Approximated and User Steerable tSNE for Progressive Visual Analytics

S2Map: a novel computational platform for identifying secretio-types through cell secretion-signal map

Motivation

Cell communication is predominantly governed by secreted proteins, whose diverse secretion patterns often signify underlying physiological irregularities. Understanding these secreted signals at an individual cell level is crucial for gaining insights into regulatory mechanisms involving various molecular agents. To elucidate the array of cell secretion signals, which encompass different types of biomolecular secretion cues from individual immune cells, we introduce the secretion-signal map (S2Map).

Results

S2Map is an online interactive analytical platform designed to explore and interpret distinct cell secretion-signal patterns visually. It incorporates two innovative qualitative metrics, the signal inequality index and the signal coverage index, which are exquisitely sensitive in measuring dissymmetry and diffusion of signals in temporal data. S2Map's innovation lies in its depiction of signals through time-series analysis with multi-layer visualization. We tested the SII and SCI performance in distinguishing the simulated signal diffusion models. S2Map hosts a repository for the single-cell's secretion-signal data for exploring cell secretio-types, a new cell phenotyping based on the cell secretion signal pattern. We anticipate that S2Map will be a powerful tool to delve into the complexities of physiological systems, providing insights into the regulation of protein production, such as cytokines at the remarkable resolution of single cells.

Availability and implementation

The S2Map server is publicly accessible via https://au-s2map.streamlit.app/.

A Novel Instruction Gesture Set Determination Scheme for Robust Myoelectric Control Applications

OBJECTIVE

Myoelectric control technology has important application value in rehabilitation medicine, prosthesis control, human-computer interaction (HCI) and other fields. However, the user dependence of electromyography (EMG) pattern recognition is one of the key problems hindering the implementation of robust myoelectric control applications. Aimed at solving the user dependence problem, this paper proposed a novel instruction gesture set determination scheme for EMG pattern recognition in user-independent mode.

METHODS

The scheme uses T-distributed stochastic neighbor embedding (T-SNE) dimensionality reduction to analyze high-dimensional surface EMG data from multiple users and gestures. This process can identify gesture combinations with minimal individual differences and high separability.

RESULTS

The proposed scheme was validated using two large-scale EMG gesture databases with different acquisition devices, subjects, and gestures. Optimal and inferior gesture sets of varying sizes were identified. In recognition experiments conducted in both user-independent and electrode-offset modes, the optimal gesture sets demonstrated significantly higher recognition accuracies compared to the inferior sets, with improvements ranging from 12.57% to 36.92%.

CONCLUSION

The results demonstrated that the separability of the obtained optimal gesture sets was significantly superior to that of the inferior sets, confirming the effectiveness of the proposed scheme in reducing user dependence in EMG pattern recognition.

SIGNIFICANCE

The study has certain application value to promote the development of myoelectric control technology. Specifically, the scheme proposed can be used to determine instruction gesture sets with low user dependence and high separability for myoelectric control applications.

Identification and Verification of Key Genes in Colorectal Cancer Liver Metastases Through Analysis of Single-Cell Sequencing Data and TCGA Data

BACKGROUND

Colorectal cancer (CRC) is highly prevalent worldwide, with more patients experiencing colorectal cancer liver metastases (CRLM). This study aimed to identify key genes in CRLM through single-cell sequencing data reanalysis and experimental validation.

METHODS

The study analyzed single-cell RNA-sequencing (scRNA-seq) data from the Gene Expression Omnibus (GEO) database. Gene ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) were used for gene functional enrichment analysis. The Cancer Genome Atlas (TCGA) data enabled bulk-RNA expression and survival prognosis analysis. Real-time polymerase chain reaction (qPCR) detected mRNA expression, whereas Western blot determined protein levels. Cell function experiments assessed SPARC's impact on CRC cell behavior.

