A novel nomogram model for lung adenocarcinoma subtypes based on RNA-modification regulatory genes.

Background: In non-small cell lung cancer (NSCLC), lung adenocarcinoma (LUAD) is the most common subtype. RNA modification has become the frontier and hotspot of current tumor research. Results: In this study, 109 genes that regulate RNA modifications were identified according to The Cancer Genome Atlas (TCGA). A differential gene expression analysis identified 46 differentially expressed RNA modification regulatory genes (DERRGs). LUAD samples were stratified into two distinct clusters based on the expression of these DERRGs. A significant correlation was observed between these clusters and patient survival rates, as well as clinical features. Furthermore, a four-DERRG signature (EIF3B, HNRNPC, IGF2BP1, and METTL3) developed using LASSO regression. According to the calculated risk scores from this signature, LUAD patients were categorized into high-risk and low-risk groups. Patients in the low-risk group exhibited a more favorable prognosis. A prognostic nomogram was crafted, integrating the four-DERRGs signature with clinical parameters. The nomogram was revealed that OS, age, clinical stage, immune cell infiltration, and immune checkpoint molecule expression were significantly linked to the OS of LUAD. GSEA analysis found that the DERRGs were primarily regulated immune pathways. Conclusions: This study developed four DERRGs signatures and formulated a nomogram model for precise prognosis estimation in LUAD patients. The study's insights are instrumental for advancing diagnosis, prognosis, and therapeutic strategies for LUAD.

Phase division and recognition of crystal HRTEM images based on machine learning and deep learning.

The High Resolution Transmission Electron Microscope (HRTEM) images provide valuable insights into the atomic microstructure, dislocation patterns, defects, and phase characteristics of materials. However, the current analysis and research of HRTEM images of crystal materials heavily rely on manual expertise, which is labor-intensive and susceptible to subjective errors. This study proposes a combined machine learning and deep learning approach to automatically partition the same phase regions in crystal HRTEM images. The entire image is traversed by a sliding window to compute the amplitude spectrum of the Fast Fourier Transform (FFT) in each window. The generated data is transformed into a 4-dimensional (4D) format. Principal component analysis (PCA) on this 4D data estimates the number of feature regions. Non-negative matrix factorization (NMF) then decomposes the data into a coefficient matrix representing feature region distribution, and a feature matrix corresponding to the FFT magnitude spectra. Phase recognition based on deep learning enables identifying the phase of each feature region, thereby achieving automatic segmentation and recognition of phase regions in HRTEM images of crystals. Experiments on zirconium and oxide nanoparticle HRTEM images demonstrate the proposed method achieve the consistency of manual analysis. Code and supplementary material are available at https://github.com/rememberBr/HRTEM2.

Clinically relevant immune subtypes based on alternative splicing landscape of immune-related genes for lung cancer advanced PPPM approach.

