Identification of a Sixteen-gene Prognostic Biomarker for Lung Adenocarcinoma Using a Machine Learning Method

Mortality prediction and influencing factors for intensive care unit patients with acute tubular necrosis: random survival forest and cox regression analysis

Background: Patients with acute tubular necrosis (ATN) not only have severe renal failure, but also have many comorbidities, which can be life-threatening and require timely treatment. Identifying the influencing factors of ATN and taking appropriate interventions can effectively shorten the duration of the disease to reduce mortality and improve patient prognosis. Methods: Mortality prediction models were constructed by using the random survival forest (RSF) algorithm and the Cox regression. Next, the performance of both models was assessed by the out-of-bag (OOB) error rate, the integrated brier score, the prediction error curve, and area under the curve (AUC) at 30, 60 and 90 days. Finally, the optimal prediction model was selected and the decision curve analysis and nomogram were established. Results: RSF model was constructed under the optimal combination of parameters (mtry = 10, nodesize = 88). Vasopressors, international normalized ratio (INR)_min, chloride_max, base excess_min, bicarbonate_max, anion gap_min, and metastatic solid tumor were identified as risk factors that had strong influence on mortality in ATN patients. Uni-variate and multivariate regression analyses were used to establish the Cox regression model. Nor-epinephrine, vasopressors, INR_min, severe liver disease, and metastatic solid tumor were identified as important risk factors. The discrimination and calibration ability of both predictive models were demonstrated by the OOB error rate and the integrated brier score. However, the prediction error curve of Cox regression model was consistently lower than that of RSF model, indicating that Cox regression model was more stable and reliable. Then, Cox regression model was also more accurate in predicting mortality of ATN patients based on the AUC at different time points (30, 60 and 90 days). The analysis of decision curve analysis shows that the net benefit range of Cox regression model at different time points is large, indicating that the model has good clinical effectiveness. Finally, a nomogram predicting the risk of death was created based on Cox model. Conclusion: The Cox regression model is superior to the RSF algorithm model in predicting mortality of patients with ATN. Moreover, the model has certain clinical utility, which can provide clinicians with some reference basis in the treatment of ATN and contribute to improve patient prognosis.

Identification of an 11-miRNA-regulated and surface-protein genes signature predicts the prognosis of lung adenocarcinoma based on multi-omics study

Lung adenocarcinoma (LUAD) is one of the most prevalent and lethal cancers worldwide, signifying a critical need for improved prognostic tools. A growing number of studies have highlighted the role of microRNAs (miRNAs) and their regulatory functions in tumorigenesis and cancer progression. In this context, we performed an extensive analysis of bulk RNA- and miRNA-sequencing to identify LUAD-associated prognostic genes. A risk score system based on 11 miRNA-regulated and surface-protein genes was developed, which was later validated by internally and externally using the Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO), respectively. Further single-cell RNA sequencing analysis revealed significant interactions between various cellular subpopulations within the tumor microenvironment, with the most pronounced differences observed between endothelial and epithelial cells. The mutational analysis highlighted TP53 as a key signaling pathway associated with the risk score. The study underscores that immune suppression, indicated by a positive association with regulatory T cells (Tregs) and an inverse correlation with M1-type macrophages, is prevalent in high-risk LUAD patients. These findings provide a promising prognostic tool for clinical outcomes of LUAD patients, facilitating future development of therapeutic strategies and enhancing our understanding of the regulatory function of miRNAs in LUAD.

Surrogate Biomarker Prediction from Whole-Slide Images for Evaluating Overall Survival in Lung Adenocarcinoma

BACKGROUND

Recent advances in computational pathology have shown potential in predicting biomarkers from haematoxylin and eosin (H&E) whole-slide images (WSI). However, predicting the outcome directly from WSIs remains a substantial challenge. In this study, we aimed to investigate how gene expression, predicted from WSIs, could be used to evaluate overall survival (OS) in patients with lung adenocarcinoma (LUAD).

METHODS

Differentially expressed genes (DEGs) were identified from The Cancer Genome Atlas (TCGA)-LUAD cohort. Cox regression analysis was performed on DEGs to identify the gene prognostics of OS. Attention-based multiple instance learning (AMIL) models were trained to predict the expression of identified prognostic genes from WSIs using the TCGA-LUAD dataset. Models were externally validated in the Clinical Proteomic Tumour Analysis Consortium (CPTAC)-LUAD dataset. The prognostic value of predicted gene expression values was then compared to the true gene expression measurements.

RESULTS

The expression of 239 prognostic genes could be predicted in TCGA-LUAD with cross-validated Pearson's R > 0.4. Predicted gene expression demonstrated prognostic performance, attaining a cross-validated concordance index of up to 0.615 in TCGA-LUAD through Cox regression. In total, 36 genes had predicted expression in the external validation cohort that was prognostic of OS.

CONCLUSIONS

Gene expression predicted from WSIs is an effective method of evaluating OS in patients with LUAD. These results may open up new avenues of cost- and time-efficient prognosis assessment in LUAD treatment.

AI/ML advances in non-small cell lung cancer biomarker discovery

Lung cancer is the leading cause of cancer deaths among both men and women, representing approximately 25% of cancer fatalities each year. The treatment landscape for non-small cell lung cancer (NSCLC) is rapidly evolving due to the progress made in biomarker-driven targeted therapies. While advancements in targeted treatments have improved survival rates for NSCLC patients with actionable biomarkers, long-term survival remains low, with an overall 5-year relative survival rate below 20%. Artificial intelligence/machine learning (AI/ML) algorithms have shown promise in biomarker discovery, yet NSCLC-specific studies capturing the clinical challenges targeted and emerging patterns identified using AI/ML approaches are lacking. Here, we employed a text-mining approach and identified 215 studies that reported potential biomarkers of NSCLC using AI/ML algorithms. We catalogued these studies with respect to BEST (Biomarkers, EndpointS, and other Tools) biomarker sub-types and summarized emerging patterns and trends in AI/ML-driven NSCLC biomarker discovery. We anticipate that our comprehensive review will contribute to the current understanding of AI/ML advances in NSCLC biomarker research and provide an important catalogue that may facilitate clinical adoption of AI/ML-derived biomarkers.