RESULTS

Cluster analysis showed 23 classes among 17 CRLM samples, representing six cell types. A GO and KEGG analysis identified interleukin-1 beta (IL1B), CD2 molecule (CD2), and C-X-C motif chemokine ligand 8 (CXCL8) as significant prognostic factors in CRC. Secreted protein acidic and cysteine rich (SPARC) was one of the top differentially expressed genes (DEGs) in tissue stem cells, confirmed in primary and metastatic lesions. Metastatic lesions showed higher expression of SPARC and CRC stem cell marker leucine-rich repeat containing G protein-coupled receptor 5 (LGR5), which was significantly correlated positively with LGR5 expression. Knockdown of SPARC reduced CRC cell sphere- and colony-formation, invasion, and migration abilities. Overexpression of SPARC significantly increased the malignancy of CRC cells.

CONCLUSIONS

Several key genes were identified in the process of CRLM. In CRLM samples and those corresponding to CRC stem cells, SPARC was significantly upregulated. In the therapy of CRLM, SPARC might be a potential target.

Performance comparison of high throughput single-cell RNA-Seq platforms in complex tissues

Single-cell transcriptomics has emerged as the preferred tool to define cell identity through the analysis of gene expression signatures. However, there are limited studies that have comprehensively compared the performance of different scRNAseq systems in complex tissues. Here, we present a systematic comparison of two well-established high throughput 3'-scRNAseq platforms: 10× Chromium and BD Rhapsody, using tumours that present high cell diversity. Our experimental design includes both fresh and artificially damaged samples from the same tumours, which also provides a comparable dataset to examine their performance under challenging conditions. The performance metrics used in this study consist of gene sensitivity, mitochondrial content, reproducibility, clustering capabilities, cell type representation and ambient RNA contamination. These analyses showed that BD Rhapsody and 10× Chromium have similar gene sensitivity, while BD Rhapsody has the highest mitochondrial content. Interestingly, we found cell type detection biases between platforms, including a lower proportion of endothelial and myofibroblast cells in BD Rhapsody and lower gene sensitivity in granulocytes for 10× Chromium. Moreover, the source of the ambient noise was different between plate-based and droplet-based platforms. In conclusion, our reported platform differential performance should be considered for the selection of the scRNAseq method during the study experimental designs.

As a novel prognostic model for breast cancer, the identification and validation of telomere-related long noncoding RNA signatures

BACKGROUND

Telomeres are a critical component of chromosome integrity and are essential to the development of cancer and cellular senescence. The regulation of breast cancer by telomere-associated lncRNAs is not fully known, though. The goals of this study were to describe predictive telomere-related LncRNAs (TRL) in breast cancer and look into any possible biological roles for these RNAs.

METHODS

We obtained RNA-seq data, pertinent clinical data, and a list of telomere-associated genes from the cancer genome atlas and telomere gene database, respectively. We subjected differentially expressed TRLs to co-expression analysis and univariate Cox analysis to identify a prognostic TRL. Using LASSO regression analysis, we built a prognostic model with 14 TRLs. The accuracy of the model's prognostic predictions was evaluated through the utilization of Kaplan-Meier (K-M) analysis as well as receiver operating characteristic (ROC) curve analysis. Additionally, immunological infiltration and immune drug prediction were done using this model. Patients with breast cancer were divided into two subgroups using cluster analysis, with the latter analyzed further for variations in response to immunotherapy, immune infiltration, and overall survival, and finally, the expression of 14-LncRNAs was validated by RT-PCR.

RESULTS

We developed a risk model for the 14-TRL, and we used ROC curves to demonstrate how accurate the model is. The model may be a standalone prognostic predictor for patients with breast cancer, according to COX regression analysis. The immune infiltration and immunotherapy results indicated that the high-risk group had a low level of PD-1 sensitivity and a high number of macrophages infiltrating. In addition, we've discovered a number of small-molecule medicines with considerable for use in treating high-risk groups. The cluster 2 subtype showed the highest immune infiltration, the highest immune checkpoint expression, and the worst prognosis among the two subtypes defined by cluster analysis, which requires more attention and treatment.

CONCLUSION

As a possible biomarker, the proposed 14-TRL signature could be utilized to evaluate clinical outcomes and treatment efficacy in breast cancer patients.

