Decision tree-based classifiers for lung cancer diagnosis and subtyping using TCGA miRNA expression data

"Crosstalk between non-coding RNAs and transcription factor LRF in non-small cell lung cancer"

Epigenetic approaches in direct correlation with assessment of critical genetic mutations in non-small cell lung cancer (NSCLC) are currently very intensive, as the epigenetic components underlying NSCLC development and progression have attained high recognition. In this level of research, established human NSCLC cell lines as well as experimental animals are widely used to detect novel biomarkers and pharmacological targets to treat NSCLC. The epigenetic background holds a great potential for the identification of epi-biomarkers for treatment response however, it is highly complex and requires precise definition as these phenomena are variable between NSCLC subtypes and systems origin. We engaged an in-depth characterization of non-coding (nc)RNAs prevalent in human KRAS-mutant NSCLC cell lines A549 and H460 and mouse KRAS-mutant NSCLC tissue by Next Generation Sequencing (NGS) and quantitative Real Time PCRs (qPCRs). Also, the transcription factor (TF) LRF, a known epigenetic silencer, was examined as a modulator of non-coding RNAs expression. Finally, interacting networks underlying epigenetic variations in NSCLC subtypes were created. Data derived from our study highlights the divergent epigenetic profiles of NSCLC of human and mouse origin, as well as the significant contribution of 12qf1: 109,709,060-109,747,960 mouse chromosomal region to micro-RNA upregulated species. Furthermore, the novel epigenetic miR-148b-3p/lncPVT1/ZBTB7A axis was identified, which differentiates human cell line of lung adenocarcinoma from large cell lung carcinoma, two characteristic NSCLC subtypes. The detailed recording of epigenetic events in NSCLC and combinational studies including networking between ncRNAs and TFs validate the identification of significant epigenetic features, prevailing in NSCLC subtypes and among experimental models. Our results enrich knowledge in the field and empower research on the epigenetic prognostic biomarkers of the disease progression, NSCLC subtypes discrimination and advancement to patient-tailored treatments.

A model-free and distribution-free multi-omics integration approach for detecting novel lung adenocarcinoma genes

Detection of important genes affecting lung adenocarcinoma (LUAD) is critical to finding effective therapeutic targets for this highly lethal cancer. However, many existing approaches have focused on single outcomes or phenotypic associations, which may not be as thorough as investigating molecular transcript levels within cells. In this article, we apply a novel multivariate rank-distance correlation-based gene selection procedure (MrDcGene) to LUAD multi-omics data downloaded from The Cancer Genome Atlas (TCGA). MrDcGene provides additional opportunities for detecting novel susceptibility genes as it leverages information from multiple platforms, while efficiently handling challenges such as high dimensionality, low signal-to-noise ratio, unknown distributions, and non-linear structures, etc. Notably, the MrDcGene method is able to detect two different scenarios, i.e., strong association strength with a few gene expressions and weak association strength with several gene expressions. After thoroughly exploring the association between gene expression (GE) and multiple other platforms, including reverse phase protein array (RPPA), miRNA, copy number variation (CNV) and DNA methylation (ME), we detect several novel genes that may play an important role in LUAD (ZNF133, CCDC159, YWHAZ, HNRNPR. ITPR2, PTHLH, and WIPI2). In addition, we quantitatively validate several other susceptibility genes that were reported in the literature using different methods and studies. The accuracy of the MrDcGene approach is theoretically assured and empirically demonstrated by the simulation studies.

Robust and consistent biomarker candidates identification by a machine learning approach applied to pancreatic ductal adenocarcinoma metastasis

BACKGROUND

Machine Learning (ML) plays a crucial role in biomedical research. Nevertheless, it still has limitations in data integration and irreproducibility. To address these challenges, robust methods are needed. Pancreatic ductal adenocarcinoma (PDAC), a highly aggressive cancer with low early detection rates and survival rates, is used as a case study. PDAC lacks reliable diagnostic biomarkers, especially metastatic biomarkers, which remains an unmet need. In this study, we propose an ML-based approach for discovering disease biomarkers, apply it to the identification of a PDAC metastatic composite biomarker candidate, and demonstrate the advantages of harnessing data resources.

