Matrix Factorization Algorithm Research Articles

Tumor-associated characteristics and immune dysregulation in nasopharyngeal carcinoma under the regulation of m7G-related tumor microenvironment cells

BackgroundNasopharyngeal carcinoma (NPC) is a type of malignant tumor with high morbidity. Aberrant levels of N7-methylguanosine (m7G) are closely associated with tumor progression. However, the characteristics of the tumor microenvironment (TME) in NPC associated with m7G modification remain unclear.MethodsA total of 68,795 single cells from single-cell RNA sequencing data derived from 11 NPC tumor samples and 3 nasopharyngeal lymphatic hyperplasia (NLH) samples were clustered using a nonnegative matrix factorization algorithm according to 61 m7G RNA modification regulators.ResultsThe m7G regulators were found differential expression in the TME cells of NPC, and most m7G-related immune cell clusters in NPC tissues had a higher abundance compared to non-NPC tissues. Specifically, m7G scores in the CD4+ and CD8+ T cell clusters were significantly lower in NPC than in NLH. T cell clusters differentially expressed immune co-stimulators and co-inhibitors. Macrophage clusters differentially expressed EIF4A1, and high EIF4A1 expression was associated with poor survival in patients with head and neck squamous carcinoma. EIF4A1 was upregulated in NPC tissues compared to the non-NPC tissues and mainly expressed in CD86+ macrophages. Moreover, B cell clusters exhibited tumor biological characteristics under the regulation of m7G-related genes in NPC. The fibroblast clusters interacted with the above immune cell clusters and enriched tumor biological pathways, such as FGER2 signaling pathway. Importantly, there were correlations and interactions through various ligand-receptor links among epithelial cells and m7G-related TME cell clusters.ConclusionOur study revealed tumor-associated characteristics and immune dysregulation in the NPC microenvironment under the regulation of m7G-related TME cells. These results demonstrated the underlying regulatory roles of m7G in NPC.

Revisiting data reduction for boolean matrix factorization algorithms based on formal concept analysis

Revisiting data reduction for boolean matrix factorization algorithms based on formal concept analysis

Identifying disulfidptosis subtypes in hepatocellular carcinoma through machine learning and preliminary exploration of its connection with immunotherapy

BackgroundHepatocellular carcinoma (HCC) is a highly prevalent and deadly cancer, with limited treatment options for advanced-stage patients. Disulfidptosis is a recently identified mechanism of programmed cell death that occurs in SLC7A11 high-expressing cells due to glucose starvation-induced disintegration of the cellular disulfide skeleton. We aimed to explore the potential of disulfidptosis, as a prognostic and therapeutic marker in HCC.MethodsWe classified HCC patients into two disulfidptosis subtypes (C1 and C2) based on the transcriptional profiles of 31 disulfrgs using a non-negative matrix factorization (NMF) algorithm. Further, five genes (NEIL3, MMP1, STC2, ADH4 and CFHR3) were screened by Cox regression analysis and machine learning algorithm to construct a disulfidptosis scoring system (disulfS). Cell proliferation assay, F-actin staining and PBMC co-culture model were used to validate that disulfidptosis occurs in HCC and correlates with immunotherapy response.ResultsOur results suggests that the low disulfidptosis subtype (C2) demonstrated better overall survival (OS) and progression-free survival (PFS) prognosis, along with lower levels of immunosuppressive cell infiltration and activation of the glycine/serine/threonine metabolic pathway. Additionally, the low disulfidptosis group showed better responses to immunotherapy and potential antagonism with sorafenib treatment. As a total survival risk factor, disulfS demonstrated high predictive efficacy in multiple validation cohorts. We demonstrated the presence of disulfidptosis in HCC cells and its possible relevance to immunotherapeutic sensitization.ConclusionThe present study indicates that novel biomarkers related to disulfidptosis may serve as useful clinical diagnostic indicators for liver cancer, enabling the prediction of prognosis and identification of potential treatment targets.Graphical

Unraveling the Molecular Landscape of Neutrophil Extracellular Traps in Severe Asthma: Identification of Biomarkers and Molecular Clusters.