Predicting lung cancer survival based on clinical data using machine learning: A review

Machine learning has gained popularity in predicting survival time in the medical field. This review examines studies utilizing machine learning and data-mining techniques to predict lung cancer survival using clinical data. A systematic literature review searched MEDLINE, Scopus, and Google Scholar databases, following reporting guidelines and using the COVIDENCE system. Studies published from 2000 to 2023 employing machine learning for lung cancer survival prediction were included. Risk of bias assessment used the prediction model risk of bias assessment tool. Thirty studies were reviewed, with 13 (43.3%) using the surveillance, epidemiology, and end results database. Missing data handling was addressed in 12 (40%) studies, primarily through data transformation and conversion. Feature selection algorithms were used in 19 (63.3%) studies, with age, sex, and N stage being the most chosen features. Random forest was the predominant machine learning model, used in 17 (56.6%) studies. While the number of lung cancer survival prediction studies is limited, the use of machine learning models based on clinical data has grown since 2012. Consideration of diverse patient cohorts and data pre-processing are crucial. Notably, most studies did not account for missing data, normalization, scaling, or standardized data, potentially introducing bias. Therefore, a comprehensive study on lung cancer survival prediction using clinical data is needed, addressing these challenges.

Autoencoder-based multimodal prediction of non-small cell lung cancer survival

The ability to accurately predict non-small cell lung cancer (NSCLC) patient survival is crucial for informing physician decision-making, and the increasing availability of multi-omics data offers the promise of enhancing prognosis predictions. We present a multimodal integration approach that leverages microRNA, mRNA, DNA methylation, long non-coding RNA (lncRNA) and clinical data to predict NSCLC survival and identify patient subtypes, utilizing denoising autoencoders for data compression and integration. Survival performance for patients with lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) was compared across modality combinations and data integration methods. Using The Cancer Genome Atlas data, our results demonstrate that survival prediction models combining multiple modalities outperform single modality models. The highest performance was achieved with a combination of only two modalities, lncRNA and clinical, at concordance indices (C-indices) of 0.69 ± 0.03 for LUAD and 0.62 ± 0.03 for LUSC. Models utilizing all five modalities achieved mean C-indices of 0.67 ± 0.04 and 0.63 ± 0.02 for LUAD and LUSC, respectively, while the best individual modality performance reached C-indices of 0.64 ± 0.03 for LUAD and 0.59 ± 0.03 for LUSC. Analysis of biological differences revealed two distinct survival subtypes with over 900 differentially expressed transcripts.

Development and validation of a multimodal feature fusion prognostic model for lumbar degenerative disease based on machine learning: a study protocol

INTRODUCTION

Lumbar degenerative disease (LDD) is one of the most common reasons for patients to present with low back pain. Proper evaluation and treatment of patients with LDD are important, which clinicians perform using a variety of predictors for guidance in choosing the most appropriate treatment. Because evidence on which treatment is best for LDD is limited, the purpose of this study is to establish a clinical prediction model based on machine learning (ML) to accurately predict outcomes of patients with LDDs in the early stages by their clinical characteristics and imaging changes.

METHODS AND ANALYSIS

In this study, we develop and validate a clinical prognostic model to determine whether patients will experience complications within 6 months after percutaneous endoscopic lumbar discectomy (PELD). Baseline data will be collected from patients' electronic medical records. As of now, we have recruited a total of 580 participants (n=400 for development, n=180 for validation). The study's primary outcome will be the incidence of complications within 6 months after PELD. We will use an ML algorithm and a multiple logistic regression analysis model to screen factors affecting surgical efficacy. We will evaluate the calibration and differentiation performance of the model by the area under the curve. Sensitivity (Sen), specificity, positive predictive value and negative predictive value will be reported in the validation data set, with a target of 80% Sen. The results of this study could better illustrate the performance of the clinical prediction model, ultimately helping both clinicians and patients.

ETHICS AND DISSEMINATION

Ethical approval was obtained from the medical ethics committee of the Affiliated Hospital of Gansu University of Traditional Chinese Medicine (Lanzhou, China; No. 2022-57). Findings and related data will be disseminated in peer-reviewed journals, at conferences, and through open scientific frameworks.

TRIAL REGISTRATION NUMBER

Chinese Clinical Trial Register (www.chictr.org.cn) No. ChiCTR2200064421.

Bioinformatics, RNA sequencing, and targeted bisulfite sequencing analyses identify the role of PROM2 as a diagnostic and prognostic biomarker

OBJECTIVES

Prominin 2 (PROM2) gene has been reported as a molecular biomarker of human cancers; however, its role is still controversial. This study was therefore arranged to seek the role of PROM2 in different cancers with Bioinformatics and in vitro analyses.

METHODS

A combination of bioinformatics and molecular experiments.

RESULTS

Through the utilization of Bioinformatics analysis, it was observed that in 19 out of the 24 human cancers studied, there was a significant increase in the expression of PROM2 compared to the respective control samples. Additionally, the overexpression of PROM2 was linked specifically to a decrease in overall survival (OS) among breast cancer (BRCA), lung adenocarcinoma (LUAD), and uterine corpus endometrial carcinoma (UCEC) patients. Furthermore, advanced molecular investigations were conducted, encompassing RNA sequencing (RNA-seq) as well as targeted bisulfite sequencing (bisulfite-seq) assessments of PROM2. These analyses were performed across an array of lung cancer cell lines (A549, ABC-1, EBC-1, and LK-2) and a normal control lung cell line (MRC-9). Results of these analysis revealed overexpression and reduced methylation of PROM2 within lung cancer cell lines, relative to the corresponding control cell line. This suggests that PROM2 assumes a substantial function in the advancement and course of BRCA, LUAD, and UCEC cancers. Subsequent pathway analysis revealed that genes enriched by PROM2 are actively engaged in four pivotal pathways. Additionally, intriguing associations were observed between PROM2 expression, tumor purity, infiltration of CD8+ T immune cells, and genetic modifications. Moreover, we also predicted a few MicroRNAs (miRNAs), transcription factors (TFs), and potential drugs that could help to understand and better manage these cancers via designing appropriate therapies targeting PROM2.