METHODS

We utilised primary tumour RNAseq data from five public repositories, pooling samples to maximise statistical power and integrating data by correcting for technical variance. Data were split into train and validation sets. The train dataset underwent variable selection via a 10-fold cross-validation process that combined three algorithms in 100 models per fold. Genes found in at least 80% of models and five folds were considered robust to build a consensus multivariate model. A random forest model was constructed using selected genes from the train dataset and tested in the validation set. We also assessed the goodness of prediction by recalibrating a model using only the validation data. The biological context and relevance of signals was explored through enrichment and pathway analyses using QIAGEN Ingenuity Pathway Analysis and GeneMANIA.

RESULTS

We developed a pipeline that can detect robust signatures to build composite biomarkers. We tested the pipeline in PDAC, exploiting transcriptomics data from different sources, proposing a composite biomarker candidate comprised of fifteen genes consistently selected that showed very promising predictive capability. Biological contextualisation revealed links with cancer progression and metastasis, underscoring their potential relevance. All code is available in GitHub.

CONCLUSION

This study establishes a robust framework for identifying composite biomarkers across various disease contexts. We demonstrate its potential by proposing a plausible composite biomarker candidate for PDAC metastasis. By reusing data from public repositories, we highlight the sustainability of our research and the wider applications of our pipeline. The preliminary findings shed light on a promising validation and application path.

MicroRNA-875-5p inhibits the growth and metastasis of cervical cancer cells by promoting autophagy and apoptosis and inhibiting the epithelial-mesenchymal transition

Introduction

MicroRNA-875-5p (miR-875-5p) is a cancer-related microRNA. It has been demonstrated that miR-875-5p participates in the development of various types of cancer such as hepatocellular carcinoma, gastric carcinoma, prostate and bladder cancer. Previous research suggested that miR-875 is implicated in the development of cervical cancer cells. However, the exact role and function of miR-875-5p in cervical cancer remain unexplored. It is important to examine the role and function of miR-875-5p and the associated signaling pathway, as the findings may have diagnostic and therapeutic significance. Thus, in this study, we investigated the effect of miR-875-5p on the growth and metastasis of cervical cancer cells and the possible underlying mechanisms.

Methods

Reverse transcription-quantitative polymerase chain reaction (RT-qPCR) was used to detect the expression of miR-875-5p in cervical cancer cells and normal cervical epithelium. After overexpression or co-expression of miR-875-5p in cells, the changes in cell function were analyzed. Western blot was used to detect the expression changes of epithelial-mesenchymal transition (EMT) -related proteins and autophagy-related proteins.

Results

Functional studies demonstrated that miR-875-5p overexpression significantly inhibited the proliferation, migration, invasion, and EMT, and promotes apoptosis and autophagy of cervical cancer cells., while miR-875-5p knockdown promoted the proliferation, migration, invasion, and EMT, and inhibited apoptosis and autophagy cervical cancer cells. Furthermore, Western blot results showed that overexpression of miR-875-5p downregulated the expressions of N-cadherin, Snail, Vimentin and microtubule-associated protein 1 light chain 3B I (LC3B I). Conversely, miR-875-5p upregulated the expression of E-cadherin.

Conclusion

In conclusion, our findings suggest that miR-875-5p functions as a tumor inhibitor suppressing the growth and metastasis of cervical cancer. Overexpression of miR-875-5p inhibits malignant behavior and promotes autophagy and apoptosis in cervical cancer cells. These findings advance our understanding of the role and function of miR-875-5p in cervical cancer and could facilitate the development of early genetic markers or biomarkers and therapeutic targets for cervical cancer.

Factors related to tumor response rate from TCGA three omics data-variants, expression, methylation

The Cancer Genome Atlas (TCGA) and its patient-derived multi-omics datasets have been the backbone of cancer research, and with novel approaches, it continues to shed new insight into the disease. In this study, we delved into a method of multi-omics integration of patient datasets and the association of biological pathways related to the disease. First, across thirty-three types of cancer present in TCGA, we merged genomic mutations and drug response datasets and filtered for the viable variant-drug response combinations available in TCGA, containing more than three samples for each drug response label with RNA sequencing (RNA-seq) and genomic methylation data available for each patient. We identified two distinct combinations in TCGA, one being pancreatic adenocarcinoma patients with/without rs121913529 variant in KRAS gene treated with gemcitabine, and the other low-grade glioma with/without rs121913500 variant in IDH1 gene administered with temozolomide. In these two groups, different patterns of gene expression were observed in the pathways often associated with cancer progression, such as mTOR and PDGF between the patients with complete response and progressive disease. Our result will provide yet another example of the relevance of these biological pathways in cancer drug response and a way for multi-omics integration in cancer datasets.