Revisiting the Application of Machine Learning Approaches in Predicting Aqueous Solubility

The solubility of chemical substances in water is a critical parameter in pharmaceutical development, environmental chemistry, agrochemistry, and other fields; however, accurately predicting it remains a challenge. This study aims to evaluate and compare the effectiveness of some of the most popular machine learning modeling methods and molecular featurization techniques in predicting aqueous solubility. Although these methods were not implemented in a competitive environment, some of their performance surpassed previous benchmarks, offering gradual but significant improvements. Our results show that methods based on graph convolution and graph attention mechanisms demonstrated exceptional predictive abilities with high-quality data sets, albeit with a sensitivity to data noise and errors. In contrast, models leveraging molecular descriptors not only provided better interpretability but also showed more resilience when dealing with inherent noise and errors in data. Our analysis of over 4000 molecular descriptors used in various models identified that approximately 800 of these descriptors make a significant contribution to solubility prediction. These insights offer guidance and direction for future developments in solubility prediction.

Integrating multi-omics data of childhood asthma using a deep association model

Childhood asthma is one of the most common respiratory diseases with rising mortality and morbidity. The multi-omics data is providing a new chance to explore collaborative biomarkers and corresponding diagnostic models of childhood asthma. To capture the nonlinear association of multi-omics data and improve interpretability of diagnostic model, we proposed a novel deep association model (DAM) and corresponding efficient analysis framework. First, the Deep Subspace Reconstruction was used to fuse the omics data and diagnostic information, thereby correcting the distribution of the original omics data and reducing the influence of unnecessary data noises. Second, the Joint Deep Semi-Negative Matrix Factorization was applied to identify different latent sample patterns and extract biomarkers from different omics data levels. Third, our newly proposed Deep Orthogonal Canonical Correlation Analysis can rank features in the collaborative module, which are able to construct the diagnostic model considering nonlinear correlation between different omics data levels. Using DAM, we deeply analyzed the transcriptome and methylation data of childhood asthma. The effectiveness of DAM is verified from the perspectives of algorithm performance and biological significance on the independent test dataset, by ablation experiment and comparison with many baseline methods from clinical and biological studies. The DAM-induced diagnostic model can achieve a prediction AUC of 0.912, which is higher than that of many other alternative methods. Meanwhile, relevant pathways and biomarkers of childhood asthma are also recognized to be collectively altered on the gene expression and methylation levels. As an interpretable machine learning approach, DAM simultaneously considers the non-linear associations among samples and those among biological features, which should help explore interpretative biomarker candidates and efficient diagnostic models from multi-omics data analysis for human complex diseases.

interFLOW: maximum flow framework for the identification of factors mediating the signaling convergence of multiple receptors

Cell-cell crosstalk involves simultaneous interactions of multiple receptors and ligands, followed by downstream signaling cascades working through receptors converging at dominant transcription factors, which then integrate and propagate multiple signals into a cellular response. Single-cell RNAseq of multiple cell subsets isolated from a defined microenvironment provides us with a unique opportunity to learn about such interactions reflected in their gene expression levels. We developed the interFLOW framework to map the potential ligand-receptor interactions between different cell subsets based on a maximum flow computation in a network of protein-protein interactions (PPIs). The maximum flow approach further allows characterization of the intracellular downstream signal transduction from differentially expressed receptors towards dominant transcription factors, therefore, enabling the association between a set of receptors and their downstream activated pathways. Importantly, we were able to identify key transcription factors toward which the convergence of multiple receptor signaling pathways occurs. These identified factors have a unique role in the integration and propagation of signaling following specific cell-cell interactions.