CONCLUSION

Via this study, we effectively revealed PROM2 overexpression as a potential diagnostic and prognostic biomarker of survival in BRCA, LUAD, and UCEC.

Machine Learning Models for the Identification of Prognostic and Predictive Cancer Biomarkers: A Systematic Review

The identification of biomarkers plays a crucial role in personalized medicine, both in the clinical and research settings. However, the contrast between predictive and prognostic biomarkers can be challenging due to the overlap between the two. A prognostic biomarker predicts the future outcome of cancer, regardless of treatment, and a predictive biomarker predicts the effectiveness of a therapeutic intervention. Misclassifying a prognostic biomarker as predictive (or vice versa) can have serious financial and personal consequences for patients. To address this issue, various statistical and machine learning approaches have been developed. The aim of this study is to present an in-depth analysis of recent advancements, trends, challenges, and future prospects in biomarker identification. A systematic search was conducted using PubMed to identify relevant studies published between 2017 and 2023. The selected studies were analyzed to better understand the concept of biomarker identification, evaluate machine learning methods, assess the level of research activity, and highlight the application of these methods in cancer research and treatment. Furthermore, existing obstacles and concerns are discussed to identify prospective research areas. We believe that this review will serve as a valuable resource for researchers, providing insights into the methods and approaches used in biomarker discovery and identifying future research opportunities.

Construction of the model for predicting prognosis by key genes regulating EGFR-TKI resistance

Background: Previous studies have suggested that patients with lung adenocarcinoma (LUAD) will significantly benefit from epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKI). However, many LUAD patients will develop resistance to EGFR-TKI. Thus, our study aims to develop models to predict EGFR-TKI resistance and the LUAD prognosis. Methods: Two Gene Expression Omnibus (GEO) datasets (GSE31625 and GSE34228) were used as the discovery datasets to find the common differentially expressed genes (DEGs) in EGFR-TKI resistant LUAD profiles. The association of these common DEGs with LUAD prognosis was investigated in The Cancer Genome Atlas (TCGA) database. Moreover, we constructed the risk score for prognosis prediction of LUAD by LASSO analysis. The performance of the risk score for predicting LUAD prognosis was calculated using an independent dataset (GSE37745). A random forest model by risk score genes was trained in the training dataset, and the diagnostic ability for distinguishing sensitive and EGFR-TKI resistant samples was validated in the internal testing dataset and external testing datasets (GSE122005, GSE80344, and GSE123066). Results: From the discovery datasets, 267 common upregulated genes and 374 common downregulated genes were identified. Among these common DEGs, there were 59 genes negatively associated with prognosis, while 21 genes exhibited positive correlations with prognosis. Eight genes (ABCC2, ARL2BP, DKK1, FUT1, LRFN4, PYGL, SMNDC1, and SNAI2) were selected to construct the risk score signature. In both the discovery and independent validation datasets, LUAD patients with the higher risk score had a poorer prognosis. The nomogram based on risk score showed good performance in prognosis prediction with a C-index of 0.77. The expression levels of ABCC2, ARL2BP, DKK1, LRFN4, PYGL, SMNDC1, and SNAI2 were positively related to the resistance of EGFR-TKI. However, the expression level of FUT1 was favorably correlated with EGFR-TKI responsiveness. The RF model worked wonderfully for distinguishing sensitive and resistant EGFR-TKI samples in the internal and external testing datasets, with predictive area under the curves (AUC) of 0.973 and 0.817, respectively. Conclusion: Our investigation revealed eight genes associated with EGFR-TKI resistance and provided models for EGFR-TKI resistance and prognosis prediction in LUAD patients.

SurviveAI: Long Term Survival Prediction of Cancer Patients Based on Somatic RNA-Seq Expression

Motivation

Prediction of cancer outcome is a major challenge in oncology and is essential for treatment planning. Repositories such as The Cancer Genome Atlas (TCGA) contain vast amounts of data for many types of cancers. Our goal was to create reliable prediction models using TCGA data and validate them using an external dataset.

Results

For 16 TCGA cancer type cohorts we have optimized a Random Forest prediction model using parameter grid search followed by a backward feature elimination loop for dimensions reduction. For each feature that was removed, the model was retrained and the area under the curve of the receiver operating characteristic (AUC-ROC) was calculated using test data. Five prediction models gave AUC-ROC bigger than 80%. We used Clinical Proteomic Tumor Analysis Consortium v3 (CPTAC3) data for validation. The most enriched pathways for the top models were those involved in basic functions related to tumorigenesis and organ development. Enrichment for 2 prediction models of the TCGA-KIRP cohort was explored, one with 42 genes (AUC-ROC = 0.86) the other is composed of 300 genes (AUC-ROC = 0.85). The most enriched networks for both models share only 5 network nodes: DMBT1, IL11, HOXB6, TRIB3, PIM1. These genes play a significant role in renal cancer and might be used for prognosis prediction and as candidate therapeutic targets.

Availability And Implementation

The prediction models were created and tested using Python SciKit-Learn package. They are freely accessible via a friendly web interface we called surviveAI at https://tinyurl.com/surviveai.