Artificial neural network-based gene screening and immune cell infiltration analysis of osteosarcoma feature

BACKGROUND

The present study aimed to construct an artificial neural network (ANN) model that leverages characteristic genes associated with osteosarcoma (OS) to enable accurate prognostication for OS patients.

METHODS

Our research revealed 467 differentially expressed genes (DEGs) via gene expression contrast analysis, consisting of 345 downregulated genes and 122 upregulated genes. Gene Ontology (GO) enrichment analysis illuminated functions primarily encompassing T-cell activation, secretory granule lumen and antioxidant activity, among others. Through Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis, we discovered significant correlations between the DEGs and certain pathways, including phagosome, Staphylococcus aureus infection and human T-cell leukemia virus 1 infection. We then screened out 30 characteristic DEGs (CDEGs) based on random forest analysis and constructed the ANN model using the gene score matrix. To verify the credibility and accuracy of the ANN model, we performed internal and external validation processes, which affirmed our model's predictive capabilities.

RESULTS

The study further delved into the analysis of immune cell infiltration and its correlation with the target CDEGs, revealing disparities in the infiltration of 22 types of immune cells across different groups and their interrelationships. Moreover, we probed the expression of the two foremost CDEGs (YES1 and MFNG) in OS and normal tissues. We noted a positive relationship between the expression of YES1 and MFNG in OS tissues and the clinicopathological characteristics of OS patients.

CONCLUSIONS

Collectively, the findings of the present study validate the effectiveness of the CDEGs-based ANN model in predicting OS patients, which might facilitate early diagnosis and treatment of OS.

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.

Research on Predicting the Occurrence of Hepatocellular Carcinoma Based on Notch Signal-Related Genes Using Machine Learning Algorithms

BACKGROUND/AIMS

Hepatocellular carcinoma, a highly malignant tumor, is difficult to diagnose, treat, and predict the prognosis. Notch signaling pathway can affect hepatocellular carcinoma. We aimed to predict the occurrence of hepatocellular carcinoma based on Notch signal-related genes using machine learning algorithms.

MATERIALS AND METHODS

We downloaded hepatocellular carcinoma data from the Cancer Genome Atlas and Gene Expression Omnibus databases and used machine learning methods to screen the hub Notch signal-related genes. Machine learning classification was used to construct a prediction model for the classification and diagnosis of hepatocellular carcinoma cancer. Bioinformatics methods were applied to explore the expression of these hub genes in the hepatocellular carcinoma tumor immune microenvironment.

RESULTS

We identified 4 hub genes, namely, LAMA4, POLA2, RAD51, and TYMS, which were used as the final variables, and found that AdaBoostClassifie was the best algorithm for the classification and diagnosis model of hepatocellular carcinoma. The area under curve, accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score of this model in the training set were 0.976, 0.881, 0.877, 0.977, 0.996, 0.500, and 0.932; respectively. The area under curves were 0.934, 0.863, 0.881, 0.886, 0.981, 0.489, and 0.926. The area under curve in the external validation set was 0.934. Immune cell infiltration was related to the expression of 4 hub genes. Patients in the low-risk group of hepatocellular carcinoma were more likely to have an immune escape.

CONCLUSION

The Notch signaling pathway was closely related to the occurrence and development of hepatocellular carcinoma. The hepatocellular carcinoma classification and diagnosis model established based on this had a high degree of reliability and stability.

Artificial intelligence in clinical applications for lung cancer: diagnosis, treatment and prognosis

Artificial Intelligence (AI) is a branch of computer science that includes research in robotics, language recognition, image recognition, natural language processing, and expert systems. AI is poised to change medical practice, and oncology is not an exception to this trend. As the matter of fact, lung cancer has the highest morbidity and mortality worldwide. The leading cause is the complexity of associating early pulmonary nodules with neoplastic changes and numerous factors leading to strenuous treatment choice and poor prognosis. AI can effectively enhance the diagnostic efficiency of lung cancer while providing optimal treatment and evaluating prognosis, thereby reducing mortality. This review seeks to provide an overview of AI relevant to all the fields of lung cancer. We define the core concepts of AI and cover the basics of the functioning of natural language processing, image recognition, human-computer interaction and machine learning. We also discuss the most recent breakthroughs in AI technologies and their clinical application regarding diagnosis, treatment, and prognosis in lung cancer. Finally, we highlight the future challenges of AI in lung cancer and its impact on medical practice.

