An NMF-Based Methodology for Selecting Biomarkers in the Landscape of Genes of Heterogeneous Cancer-Associated Fibroblast Populations

Review of Patient Gene Profiles Obtained through a Non-Negative Matrix Factorization-Based Framework to Determine the Role Inflammation Plays in Neuroblastoma Pathogenesis

Neuroblastoma is the most common extracranial solid tumor in children. It is a highly heterogeneous tumor consisting of different subcellular types and genetic abnormalities. Literature data confirm the biological and clinical complexity of this cancer, which requires a wider availability of gene targets for the implementation of personalized therapy. This paper presents a study of neuroblastoma samples from primary tumors of untreated patients. The focus of this analysis is to evaluate the impact that the inflammatory process may have on the pathogenesis of neuroblastoma. Eighty-eight gene profiles were selected and analyzed using a non-negative matrix factorization framework to extract a subset of genes relevant to the identification of an inflammatory phenotype, whose targets (PIK3CG, NFATC2, PIK3R2, VAV1, RAC2, COL6A2, COL6A3, COL12A1, COL14A1, ITGAL, ITGB7, FOS, PTGS2, PTPRC, ITPR3) allow further investigation. Based on the genetic signals automatically derived from the data used, neuroblastoma could be classified according to stage rather than as a "cold" or "poorly immunogenic" tumor.

Improving Diagnostics with Deep Forest Applied to Electronic Health Records

An electronic health record (EHR) is a vital high-dimensional part of medical concepts. Discovering implicit correlations in the information of this data set and the research and informative aspects can improve the treatment and management process. The challenge of concern is the data sources' limitations in finding a stable model to relate medical concepts and use these existing connections. This paper presents Patient Forest, a novel end-to-end approach for learning patient representations from tree-structured data for readmission and mortality prediction tasks. By leveraging statistical features, the proposed model is able to provide an accurate and reliable classifier for predicting readmission and mortality. Experiments on MIMIC-III and eICU datasets demonstrate Patient Forest outperforms existing machine learning models, especially when the training data are limited. Additionally, a qualitative evaluation of Patient Forest is conducted by visualising the learnt representations in 2D space using the t-SNE, which further confirms the effectiveness of the proposed model in learning EHR representations.

A new gene-scoring method for uncovering novel glaucoma-related genes using non-negative matrix factorization based on RNA-seq data

Early diagnosis and treatment of glaucoma are challenging. The discovery of glaucoma biomarkers based on gene expression data could potentially provide new insights for early diagnosis, monitoring, and treatment options of glaucoma. Non-negative Matrix Factorization (NMF) has been widely used in numerous transcriptome data analyses in order to identify subtypes and biomarkers of different diseases; however, its application in glaucoma biomarker discovery has not been previously reported. Our study applied NMF to extract latent representations of RNA-seq data from BXD mouse strains and sorted the genes based on a novel gene scoring method. The enrichment ratio of the glaucoma-reference genes, extracted from multiple relevant resources, was compared using both the classical differentially expressed gene (DEG) analysis and NMF methods. The complete pipeline was validated using an independent RNA-seq dataset. Findings showed our NMF method significantly improved the enrichment detection of glaucoma genes. The application of NMF with the scoring method showed great promise in the identification of marker genes for glaucoma.

Cluster of resistance-inducing genes in MCF-7 cells by estrogen, insulin, methotrexate and tamoxifen extracted via NMF

Breast cancer has become a leading cause of death for women as the economy has grown and the number of women in the labor force has increased. Several biomarkers with diagnostic, prognostic, and therapeutic implications for breast cancer have been identified in studies, leading to therapeutic advances. Resistance, on the other hand, is one of clinical practice's limitations. In this paper, we use Nonnegative Matrix Factorization to automatically extract two gene signatures from gene expression profiles of wild-type and resistance MCF-7 cells, which were then investigated further using pathways analysis and proved useful in relating resistance pathways to breast cancer regardless of the stimulus that caused it. A few extracted genes (including MAOA, IL4I1, RRM2, DUT, NME4, and SUMO3) represent new elements in the functional network for resistance in MCF-7 ER+ breast cancer. As a result of this research, a better understanding of how resistance occurs or the pathways that contribute to it may allow more effective therapies to be developed.