Tumor-associated macrophage-derived exosomal miR21-5p promotes tumor angiogenesis by regulating YAP1/HIF-1α axis in head and neck squamous cell carcinoma

Extracellular vesicles (EVs) have recently received increasing attention as essential mediators of communication between tumor cells and their microenvironments. Tumor-associated macrophages (TAMs) play a proangiogenic role in various tumors, especially head and neck squamous cell carcinoma (HNSCC), and angiogenesis is closely related to tumor growth and metastasis. This research focused on exploring the mechanisms by which EVs derived from TAMs modulate tumor angiogenesis in HNSCC. Our results indicated that TAMs infiltration correlated positively with microvascular density in HNSCC. Then we collected and identified EVs from TAMs. In the microfluidic chip, TAMs derived EVs significantly enhanced the angiogenic potential of pHUVECs and successfully induced the formation of perfusable blood vessels. qPCR and immunofluorescence analyses revealed that EVs from TAMs transferred miR-21-5p to endothelial cells (ECs). And targeting miR-21-5p of TAMs could effectively inhibit TAM-EVs induced angiogenesis. Western blot and tube formation assays showed that miR-21-5p from TAM-EVs downregulated LATS1 and VHL levels but upregulated YAP1 and HIF-1α levels, and the inhibitors of YAP1 and HIF-1α could both reduce the miR-21-5p enhanced angiogenesis in HUVECs. The in vivo experiments further proved that miR-21-5p carried by TAM-EVs promoted the process of tumor angiogenesis via YAP1/HIF-1α axis in HNSCC. Conclusively, TAM-derived EVs transferred miR-21-5p to ECs to target the mRNA of LATS1 and VHL, which inhibited YAP1 phosphorylation and subsequently enhanced YAP1-mediated HIF-1α transcription and reduced VHL-mediated HIF-1α ubiquitination, contributing to angiogenesis in HNSCC. These findings present a novel regulatory mechanism of tumor angiogenesis, and miR-21-5p/YAP1/HIF-1α might be a potential therapeutic target for HNSCC.

SuperCellCyto: enabling efficient analysis of large scale cytometry datasets

Advancements in cytometry technologies have enabled quantification of up to 50 proteins across millions of cells at single cell resolution. Analysis of cytometry data routinely involves tasks such as data integration, clustering, and dimensionality reduction. While numerous tools exist, many require extensive run times when processing large cytometry data containing millions of cells. Existing solutions, such as random subsampling, are inadequate as they risk excluding rare cell subsets. To address this, we propose SuperCellCyto, an R package that builds on the SuperCell tool which groups highly similar cells into supercells. SuperCellCyto is available on GitHub ( https://github.com/phipsonlab/SuperCellCyto ) and Zenodo ( https://doi.org/10.5281/zenodo.10521294 ).

Exercise potentially prevents colorectal cancer liver metastases by suppressing tumor epithelial cell stemness via RPS4X downregulation

BACKGROUND

Colorectal cancer (CRC) is the third most prevalent tumor globally. The liver is the most common site for CRC metastasis, and the involvement of the liver is a common cause of death in patients with late-stage CRC. Consequently, mitigating CRC liver metastasis (CRLM) is key to improving CRC prognosis and increasing survival. Exercise has been shown to be an effective method of improving the prognosis of many tumor types. However, the ability of exercise to inhibit CRLM is yet to be thoroughly investigated.

METHODS

The GSE157600 and GSE97084 datasets were used for analysis. A pan-cancer dataset which was uniformly normalized was downloaded and analyzed from the UCSC database: TCGA, TARGET, GTEx (PANCAN, n = 19,131, G = 60,499). Several advanced bioinformatics analyses were conducted, including single-cell sequencing analysis, correlation algorithm, and prognostic screen. CRC tumor microarray (TMA) as well as cell/animal experiments are used to further validate the results of the analysis.

RESULTS

The greatest variability was found in epithelial cells from the tumor group. RPS4X was generally upregulated in all types of CRC, while exercise downregulated RPS4X expression. A lowered expression of RPS4X may prolong tumor survival and reduce CRC metastasis. RPS4X and tumor stemness marker-CD44 were highly positively correlated and knockdown of RPS4X expression reduced tumor stemness both in vitro and in vivo.

CONCLUSION

RPS4X upregulation may enhance CRC stemness and increase the odds of metastasis. Exercise may reduce CRC metastasis through the regulation of RPS4X.