Epigenetic Alterations of DNA Methylation and miRNA Contribution to Lung Adenocarcinoma

This study focused on the epigenetic alterations of DNA methylation and miRNAs for lung adenocarcinoma (LUAD) diagnosis and treatment using bioinformatics analyses. DNA methylation data and mRNA and miRNA expression microarray data were obtained from The Cancer Genome Atlas (TCGA) database. The differentially methylated genes (DMGs), differentially expressed genes (DEGs), and differentially expressed miRNAs were analyzed by using the limma package. The DAVID database performed GO and KEGG pathway enrichment analyses. Using STRING and Cytoscape, we constructed the protein-protein interaction (PPI) network and achieved visualization. The online analysis tool CMap was used to identify potential small-molecule drugs for LUAD. In LUAD, 607 high miRNA-targeting downregulated genes and 925 low miRNA-targeting upregulated genes, as well as 284 hypermethylated low-expression genes and 315 hypomethylated high-expression genes, were obtained. They were mainly enriched in terms of pathways in cancer, neuroactive ligand-receptor interaction, cAMP signaling pathway, and cytosolic DNA-sensing pathway. In addition, 40 upregulated and 84 downregulated genes were regulated by both aberrant alternations of DNA methylation and miRNAs. Five small-molecule drugs were identified as a potential treatment for LUAD, and five hub genes (SLC2A1, PAX6, LEP, KLF4, and FGF10) were found in PPI, and two of them (SLC2A1 and KLF4) may be related to the prognosis of LUAD. In summary, our study identified a series of differentially expressed genes associated with epigenetic alterations of DNA methylation and miRNA in LUAD. Five small-molecule drugs and five hub genes may be promising drugs and targets for LUAD treatment.

miR-92a-3p Promoted EMT via Targeting LATS1 in Cervical Cancer Stem Cells

miR-92a-3p (microRNA-92a-3p) has been reported to be dysregulated in several cancers, and as such, it is considered to be a cancer-related microRNA. However, the influence of miR-92a-3p on biological behaviors in cervical cancer (CC) still remains unclear. Quantitative real-time PCR was used to detect miR-92a-3p levels in CC stem cells. Here, Cell Counting Kit-8 (CCK8) assay, Transwell cell invasion assay and flow cytometry assay were used to characterize the effects that miR-92a-3p and large tumor suppressor l (LATS1) had on proliferation, invasion and cell cycle transition. The luciferase reporter gene assay was used to verify the targeting relationship between miR-92a-3p and LATS1. Western Blotting was used to investigate the related signaling pathways and proteins. Data from The Cancer Genome Atlas (TCGA) showed that miR-92a-3p was upregulated in CC tissues and closely associated with overall survival. miR-92a-3p promoted proliferation, invasion and cell cycle transition in CC stem cells. The luciferase reporter assay showed that miR-92a-3p bound to the 3′-untranslated region (3′-UTR) of the LATS1 promoter. LATS1 inhibited proliferation, invasion and cell cycle transition. Results measured by Western Blotting showed that LATS1 downregulated expressions of transcriptional co-activator with PDZ-binding motif (TAZ), vimentin and cyclin E, but upregulated the expression of E-cadherin. Re-expression of LATS1 partly reversed the effects of miR-92a-3p on proliferation, invasion and cell cycle transition, as well as on TAZ, E-cadherin, vimentin, and cyclin E. miR-92a-3p promoted the malignant behavior of CC stem cells by targeting LATS1, which regulated TAZ and E-cadherin.