Background: Alternative splicing (AS) occurs in the process of gene post-transcriptional process, which is very important for the correct synthesis and function of protein. The change of AS pattern may lead to the change of expression level or function of lung cancer-related genes, and then affect the occurrence and development of lung cancers. The specific AS pattern might be used as a biomarker for early warning and prognostic assessment of a cancer in the framework of predictive, preventive, and personalized medicine (PPPM; 3PM). AS events of immune-related genes (IRGs) were closely associated with tumor progression and immunotherapy. We hypothesize that IRG-AS events are significantly different in lung adenocarcinomas (LUADs) vs. controls or in lung squamous cell carcinomas (LUSCs) vs. controls. IRG-AS alteration profiling was identified to construct IRG-differentially expressed AS (IRG-DEAS) signature models. Study on the selective AS events of specific IRGs in lung cancer patients might be of great significance for further exploring the pathogenesis of lung cancer, realizing early detection and effective monitoring of lung cancer, finding new therapeutic targets, overcoming drug resistance, and developing more effective therapeutic strategies, and better used for the prediction, diagnosis, prevention, and personalized medicine of lung cancer. Methods: The transcriptomic, clinical, and AS data of LUADs and LUSCs were downloaded from TCGA and its SpliceSeq databases. IRG-DEAS events were identified in LUAD and LUSC, followed by their functional characteristics, and overall survival (OS) analyses. OS-related IRG-DEAS prognostic models were constructed for LUAD and LUSC with Lasso regression, which were used to classify LUADs and LUSCs into low- and high-risk score groups. Furthermore, the immune cell distribution, immune-related scores, drug sensitivity, mutation status, and GSEA/GSVA status were analyzed between low- and high-risk score groups. Also, low- and high-immunity clusters and AS factor (SF)-OS-related-AS co-expression network and verification of cell function of CELF6 were analyzed in LUAD and LUSC. Results: Comprehensive analysis of transcriptomic, clinical, and AS data of LUADs and LUSCs identified IRG-AS events in LUAD (n = 1607) and LUSC (n = 1656), including OS-related IRG-AS events in LUAD (n = 127) and LUSC (n = 105). A total of 66 IRG-DEAS events in LUAD and 89 IRG-DEAS events in LUSC were identified compared to controls. The overlapping analysis between IRG-DEASs and OS-related IRG-AS events revealed 14 OS-related IRG-DEAS events for LUAD and 16 OS-related IRG-DEAS events for LUSC, which were used to identify and optimize a 12-OS-related-IRG-DEAS signature prognostic model for LUAD and an 11-OS-related-IRG-DEAS signature prognostic model for LUSC. These two prognostic models effectively divided LUAD or LUSC samples into low- and high-risk score groups that were closely associated with OS, clinical characteristics, and tumor immune microenvironment, with significant gene sets and pathways enriched in the two groups. Moreover, weighted gene co-expression network (WGCNA) and nonnegative matrix factorization method (NMF) analyses identified four OS-relevant subtypes of LUAD and six OS-relevant subtypes of LUSC, and ssGSEA identified five immunity-relevant subtypes of LUAD and five immunity-relevant subtypes of LUSC. Interestingly, splicing factors-OS-related-AS network revealed hub molecule CELF6 was significantly related to the malignant phenotype in lung cancer cells. Conclusions: This study established two reliable IRG-DEAS signature prognostic models and constructed interesting splicing factor-splicing event networks in LUAD and LUSC, which can be used to construct clinically relevant immune subtypes, patient stratification, prognostic prediction, and personalized medical services in the PPPM practice. Supplementary Information: The online version contains supplementary material available at 10.1007/s13167-024-00366-4.

Screening Disinfection Byproducts in Arid-Coastal Wastewater: A Workflow Using GC×GC-TOFMS, Passive Sampling, and NMF Deconvolution Algorithm.

Disinfection during tertiary municipal wastewater treatment is a necessary step to control the spread of pathogens; unfortunately, it also gives rise to numerous disinfection byproducts (DBPs), only a few of which are regulated because of the analytical challenges associated with the vast number of potential DBPs. This study utilized polydimethylsiloxane (PDMS) passive samplers, comprehensive two-dimensional gas chromatography (GC×GC) coupled with time-of-flight mass spectrometry (TOFMS), and non-negative matrix factorization (NMF) spectral deconvolution for suspect screening of DBPs in treated wastewater. PDMS samplers were deployed upstream and downstream of the chlorination unit in a municipal wastewater treatment plant located in Abu Dhabi, and their extracts were analyzed using GC×GC-TOFMS. A workflow incorporating a multi-tiered, eight-filter screening process was developed, which successfully enabled the reliable isolation of 22 candidate DBPs from thousands of peaks. The NMF spectral deconvolution improved the match factor score of unknown mass spectra to the reference mass spectra available in the NIST library by 17% and facilitated the identification of seven additional DBPs. The close match of the first-dimension retention index data and the GC×GC elution patterns of DBPs, both predicted using the Abraham solvation model, with their respective experimental counterparts-with the measured data available in the NIST WebBook and the GC×GC elution patterns being those observed for the candidate peaks-significantly enhanced the accuracy of peak assignment. Isotopic pattern analysis revealed a close correspondence for 11 DBPs with clearly visible isotopologues in reference spectra, thereby further strengthening the confidence in the peak assignment of these DBPs. Brominated analogues were prevalent among the detected DBPs, possibly due to seawater intrusion. The fate, behavior, persistence, and toxicity of tentatively identified DBPs were assessed using EPI Suite™ and the CompTox Chemicals Dashboard. This revealed their significant toxicity to aquatic organisms, including developmental, mutagenic, and endocrine-disrupting effects in certain DBPs. Some DBPs also showed activity in various CompTox bioassays, implicating them in adverse molecular pathways. Additionally, 11 DBPs demonstrated high environmental persistence and resistance to biodegradation. This combined approach offers a powerful tool for future research and environmental monitoring, enabling accurate identification and assessment of DBPs and their potential risks.