Non-negative matrix factorization and differential expression analyses identify hub genes linked to progression and prognosis of glioblastoma multiforme

One of the most prevailing primary brain tumors in adult human male is glioblastoma multiforme (GBM), which is categorized by rapid cellular growth. Even though the combination therapy comprises surgery, chemotherapy, and adjuvant therapies, the survival rate, on average, is 14.6 months. Glioma stem cells (GSCs) have key roles in tumorigenesis, progression, and defiance against chemotherapy and radiotherapy. In our study, firstly, the gene expression dataset GSE124145 was retrieved; the non-negative matrix factorization (NMF) method was applied on GBM dataset, and differentially expressed genes analysis (DEGs) was performed. After which, overlapping genes between metagenes and DEGs were detected to examine the Gene Ontology (GO) categories in the biological process (BP) in the stemness of GBM. The common hub genes were used to construct protein-protein interaction (PPI) network and further GO, while Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway was utilized to pinpoint the real hub genes. The analysis of hub genes particular for the same GO categories demonstrated that specific hub genes triggered distinct features of the same biological processes. After utilizing GSE124145 and The Cancer Genome Atlas (TCGA) dataset for survival analysis, we screened five real hub genes: GUCA1A, RFC2, GNG11, MMP19, and NRG1, which are strongly associated with the progression and prognosis of GBM. The DEGs analysis revealed that all real hub genes were overexpressed in GBM and TCGA datasets, which further validates our results. The constructed study of PPI, GO, and KEGG pathway on common hub genes was performed. Finally, the KEGG pathways performed on the top 15 candidate hub genes (including six real hub genes) of the PPI network in the GBM gene expression dataset study found mitogen-activated protein kinase (Mapk) signaling pathway to be the most significant pathway. The rest of the hub genes reviewed throughout the analysis might be favorable targets for diagnosing and treating GBM and lower-grade gliomas.

Patterns of Nighttime Crowd Flows in Tourism Cities Based on Taxi Data—Take Haikou Prefecture as an Example

The study of patterns of crowd flows represents an emerging and expanding research field. The most straightforward and efficient approach to investigate the patterns of crowd flows is to concentrate on traffic flow. However, assessments of simple point-to-point movement frequently lack universal validity, and little research has been conducted on the regularity of nighttime movement. Due to the suspension of public transportation at night, taxi orders are critical in capturing the features of nighttime crowd flows in a tourism city. Using Haikou as an example, this paper proposes a mixed Geogrid Spatio-temporal model (MG-STM) for the tourism city in order to address the challenges. Firstly, by collecting the pick-up/drop-off/in-out flow of crowds, this research uses DCNMF dimensionality reduction to extract semi-supervised spatio-temporal variation features and the K-Means clustering method to determine the cluster types of nighttime crowd flows’ changes in each geogrid. Secondly, by constructing a mixed-evaluation model based on LJ1-01 nighttime light data, crowd flows’ clusters, and land use data in geogrid-based regions, the pattern of nighttime crowd flows in urban land use areas is successfully determined. The results suggest that MG-STM can estimate changes in the number of collective flows in various regions of Haikou effectively and appropriately. Moreover, population density of land use areas shows a high positive correlation with the lag of crowd flows. Each 5% increase in population density results in a 30-min delay in the peak of crowd flows. The MG-STM will be extremely beneficial in developing and implementing systems for criminal tracking and pandemic prevention.

Colorectal cancer in Crohn's disease evaluated with genes belonging to fibroblasts of the intestinal mucosa selected by NMF

Crohn's disease (CD) is a type of chronic, inflammatory bowel disease (IBD) which affects any part of the gastrointestinal tract. This study aims to understand the mechanism which activate mucosal fibroblasts in the microenvironment of the colon in CD and colorectal carcinomas and to extract fibroblasts phenotypes via a novel framework based on non-negative factorization of matrix (NMF). The results identify a fibroblast phenotype characterized by intense pro-inflammatory activity ensured by the presence of genes belonging to the APOBEC1 family, such as APOBEC3F and APOBEC3G. These results demonstrated that there is a difference in fibroblast response in producing a pro-tumorigenic effect in CD. The different activation mechanisms could represent useful biomarkers in controlling CD development without generalizing its significance as IBD.

