Wx: a neural network-based feature selection algorithm for transcriptomic data

Machine Learning Methods for Cancer Classification Using Gene Expression Data: A Review

Cancer is a term that denotes a group of diseases caused by the abnormal growth of cells that can spread in different parts of the body. According to the World Health Organization (WHO), cancer is the second major cause of death after cardiovascular diseases. Gene expression can play a fundamental role in the early detection of cancer, as it is indicative of the biochemical processes in tissue and cells, as well as the genetic characteristics of an organism. Deoxyribonucleic acid (DNA) microarrays and ribonucleic acid (RNA)-sequencing methods for gene expression data allow quantifying the expression levels of genes and produce valuable data for computational analysis. This study reviews recent progress in gene expression analysis for cancer classification using machine learning methods. Both conventional and deep learning-based approaches are reviewed, with an emphasis on the application of deep learning models due to their comparative advantages for identifying gene patterns that are distinctive for various types of cancers. Relevant works that employ the most commonly used deep neural network architectures are covered, including multi-layer perceptrons, as well as convolutional, recurrent, graph, and transformer networks. This survey also presents an overview of the data collection methods for gene expression analysis and lists important datasets that are commonly used for supervised machine learning for this task. Furthermore, we review pertinent techniques for feature engineering and data preprocessing that are typically used to handle the high dimensionality of gene expression data, caused by a large number of genes present in data samples. The paper concludes with a discussion of future research directions for machine learning-based gene expression analysis for cancer classification.

A Computational Approach to Identification of Candidate Biomarkers in High-Dimensional Molecular Data

Complex high-dimensional datasets that are challenging to analyze are frequently produced through ‘-omics’ profiling. Typically, these datasets contain more genomic features than samples, limiting the use of multivariable statistical and machine learning-based approaches to analysis. Therefore, effective alternative approaches are urgently needed to identify features-of-interest in ‘-omics’ data. In this study, we present the molecular feature selection tool, a novel, ensemble-based, feature selection application for identifying candidate biomarkers in ‘-omics’ data. As proof-of-principle, we applied the molecular feature selection tool to identify a small set of immune-related genes as potential biomarkers of three prostate adenocarcinoma subtypes. Furthermore, we tested the selected genes in a model to classify the three subtypes and compared the results to models built using all genes and all differentially expressed genes. Genes identified with the molecular feature selection tool performed better than the other models in this study in all comparison metrics: accuracy, precision, recall, and F1-score using a significantly smaller set of genes. In addition, we developed a simple graphical user interface for the molecular feature selection tool, which is available for free download. This user-friendly interface is a valuable tool for the identification of potential biomarkers in gene expression datasets and is an asset for biomarker discovery studies.

Identification and Characterization of Cancer-Associated Fibroblast Subpopulations in Lung Adenocarcinoma

Cancer-associated fibroblasts (CAFs) reside within the tumor microenvironment, facilitating cancer progression and metastasis via direct and indirect interactions with cancer cells and other stromal cell types. CAFs are composed of heterogeneous subpopulations of activated fibroblasts, including myofibroblastic, inflammatory, and immunosuppressive CAFs. In this study, we sought to identify subpopulations of CAFs isolated from human lung adenocarcinomas and describe their transcriptomic and functional characteristics through single-cell RNA sequencing (scRNA-seq) and subsequent bioinformatics analyses. Cell trajectory analysis of combined total and THY1 + CAFs revealed two branching points with five distinct branches. Based on Gene Ontology analysis, we denoted Branch 1 as "immunosuppressive", Branch 2 as "neoantigen presenting", Branch 4 as "myofibroblastic", and Branch 5 as "proliferative" CAFs. We selected representative branch-specific markers and measured their expression levels in total and THY1 + CAFs. We also investigated the effects of these markers on CAF activity under coculture with lung cancer cells. This study describes novel subpopulations of CAFs in lung adenocarcinoma, highlighting their potential value as therapeutic targets.

Multimetric feature selection for analyzing multicategory outcomes of colorectal cancer: random forest and multinomial logistic regression models

Colorectal cancer (CRC) is one of the most common cancers worldwide, and a leading cause of cancer deaths. Better classifying multicategory outcomes of CRC with clinical and omic data may help adjust treatment regimens based on individual's risk. Here, we selected the features that were useful for classifying four-category survival outcome of CRC using the clinical and transcriptomic data, or clinical, transcriptomic, microsatellite instability and selected oncogenic-driver data (all data) of TCGA. We also optimized multimetric feature selection to develop the best multinomial logistic regression (MLR) and random forest (RF) models that had the highest accuracy, precision, recall and F1 score, respectively. We identified 2073 differentially expressed genes of the TCGA RNASeq dataset. MLR overall outperformed RF in the multimetric feature selection. In both RF and MLR models, precision, recall and F1 score increased as the feature number increased and peaked at the feature number of 600-1000, while the models' accuracy remained stable. The best model was the MLR one with 825 features based on sum of squared coefficients using all data, and attained the best accuracy of 0.855, F1 of 0.738 and precision of 0.832, which were higher than those using clinical and transcriptomic data. The top-ranked features in the MLR model of the best performance using clinical and transcriptomic data were different from those using all data. However, pathologic staging, HBS1L, TSPYL4, and TP53TG3B were the overlapping top-20 ranked features in the best models using clinical and transcriptomic, or all data. Thus, we developed a multimetric feature-selection based MLR model that outperformed RF models in classifying four-category outcome of CRC patients. Interestingly, adding microsatellite instability and oncogenic-driver data to clinical and transcriptomic data improved models' performances. Precision and recall of tuned algorithms may change significantly as the feature number changes, but accuracy appears not sensitive to these changes.