Unveiling the molecular complexity of proliferative diabetic retinopathy through scRNA-seq, AlphaFold 2, and machine learning.

Background: Proliferative diabetic retinopathy (PDR), a major cause of blindness, is characterized by complex pathogenesis. This study integrates single-cell RNA sequencing (scRNA-seq), Non-negative Matrix Factorization (NMF), machine learning, and AlphaFold 2 methods to explore the molecular level of PDR. Methods: We analyzed scRNA-seq data from PDR patients and healthy controls to identify distinct cellular subtypes and gene expression patterns. NMF was used to define specific transcriptional programs in PDR. The oxidative stress-related genes (ORGs) identified within Meta-Program 1 were utilized to construct a predictive model using twelve machine learning algorithms. Furthermore, we employed AlphaFold 2 for the prediction of protein structures, complementing this with molecular docking to validate the structural foundation of potential therapeutic targets. We also analyzed protein-protein interaction (PPI) networks and the interplay among key ORGs. Results: Our scRNA-seq analysis revealed five major cell types and 14 subcell types in PDR patients, with significant differences in gene expression compared to those in controls. We identified three key meta-programs underscoring the role of microglia in the pathogenesis of PDR. Three critical ORGs (ALKBH1, PSIP1, and ATP13A2) were identified, with the best-performing predictive model demonstrating high accuracy (AUC of 0.989 in the training cohort and 0.833 in the validation cohort). Moreover, AlphaFold 2 predictions combined with molecular docking revealed that resveratrol has a strong affinity for ALKBH1, indicating its potential as a targeted therapeutic agent. PPI network analysis, revealed a complex network of interactions among the hub ORGs and other genes, suggesting a collective role in PDR pathogenesis. Conclusion: This study provides insights into the cellular and molecular aspects of PDR, identifying potential biomarkers and therapeutic targets using advanced technological approaches.

Crosstalk among proximal tubular cells, macrophages, and fibroblasts in acute kidney injury: single-cell profiling from the perspective of ferroptosis.

The link between ferroptosis, a form of cell death mediated by iron and acute kidney injury (AKI) is recently gaining widespread attention. However, the mechanism of the crosstalk between cells in the pathogenesis and progression of acute kidney injury remains unexplored. In our research, we performed a non-negative matrix decomposition (NMF) algorithm on acute kidney injury single-cell RNA sequencing data based specifically focusing in ferroptosis-associated genes. Through a combination with pseudo-time analysis, cell-cell interaction analysis and SCENIC analysis, we discovered that proximal tubular cells, macrophages, and fibroblasts all showed associations with ferroptosis in different pathways and at various time. This involvement influenced cellular functions, enhancing cellular communication and activating multiple transcription factors. In addition, analyzing bulk expression profiles and marker genes of newly defined ferroptosis subtypes of cells, we have identified crucial cell subtypes, including Egr1 + PTC-C1, Jun + PTC-C3, Cxcl2 + Mac-C1 and Egr1 + Fib-C1. All these subtypes which were found in AKI mice kidneys and played significantly distinct roles from those of normal mice. Moreover, we verified the differential expression of Egr1, Jun, and Cxcl2 in the IRI mouse model and acute kidney injury human samples. Finally, our research presented a novel analysis of the crosstalk of proximal tubular cells, macrophages and fibroblasts in acute kidney injury targeting ferroptosis, therefore, contributing to better understanding the acute kidney injury pathogenesis, self-repairment and acute kidney injury-chronic kidney disease (AKI-CKD) progression.

Dual-learning Multi-hop Nonnegative Matrix Factorization for community detection.