Neutrophil extracellular traps (NETs) play a central role in chronic airway diseases. However, the precise genetic basis linking NETs to the development of severe asthma remains elusive. This study aims to unravel the molecular characterization of NET-related genes (NRGs) in severe asthma and to reliably identify relevant molecular clusters and biomarkers. We analyzed RNA-seq data from the Gene Expression Omnibus database. Interaction analysis revealed fifty differentially expressed NRGs (DE-NRGs). Subsequently, the non-negative matrix factorization algorithm categorized samples from severe asthma patients. A machine learning algorithm then identified core NRGs that were highly associated with severe asthma. DE-NRGs were correlated and subjected to protein-protein interaction analysis. Unsupervised consensus clustering of the core gene expression profiles delineated two distinct clusters (C1 and C2) characterizing severe asthma. Functional enrichment highlighted immune-related pathways in the C2 cluster. Core gene selection included the Boruta algorithm, support vector machine, and least absolute contraction and selection operator algorithms. Diagnostic performance was assessed by receiver operating characteristic curves. This study addresses the molecular characterization of NRGs in adult severe asthma, revealing distinct clusters based on DE-NRGs. Potential biomarkers (TIMP1 and NFIL3) were identified that may be important for early diagnosis and treatment of severe asthma.

Discovery of a T cell proliferation-associated regulator signature correlates with prognosis risk and immunotherapy response in bladder cancer.

The efficacy of immunotherapy is heavily influenced by T cell activity. This study aimed to examine how T cell proliferation regulators can predict the prognosis and response to immunotherapy in patients with bladder cancer (BCa). T cell proliferation-related subtypes were determined by employing the non-negative matrix factorization (NMF) algorithm that analyzed the expression patterns of T cell proliferation regulators. Subtypes were assessed for variations in prognosis, immune infiltration, and functional behaviors. Subsequently, a risk model related to T cell proliferation was created through Cox and Lasso regression analyses in the TCGA cohort and then confirmed in two GEO cohorts and an immunotherapy cohort. BCa patients were categorized into two subtypes (C1 and C2) according to the expression profiles of 31T cell proliferation-related genes (TRGs) with distinct prognoses and immune landscapes. The C2 subtype had a shorter overall survival (OS), with higher levels of M2 macrophage infiltration, and the activation of cancer-related pathways than the C1 subtype. Following this, thirteen prognosis-related genes that were involved in T cell proliferation were utilized to create the prognostic signature. The model's predictive accuracy was confirmed by analyzing both internal and external datasets. Individuals in the high-risk category experienced a poorer prognosis, increased immunosuppressive factors in the tumor microenvironment, and diminished responses to immunotherapy. Additionally, the immunotherapeutic prediction efficacy of the model was further confirmed by an immunotherapy cohort (anti-PD-L1 in the IMvigor210 cohort). Our study characterized two subtypes linked to T cell proliferation in BCa patients with distinct prognoses and tumor microenvironment (TME) patterns, providing new insights into the heterogeneity of T cell proliferation in BCa and its connection to the immune landscape. The signature has prospective clinical implications for predicting outcomes and may help physicians to select prospective responders who prioritize current immunotherapy.

Comprehensive analysis of KLF family reveals KLF6 as a promising prognostic and immune biomarker in pancreatic ductal adenocarcinoma

BackgroundPancreatic ductal adenocarcinoma (PDAC) is one of the deadliest tumors worldwide, with extremely aggressive and complicated biology. Krüppel-like factors (KLFs) encode a series of transcriptional regulatory proteins and play crucial roles in a variety of processes, including tumor cell differentiation and proliferation. However, the potential biological functions and possible pathways of KLFs in the progression of PDAC remain elusive.MethodsWe systematically evaluated the transcriptional variations and expression patterns of KLFs in pancreatic cancer from the UCSC Xena. Based on difference analysis, the non-negative matrix factorization (NMF) algorithm was utilized to identify the immune characteristics and clinical significance of two different subtypes. The multivariate Cox regression was used to construct the risk model and then explore the differences in tumor immune microenvironment (TIME) and drug sensitivity between high and low groups. Through single-cell RNA sequencing (scRNA-seq) analysis, we screened KLF6 and further investigated its biological functions in pancreatic cancer and pan-cancer.ResultsThe KLFs exhibited differential expression and mutations in the transcriptomic profile of PDAC. According to the expression of KLFs, patients were classified into two distinct subtypes, each exhibiting significant differences in prognosis and TIME. Moreover, the KLF signature was developed using univariate Cox and Lasso regression, which proved to be a reliable and effective prognostic model. Furthermore, the KLF_Score was closely associated with immune infiltration, response to immunotherapy, and drug sensitivity and we screened small molecule compounds targeting prognostic genes separately. Through scRNA-seq analysis, KLF6 was selected to further demonstrate its role in the malignance of PC in vitro. Finally, pan-cancer analysis emphasized the biological significance of KLF6 in multiple types of tumors and its clinical utility in assessing cancer prognosis.ConclusionThis study elucidated the pivotal role of KLF family genes in the malignant development of PC through comprehensive analysis and revealed that KLF6 would be a novel diagnostic biomolecule marker and potential therapeutic target for PDAC.