Analysis of fibroblast genes selected by NMF to reveal the potential crosstalk between ulcerative colitis and colorectal cancer

Patients with ulcerative colitis (UC) have an increased risk of developing colorectal cancer (CRC). The CRC risk extent raises with increasing age, duration of symptoms, severity of inflammation and dysplasia. CRC is a complex multi-stage process and associated with UC represents 2% of all colon cancers. With the aim of clarifying some aspects of the evolution of UC towards CRC, we characterized the phenotype of fibroblasts present in the mucosa of subjects affected by UC to verify whether they can contribute to the genesis of a microenvironment favorable to tumor transformation. The fibroblast phenotype was obtained with the help of transcriptome analysis adopting a novel framework based on Nonnegative Matrix Factorization (NMF) which automatically extracts a limited number of genes from fibroblast gene expression profiles of patients with UC and CRC. These genes may be considered possible candidates in generating a permissive microenvironment for the evolution of disease under study.

A New Ensemble Method for Detecting Anomalies in Gene Expression Matrices

One of the main problems in the analysis of real data is often related to the presence of anomalies. Namely, anomalous cases can both spoil the resulting analysis and contain valuable information at the same time. In both cases, the ability to detect these occurrences is very important. In the biomedical field, a correct identification of outliers could allow the development of new biological hypotheses that are not considered when looking at experimental biological data. In this work, we address the problem of detecting outliers in gene expression data, focusing on microarray analysis. We propose an ensemble approach for detecting anomalies in gene expression matrices based on the use of Hierarchical Clustering and Robust Principal Component Analysis, which allows us to derive a novel pseudo-mathematical classification of anomalies.

A Block Coordinate Descent-Based Projected Gradient Algorithm for Orthogonal Non-Negative Matrix Factorization

This article uses the projected gradient method (PG) for a non-negative matrix factorization problem (NMF), where one or both matrix factors must have orthonormal columns or rows. We penalize the orthonormality constraints and apply the PG method via a block coordinate descent approach. This means that at a certain time one matrix factor is fixed and the other is updated by moving along the steepest descent direction computed from the penalized objective function and projecting onto the space of non-negative matrices. Our method is tested on two sets of synthetic data for various values of penalty parameters. The performance is compared to the well-known multiplicative update (MU) method from Ding (2006), and with a modified global convergent variant of the MU algorithm recently proposed by Mirzal (2014). We provide extensive numerical results coupled with appropriate visualizations, which demonstrate that our method is very competitive and usually outperforms the other two methods.

Explaining Ovarian Cancer Gene Expression Profiles with Fuzzy Rules and Genetic Algorithms

The analysis of gene expression data is a complex task, and many tools and pipelines are available to handle big sequencing datasets for case-control (bivariate) studies. In some cases, such as pilot or exploratory studies, the researcher needs to compare more than two groups of samples consisting of a few replicates. Both standard statistical bioinformatic pipelines and innovative deep learning models are unsuitable for extracting interpretable patterns and information from such datasets. In this work, we apply a combination of fuzzy rule systems and genetic algorithms to analyze a dataset composed of 21 samples and 6 classes, useful for approaching the study of expression profiles in ovarian cancer, compared to other ovarian diseases. The proposed method is capable of performing a feature selection among genes that is guided by the genetic algorithm, and of building a set of if-then rules that explain how classes can be distinguished by observing changes in the expression of selected genes. After testing several parameters, the final model consists of 10 genes involved in the molecular pathways of cancer and 10 rules that correctly classify all samples.

Tumor immune microenvironment-based classifications of bladder cancer for enhancing the response rate of immunotherapy

Immunotherapy is a potential way to save the lives of patients with bladder cancer, but it only benefits approximately 20% of them. A total of 4,028 bladder cancer patients were collected for this study. Unsupervised non-negative matrix factorization and the nearest template prediction algorithms were employed for the classification. We identified the immune and non-immune classes from The Cancer Genome Atlas Bladder Urothelial Carcinoma (TCGA-BLCA) training cohort. The 150 most differentially expressed genes between these two classes were extracted, and the classification reappeared in 20 validation cohorts. For the activated and exhausted subgroups, a stromal activation signature was assessed by the NTP algorithm. Patients in the immune class showed highly enriched signatures of immunocytes, while the exhausted subgroup also exhibited activated transforming growth factor (TGF)-β1, and cancer-associated extracellular matrix signatures. Patients in the immune-activated subgroup showed a lower genetic alteration and better overall survival. Anti-PD-1/PD-L1 immunotherapy was more beneficial for the immune-activated subgroup, while immune checkpoint blockade therapy plus a TGF-β inhibitor or an EP300 inhibitor might achieve greater efficacy for patients in the immune-exhausted subgroup. Novel immune molecular classifier was identified for the innovative immunotherapy of patients with bladder cancer.