A novel epithelial-mesenchymal transition (EMT)-related gene signature of predictive value for the survival outcomes in lung adenocarcinoma

Lung adenocarcinoma (LUAD) is a remarkably heterogeneous and aggressive disease with dismal prognosis of patients. The identification of promising prognostic biomarkers might enable effective diagnosis and treatment of LUAD. Aberrant activation of epithelial-mesenchymal transition (EMT) is required for LUAD initiation, progression and metastasis. With the purpose of identifying a robust EMT-related gene signature (E-signature) to monitor the survival outcomes of LUAD patients. In The Cancer Genome Atlas (TCGA) database, least absolute shrinkage and selection operator (LASSO) analysis and cox regression analysis were conducted to acquire prognostic and EMT-related genes. A 4 EMT-related and prognostic gene signature, comprising dickkopf-like protein 1 (DKK1), lysyl oxidase-like 2 (LOXL2), matrix Gla protein (MGP) and slit guidance ligand 3 (SLIT3), was identified. By the usage of datum derived from TCGA database and Western blotting analysis, compared with adjacent tissue samples, DKK1 and LOXL2 protein expression in LUAD tissue samples were significantly higher, whereas the trend of MGP and SLIT3 expression were opposite. Concurrent with upregulation of epithelial markers and downregulation of mesenchymal markers, knockdown of DKK1 and LOXL2 impeded the migration and invasion of LUAD cells. Simultaneously, MGP and SLIT3 silencing promoted metastasis and induce EMT of LUAD cells. In the TCGA-LUAD set, receiver operating characteristic (ROC) analysis indicated that our risk model based on the identified E-signature was superior to those reported in literatures. Additionally, the E-signature carried robust prognostic significance. The validity of prediction in the E-signature was validated by the three independent datasets obtained from Gene Expression Omnibus (GEO) database. The probabilistic nomogram including the E-signature, pathological T stage and N stage was constructed and the nomogram demonstrated satisfactory discrimination and calibration. In LUAD patients, the E-signature risk score was associated with T stage, N stage, M stage and TNM stage. GSEA (gene set enrichment analysis) analysis indicated that the E-signature might be linked to the pathways including GLYCOLYSIS, MYC TARGETS, DNA REPAIR and so on. In conclusion, our study explored an innovative EMT based prognostic signature that might serve as a potential target for personalized and precision medicine.

A feature selection-based framework to identify biomarkers for cancer diagnosis: A focus on lung adenocarcinoma

Lung cancer (LC) represents most of the cancer incidences in the world. There are many types of LC, but Lung Adenocarcinoma (LUAD) is the most common type. Although RNA-seq and microarray data provide a vast amount of gene expression data, most of the genes are insignificant to clinical diagnosis. Feature selection (FS) techniques overcome the high dimensionality and sparsity issues of the large-scale data. We propose a framework that applies an ensemble of feature selection techniques to identify genes highly correlated to LUAD. Utilizing LUAD RNA-seq data from the Cancer Genome Atlas (TCGA), we employed mutual information (MI) and recursive feature elimination (RFE) feature selection techniques along with support vector machine (SVM) classification model. We have also utilized Random Forest (RF) as an embedded FS technique. The results were integrated and candidate biomarker genes across all techniques were identified. The proposed framework has identified 12 potential biomarkers that are highly correlated with different LC types, especially LUAD. A predictive model has been trained utilizing the identified biomarker expression profiling and performance of 97.99% was achieved. In addition, upon performing differential gene expression analysis, we could find that all 12 genes were significantly differentially expressed between normal and LUAD tissues, and strongly correlated with LUAD according to previous reports. We here propose that using multiple feature selection methods effectively reduces the number of identified biomarkers and directly affects their biological relevance.

Construction of Lymph Node Metastasis-Related Prognostic Model and Analysis of Immune Infiltration Mode in Lung Adenocarcinoma

Background

Lung adenocarcinoma (LUAD) is a major cause for global cancer-related deaths. Research reports demonstrate that lymph node metastasis (LNM) is pertinent to the survival rate of LUAD patients, and crux lies in the lack of biomarkers that could distinguish patients with LNM. We aimed to verify the LNM-related prognostic biomarkers in LUAD.

Methods

We firstly accessed the expression data of mRNA from The Cancer Genome Atlas (TCGA) database and then obtained samples with LNM (N+) and without LNM (N-). Differential expression analysis was conducted to acquire differentially expressed genes (DEGs). Univariate-LASSO-multivariate Cox regression analyses were performed on DEGs to build a risk model and obtain optimal genes. Afterwards, effectiveness and independence of risk model were assessed based on TCGA-LUAD and GSE31210 datasets. Moreover, a nomogram was established combining clinical factors and riskscores. Nomogram performance was measured by calibration curves. The infiltration abundance of immune cells was scored with CIBERSORT to explore the differences between high- and low-risk groups. Lastly, gene set enrichment analysis (GSEA) was used to investigate differences in immune features between the two risk groups.

Results

Nine optimal feature genes closely related to LNM in LUAD were identified to construct a risk model. Prognostic ability of the risk model was verified in independent databases. Patients were classified into high- and low-risk groups in accordance with their median riskscores. CIBERSORT score displayed differences in immune cell infiltration like T cells CD4 memory resting between high/low-risk groups. LNM-related genes may also be closely relevant to immune features. Additionally, GSEA indicated that differential genes in the two risk groups were enriched in genes related to immune cells.

Conclusion

This research built a risk model including nine optimal feature genes, which may be potential biomarkers for LUAD.