Real-time decomposition technique for compressive light field display using the multiplex correlations

How to compress and decompose the high-dimensional light field information in real time is still a challenging task for compressive light field display. Traditional iterative algorithms suffer from slow convergence speed and limited image quality. Therefore, a real-time decomposition technique for compressive light field display using multiplex correlations is proposed. Firstly, the iteration initial value of the algorithm is optimized, by utilizing the spatial correlations of pixel multiplex light fields, which significantly improves the convergence speed and reduces noise. Secondly, the iterative task of high-dimensional matrix in the non-negative matrix factorization (NMF) algorithm is divided into highly parallel linear iterative tasks. A stochastic gradient descent (SGD) optimizer and GPU are used to parallel compress and decompose the light fields. Thirdly, addresses of light field data are reordered using the sign distance field (SDF) transformation in sheared camera frustum space, making the addressing process of compression and decomposition more efficient. A rendering pipeline is constructed that renders the compressive light fields using 3D model data directly. For a light field containing 5 × 5 viewpoints and 1024 × 1024 × 2 pixels, only 2-3 iterations are needed to approach the optimal solution. The decomposition efficiency is increased by 15.24 times. The frame rate of decomposition exceeds 30 frames per second (fps). A compressive light field display system has been built to realize 3D display, verifying the feasibility of the technique.

Investigating gene signatures associated with immunity in colon adenocarcinoma to predict the immunotherapy effectiveness using NFM and WGCNA algorithms.

Colon adenocarcinoma (COAD), a frequently encountered and highly lethal malignancy of the digestive system, has been the focus of intensive research regarding its prognosis. The intricate immune microenvironment plays a pivotal role in the pathological progression of COAD; nevertheless, the underlying molecular mechanisms remain incompletely understood. This study aims to explore the immune gene expression patterns in COAD, construct a robust prognostic model, and delve into the molecular mechanisms and potential therapeutic targets for COAD liver metastasis, thereby providing critical support for individualized treatment strategies and prognostic evaluation. Initially, we curated a comprehensive dataset by screening 2600 immune-related genes (IRGs) from the ImmPort and InnateDB databases, successfully obtaining a rich data resource. Subsequently, the COAD patient cohort was classified using the non-negative matrix factorization (NMF) algorithm, enabling accurate categorization. Continuing on, utilizing the weighted gene co-expression network analysis (WGCNA) method, we analyzed the top 5000 genes with the smallest p-values among the differentially expressed genes (DEGs) between immune subtypes. Through this rigorous screening process, we identified the gene modules with the strongest correlation to the COAD subpopulation, and the intersection of genes in these modules with DEGs (COAD vs COAD vs Normal colon tissue) is referred to as Differentially Expressed Immune Genes Associated with COAD (DEIGRC). Employing diverse bioinformatics methodologies, we successfully developed a prognostic model (DPM) consisting of six genes derived from the DEIGRC, which was further validated across multiple independent datasets. Not only does this predictive model accurately forecast the prognosis of COAD patients, but it also provides valuable insights for formulating personalized treatment regimens. Within the constructed DPM, we observed a downregulation of CALB2 expression levels in COAD tissues, whereas NOXA1, KDF1, LARS2, GSR, and TIMP1 exhibited upregulated expression levels. These genes likely play indispensable roles in the initiation and progression of COAD and thus represent potential therapeutic targets for patient management. Furthermore, our investigation into the molecular mechanisms and therapeutic targets for COAD liver metastasis revealed associations with relevant processes such as fat digestion and absorption, cancer gene protein polysaccharides, and nitrogen metabolism. Consequently, genes including CAV1, ANXA1, CPS1, EDNRA, and GC emerge as promising candidates as therapeutic targets for COAD liver metastasis, thereby providing crucial insights for future clinical practices and drug development. In summary, this study uncovers the immune gene expression patterns in COAD, establishes a robust prognostic model, and elucidates the molecular mechanisms and potential therapeutic targets for COAD liver metastasis, thereby possessing significant theoretical and clinical implications. These findings are anticipated to offer substantial support for both the treatment and prognosis management of COAD patients.