Integrated analysis of single-cell sequencing and weighted co-expression network identifies a novel signature based on cellular senescence-related genes to predict prognosis in glioblastoma

BACKGROUND

Glioblastoma (GBM) is a highly aggressive cancer with heavy mortality rates and poor prognosis. Cellular senescence exerts a pivotal influence on the development and progression of various cancers. However, the underlying effect of cellular senescence on the outcomes of patients with GBM remains to be elucidated.

METHODS

Transcriptome RNA sequencing data with clinical information and single-cell sequencing data of GBM cases were obtained from CGGA, TCGA, and GEO (GSE84465) databases respectively. Single-sample gene set enrichment analysis (ssGSEA) analysis was utilized to calculate the cellular senescence score. WGCNA analysis was employed to ascertain the key gene modules and identify differentially expressed genes (DEGs) associated with the cellular senescence score in GBM. The prognostic senescence-related risk model was developed by least absolute shrinkage and selection operator (LASSO) regression analyses. The immune infiltration level was calculated by microenvironment cell populations counter (MCPcounter), ssGSEA, and xCell algorithms. Potential anti-cancer small molecular compounds of GBM were estimated by "oncoPredict" R package.

RESULTS

A total of 150 DEGs were selected from the pink module through WGCNA analysis. The risk-scoring model was constructed based on 5 cell senescence-associated genes (CCDC151, DRC1, C2orf73, CCDC13, and WDR63). Patients in low-risk group had a better prognostic value compared to those in high-risk group. The nomogram exhibited excellent predictive performance in assessing the survival outcomes of patients with GBM. Top 30 potential anti-cancer small molecular compounds with higher drug sensitivity scores were predicted.

CONCLUSION

Cellular senescence-related genes and clusters in GBM have the potential to provide valuable insights in prognosis and guide clinical decisions.

B cells in head and neck squamous cell carcinoma: current opinion and novel therapy

Head and neck squamous cell carcinoma (HNSCC) is a common malignant tumour. Despite advancements in surgery, radiotherapy and chemotherapy, which have improved the prognosis of most patients, a subset of patients with poor prognoses still exist due to loss of surgical opportunities, postoperative recurrence, and metastasis, among other reasons. The tumour microenvironment (TME) is a complex organization composed of tumour, stromal, and endothelial cells. Communication and interaction between tumours and immune cells within the TME are increasingly being recognized as pivotal in inhibiting or promoting tumour development. Previous studies on T cells in the TME of HNSCC have yielded novel therapeutic possibilities. However, the function of B cells, another adaptive immune cell type, in the TME of HNSCC patients has yet to be determined. Recent studies have revealed various distinct subtypes of B cells and tertiary lymphoid structures (TLSs) in the TME of HNSCC patients, which are believed to impact the efficacy of immune checkpoint inhibitors (ICIs). Therefore, this paper focuses on B cells in the TME to explore potential directions for future immunotherapy for HNSCC.

Deciphering decidual leukocyte traffic with serial intravascular staining

The decidual immunome is dynamic, dramatically changing its composition across gestation. Early pregnancy is dominated by decidual NK cells, with a shift towards T cells later in pregnancy. However, the degree, timing, and subset-specific nature of leukocyte traffic between the decidua and systemic circulation during gestation remains poorly understood. Herein, we employed intravascular staining in pregnant C57BL/6J mice and cynomolgus macaques (Macaca fascicularis) to examine leukocyte traffic into the decidual basalis during pregnancy. Timed-mated or virgin mice were tail-vein injected with labelled αCD45 antibodies 24 hours and 5 minutes before sacrifice. Pregnant cynomolgus macaques (GD155) were infused with labelled αCD45 at 2 hours or 5 mins before necropsy. Decidual cells were isolated and resulting suspensions analyzed by flow cytometry. We found that the proportion of intravascular (IVAs)-negative leukocytes (cells labeled by the 24h infusion of αCD45 or unlabeled) decreased across murine gestation while recent immigrants (24h label only) increased in mid- to late-gestation. In the cynomolgus model our data confirmed differential labeling of decidual leukocytes by the infused antibody, with the 5 min infused animal having a higher proportion of IVAs+ cells compared to the 2hr infused animal. Decidual tissue sections from both macaques showed the presence of intravascularly labeled cells, either in proximity to blood vessels (5min infused animal) or deeper into decidual stroma (2hr infused animal). These results demonstrate the value of serial intravascular staining as a sensitive tool for defining decidual leukocyte traffic during pregnancy.