Predicting the Lung Adenocarcinoma and Its Biomarkers by Integrating Gene Expression and DNA Methylation Data

The early symptoms of lung adenocarcinoma patients are inapparent, and the clinical diagnosis of lung adenocarcinoma is primarily through X-ray examination and pathological section examination, whereas the discovery of biomarkers points out another direction for the diagnosis of lung adenocarcinoma with the development of bioinformatics technology. However, it is not accurate and trustworthy to diagnose lung adenocarcinoma due to omics data with high-dimension and low-sample size (HDLSS) features or biomarkers produced by utilizing only single omics data. To address the above problems, the feature selection methods of biological analysis are used to reduce the dimension of gene expression data (GSE19188) and DNA methylation data (GSE139032, GSE49996). In addition, the Cartesian product method is used to expand the sample set and integrate gene expression data and DNA methylation data. The classification is built by using a deep neural network and is evaluated on K-fold cross validation. Moreover, gene ontology analysis and literature retrieving are used to analyze the biological relevance of selected genes, TCGA database is used for survival analysis of these potential genes through Kaplan-Meier estimates to discover the detailed molecular mechanism of lung adenocarcinoma. Survival analysis shows that COL5A2 and SERPINB5 are significant for identifying lung adenocarcinoma and are considered biomarkers of lung adenocarcinoma.

Potential Impact of Cancer Susceptibility Genes on Lung Cancer Metastasis

Background. Studies of prognosis-related molecular markers are an important tool to uncover the mechanism of tumour metastasis. Cancer susceptibility gene testing is an important tool for genetic counselling of cancer risk. However, the impact of lung cancer susceptibility genes (LCSGs) on lung cancer metastasis and prognosis has not been well studied. Methods. The list of lung cancer susceptibility genes was retrospectively analysed and updated. After expression profiling and functional analysis, LCSG-based signatures for prognosis were identified by Cox regression and LASSO regression analyses. For translational purposes, nomograms integrating LCSGs and clinical characteristics were constructed. Results. A total of 301 LCSGs were employed for modelling. For lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), 10-gene and 7-gene signatures were created and independently validated. The LCSG-based risk score could stratify LUAD survival (univariate: hazard ratio $\left(\text{HR}\right)=1.076$ , 95% confidence interval $\left(\text{CI}\right)=1.049$ –1.103, $P<0.001$ ; multivariate: $\text{HR}=1.066$ , 95% $\text{CI}=1.037$ –1.095, $P<0.001$ ) and LUSC survival (univariate: $\text{HR}=1.149$ , 95% $\text{CI}=1.066$ −1.239, $P<0.001$ ; multivariate: $\text{HR}=1.129$ , 95% $\text{CI}=1.038$ −1.228, $P=0.005$ ). One of the processes affected by differentially expressed genes in both LUAD and LUSC was the negative regulation of epithelial cell differentiation. Conclusions. Overall, novel LCSG-based gene signatures for LUAD and LUSC were constructed. These findings could expand the understanding of the impact of LCSG expression on cancer metastasis and prognosis.

Methylation- and homologous recombination deficiency-related mutant genes predict the prognosis of lung adenocarcinoma

Background

Lung adenocarcinoma (LUAD) is a lung cancer subtype with poor prognosis. We investigated the prognostic value of methylation‐ and homologous recombination deficiency (HRD)‐associated gene signatures in LUAD.

Methods

Data on RNA sequencing, somatic mutations, and methylation were obtained from TCGA database. HRD scores were used to stratify patients with LUAD into high and low HRD groups and identify differentially mutated and expressed genes (DMEGs). Pearson correlation analysis between DMEGs and methylation yielded methylation‐associated DMEGs. Cox regression analysis was used to construct a prognostic model, and the distribution of clinical features in the high‐ and low‐risk groups was compared.

Results

Patients with different HRD scores showed different DNA mutation patterns. There were 272 differentially mutated genes and 6294 differentially expressed genes. Fifty‐seven DMEGs were obtained; the top 10 upregulated genes were COL11A1, EXO1, ASPM, COL12A1, COL2A1, COL3A1, COL5A2, DIAPH3, CAD, and SLC25A13, while the top 10 downregulated genes were C7, ERN2, DLC1, SCN7A, SMARCA2, CARD11, LAMA2, ITIH5, FRY, and EPHB6. Forty‐two DMEGs were negatively correlated with 259 methylation sites. Gene ontology and pathway enrichment analysis of the DMEGs revealed enrichment of loci involved in extracellular matrix‐related remodeling and signaling. Six out of the 42 methylation‐associated DMEGs were significantly associated with LUAD prognosis and included in the prognostic model. The model effectively stratified high‐ and low‐risk patients, with the high‐risk group having more patients with advanced stage disease.

Conclusion

We developed a novel prognostic model for LUAD based on methylation and HRD. Methylation‐associated DMEGs may function as biomarkers and therapeutic targets for LUAD. Further studies are needed to elucidate their roles in LUAD carcinogenesis.

Establishment and Validation of a Ferroptosis-Related Gene Signature to Predict Overall Survival in Lung Adenocarcinoma

Background: Lung adenocarcinoma (LUAD) is the most common and lethal subtype of lung cancer. Ferroptosis, an iron-dependent form of regulated cell death, has emerged as a target in cancer therapy. However, the prognostic value of ferroptosis-related genes (FRGs)x in LUAD remains to be explored.

Methods: In this study, we used RNA sequencing data and relevant clinical data from The Cancer Genome Atlas (TCGA) dataset and Gene Expression Omnibus (GEO) dataset to construct and validate a prognostic FRG signature for overall survival (OS) in LUAD patients and defined potential biomarkers for ferroptosis-related tumor therapy.

Results: A total of 86 differentially expressed FRGs were identified from LUAD tumor tissues versus normal tissues, of which 15 FRGs were significantly associated with OS in the survival analysis. Through the LASSO Cox regression analysis, a prognostic signature including 11 FRGs was established to predict OS in the TCGA tumor cohort. Based on the median value of risk scores calculated according to the signature, patients were divided into high-risk and low-risk groups. Kaplan–Meier analysis indicated that the high-risk group had a poorer OS than the low-risk group. The area under the curve of this signature was 0.74 in the TCGA tumor set, showing good discrimination. In the GEO validation set, the prognostic signature also had good predictive performance. Functional enrichment analysis showed that some immune-associated gene sets were significantly differently enriched in two risk groups.

