissues from 119 patients was evaluated by immunohistochemistry, and the results demonstrated that FOXM1 overexpression in patients with OSCC was associated with tumour recurrence and poor prognosis. To study the in vitro effects of FOXM1, its expression was decreased by small interfering RNA (siRNA) in OSCC cell lines, and FOXM1 knockdown decreased the proliferative, migratory and invasive capacities of cells. FOXM1 inhibition by siRNA gave rise to reduced expression of vimentin and increased expression of E‑cadherin. The present study reported FOXM1 as a novel predictor of tumour recurrence in patients with OSCC and its potential involvement in epithelial‑mesenchymal transition in OSCC cells.

Identification of subtype-specific prognostic signatures using Cox models with redundant gene elimination

Lung cancer (LC) is a leading cause of cancer-associated mortalities worldwide. Adenocarcinoma (AC) and squamous cell carcinoma (SCC) account for ~70% of all cases of LC. Since AC and SCC are two distinct diseases, their corresponding prognostic genes associated with patient survival time are expected to be different. To date, only a few studies have distinguished patients with good prognosis from those with poor prognosis for each specific subtype. In the present study, the Cox filter model, a feature selection algorithm that identifies subtype-specific prognostic genes to incorporate pathway information and eliminate redundant genes, was adopted. By applying the proposed model to data on non-small cell lung cancer (NSCLC), it was demonstrated that both redundant gene elimination and search space restriction can improve the predictive capacity and the model stability of resulting prognostic gene signatures. To conclude, a pre-filtering procedure that incorporates pathway information for screening likely irrelevant genes prior to complex downstream analysis is recommended. Furthermore, a feature selection algorithm that considers redundant gene elimination may be preferable to one without such a consideration.

Esophageal squamous cell carcinoma transcriptome reveals the effect of FOXM1 on patient outcome through novel PIK3R3 mediated activation of PI3K signaling pathway

Esophageal squamous cell carcinoma (ESCC) presents poor prognosis, and patients diagnosed with this tumor currently lack target treatments. Therefore, in order to identify potential targets for ESCC treatment, we carried out a transcriptome analysis with ESCC and paired nonmalignant surrounding mucosa samples, followed by a master regulator analysis, and further explored the role of the identified central regulatory genes through in vivo and in vitro assays. Among the transcription factors deregulated/enriched in ESCC, we focused on FOXM1 because of its involvement in the regulation of critical biological processes. A new transcriptome analysis performed with ESCC cell lineage TE-1 showed that the modulation of FOXM1 expression resulted in PIK3R3 expression changes, whereas chromatin immunoprecipitation assay revealed that FOXM1 was capable of binding onto PIK3R3 promoter, thus demonstrating that PIK3R3 is a new FOXM1 target. Furthermore, FOXM1 overexpression resulted in the activation of PIK3/AKT signaling pathway through PIK3R3-mediated AKT phosphorylation. Finally, the analysis of the clinic-pathological data of ESCC patients revealed that overexpression of both FOXM1 and PIK3R3 was associated with poor prognosis, but only the latter was an independent prognosis factor for ESCC patients. In conclusion, our results show that FOXM1 seems to play a central role in ESCC carcinogenesis by upregulating many oncogenes found overexpressed in this tumor. Furthermore, PIK3R3 is a novel FOXM1 target that triggers the activation of the PI3K/AKT pathway in ESCC cells.

Classification and survival prediction for early-stage lung adenocarcinoma and squamous cell carcinoma patients

Non-small cell lung cancer (NSCLC) is a leading cause of cancer-associated mortality worldwide. Adenocarcinoma (AC) and squamous cell carcinoma (SCC) are two primary histological subtypes of NSCLC, accounting for ~70% of lung cancer cases. Increasing evidence suggests that AC and SCC differ in the composition of genes and molecular characteristics. Previous research has focused on distinguishing AC from SCC or predicting the NSCLC patient survival rates using gene expression profiles, usually with the aid of a feature selection method. The present study conducted a pre-filtering to identify the genes that have significant expression values and a high connection with other genes in the gene network, and then used the radial coordinate visualization method to identify relevant genes. By applying the proposed procedure to NSCLC data, it was demonstrated that there is a clear segmentation between AC and SCC, however not between patients with a good prognosis and bad prognosis. The focus of discriminating AC and SCC differs from survival prediction and there are almost no overlaps between the two gene signatures. Overall, a supervised learning method is preferred and future studies aiming to identify prognostic gene signatures with an increased prediction efficiency are required.