Abstract PS09-09: Multiomics profiling and molecular classification refine precision treatment strategies for HER2-positive breast cancer

Abstract Background: Anti-HER2 targeted therapy has achieved a series of breakthroughs. However, the current treatment strategy regarding HER2-positive breast cancer remains indiscriminate and lacks specificity, which limits the further improvement of overall treatment response and may lead to overtreatment and extra cost for some patients. Our study aims to reveal the molecular heterogeneity of HER2-positive breast cancer to guide a more precise treatment. Patients and methods: We selected HER2-positive breast cancer patients treated at Fudan University Shanghai Cancer Center between 2013 and 2014 and conducted genomic, transcriptomic, proteomic and metabolomic profiling. We then applied a non-negative matrix factorization algorithm on transcriptomic data to obtain an unsupervised classification. And we further studied the correlation between subtypes and corresponding treatment strategies in multiple cohorts of adjuvant and neoadjuvant therapy. For clinical accessibility, we developed convolutional neural network models through deep learning algorithm based on digital pathology to identify different subtypes. Additionally, we explored novel treatment strategies using the patient-derived organoids (PDOs) models. Results: We established a novel multiomics cohort of 180 HER2- breast cancer patients and classified them into four clinically significant molecular subtypes: (1) A classical HER2-enriched (HER2-CLA, N=51) subtype characterized by strong ERBB2 signaling and remarkable sensitivity to anti-HER2-targeted therapy (pathologic complete response with dual-targeted therapy: 93%). (2) an immunomodulatory (HER2-IM, N=36) subtype characterized by an immune-activated microenvironment and excellent prognosis with current treatment (no relapse in 97% of patients with a median follow-up of 86 months). Tumors of this subtype were therefore candidates for de-escalatory treatment. (3) A luminal-like (HER2-LUM, N=55) subtype distinguished by activated estrogen receptor signaling and (4) a basal/mesenchymal-like (HER2-BM, N=38) subtype enriched in activated receptor tyrosine kinase pathways. HER2-LUM and HER2- BM showed limited benefit from anti-HER2 therapy, and thus, add-on therapies might be needed. The overall area under the curve (AUC) of the convolutional neural network model based on digital pathology for identifying different subtypes is 0.77. In the exploration of novel treatment strategies, we found in the PDO model that the HER2-LUM subtype is more sensitive to a treatment regimen combining standard (chemotherapy and targeted therapy) with subsequent endocrine therapy and CDK4/6 inhibitors compared to other subtypes. Additionally, the HER2-BM subtype demonstrated greater sensitivity to treatment with a combination of EGFR inhibitors, PDGFR inhibitors or VEGFR inhibitors. Conclusion: We uncovered a high degree of molecular heterogeneity in HER2-positive breast cancer and illustrated its impact on treatment response. More precise treatment can be given according to the characteristics of different subtypes, which may achieve good efficacy and simultaneously reduce overtreatment and extra cost. The comprehensive profiling of HER2-positive breast cancers could also serve as an important resource for further exploration. Key Words: HER2-positive breast cancer cohort; molecular classification; targeted therapy; precision treatment; de-escalatory treatment. Citation Format: Yu-Wei Li, Ding Ma, Xiang-Rong Wu, Lei-Jie Dai, Shen Zhao, Yu-Zheng Xu, Xi Jin, Xiao Yi, Ying Wang, Cai-Jin Lin, Yi-Fan Zhou, Tong Fu, Wen-Tao Yang, Ming Li, Hong Lv, Yi-Zhou Jiang, Zhi-Ming Shao. Multiomics profiling and molecular classification refine precision treatment strategies for HER2-positive breast cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PS09-09.