Conclusion: Our study unearthed a novel ferroptosis-related gene signature for predicting the prognosis of LUAD, and the signature may provide useful prognostic biomarkers and potential treatment targets.

Switched alternative splicing events as attractive features in lung squamous cell carcinoma

Background

Alternative splicing (AS) plays important roles in transcriptome and proteome diversity. Its dysregulation has a close affiliation with oncogenic processes. This study aimed to evaluate AS-based biomarkers by machine learning algorithms for lung squamous cell carcinoma (LUSC) patients.

Method

The Cancer Genome Atlas (TCGA) database and TCGA SpliceSeq database were utilized. After data composition balancing, Boruta feature selection and Spearman correlation analysis were used for differentially expressed AS events. Random forests and a nested fivefold cross-validation were applied for lymph node metastasis (LNM) classifier building. Random survival forest combined with Cox regression model was performed for a prognostic model, based on which a nomogram was developed. Functional enrichment analysis and Spearman correlation analysis were also conducted to explore underlying mechanisms. The expression of some switch-involved AS events along with parent genes was verified by qRT-PCR with 20 pairs of normal and LUSC tissues.

Results

We found 16 pairs of splicing events from same parent genes which were strongly related to the splicing switch (intrapair correlation coefficient = − 1). Next, we built a reliable LNM classifier based on 13 AS events as well as a nice prognostic model, in which switched AS events behaved prominently. The qRT-PCR presented consistent results with previous bioinformatics analysis, and some AS events like ITIH5-10715-AT and QKI-78404-AT showed remarkable detection efficiency for LUSC.

Conclusion

AS events, especially switched ones from the same parent genes, could provide new insights into the molecular diagnosis and therapeutic drug design of LUSC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12935-021-02429-2.

XGBLC: an improved survival prediction model based on XGBoost

MOTIVATION

Survival analysis using gene expression profiles plays a crucial role in the interpretation of clinical research and assessment of disease therapy programs. Several prediction models have been developed to explore the relationship between patients' covariates and survival. However, the high-dimensional genomic features limit the prediction performance of the survival model. Thus, an accurate and reliable prediction model is necessary for survival analysis using high-dimensional genomic data.

RESULTS

In this study, we proposed an improved survival prediction model based on XGBoost framework called XGBLC, which used Lasso-Cox to enhance the ability to analyze high-dimensional genomic data. The novel first- and second-order gradient statistics of Lasso-Cox were defined to construct the loss function of XGBLC. We extensively tested our XGBLC algorithm on both simulated and real-world datasets, and estimated the performance of models with 5-fold cross-validation. Based on 20 cancer datasets from The Cancer Genome Atlas (TCGA), XGBLC outperforms five state-of-the-art survival methods in terms of C-index, Brier score and AUC. The results show that XGBLC still keeps good accuracy and robustness by comparing the performance on the simulated datasets with different scales. The developed prediction model would be beneficial for physicians to understand the effects of patient's genomic characteristics on survival and make personalized treatment decisions.

AVAILABILITY AND IMPLEMENTATION

The implementation of XGBLC algorithm based on R language is available at: https://github.com/lab319/XGBLC.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Antitumor efficacy of XPO1 inhibitor Selinexor in KRAS-mutant lung adenocarcinoma patient-derived xenografts

Gain-of-function Kirsten rat sarcoma viral oncogene homolog (KRAS) mutations occur in 25% of lung adenocarcinomas, and these tumors are challenging to treat. Some preclinical work, largely based on cell lines, suggested KRASmut lung cancers are especially dependent on the nuclear export protein exportin-1 (XPO1), while other work supports XPO1 being a broader cancer dependency. To investigate the sensitivity of KRASmut lung cancers to XPO1 inhibition in models that more closely match clinical tumors, we treated 10 independently established lung cancer patient-derived tumor xenografts (PDXs) with the clinical XPO1 inhibitor, Selinexor. Monotherapy with Selinexor reduced tumor growth in all KRASmut PDXs, which included 4 different codon mutations, and was more effective than the clinical MEK1/2 inhibitor, Trametinib. Selinexor was equally effective in KRASG12C and KRASG12D tumors, with TP53 mutations being a biomarker for a weaker drug response. By mining genome-wide dropout datasets, we identified XPO1 as a universal cancer cell dependency and confirmed this functionally in two KRASWT PDX models harboring kinase drivers. However, targeted kinase inhibitors were more effective than Selinexor in these models. Our findings support continued investigation of XPO1 inhibitors in KRASmut lung adenocarcinoma, regardless of the codon alteration.

Non-small-cell lung cancer classification via RNA-Seq and histology imaging probability fusion

BACKGROUND

Adenocarcinoma and squamous cell carcinoma are the two most prevalent lung cancer types, and their distinction requires different screenings, such as the visual inspection of histology slides by an expert pathologist, the analysis of gene expression or computer tomography scans, among others. In recent years, there has been an increasing gathering of biological data for decision support systems in the diagnosis (e.g. histology imaging, next-generation sequencing technologies data, clinical information, etc.). Using all these sources to design integrative classification approaches may improve the final diagnosis of a patient, in the same way that doctors can use multiple types of screenings to reach a final decision on the diagnosis. In this work, we present a late fusion classification model using histology and RNA-Seq data for adenocarcinoma, squamous-cell carcinoma and healthy lung tissue.

RESULTS

The classification model improves results over using each source of information separately, being able to reduce the diagnosis error rate up to a 64% over the isolate histology classifier and a 24% over the isolate gene expression classifier, reaching a mean F1-Score of 95.19% and a mean AUC of 0.991.

CONCLUSIONS

These findings suggest that a classification model using a late fusion methodology can considerably help clinicians in the diagnosis between the aforementioned lung cancer cancer subtypes over using each source of information separately. This approach can also be applied to any cancer type or disease with heterogeneous sources of information.