As an important branch of network science, community detection has garnered significant attention. Among various community detection methods, nonnegative matrix factorization (NMF)-based community detection approaches have become a popular research topic. However, most NMF-based methods overlook the network's multi-hop information, let alone the community detection results specific to each hop of the network. In this paper, we propose Dual-learning Multi-hop NMF (DL-MHNMF), a method that considers not only the multi-hop connectivity between two nodes but also factors in the shared results across multiple hops and the impact of differences in the specific results at each hop on the shared outcomes. An efficient iterative optimization algorithm with guaranteed theoretical convergence is proposed for solving DL-MHNMF. Methodologically, by iteratively removing the specific results during the optimization process of DL-MHNMF, we achieve enhanced detection accuracy, which is also verified by subsequent experiments. Specifically, we compare fourteen algorithms on eleven publicly available datasets, and experimental results show that our algorithm outperforms most state-of-the-art methods. The source code is availiable at https://github.com/bx20000827/DL-MHNMF.git.

Non-negative matrix factorization-aided phase unmixing and trace element quantification of STEM-EDXS data.

Energy-dispersive X-ray spectroscopy (EDXS) mapping with a scanning transmission electron microscope (STEM) is commonly used for chemical characterization of materials. However, STEM-EDXS quantification becomes challenging when the phases constituting the sample under investigation share common elements and overlap spatially. In this paper, we present a methodology to identify, segment, and unmix phases with a substantial spectral and spatial overlap in a semi-automated fashion through combining non-negative matrix factorization with a priori knowledge of the sample. We illustrate the methodology using a sample taken from an electron beam-sensitive mineral assemblage representing Earth's deep mantle. With it, we retrieve the true EDX spectra of the constituent phases and their corresponding phase abundance maps. It further enables us to achieve a reliable quantification for trace elements having concentration levels of ∼100 ppm. Our approach can be adapted to aid the analysis of many materials systems that produce STEM-EDXS datasets having phase overlap and/or limited signal-to-noise ratio (SNR) in spatially-integrated spectra.

Flexible model-based non-negative matrix factorization with application to mutational signatures.

Somatic mutations in cancer can be viewed as a mixture distribution of several mutational signatures, which can be inferred using non-negative matrix factorization (NMF). Mutational signatures have previously been parametrized using either simple mono-nucleotide interaction models or general tri-nucleotide interaction models. We describe a flexible and novel framework for identifying biologically plausible parametrizations of mutational signatures, and in particular for estimating di-nucleotide interaction models. Our novel estimation procedure is based on the expectation-maximization (EM) algorithm and regression in the log-linear quasi-Poisson model. We show that di-nucleotide interaction signatures are statistically stable and sufficiently complex to fit the mutational patterns. Di-nucleotide interaction signatures often strike the right balance between appropriately fitting the data and avoiding over-fitting. They provide a better fit to data and are biologically more plausible than mono-nucleotide interaction signatures, and the parametrization is more stable than the parameter-rich tri-nucleotide interaction signatures. We illustrate our framework in a large simulation study where we compare to state of the art methods, and show results for three data sets of somatic mutation counts from patients with cancer in the breast, Liver and urinary tract.

Impact of fed-batch process intensification on the productivity and product quality of two CHO cell lines expressing unique novel molecular format proteins.

While monospecific antibodies have long been the foundational offering of protein therapeutics, recent advancements in antibody engineering have allowed for the development of far more complex antibody structures. Novel molecular format (NMF) proteins, such as bispecific antibodies (BsAbs), are structures capable of multispecific binding, allowing for expanded therapeutic functionality. As demand for NMF proteins continues to rise, biomanufacturers face the challenge of increasing bioreactor process productivity while simultaneously maintaining consistent product quality. This challenge is exacerbated when producing structurally complex proteins with asymmetric modalities, as seen in NMFs. In this study, the impact of a high inoculation density (HID) fed-batch process on the productivity and product quality attributes of two CHO cell lines expressing unique NMFs, a monospecific antibody with an Fc-fusion protein and a bispecific antibody, compared to low inoculation density (LID) platform fed-batch processes was evaluated. It was observed that an intensified platform fed-batch process increased product concentrations by 33 and 109% for the two uniquely structured complex proteins in a shorter culture duration while maintaining similar product quality attributes to traditional fed-batch processes.

Data-driven decomposition and staging of flortaucipir uptake in Alzheimer's disease.