Exploring Endocrine Signaling between Adipose Tissues and the Heart using Transfer Learning and Induced Pluripotent Stem Cell Models

Background: Because of the amount of evidence pointed toward obesity as a co-morbidity of heart disease, our goal in this study is to use a data-driven method to discover potential cross talk signals between adipose and cardiac tissues, which may reveal a physiological reason for this association. For this study, we hypothesized that adipose-cardiac crosstalk signaling can be found by unexpected co-expression between adipose tissue genes encoding secreted proteins and cardiac tissue genes and vice versa. By discovering new crosstalk signals between these two tissues, we can find new associations between heart disease and obesity. Methods: Cross-tissue correlations of gene expression have been used to identify candidate endocrine signals that mediate tissue crosstalk, which are otherwise diffcult to detect in circulation. However, the identification of significant cross-tissue gene co-expression is hindered by immense multiple-testing burden. Our goal here is to abstract gene expression patterns of tissues into eigengenes and then test their correlation with secreted protein coding genes across tissues in a pairwise fashion. We first used the NIH Common Fund Genotype-Tissue Expression data set (GTEx v8) which contains RNA seq gene expression data from matched tissues of over 17,000 transcriptomes, to learn the latent structure of gene expression across tissues. To do so, we used PLIER (pathway level information extractor), a matrix factorization algorithm to extract the latent targets as eigengenes that map to specific biological pathways in the target tissue (e.g., pathways in the heart in the case of adipose to heart crosstalk). The learned gene expression structure is then transferred to a smaller data set with matching donor adipose and heart transcript expression data, from which a correlation matrix is constructed to find significant relationships between source tissue crosstalk signals and target tissue eigengenes and nominate novel crosstalk signals. Results: Adipose to heart tissue cross talk correlations using PLIER derived latent eigengene targets revealed many adipokines that had strong correlations with pathways found in the heart tissue through similar gene expression. Among these strong correlations were eigengene targets that were wrapped in metabolism pathways particularly those of fatty acid, phospholipid, and protein metabolism. Adipokines that showed high significant and positive correlation with cardiac latent variable expression included Adiponectin (R = 0.32, p = 4.7e−13), Glutathione Peroxidase 3 (R = 0.34, p = 5e−15) and Galectin 9 (R = 0.37, p < 2.2e−16) among others. Based on these results, we nominated new potential relationships between adipose and cardiac tissue. Work is currently under way to validate these candidate crosstalk signals using human induced pluripotent stem cell (iPSC)-derived cardiomyocytes. Future Directions In conclusion, we have found strong evidence in silico to suggest a relationship between known secreted proteins from adipose tissue (adipokine) and the expression of important pathways (such as fatty acid and protein metabolism) in the heart. Based on the findings of these correlations between adipokines and latent eigengene pathways within the heart, our future directions will involved the understanding of potential downstream functional consequences mediated by the adipose secreted proteins in iPSC derived models. This project was supported in part by NIH award R03-OD032666 and the University of Colorado Translational Research Scholar Program to E.L. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Personalised Outfit Recommendation System Using Deep Learning

Abstract: Fashion engineering presents a significant challenge in efficiently coordinating outfits to suit personal preferences. In this study, we introduce a Fashion Coordination Assistant featuring a hybrid recommendation system. Our approach combines content-based and collaborative filtering techniques, utilizing Singular Value Decomposition (SVD) and Non-negative Matrix Factorization (NMF) algorithms. By thoroughly analyzing clothing characteristics and user behavior, we address the technical complexities of fashion coordination. Leveraging the latent features identified by SVD and the non-linear relationships captured by NMF, our system generates tailored outfit suggestions based on individual preferences and style profiles. Extensive testing validates the system's ability to provide diverse and efficient recommendations. By integrating innovative recommendation methods, the Fashion Coordination Assistant adapts to evolving fashion trends and user preferences, enhancing its practical utility in real-world scenarios

Semi-supervised Multi-view Clustering based on NMF with Fusion Regularization

Multi-view clustering has attracted significant attention and application. Nonnegative matrix factorization is one popular feature of learning technology in pattern recognition. In recent years, many semi-supervised nonnegative matrix factorization algorithms were proposed by considering label information, which has achieved outstanding performance for multi-view clustering. However, most of these existing methods have either failed to consider discriminative information effectively or included too much hyper-parameters. Addressing these issues, a semi-supervised multi-view nonnegative matrix factorization with a novel fusion regularization (FRSMNMF) is developed in this article. In this work, we uniformly constrain alignment of multiple views and discriminative information among clusters with designed fusion regularization. Meanwhile, to align the multiple views effectively, two kinds of compensating matrices are used to normalize the feature scales of different views. Additionally, we preserve the geometry structure information of labeled and unlabeled samples by introducing the graph regularization simultaneously. Due to the proposed methods, two effective optimization strategies based on multiplicative update rules are designed. Experiments implemented on six real-world datasets have demonstrated the effectiveness of our FRSMNMF comparing with several state-of-the-art unsupervised and semi-supervised approaches.