N6-Methyladenosine-Regulated mRNAs: Potential Prognostic Biomarkers for Patients With Lung Adenocarcinoma

Aberrant regulation of m6A mRNA modification can lead to changes in gene expression, thus contributing to tumorigenesis in several types of solid tumors. In this study, by integrating analyses of m6A methylation and mRNA expression, we identified 84 m6A-regulated mRNAs in lung adenocarcinoma (LUAD). Although the m6A methylation levels of total RNA in LUAD patient tumor tissue were reduced, the majority (75.2%) of m6A-regulated mRNAs were hypermethylated. The m6A-hypermethylated mRNAs were mainly enriched in terms related to transcription factor activity. We established a 10-m6A-regulated-mRNA signature score system through least absolute shrinkage and selection operator Cox regression analysis, with its predictive value validated by Kaplan–Meier curve and time-dependent receiver operating characteristic curves. RFXAP and KHDRBS2 from the signature also exhibited an independent prognostic value. The co-expression and interaction network analyses demonstrated the strong correlation between m6A regulators and the genes in the signature, further supporting the results of the m6A methylation modification patterns. These findings highlight the potential utility of integrating multi-omics data (m6A methylation level and mRNA expression) to accurately obtain potential prognostic biomarkers, which may provide important insights into developing novel and effective therapies for LUAD.

A novel ferroptosis-related gene signature for prognostic prediction of patients with lung adenocarcinoma

BACKGROUND

Lung adenocarcinoma (LUAD) is a heterogeneous disease characterized by high mortality and poor prognosis. Ferroptosis, a newly discovered iron-dependent type of cell death, has been found to play a crucial role in the development of cancers. However, little is known about the prognostic value of ferroptosis-related genes (FRGs) in LUAD.

METHODS

In the present study, RNA-seq transcriptome data of LUAD patients were obtained from The Cancer Genome Atlas (TCGA) database. Cox regression analysis was used to construct a multigene signature. Kaplan-Meier survival and receiver operating characteristic (ROC) curves were utilized to assess the prognostic prediction efficiency of the constructed survival model. LUAD patients from the GSE30219 dataset were used for validation.

RESULTS

We found 46 differentially expressed FRGs between LUAD and adjacent normal tissues. Via univariate and multivariate Cox regression analyses, 5 differentially expressed FRGs were identified as being highly correlated with LUAD. Patients were divided into low- and high-risk groups according to the risk score. We found that the overall survival (OS) of patients in the high-risk group was significantly worse than that of their low-risk counterparts. (P < 0.0001 in the TCGA dataset and P = 0.044 in the GSE30219 cohort). In addition, gene set variation analysis (GSVA) of the tumor microenvironment of the two groups may explain the different survival of LUAD patients.

CONCLUSIONS

Our study identified a novel FRG signature that could be used to evaluate and predict the prognosis of LUAD patients, which might provide a new therapeutic target for the treatment of LUAD patients.

Exploration of predictive and prognostic alternative splicing signatures in lung adenocarcinoma using machine learning methods

Background

Alternative splicing (AS) plays critical roles in generating protein diversity and complexity. Dysregulation of AS underlies the initiation and progression of tumors. Machine learning approaches have emerged as efficient tools to identify promising biomarkers. It is meaningful to explore pivotal AS events (ASEs) to deepen understanding and improve prognostic assessments of lung adenocarcinoma (LUAD) via machine learning algorithms.

Method

RNA sequencing data and AS data were extracted from The Cancer Genome Atlas (TCGA) database and TCGA SpliceSeq database. Using several machine learning methods, we identified 24 pairs of LUAD-related ASEs implicated in splicing switches and a random forest-based classifiers for identifying lymph node metastasis (LNM) consisting of 12 ASEs. Furthermore, we identified key prognosis-related ASEs and established a 16-ASE-based prognostic model to predict overall survival for LUAD patients using Cox regression model, random survival forest analysis, and forward selection model. Bioinformatics analyses were also applied to identify underlying mechanisms and associated upstream splicing factors (SFs).

Results

Each pair of ASEs was spliced from the same parent gene, and exhibited perfect inverse intrapair correlation (correlation coefficient = − 1). The 12-ASE-based classifier showed robust ability to evaluate LNM status of LUAD patients with the area under the receiver operating characteristic (ROC) curve (AUC) more than 0.7 in fivefold cross-validation. The prognostic model performed well at 1, 3, 5, and 10 years in both the training cohort and internal test cohort. Univariate and multivariate Cox regression indicated the prognostic model could be used as an independent prognostic factor for patients with LUAD. Further analysis revealed correlations between the prognostic model and American Joint Committee on Cancer stage, T stage, N stage, and living status. The splicing network constructed of survival-related SFs and ASEs depicts regulatory relationships between them.

Conclusion

In summary, our study provides insight into LUAD researches and managements based on these AS biomarkers.

Classify multicategory outcome in patients with lung adenocarcinoma using clinical, transcriptomic and clinico-transcriptomic data: machine learning versus multinomial models

Classification of multicategory survival-outcome is important for precision oncology. Machine learning (ML) algorithms have been used to accurately classify multi-category survival-outcome of some cancer-types, but not yet that of lung adenocarcinoma. Therefore, we compared the performances of 3 ML models (random forests, support vector machine [SVM], multilayer perceptron) and multinomial logistic regression (Mlogit) models for classifying 4-category survival-outcome of lung adenocarcinoma using the TCGA. Mlogit model overall performed similar to SVM and multilayer perceptron models (micro-average area under curve=0.82), while random forests model was inferior. Surprisingly, transcriptomic data alone and clinico-transcriptomic data appeared sufficient to accurately classify the 4-category survival-outcome in these patients, but no models using clinical data alone performed well. Notably, NDUFS5, P2RY2, PRPF18, CCL24, ZNF813, MYL6, FLJ41941, POU5F1B, and SUV420H1 were the top-ranked genes that were associated with alive without disease and inversely linked to other outcomes. Similarly, BDKRB2, TERC, DNAJA3, MRPL15, SLC16A13, CRHBP and ACSBG2 were associated with alive with progression and GAL3ST3, AD2, RAB41, HDC, and PLEKHG1 associated with dead with disease, respectively, while also inversely linked other outcomes. These cross-linked genes may be used for risk-stratification and future treatment development.