Development of a prognostic model to predict BLCA based on anoikis-related gene signature: preliminary findings

BACKGROUND

The prevalence of bladder urothelial carcinoma (BLCA) is significant on a global scale. Anoikis is a type of procedural cell death that has an important role in tumor invasion and metastasis. The advent of single-cell RNA sequencing (scRNA-seq) approaches has revolutionized the genomics field by providing unprecedented opportunities for elucidating cellular heterogeneity. Understanding the mechanisms associated with anoikis in BLCA is essential to improve its survival rate.

METHODS

Data on BLCA and clinical information were acquired from the databases of The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO). ARGs were obtained from Genecards and Harmonizome databases. According to univariate Cox regression analysis, the least absolute shrinkage and selection operator (LASSO) algorithm was utilized to select the ARGs associated with the overall rate (OS). A multivariate Cox regression analysis was carried out to identify eight prognostic ARGs, leading to the establishment of a risk model. The OS rate of BLCA patients was evaluated using Kaplan-Meier survival analysis. To explore the molecular mechanism in low- and high-risk groups, we employed Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Gene Set Enrichment Analysis (GSVA). Immune infiltration landscape estimation was performed using ESTIMATE, CIBERSOT, and single sample gene set enrichment analysis (ssGSEA) algorithms. Patients were categorized into different subgroups through consensus clustering analysis. We employed biological functional enrichment analysis and conducted immune infiltration analysis to examine the disparities in potential biological functions, infiltration of immune cells, immune activities, and responses to immunotherapy.

RESULTS

We identified 647 ARGs and 37 survival-related genes. We further developed a risk scoring model to quantitatively assess the predictive capacity of ARGs. The high-risk score group exhibited an unfavorable prognosis, whereas the low-risk score group demonstrated a converse effect. We also found that the two groups of patients might respond differently to immune targets and anti-tumor drugs.

CONCLUSION

The nomogram with 8 ARGs may help guide treatment of BLCA. The systematic assessment of risk scores can help to design more individualized and precise treatment strategies for BLCA patients.

Identification of necroptosis-related genes in Parkinson's disease by integrated bioinformatics analysis and experimental validation

Background

Parkinson's disease (PD) is the second most common neurodegeneration disease worldwide. Necroptosis, which is a new form of programmed cell death with high relationship with inflammation, plays a vital role in the progression of PD. However, the key necroptosis related genes in PD are not fully elucidated.

Purpose

Identification of key necroptosis-related genes in PD.

Method

The PD associated datasets and necroptosis related genes were downloaded from the GEO Database and GeneCards platform, respectively. The DEGs associated with necroptosis in PD were obtained by gap analysis, and followed by cluster analysis, enrichment analysis and WGCNA analysis. Moreover, the key necroptosis related genes were generated by PPI network analysis and their relationship by spearman correlation analysis. Immune infiltration analysis was used for explore the immune state of PD brain accompanied with the expression levels of these genes in various types of immune cells. Finally, the gene expression levels of these key necroptosis related genes were validated by an external dataset, blood samples from PD patients and toxin-induced PD cell model using real-time PCR analysis.

Result

Twelve key necroptosis-related genes including ASGR2, CCNA1, FGF10, FGF19, HJURP, NTF3, OIP5, RRM2, SLC22A1, SLC28A3, WNT1 and WNT10B were identified by integrated bioinformatics analysis of PD related dataset GSE7621. According to the correlation analysis of these genes, RRM2 and WNT1 were positively and negatively correlated with SLC22A1 respectively, while WNT10B was positively correlated with both OIF5 and FGF19. As the results from immune infiltration analysis, M2 macrophage was the highest population of immune cell in analyzed PD brain samples. Moreover, we found that 3 genes (CCNA1, OIP5 and WNT10B) and 9 genes (ASGR2, FGF10, FGF19, HJURP, NTF3, RRM2, SLC22A1, SLC28A3 and WNT1) were down- and up- regulated in an external dataset GSE20141, respectively. All the mRNA expression levels of these 12 genes were obviously upregulated in 6-OHDA-induced SH-SY5Y cell PD model while CCNA1 and OIP5 were up- and down- regulated, respectively, in peripheral blood lymphocytes of PD patients.