Integrating machine learning algorithms and single-cell analysis to identify gut microbiota-related macrophage biomarkers in atherosclerotic plaques.

The relationship between macrophages and the gut microbiota in patients with atherosclerosis remains poorly defined, and effective biological markers are lacking. This study aims to elucidate the interplay between gut microbial communities and macrophages, and to identify biomarkers associated with the destabilization of atherosclerotic plaques. The goal is to enhance our understanding of the underlying molecular pathways and to pave new avenues for diagnostic approaches and therapeutic strategies in the disease. This study employed Weighted Gene Co-expression Network Analysis (WGCNA) and differential expression analysis on atherosclerosis datasets to identify macrophage-associated genes and quantify the correlation between these genes and gut microbiota gene sets. The Random Forest algorithm was utilized to pinpoint PLEK, IRF8, BTK, CCR1, and CD68 as gut microbiota-related macrophage genes, and a nomogram was constructed. Based on the top five genes, a Non-negative Matrix Factorization (NMF) algorithm was applied to construct gut microbiota-related macrophage clusters and analyze their potential biological alterations. Subsequent single-cell analyses were conducted to observe the expression patterns of the top five genes and the interactions between immune cells. Finally, the expression profiles of key molecules were validated using clinical samples from atherosclerosis patients. Utilizing the Random Forest algorithm, we ultimately identified PLEK, IRF8, CD68, CCR1, and BTK as gut microbiota-associated macrophage genes that are upregulated in atherosclerotic plaques. A nomogram based on the expression of these five genes was constructed for use as an auxiliary tool in clinical diagnosis. Single-cell analysis confirmed the specific expression of gut microbiota-associated macrophage genes in macrophages. Clinical samples substantiated the high expression of PLEK in unstable atherosclerotic plaques. Gut microbiota-associated macrophage genes (PLEK, IRF8, CD68, CCR1, and BTK) may be implicated in the pathogenesis of atherosclerotic plaques and could serve as diagnostic markers to aid patients with atherosclerosis.

Identification of two distinct head and neck squamous cell carcinoma subtypes based on fatty acid metabolism-related signatures: Implications for immunotherapy and chemotherapy.

The dysregulation of lipid metabolism is a critical factor in the initiation and progression of tumors. In this investigation, we aim to characterize the molecular subtypes of head and neck squamous cell carcinoma (HNSCC) based on their association with fatty acid metabolism and develop a prognostic risk model. The transcriptomic and clinical data about HNSCC were obtained from public databases. Clustering analysis was conducted on fatty acid metabolism genes (FAMG) associated with prognosis, utilizing the non-negative matrix factorization algorithm. The immune infiltration, response to immune therapy, and drug sensitivity between molecular subtypes were evaluated. Differential expression genes were identified between subtypes, and a prognostic model was constructed using Cox regression analyses. A nomogram for HNSCC was constructed and evaluated. Thirty FAMGs have been found to exhibit differential expression in HNSCC, out of which three are associated with HNSCC prognosis. By performing clustering analysis on these 3 genes, 2 distinct molecular subtypes of HNSCC were identified that exhibit significant heterogeneity in prognosis, immune landscape, and treatment response. Using a set of 7778 genes that displayed differential expression between the 2 molecular subtypes, a prognostic risk model for HNSCC was constructed comprising 11 genes. This model has the ability to stratify HNSCC patients into high-risk and low-risk groups, which exhibit significant differences in prognosis, immune infiltration, and immune therapy response. Moreover, our data suggest that this risk model is negatively correlated with B cells and most T cells, but positively correlated with macrophages, mast cells, and dendritic cells. Ultimately, we constructed a nomogram incorporating both the risk signature and radiotherapy, which has demonstrated exceptional performance in predicting prognosis for HNSCC patients. A molecular classification system and prognostic risk models were developed for HNSCC based on FAMGs. This study revealed the potential involvement of FAMGs in modulating tumor immune microenvironment and response to treatment.