Artificial Intelligence in Bulk and Single-Cell RNA-Sequencing Data to Foster Precision Oncology

Artificial intelligence, or the discipline of developing computational algorithms able to perform tasks that requires human intelligence, offers the opportunity to improve our idea and delivery of precision medicine. Here, we provide an overview of artificial intelligence approaches for the analysis of large-scale RNA-sequencing datasets in cancer. We present the major solutions to disentangle inter- and intra-tumor heterogeneity of transcriptome profiles for an effective improvement of patient management. We outline the contributions of learning algorithms to the needs of cancer genomics, from identifying rare cancer subtypes to personalizing therapeutic treatments.

The identification of co-expressed gene modules in Streptococcus pneumonia from colonization to infection to predict novel potential virulence genes

Background

Streptococcus pneumonia (pneumococcus) is a human bacterial pathogen causing a range of mild to severe infections. The complicated transcriptome patterns of pneumococci during the colonization to infection process in the human body are usually determined by measuring the expression of essential virulence genes and the comparison of pathogenic with non-pathogenic bacteria through microarray analyses. As systems biology studies have demonstrated, critical co-expressing modules and genes may serve as key players in biological processes. Generally, Sample Progression Discovery (SPD) is a computational approach traditionally used to decipher biological progression trends and their corresponding gene modules (clusters) in different clinical samples underlying a microarray dataset. The present study aimed to investigate the bacterial gene expression pattern from colonization to severe infection periods (specimens isolated from the nasopharynx, lung, blood, and brain) to find new genes/gene modules associated with the infection progression. This strategy may lead to finding novel gene candidates for vaccines or drug design.

Results

The results included essential genes whose expression patterns varied in different bacterial conditions and have not been investigated in similar studies.

Conclusions

In conclusion, the SPD algorithm, along with differentially expressed genes detection, can offer new ways of discovering new therapeutic or vaccine targeted gene products.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12866-020-02059-0.

Identification of Novel microRNA Prognostic Markers Using Cascaded Wx, a Neural Network-Based Framework, in Lung Adenocarcinoma Patients

The evolution of next-generation sequencing technology has resulted in a generation of large amounts of cancer genomic data. Therefore, increasingly complex techniques are required to appropriately analyze this data in order to determine its clinical relevance. In this study, we applied a neural network-based technique to analyze data from The Cancer Genome Atlas and extract useful microRNA (miRNA) features for predicting the prognosis of patients with lung adenocarcinomas (LUAD). Using the Cascaded Wx platform, we identified and ranked miRNAs that affected LUAD patient survival and selected the two top-ranked miRNAs (miR-374a and miR-374b) for measurement of their expression levels in patient tumor tissues and in lung cancer cells exhibiting an altered epithelial-to-mesenchymal transition (EMT) status. Analysis of miRNA expression from tumor samples revealed that high miR-374a/b expression was associated with poor patient survival rates. In lung cancer cells, the EMT signal induced miR-374a/b expression, which, in turn, promoted EMT and invasiveness. These findings demonstrated that this approach enabled effective identification and validation of prognostic miRNA markers in LUAD, suggesting its potential efficacy for clinical use.

Expression of EEF1A1 Is Associated with Prognosis of Patients with Colon Adenocarcinoma

Background: The prognostic role of the translational factor, elongation factor-1 alpha 1 (EEF1A1), in colon cancer is unclear. Objectives: The present study aimed to investigate the expression of EEF1A in tissues obtained from patients with stage II and III colon cancer and analyze its association with patient prognosis. Methods: A total of 281 patients with colon cancer who underwent curative resection were analyzed according to EEF1A1 expression. Results: The five-year overall survival in the high-EEF1A1 group was 87.7%, whereas it was 65.6% in the low-EEF1A1 expression group (hazard ratio (HR) 2.47, 95% confidence interval (CI) 1.38–4.44, p = 0.002). The five-year disease-free survival of patients with high EEF1A1 expression was 82.5%, which was longer than the rate of 55.4% observed for patients with low EEF1A1 expression (HR 2.94, 95% CI 1.72–5.04, p < 0.001). Univariate Cox regression analysis indicated that age, preoperative carcinoembryonic antigen level, adjuvant treatment, total number of metastatic lymph nodes, and EEF1A1 expression level were significant prognostic factors for death. In multivariate analysis, expression of EEF1A1 was an independent prognostic factor associated with death (HR 3.01, 95% CI 1.636–5.543, p < 0.001). EEF1A1 expression was also an independent prognostic factor for disease-free survival in multivariate analysis (HR 2.54, 95% CI 1.459–4.434, p < 0.001). Conclusions: Our study demonstrated that high expression of EEF1A1 has a favorable prognostic effect on patients with colon adenocarcinoma.