INTRODUCTION: Previous approaches pursuing in vivo staging of tau pathology in Alzheimer's disease (AD) have typically relied on neuropathologically defined criteria. In using predefined systems, these studies may miss spatial deposition patterns which are informative of disease progression. METHODS: We selected discovery (n = 418) and replication (n = 132) cohorts with flortaucipir imaging. Non-negative matrix factorization (NMF) was applied to learn tau covariance patterns and develop a tau staging system. Flortaucipir components were also validated by comparison with amyloid burden, gray matter loss, and the expression of AD-related genes. RESULTS: We found eight flortaucipir covariance patterns which were reproducible and overlapped with relevant gene expression maps. Tau stages were associated with AD severity as indexed by dementia status and neuropsychological performance. Comparisons of flortaucipir uptake with amyloid and atrophy also supported our model of tau progression. DISCUSSION: Data-driven decomposition of flortaucipir uptake provides a novel framework for tau staging which complements existing systems. HIGHLIGHTS: NMF reveals patterns of tau deposition in AD. Data-driven staging of flortaucipir tracks AD severity. Learned flortaucipir patterns overlap with AD-related gene expression.

Eliminating bias: enhancing children's book recommendation using a hybrid model of graph convolutional networks and neural matrix factorization.

Managing user bias in large-scale user review data is a significant challenge in optimizing children's book recommendation systems. To tackle this issue, this study introduces a novel hybrid model that combines graph convolutional networks (GCN) based on bipartite graphs and neural matrix factorization (NMF). This model aims to enhance the precision and efficiency of children's book recommendations by accurately capturing user biases. In this model, the complex interactions between users and books are modeled as a bipartite graph, with the users' book ratings serving as the weights of the edges. Through GCN and NMF, we can delve into the structure of the graph and the behavioral patterns of users, more accurately identify and address user biases, and predict their future behaviors. Compared to traditional recommendation systems, our hybrid model excels in handling large-scale user review data. Experimental results confirm that our model has significantly improved in terms of recommendation accuracy and scalability, positively contributing to the advancement of children's book recommendation systems.

Analysis and modelling of profiles to understand fractionation processes for contaminations with polychlorinated biphenyls observed in fish.

Polychlorinated biphenyls (PCB) both continue to spread into the environment and to bioaccumulate from primary urban and industrial sources as well as from secondary sources such as soils and the oceans. Fractions of congeners in PCB mixtures, i.e. PCB profiles, can be used as fingerprints to trace contamination pathways from sources to sinks because PCB mixtures fractionate during transport due to congener specific phase changes and degradation. Using a statistical analysis of a total of 8584 PCB profiles with seven congeners (CB28, CB52, CB101, CB118, CB138, CB153, CB180) for contaminated fish from two international datasets as well as a modelling of profiles, two major fractionation processes related to distinct contamination pathways were identified: (1) A relative enrichment of lighter congeners (CB28, CB52, CB101) in seawater fish due to a predominantly atmospheric transport, whereas freshwater and some coastal fish had higher fractions of heavier congeners (CB138, CB153) because those were mainly contaminated by particle-sorbed PCB from surface runoff. (2) A temperature driven fractionation tended to affect congeners with a medium molecular weight (CB118) as well as the heaviest congeners (CB180), a fractionation process which was conceptually associated with transport of PCB from secondary sources. Specifically, medium chlorinated PCB is sufficiently volatile and persistent for a preferred transport into cooler waters. In warmer climates, only the highest chlorinated congeners are persistent enough to ultimately accumulate in fish. Our analysis and modelling provide a starting point for the development of systems to trace - better than before - sources of PCB contaminations observed in fish.

Robust Multi-Dimensional Time Series Forecasting.

Large-scale and high-dimensional time series data are widely generated in modern applications such as intelligent transportation and environmental monitoring. However, such data contains much noise, outliers, and missing values due to interference during measurement or transmission. Directly forecasting such types of data (i.e., anomalous data) can be extremely challenging. The traditional method to deal with anomalies is to cut out the time series with anomalous value entries or replace the data. Both methods may lose important knowledge from the original data. In this paper, we propose a multidimensional time series forecasting framework that can better handle anomalous values: the robust temporal nonnegative matrix factorization forecasting model (RTNMFFM) for multi-dimensional time series. RTNMFFM integrates the autoregressive regularizer into nonnegative matrix factorization (NMF) with the application of the L2,1 norm in NMF. This approach improves robustness and alleviates overfitting compared to standard methods. In addition, to improve the accuracy of model forecasts on severely missing data, we propose a periodic smoothing penalty that keeps the sparse time slices as close as possible to the time slice with high confidence. Finally, we train the model using the alternating gradient descent algorithm. Numerous experiments demonstrate that RTNMFFM provides better robustness and better prediction accuracy.