A seismic thin‐layer detection factor calculated by integrated S transform with non‐negative matrix factorization

AbstractTime–frequency analysis is one of the effective methods for seismic thin‐layer detection. Conventional time–frequency analysis technology for seismic thin‐layer detection is interfered by the energy of adjacent frequency signals, and there is information redundancy in the frequency‐domain analysis. Therefore, an S transform with improved window factor, which is based on the constrained non‐negative matrix factorization, is constructed to realize seismic thin‐layer detection. First, the seismic data is processed by the S transform of the improved window factor, and then we can obtain the frequency‐domain information with strong time–frequency focus by changing the adjustment factor and attenuation factor in the window function. Furthermore, the key frequency of the seismic data spectrum, which can also be called the key frequency characteristic factor, can be calculated by the non‐negative matrix factorization algorithm. Fortunately, the overthrust model shows a good correspondence between the key frequency characteristic factor and the thin‐layer interface. The field data example shows that this approach provides a new approach for thin‐layer detection.

Integrating Multi-omics Data for Alzheimer's Disease to Explore Its Biomarkers Via the Hypergraph-Regularized Joint Deep Semi-Non-Negative Matrix Factorization Algorithm.

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disorder. Its etiology may be associated with genetic, environmental, and lifestyle factors. With the advancement of technology, the integration of genomics, transcriptomics, and imaging data related to AD allows simultaneous exploration of molecular information at different levels and their interaction within the organism. This paper proposes a hypergraph-regularized joint deep semi-non-negative matrix factorization (HR-JDSNMF) algorithm to integrate positron emission tomography (PET), single-nucleotide polymorphism (SNP), and gene expression data for AD. The method employs matrix factorization techniques to nonlinearly decompose the original data at multiple layers, extracting deep features from different omics data, and utilizes hypergraph mining to uncover high-order correlations among the three types of data. Experimental results demonstrate that this approach outperforms several matrix factorization-based algorithms and effectively identifies multi-omics biomarkers for AD. Additionally, single-cell RNA sequencing (scRNA-seq) data for AD were collected, and genes within significant modules were used to categorize different types of cell clusters into high and low-risk cell groups. Finally, the study extensively explores the differences in differentiation and communication between these two cell types. The multi-omics biomarkers unearthed in this study can serve as valuable references for the clinical diagnosis and drug target discovery for AD. The realization of the algorithm in this paper code is available at https://github.com/ShubingKong/HR-JDSNMF .

A prognostic signature established based on genes related to tumor microenvironment for patients with hepatocellular carcinoma.

Complex cellular signaling network in the tumor microenvironment (TME) could serve as an indicator for the prognostic classification of hepatocellular carcinoma (HCC) patients. Univariate Cox regression analysis was performed to screen prognosis-related TME-related genes (TRGs), based on which HCC samples were clustered by running non-negative matrix factorization (NMF) algorithm. Furthermore, the correlation between different molecular HCC subtypes and immune cell infiltration level was analyzed. Finally, a risk score (RS) model was established by LASSO and Cox regression analyses (CRA) using these TRGs. Functional enrichment analysis was performed using gene set enrichment analysis (GSEA). HCC patients were divided into three molecular subtypes (C1, C2, and C3) based on 704 prognosis-related TRGs. HCC subtype C1 had significantly better OS than C2 and C3. We selected 13 TRGs to construct the RS model. Univariate and multivariate CRA showed that the RS could independently predict patients' prognosis. A nomogram integrating the RS and clinicopathologic features of the patients was further created. We also validated the reliability of the model according to the area under the receiver operating characteristic (ROC) curve value, concordance index (C-index), and decision curve analysis. The current findings demonstrated that the RS was significantly correlated with CD8+ T cells, monocytic lineage, and myeloid dendritic cells. This study provided TRGs to help classify patients with HCC and predict their prognoses, contributing to personalized treatments for patients with HCC.