Conclusion

Necroptosis and its associated inflammation play fundamental roles in the progression of PD and these identified 12 key genes might be served as new diagnostic markers and therapeutic targets for PD.

Artificial intelligence in clinical multiparameter flow cytometry and mass cytometry-key tools and progress

There are many research studies and emerging tools using artificial intelligence (AI) and machine learning to augment flow and mass cytometry workflows. Emerging AI tools can quickly identify common cell populations with continuous improvement of accuracy, uncover patterns in high-dimensional cytometric data that are undetectable by human analysis, facilitate the discovery of cell subpopulations, perform semi-automated immune cell profiling, and demonstrate potential to automate aspects of clinical multiparameter flow cytometric (MFC) diagnostic workflow. Utilizing AI in the analysis of cytometry samples can reduce subjective variability and assist in breakthroughs in understanding diseases. Here we review the diverse types of AI that are being applied to clinical cytometry data and how AI is driving advances in data analysis to improve diagnostic sensitivity and accuracy. We review supervised and unsupervised clustering algorithms for cell population identification, various dimensionality reduction techniques, and their utilities in visualization and machine learning pipelines, and supervised learning approaches for classifying entire cytometry samples.Understanding the AI landscape will enable pathologists to better utilize open source and commercially available tools, plan exploratory research projects to characterize diseases, and work with machine learning and data scientists to implement clinical data analysis pipelines.

Metabolic responses in blood-stage malaria parasites associated with increased and decreased sensitivity to PfATP4 inhibitors

BACKGROUND

Spiroindolone and pyrazoleamide antimalarial compounds target Plasmodium falciparum P-type ATPase (PfATP4) and induce disruption of intracellular Na+ homeostasis. Recently, a PfATP4 mutation was discovered that confers resistance to a pyrazoleamide while increasing sensitivity to a spiroindolone. Transcriptomic and metabolic adaptations that underlie this seemingly contradictory response of P. falciparum to sublethal concentrations of each compound were examined to understand the different cellular accommodation to PfATP4 disruptions.

METHODS

A genetically engineered P. falciparum Dd2 strain (Dd2A211V) carrying an Ala211Val (A211V) mutation in PfATP4 was used to identify metabolic adaptations associated with the mutation that results in decreased sensitivity to PA21A092 (a pyrazoleamide) and increased sensitivity to KAE609 (a spiroindolone). First, sublethal doses of PA21A092 and KAE609 causing substantial reduction (30-70%) in Dd2A211V parasite replication were identified. Then, at this sublethal dose of PA21A092 (or KAE609), metabolomic and transcriptomic data were collected during the first intraerythrocytic developmental cycle. Finally, the time-resolved data were integrated with a whole-genome metabolic network model of P. falciparum to characterize antimalarial-induced physiological adaptations.

RESULTS

Sublethal treatment with PA21A092 caused significant (p < 0.001) alterations in the abundances of 91 Plasmodium gene transcripts, whereas only 21 transcripts were significantly altered due to sublethal treatment with KAE609. In the metabolomic data, a substantial alteration (≥ fourfold) in the abundances of carbohydrate metabolites in the presence of either compound was found. The estimated rates of macromolecule syntheses between the two antimalarial-treated conditions were also comparable, except for the rate of lipid synthesis. A closer examination of parasite metabolism in the presence of either compound indicated statistically significant differences in enzymatic activities associated with synthesis of phosphatidylcholine, phosphatidylserine, and phosphatidylinositol.

CONCLUSION

The results of this study suggest that malaria parasites activate protein kinases via phospholipid-dependent signalling in response to the ionic perturbation induced by the Na+ homeostasis disruptor PA21A092. Therefore, targeted disruption of phospholipid signalling in PA21A092-resistant parasites could be a means to block the emergence of resistance to PA21A092.