A Novel Risk-Score Model With Eight MiRNA Signatures for Overall Survival of Patients With Lung Adenocarcinoma

Lung adenocarcinoma (LUAD) is the most common subtype of lung cancer with heterogeneous outcomes and diverse therapeutic responses. To classify patients into different groups and facilitate the suitable therapeutic strategy, we first selected eight microRNA (miRNA) signatures in The Cancer Genome Atlas (TCGA)-LUAD cohort based on multi-strategy combination, including differential expression analysis, regulatory relationship, univariate survival analysis, importance clustering, and multivariate combinations analysis. Using the eight miRNA signatures, we further built novel risk scores based on the predefined cutoff and beta coefficients and divided the patients into high-risk and low-risk groups with significantly different overall survival time (p-value < 2 e-16). The risk-score model was confirmed with an independent dataset (p-value = 4.71 e-4). We also observed that the risk scores of early-stage patients were significantly lower than those of late-stage patients. Moreover, our model can also provide new insights into the current clinical staging system and can be regarded as an alternative system for patient stratification. This model unified the variable value as the beta coefficient facilitating the integration of biomarkers obtained from different omics data.

A novel miRNA-based classification model of risks and stages for clear cell renal cell carcinoma patients

Background

Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal carcinoma and patients at advanced stage showed poor survival rate. Despite microRNAs (miRNAs) are used as potential biomarkers in many cancers, miRNA biomarkers for predicting the tumor stage of ccRCC are still limitedly identified. Therefore, we proposed a new integrated machine learning (ML) strategy to identify a novel miRNA signature related to tumor stage and prognosis of ccRCC patients using miRNA expression profiles. A multivariate Cox regression model with three hybrid penalties including Least absolute shrinkage and selection operator (Lasso), Adaptive lasso and Elastic net algorithms was used to screen relevant prognostic related miRNAs. The best subset regression (BSR) model was used to identify optimal prognostic model. Five ML algorithms were used to develop stage classification models. The biological significance of the miRNA signature was analyzed by utilizing DIANA-mirPath.

Results

A four-miRNA signature associated with survival was identified and the expression of this signature was strongly correlated with high risk patients. The high risk patients had unfavorable overall survival compared with the low risk group (HR = 4.523, P-value = 2.86e−08). Univariate and multivariate analyses confirmed independent and translational value of this predictive model. A combined ML algorithm identified six miRNA signatures for cancer staging prediction. After using the data balancing algorithm SMOTE, the Support Vector Machine (SVM) algorithm achieved the best classification performance (accuracy = 0.923, sensitivity = 0.927, specificity = 0.919, MCC = 0.843) when compared with other classifiers. Furthermore, enrichment analysis indicated that the identified miRNA signature involved in cancer-associated pathways.

Conclusions

A novel miRNA classification model using the identified prognostic and tumor stage associated miRNA signature will be useful for risk and stage stratification for clinical practice, and the identified miRNA signature can provide promising insight to understand the progression mechanism of ccRCC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04189-2.

A nine-gene signature to improve prognosis prediction of colon carcinoma

This study aims to establish a gene model that can robustly and effectively predict the prognosis of colon carcinoma patients via bioinformatics. Data along with clinical information in GSE39582 Series Matrix were firstly downloaded from Gene Expression Omnibus (GEO) database. Next, differentially expressed genes (DEGs) were obtained through "edgeR" analysis. Finally, a risk predication model was established through a series of regression analyses, and then prognostic performance of the model was comprehensively evaluated though Kaplan-Meier and receiver operating characteristic (ROC) analysis. Gene set enrichment analysis (GSEA) was further performed. Totally, 846 DEGs were obtained by analyzing the gene expression data in GSE39582 dataset. A 9-gene signature-based risk predication model was established via regression analyses, and the model-based risk score was formulated as: Riskscore = (-0.1214) * TNFRSF11A + (-0.2617) * TMEM97 + (-0.1041) * LGR5 + 0.0973 * KLK10 + 0.1655 * HOXB8 + 0.227 * FKBP10 + (-0.1312) * CXCL13 + (-0.1316) * CXCL10 + 0.2593 * CD36. Kaplan-Meier curve showed that colon carcinoma patients in the high-risk group had a lower survival rate. GSEA showed that high-risk group and low-risk group displayed significant difference in biological pathways including ECM RECEPTOR INTERACTION. Besides, correlation analysis between the riskscore of the model and clinical features of patients revealed that the model could effectively predict the prognosis of patients in different ages (age>65, age<65) and stages (tumor_stage I/II, tumor_stage III/IV, T3&T4, N0&N1, N2&N3, M0). This study provides a robust model for the prognosis prediction of colon carcinoma, and lays a basis for researching the molecular mechanism underlying the development of colon carcinoma.