A signature of immune-related gene pairs predicts oncologic outcomes and response to immunotherapy in lung adenocarcinoma

In this study, we established the predictive model for lung adenocarcinoma (LUAD) depending on immune-related gene pairs (IRGPs) signature, which could not consider the technical bias of different platforms. Furthermore, we explored the predictive model with regard to the immune microenvironment and response to immunotherapy and identified specific drugs targeting the IRGPs model. Twenty-three IRGPs were identified and comprised the predictive model. When compared with the high-risk group, the low-risk group displayed a distinctly favorable prognosis and was characterized by increased immune score and decreased tumor purity. In addition, the low-risk group exhibited higher expression of immune checkpoint molecules, lower tumor stemness index, and was much more sensitive to immunotherapy. Lastly, candidate drugs that aimed at LUAD subtype differentiation were identified. The derived IRGPs model is an adverse independent biomarker for estimating oncologic outcomes in LUAD patients, and may be helpful to formulate personalized immunotherapy strategy.

An interactive network of alternative splicing events with prognostic value in geriatric lung adenocarcinoma via the regulation of splicing factors

Alternative splicing (AS), an essential process for the maturation of mRNAs, is involved in tumorigenesis and tumor progression, including angiogenesis, apoptosis, and metastasis. AS changes can be frequently observed in different tumors, especially in geriatric lung adenocarcinoma (GLAD). Previous studies have reported an association between AS events and tumorigenesis but have lacked a systematic analysis of its underlying mechanisms. In the present study, we obtained splicing event information from SpliceSeq and clinical information regarding GLAD from The Cancer Genome Atlas. Survival-associated AS events were selected to construct eight prognostic index (PI) models. We also constructed a correlation network between splicing factors (SFs) and survival-related AS events to identify a potential molecular mechanism involved in regulating AS-related events in GLAD. Our study findings confirm that AS has a strong prognostic value for GLAD and sheds light on the clinical significance of targeting SFs in the treatment of GLAD.

Development of a novel prognostic score combining clinicopathologic variables, gene expression, and mutation profiles for lung adenocarcinoma

BACKGROUND

Integrating phenotypic and genotypic information to improve prognostic prediction is under active investigation for lung adenocarcinoma (LUAD). In this study, we developed a new prognostic model for event-free survival (EFS) and recurrence-free survival (RFS) based on the combination of clinicopathologic variables, gene expression, and mutation data.

METHODS

We enrolled a total of 408 patients from the Cancer Genome Atlas Lung Adenocarcinoma (TCGA-LUAD) project for the study. We pre-selected gene expression or mutation features and constructed 14 different input feature sets for predictive model development. We assessed model performance with multiple evaluation metrics including the distribution of C-index on testing dataset, risk score significance, and time-dependent AUC under competing risks scenario. We stratified patients into higher- and lower-risk subgroups by the final risk score and further investigated underlying immune phenotyping variations associated with the differential risk.

RESULTS

The model integrating all three types of data achieved the best prediction performance. The resultant risk score provided a higher-resolution risk stratification than other models within pathologically defined subgroups. The score could account for extra EFS-related variations that were not captured by clinicopathologic scores. Being validated for RFS prediction under a competing risks modeling framework, the score achieved a significantly higher time-dependent AUC as compared to that of the conventional clinicopathologic variables-based model (0.772 vs. 0.646, p value < 0.001). The higher-risk patients were characterized with transcriptional aberrations of multiple immune-related genes, and a significant depletion of mast cells and natural killer cells.

CONCLUSIONS

We developed a novel prognostic risk score with improved prediction accuracy, using clinicopathologic variables, gene expression and mutation profiles as input, for LUAD. Such score was a significant predictor of both EFS and RFS.

TRIAL REGISTRATION

This study was based on public open data from TCGA and hence the study objects were retrospectively registered.

Identification of prognostic biomarkers for major subtypes of non-small-cell lung cancer using genomic and clinical data

PURPOSE

Intra-tumor heterogeneity and high mortality among patients with non-small-cell lung carcinoma (NSCLC) emphasize the need to identify reliable prognostic markers unique to each subtype.

METHODS

In this study, univariate cox regression and prognostic index (PI)-based approaches were used to develop models for predicting NSCLC patients' subtype-specific survival.

RESULTS

Prognostic analysis of TCGA dataset identified 1334 and 2129 survival-specific genes for LUSC (488 samples) and LUAD (497 samples), respectively. Individually, 32 and 271 prognostic genes were found and validated in GSE study exclusively for LUSC and LUAD. Nearly, 9-10% of the validated genes in each subtype were already reported in multiple studies thus highlighting their importance as prognostic biomarkers. Strong literature evidence against these prognostic genes like "ELANE" (LUSC) and "AHSG" (LUAD) instigates further investigation for their therapeutic and diagnostic roles in the corresponding cohorts. Prognostic models built on five and four genes were validated for LUSC [HR = 2.10, p value = 1.86 × 10^-5] and LUAD [HR = 2.70, p value = 3.31 × 10^-7], respectively. The model based on the combination of age and tumor stage performed well in both NSCLC subtypes, suggesting that despite having distinctive histological features and treatment paradigms, some clinical features can be good prognostic predictors in both.

CONCLUSION

This study advocates that investigating the survival-specific biomarkers restricted to respective cohorts can advance subtype-specific prognosis, diagnosis, and treatment for NSCLC patients. Prognostic models and markers described for each subtype may provide insight into the heterogeneity of disease etiology and help in the development of new therapeutic approaches for the treatment of NSCLC patients.