Inferring Drug Set and Identifying the Mechanism of Drugs for PC3.

Drug repurposing is a strategy for discovering new applications of existing drugs for use in various diseases. Despite the use of structured networks in drug research, it is still unclear how drugs interact with one another or with genes. Prostate adenocarcinoma is the second leading cause of cancer mortality in the United States, with an estimated incidence of 288,300 new cases and 34,700 deaths in 2023. In our study, we used integrative information from genes, pathways, and drugs for machine learning methods such as clustering, feature selection, and enrichment pathway analysis. We investigated how drugs affect drugs and how drugs affect genes in human pancreatic cancer cell lines that were derived from bone metastases of grade IV prostate cancer. Finally, we identified significant drug interactions within or between clusters, such as estradiol-rosiglitazone, estradiol-diclofenac, troglitazone-rosiglitazone, celecoxib-rofecoxib, celecoxib-diclofenac, and sodium phenylbutyrate-valproic acid.

Surface-Enhanced Raman Spectroscopy-Based Detection of Micro-RNA Biomarkers for Biomedical Diagnosis Using a Comparative Study of Interpretable Machine Learning Algorithms.

Surface-enhanced Raman spectroscopy (SERS) has wide diagnostic applications due to narrow spectral features that allow multiplex analysis. We have previously developed a multiplexed, SERS-based nanosensor for micro-RNA (miRNA) detection called the inverse molecular sentinel (iMS). Machine learning (ML) algorithms have been increasingly adopted for spectral analysis due to their ability to discover underlying patterns and relationships within large and complex data sets. However, the high dimensionality of SERS data poses a challenge for traditional ML techniques, which can be prone to overfitting and poor generalization. Non-negative matrix factorization (NMF) reduces the dimensionality of SERS data while preserving information content. In this paper, we compared the performance of ML methods including convolutional neural network (CNN), support vector regression, and extreme gradient boosting combined with and without NMF for spectral unmixing of four-way multiplexed SERS spectra from iMS assays used for miRNA detection. CNN achieved high accuracy in spectral unmixing. Incorporating NMF before CNN drastically decreased memory and training demands without sacrificing model performance on SERS spectral unmixing. Additionally, models were interpreted using gradient class activation maps and partial dependency plots to understand predictions. These models were used to analyze clinical SERS data from single-plexed iMS in RNA extracted from 17 endoscopic tissue biopsies. CNN and CNN-NMF, trained on multiplexed data, performed most accurately with RMSElabel = 0.101 and 9.68 × 10-2, respectively. We demonstrated that CNN-based ML shows great promise in spectral unmixing of multiplexed SERS spectra, and the effect of dimensionality reduction on performance and training speed.

Immune checkpoints signature-based risk stratification for prognosis of patients with gastric cancer.

Until now, few researches have comprehensive explored the role of immune checkpoints (ICIs) and tumor microenvironment (TME) in gastric cancer (GC) patients based on the genomic data. RNA-sequence data and clinical information were obtained from The Cancer Genome Atlas Stomach Adenocarcinoma (TCGA-STAD) database, GSE84437 and GSE84433. Univariate Cox analysis identified 60 ICIs with prognostic values, and these genes were then subjected to NMF cluster analysis and the GC samples (n = 804) were classified into two distinct subtypes (Cluster 1: n = 583; Cluster 2: n = 221). The Kaplan-Meier curves for OS analysis indicated that C1 predicted a poorer prognosis. The C2 subtype illustrated a relatively better prognosis and characteristics of "hot tumors," including high immune score, overexpression of immune checkpoint molecules, and enriched tumor-infiltrated immune cells, indicating that the NMF clustering in GC was robust and stable. Regarding the patient's heterogeneity, an ICI-score was constructed to quantify the ICI patterns in individual patients. Moreover, the study found that the low ICI-score group contained mostly MSI-low events, and the high ICI-score group contained predominantly MSI-high events. In addition, the ICI-score groups had good responsiveness to CTLA4 and PD-1 based on The Cancer Immunome Atlas (TCIA) database. Our research firstly constructed ICIs signature, as well as identified some hub genes in GC patients.