The prediction of asymptomatic carotid atherosclerosis with electronic health records: a comparative study of six machine learning models

BACKGROUND

Screening carotid B-mode ultrasonography is a frequently used method to detect subjects with carotid atherosclerosis (CAS). Due to the asymptomatic progression of most CAS patients, early identification is challenging for clinicians, and it may trigger ischemic stroke. Recently, machine learning has shown a strong ability to classify data and a potential for prediction in the medical field. The combined use of machine learning and the electronic health records of patients could provide clinicians with a more convenient and precise method to identify asymptomatic CAS.

METHODS

Retrospective cohort study using routine clinical data of medical check-up subjects from April 19, 2010 to November 15, 2019. Six machine learning models (logistic regression [LR], random forest [RF], decision tree [DT], eXtreme Gradient Boosting [XGB], Gaussian Naïve Bayes [GNB], and K-Nearest Neighbour [KNN]) were used to predict asymptomatic CAS and compared their predictability in terms of the area under the receiver operating characteristic curve (AUCROC), accuracy (ACC), and F1 score (F1).

RESULTS

Of the 18,441 subjects, 6553 were diagnosed with asymptomatic CAS. Compared to DT (AUCROC 0.628, ACC 65.4%, and F1 52.5%), the other five models improved prediction: KNN + 7.6% (0.704, 68.8%, and 50.9%, respectively), GNB + 12.5% (0.753, 67.0%, and 46.8%, respectively), XGB + 16.0% (0.788, 73.4%, and 55.7%, respectively), RF + 16.6% (0.794, 74.5%, and 56.8%, respectively) and LR + 18.1% (0.809, 74.7%, and 59.9%, respectively). The highest achieving model, LR predicted 1045/1966 cases (sensitivity 53.2%) and 3088/3566 non-cases (specificity 86.6%). A tenfold cross-validation scheme further verified the predictive ability of the LR.

CONCLUSIONS

Among machine learning models, LR showed optimal performance in predicting asymptomatic CAS. Our findings set the stage for an early automatic alarming system, allowing a more precise allocation of CAS prevention measures to individuals probably to benefit most.

Construction of Decision Trees Based on Gene Expression Omnibus Data to Classify Bladder Cancer and Its Subtypes

Background

Bladder cancer is a malignant tumor of the genitourinary system. Different subtypes of bladder cancer have different treatment methods and prognoses. Therefore, identifying hub genes affecting other genes is of great significance for the treatment of bladder cancer.

Material/Methods: We obtained expression profiles from the GSE13507 and GSE77952 datasets from the Gene Expression Omnibus database. First, principal component analysis was used to identify the difference in gene expression in different types of tissues. Differential expression analysis was used to find the differentially expressed genes between normal and tumor tissues, and between tumors with and without muscle infiltration. Further, based on differentially expressed genes, we constructed 2 decision trees for differentiating between tumor and normal tissues, and between muscle-infiltrating and non-muscle-infiltrating tumor tissues. A receiver operating characteristic curve was used to evaluate the prediction effect of the decision trees.

Results

FAM107A and C8orf4 showed significantly lower expression in bladder cancer tissues than in normal tissues. Regarding muscle infiltration, CTHRC1 showed lower expression and HMGCS2 showed higher expression in non-muscle-infiltrating samples than in those with muscle infiltration. We constructed 2 decision trees for differentiating between tumor and normal tissue, and between tissues with and without muscle infiltration. Both decision trees showed good prediction results.

Conclusions

These newly discovered hub genes will be helpful in understanding the occurrence and development of different subtypes of bladder cancer, and will provide new therapeutic targets and biomarkers for bladder cancer.

A prognosis-related molecular subtype for early-stage non-small lung cell carcinoma by multi-omics integration analysis

Background

Early-stage non-small cell lung carcinoma (NSCLC) accounts for more than 80% of lung cancer, which is a kind of cancer with high heterogeneity, so the genetic heterogeneity and molecular subtype should be explored.

Methods

Partitioning Around Medoid algorithm was used to acquire the molecular subtype for early-stage NSCLC based on prognosis-related mRNAs and methylation sites. Random forest (RF) and support vector machine (SVM) were used to build prediction models for subtypes.