Identification of prognostic genes and gene sets for early-stage non-small cell lung cancer using bi-level selection methods

In contrast to feature selection and gene set analysis, bi-level selection is a process of selecting not only important gene sets but also important genes within those gene sets. Depending on the order of selections, a bi-level selection method can be classified into three categories – forward selection, which first selects relevant gene sets followed by the selection of relevant individual genes; backward selection which takes the reversed order; and simultaneous selection, which performs the two tasks simultaneously usually with the aids of a penalized regression model. To test the existence of subtype-specific prognostic genes for non-small cell lung cancer (NSCLC), we had previously proposed the Cox-filter method that examines the association between patients’ survival time after diagnosis with one specific gene, the disease subtypes, and their interaction terms. In this study, we further extend it to carry out forward and backward bi-level selection. Using simulations and a NSCLC application, we demonstrate that the forward selection outperforms the backward selection and other relevant algorithms in our setting. Both proposed methods are readily understandable and interpretable. Therefore, they represent useful tools for the researchers who are interested in exploring the prognostic value of gene expression data for specific subtypes or stages of a disease.

Classification of Non-Small Cell Lung Cancer Using Significance Analysis of Microarray-Gene Set Reduction Algorithm

Among non-small cell lung cancer (NSCLC), adenocarcinoma (AC), and squamous cell carcinoma (SCC) are two major histology subtypes, accounting for roughly 40% and 30% of all lung cancer cases, respectively. Since AC and SCC differ in their cell of origin, location within the lung, and growth pattern, they are considered as distinct diseases. Gene expression signatures have been demonstrated to be an effective tool for distinguishing AC and SCC. Gene set analysis is regarded as irrelevant to the identification of gene expression signatures. Nevertheless, we found that one specific gene set analysis method, significance analysis of microarray-gene set reduction (SAMGSR), can be adopted directly to select relevant features and to construct gene expression signatures. In this study, we applied SAMGSR to a NSCLC gene expression dataset. When compared with several novel feature selection algorithms, for example, LASSO, SAMGSR has equivalent or better performance in terms of predictive ability and model parsimony. Therefore, SAMGSR is a feature selection algorithm, indeed. Additionally, we applied SAMGSR to AC and SCC subtypes separately to discriminate their respective stages, that is, stage II versus stage I. Few overlaps between these two resulting gene signatures illustrate that AC and SCC are technically distinct diseases. Therefore, stratified analyses on subtypes are recommended when diagnostic or prognostic signatures of these two NSCLC subtypes are constructed.

Expression of Ribonucleotide Reductase Subunit-2 and Thymidylate Synthase Correlates with Poor Prognosis in Patients with Resected Stages I-III Non-Small Cell Lung Cancer

Biomarkers can help to identify patients with early-stages or locally advanced non-small cell lung cancer (NSCLC) who have high risk of relapse and poor prognosis. To correlate the expression of seven biomarkers involved in DNA synthesis and repair and in cell division with clinical outcome, we consecutively collected 82 tumour tissues from radically resected NSCLC patients. The following biomarkers were investigated using IHC and qRT-PCR: excision repair cross-complementation group 1 (ERCC1), breast cancer 1 (BRCA1), ribonucleotide reductase subunits M1 and M2 (RRM1 and RRM2), subunit p53R2, thymidylate synthase (TS), and class III beta-tubulin (TUBB3). Gene expression levels were also validated in an available NSCLC microarray dataset. Multivariate analysis identified the protein overexpression of RRM2 and TS as independent prognostic factors of shorter overall survival (OS). Kaplan-Meier analysis showed a trend in shorter OS for patients with RRM2, TS, and ERCC1, BRCA1 overexpressed tumours. For all of the biomarkers except TUBB3, the OS trends relative to the gene expression levels were in agreement with those relative to the protein expression levels. The NSCLC microarray dataset showed RRM2 and TS as biomarkers significantly associated with OS. This study suggests that high expression levels of RRM2 and TS might be negative prognostic factors for resected NSCLC patients.

Identification of Subtype-Specific Prognostic Genes for Early-Stage Lung Adenocarcinoma and Squamous Cell Carcinoma Patients Using an Embedded Feature Selection Algorithm

The existence of fundamental differences between lung adenocarcinoma (AC) and squamous cell carcinoma (SCC) in their underlying mechanisms motivated us to postulate that specific genes might exist relevant to prognosis of each histology subtype. To test on this research hypothesis, we previously proposed a simple Cox-regression model based feature selection algorithm and identified successfully some subtype-specific prognostic genes when applying this method to real-world data. In this article, we continue our effort on identification of subtype-specific prognostic genes for AC and SCC, and propose a novel embedded feature selection method by extending Threshold Gradient Descent Regularization (TGDR) algorithm and minimizing on a corresponding negative partial likelihood function. Using real-world datasets and simulated ones, we show these two proposed methods have comparable performance whereas the new proposal is superior in terms of model parsimony. Our analysis provides some evidence on the existence of such subtype-specific prognostic genes, more investigation is warranted.