Performance evaluation of IRI-Plas 2017 model with ionosonde data measurements of ionospheric parameters.

This study presents an evaluation of the performance of the International Reference Ionosphere Model augmented with the Plasmasphere (IRI Plas 2017) from the Addis Ababa Ionosonde Station, Ethiopia, for measuring ionospheric parameters at geographic (9.00o N, 38.70o E) and geomagnetic (0.16o N, 110.44o E) location on selected days of 2014. During comparison hourly and daily variability of the ionospheric parameters of the electron density profile (Neh), maximum electron density (NmF2) and maximum height (hmF2) measurements are considered. When evaluating the IRI Plas model using ionosonde data, the percentage deviation and correlation coefficient (R) were used as measures of IRI Plas model performance. In general, the overall results of the study show that the IRI Plas 2017 model mostly overestimates at most altitudes and hours of electron density measurements. The IRI Plas model has an acceptable fit with the ionosonde electron density measurements at altitudes of 100 km-200 km, mostly during the hours between 03LT and 09 LT and 15 LT-21 LT, while the model biases in other altitudes and hours with overestimates or underestimates in the ionosonde electron density measurements. The IRI-Plas 2017 model has a good correlation after midnight and around midday hours, with about ±2% point deviation from the ionosonde electron density measurement. The model has a high percentage deviation value for electron density measurements, mostly between altitudes of 200 km and 450 km and during early nighttime and before midnight hours. IRI-Plas model measurements of NmF2 and hmF2 are mostly underestimated from the ionosonde data during the nighttime (21 LT-09 LT) and overestimated during the daytime (09 LT-21 LT). The NmF2 values measured with the model are more consistent with ionosonde values than hmF2 values.

Scalable Orthonormal Projective NMF via Diversified Stochastic Optimization.

The increasing availability of large-scale neuroimaging initiatives opens exciting opportunities for discovery science of human brain structure and function. Data-driven techniques, such as Orthonormal Projective Non-negative Matrix Factorization (opNMF), are well positioned to explore multivariate relationships in big data towards uncovering brain organization. opNMF enjoys advantageous interpretability and reproducibility compared to commonly used matrix factorization methods like Principal Component Analysis (PCA) and Independent Component Analysis (ICA), which led to its wide adoption in clinical computational neuroscience. However, applying opNMF in large-scale cohort studies is hindered by its limited scalability caused by its accompanying computational complexity. In this work, we address the computational challenges of opNMF using a stochastic optimization approach that learns over mini-batches of the data. Additionally, we diversify the stochastic batches via repulsive point processes, which reduce redundancy in the mini-batches and in turn lead to lower variance in the updates. We validated our framework on gray matter tissue density maps estimated from 1000 subjects part of the Open Access Series of Imaging (OASIS) dataset. We demonstrated that operations over mini-batches of data yield significant reduction in computational cost. Importantly, we showed that our novel optimization does not compromise the accuracy or interpretability of factors when compared to standard opNMF. The proposed model enables new investigations of brain structure using big neuroimaging data that could improve our understanding of brain structure in health and disease.

Music emotion representation based on non-negative matrix factorization algorithm and user label information.

Music emotion representation learning forms the foundation of user emotion recognition, addressing the challenges posed by the vast volume of digital music data and the scarcity of emotion annotation data. This article introduces a novel music emotion representation model, leveraging the nonnegative matrix factorization algorithm (NMF) to derive emotional embeddings of music by utilizing user-generated listening lists and emotional labels. This approach facilitates emotion recognition by positioning music within the emotional space. Furthermore, a dedicated music emotion recognition algorithm is formulated, alongside the proposal of a user emotion recognition model, which employs similarity-weighted calculations to obtain user emotion representations. Experimental findings demonstrate the method's convergence after a mere 400 iterations, yielding a remarkable 47.62% increase in F1 value across all emotion classes. In practical testing scenarios, the comprehensive accuracy rate of user emotion recognition attains an impressive 52.7%, effectively discerning emotions within seven emotion categories and accurately identifying users' emotional states.