Results

Six prognosis-related subtypes for early-stage NSCLC, including 4 subtypes for lung squamous cell carcinoma (LUSC) and 2 subtypes for lung adenocarcinoma (LUAD), were identified. There were highly expressed and hypermethylated gene regions for LUSC-C1 and LUAD-C2, highly expressed region for LUAD-C1, and hypermethylated regions for LUSC-C3 and LUSC-C4. Molecular subtypes for LUSC were mainly determined by DNA methylation (14 mRNAs and 362 methylation sites). Molecular subtypes for LUAD were determined by both mRNA and DNA methylation information (143 mRNAs and 458 methylation sites). Ten methylation sites were selected as biomarkers for prediction of LUSC-C1 and LUSC-C3, respectively. Nine genes and 1 methylation site were selected as biomarkers for LUAD subtype prediction. These subtypes can be predicted by the selected biomarkers with RF and SVM models.

Conclusions

In conclusion, we proposed a prognosis-related molecular subtype for early-stage NSCLC, which can provide important information for personalized therapy of patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-07846-0.

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.

Diagnostic and Therapeutic Implications of microRNAs in Non-Small Cell Lung Cancer

microRNAs (miRNAs), endogenous suppressors of target mRNAs, are deeply involved in every step of non-small cell lung cancer (NSCLC) development, from tumor initiation to progression and metastasis. They play roles in cell proliferation, apoptosis, angiogenesis, epithelial-to-mesenchymal transition, migration, invasion, and metastatic colonization, as well as immunosuppression. Due to their versatility, numerous attempts have been made to use miRNAs for clinical applications. miRNAs can be used as cancer subtype classifiers, diagnostic markers, drug-response predictors, prognostic markers, and therapeutic targets in NSCLC. Many challenges remain ahead of their actual clinical application; however, when achieved, the use of miRNAs in the clinic is expected to enable great progress in the diagnosis and treatment of patients with NSCLC.

The Lung Cancer Associated MicroRNAs and Single Nucleotides Polymorphisms: a Mendelian Randomization Analysis

Lung cancer is a major public health burden and among the highest incidence and mortality rates of the cancers. MicroRNAs (miRNAs) play an important role in the development of lung cancer. The aim of this study was to investigate whether there was a potential causal relation between miRNAs and non-small-cell lung cancer (NSCLC). 1,026 patients with NSCLC from The Cancer Genome Atlas (TCGA) were analyzed. NSCLC associated SNPs' allele scores were established, and candidate miRNAs were filtered from differential expression analysis. Mendelian randomization (MR) analysis was conducted for 5 candidate miRNA (hsa-miR-135b, hsa-miR-142, hsa-miR-182, hsa-miR-183 and hsa-miR-3607) and 76 candidate SNPs in lung adenocarcinoma (LUAD) group. According to the core assumptions of MR, there was no clear evidence of a causal relation between the 5 candidate miRNAs and LUAD. The reads per million miRNAs mapped (RPM) level of candidate miRNAs changed less than 3% per allele score. To our knowledge, this is the first study using the TCGA data set to investigate the causal relation between miRNAs and lung cancer using the MR approach, and also one of the first MR studies to use miRNA expression as an exposure factor, with the SNPs as instrumental variables.

Applying Serum Proteins and MicroRNA as Novel Biomarkers for Early-Stage Cervical Cancer Detection

Recently, we have been seeing emerging applications of non-invasive approaches using serum biomarkers including miRNA and proteins in detection of multiple cancers. Currently, majority of these methods only use solitary type of biomarkers, which often lead to non-satisfactory sensitivity and specificity in clinical applications. To this end, we established a unique biomarker panel in this study, which determined both squamous cell carcinoma antigen (SCC Ag) degree and miRNA-29a, miRNA-25, miRNA-486-5p levels in blood for detection of early-stage cervical cancer. We designed our study with two phases: a biomarker discovery phase, followed by an independent validation phase. In total of 140 early-stage cervical cancer patients (i.e., AJCC stage I and II) and 140 healthy controls recruited in the biomarker discovery phase, we achieved sensitivity of 88.6% and specificity of 92.9%. To further assess the predictive power of our panel, we used it to an independent patient cohort that consisted of 60 early-stage cervical cancer individuals as well as 60 healthy controls, and successfully achieved both high sensitivity (80.0%) and high specificity (96.7%). Our study indicated combining analyses of multiple serum biomarkers could improve the accuracy of non-invasive detection of early-stage cervical cancer, and potentially serve as a new liquid biopsy approach for detecting early-stage cervical cancer.