Electronic Information System Signal Noise for Noise Reduction using Variational Bayesian based Robust Adaptive Filter

The most significant issues for a thousand users is the unwanted or loud signals in sound files, it is impossible to eliminate or minimize these noise signals without knowledge their types and ranges. To overcome this issue, present an Electronic Information System Signal Noise for Noise Reduction using Variational Bayesian based Robust Adaptive Filter (EIS-SNR-VBRAF) is proposed. Initially, the data is collected from Adaptive Myriad Filter using Time-Varying Noise and Signal-Dependent Parameters dataset. Then, the data is given for Pre-processing section, Variational Bayesian based Robust Adaptive Filter (VBRAF) is used to reduce the signal noise from Gaussian Noise, Traffic noise and Audio signal back ground noise. The proposed technique is implemented and efficacy of EIS-SNR-VBRAF technique is assessed by support of numerous performances such as BER, Signal-to-Noise-Ratio (SNR), Mean Squared Error, Peak Signal-to-Noise Ratio (PSNR), Root Mean Square Error, Structural Similarity Index, Cross-Correlation and Computational Complexity is analyzed. The proposed EIS-SNR-VBRAF method attains 21.18%, 23.52% and 23.65% lower RMSE, 21.52%, 21.76% and 23.24% higher PSNR, 21.19%, 21.73% and 20.48% higher Structural Similarity Index are compared with existing methods like early detection of mechanical malfunctions in vehicles utilizing sound signal processing (ED-MMV-SSP),noise reduction in infrasound signals based on mask coefficient binary weighting generalized cross correlation non-negative matrix factorization algorithm (NRID-MCWG-NMFA) and Click-event sound detection in automotive industry using machine/deep learning (CE-SDSI-DL) respectively.

Integrating transcriptomics and machine learning for immunotherapy assessment in colorectal cancer

Colorectal cancer (CRC) is a highly prevalent and lethal malignancy worldwide. Although immunotherapy has substantially improved CRC outcomes, intolerance remains a major concern among most patients. Considering the pivotal role of the tumor microenvironment (TME) in tumor progression and treatment outcomes, profiling the TME at the transcriptomic level can provide novel insights for developing CRC treatment strategies. Seventy-seven TME-associated signatures were acquired from previous studies. To elucidate variations in prognosis, clinical features, genomic alterations, and responses to immunotherapy in CRC, we employed a non-negative matrix factorization algorithm to categorize 2595 CRC samples of 27 microarrays from the Gene Expression Omnibus database. Three machine learning techniques were employed to identify a signature specific to immunotherapy. Subsequently, the mechanisms by which this signature interacts with TME subtypes and immunotherapy were investigated. Our findings revealed five distinct TME subtypes (TMESs; TMES1–TMES5) in CRC, each exhibiting a unique pattern of immunotherapy response. TMES1, TMES4, and TMES5 had relatively inferior outcomes, TMES2 was associated with the poorest prognosis, and TMES3 had a superior outcome. Subsequent investigations revealed that activated dendritic cells could enhance the immunotherapy response rate, with their augmentation effect closely associated with the activation of CD8+T cells. We successfully classified CRC into five TMESs, each demonstrating varying response rates to immunotherapy. Notably, the application of machine learning to identify activated dendritic cells helped elucidate the underlying mechanisms contributing to these differences. We posit that these TMESs hold promising clinical implications for prognostic evaluation and guidance of immunotherapy strategies, thereby providing valuable insights to inform clinical decision-making.

Abstract 3494: KINOMO: A non-negative matrix factorization framework for recovering intra- and inter-tumoral heterogeneity from single-cell RNA-seq data

Abstract Single-cell RNA-sequencing (scRNA-seq) is a powerful technology to uncover cellular heterogeneity in tumor ecosystems. Due to differences in underlying gene load, direct comparison between patient samples is challenging, and this is further complicated by the sparsity of data matrices in scRNA-seq. Here, we present a factorization method called KINOMO (Kernel dIfferentiability correlation-based NOn- negative Matrix factorization algorithm using Kullback-Leibler divergence loss Optimization). This tool uses quadratic approximation approach for error correction and an iterative multiplicative approach, which improves the quality assessment of NMF-identified factorization, while mitigating biases introduced by inter-patient genomic variability. We benchmarked this new approach against nine different methods across 150 scRNA-seq experiments and find that KINOMO outperforms prior methods when evaluated with an adjusted Rand index (ARI), ranging 0.82-0.91 compared to 0.68-0.77. Thus, KINOMO provides an improved approach for determining coherent transcriptional programs (and meta-programs) from scRNA- seq data of cancer tissues, enabling comparison of patients with variable genomic backgrounds. Citation Format: Somnath Tagore, Yiping Wang, Jana Biermann, Edridge K. D'Souza, Karan D. Luthria, Raul Rabadan, Elham Azizi, Benjamin Izar. KINOMO: A non-negative matrix factorization framework for recovering intra- and inter-tumoral heterogeneity from single-cell RNA-seq data [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3494.