Rapid identification and drug resistance screening of respiratory pathogens based on single-cell Raman spectroscopy

Respiratory infections rank fourth in the global economic burden of disease. Lower respiratory tract infections are the leading cause of death in low-income countries. The rapid identification of pathogens causing lower respiratory tract infections to help guide the use of antibiotics can reduce the mortality of patients with lower respiratory tract infections. Single-cell Raman spectroscopy is a "whole biological fingerprint" technique that can be used to identify microbial samples. It has the advantages of no marking and fast and non-destructive testing. In this study, single-cell Raman spectroscopy was used to collect spectral data of six respiratory tract pathogen isolates. The T-distributed stochastic neighbor embedding (t-SNE) isolation analysis algorithm was used to compare the differences between the six respiratory tract pathogens. The eXtreme Gradient Boosting (XGBoost) algorithm was used to establish a Raman phenotype database model. The classification accuracy of the isolated samples was 93-100%, and the classification accuracy of the clinical samples was more than 80%. Combined with heavy water labeling technology, the drug resistance of respiratory tract pathogens was determined. The study showed that single-cell Raman spectroscopy-D₂O (SCRS-D₂O) labeling could rapidly identify the drug resistance of respiratory tract pathogens within 2 h.

Visinity: Visual Spatial Neighborhood Analysis for Multiplexed Tissue Imaging Data

New highly-multiplexed imaging technologies have enabled the study of tissues in unprecedented detail. These methods are increasingly being applied to understand how cancer cells and immune response change during tumor development, progression, and metastasis, as well as following treatment. Yet, existing analysis approaches focus on investigating small tissue samples on a per-cell basis, not taking into account the spatial proximity of cells, which indicates cell-cell interaction and specific biological processes in the larger cancer microenvironment. We present Visinity, a scalable visual analytics system to analyze cell interaction patterns across cohorts of whole-slide multiplexed tissue images. Our approach is based on a fast regional neighborhood computation, leveraging unsupervised learning to quantify, compare, and group cells by their surrounding cellular neighborhood. These neighborhoods can be visually analyzed in an exploratory and confirmatory workflow. Users can explore spatial patterns present across tissues through a scalable image viewer and coordinated views highlighting the neighborhood composition and spatial arrangements of cells. To verify or refine existing hypotheses, users can query for specific patterns to determine their presence and statistical significance. Findings can be interactively annotated, ranked, and compared in the form of small multiples. In two case studies with biomedical experts, we demonstrate that Visinity can identify common biological processes within a human tonsil and uncover novel white-blood cell networks and immune-tumor interactions.

Interactive Visual Cluster Analysis by Contrastive Dimensionality Reduction

We propose a contrastive dimensionality reduction approach (CDR) for interactive visual cluster analysis. Although dimensionality reduction of high-dimensional data is widely used in visual cluster analysis in conjunction with scatterplots, there are several limitations on effective visual cluster analysis. First, it is non-trivial for an embedding to present clear visual cluster separation when keeping neighborhood structures. Second, as cluster analysis is a subjective task, user steering is required. However, it is also non-trivial to enable interactions in dimensionality reduction. To tackle these problems, we introduce contrastive learning into dimensionality reduction for high-quality embedding. We then redefine the gradient of the loss function to the negative pairs to enhance the visual cluster separation of embedding results. Based on the contrastive learning scheme, we employ link-based interactions to steer embeddings. After that, we implement a prototype visual interface that integrates the proposed algorithms and a set of visualizations. Quantitative experiments demonstrate that CDR outperforms existing techniques in terms of preserving correct neighborhood structures and improving visual cluster separation. The ablation experiment demonstrates the effectiveness of gradient redefinition. The user study verifies that CDR outperforms t-SNE and UMAP in the task of cluster identification. We also showcase two use cases on real-world datasets to present the effectiveness of link-based interactions.

Unraveling the Transcriptomic Signatures of Homologous Recombination Deficiency in Ovarian Cancers

Homologous recombination deficiency (HRD) is a crucial driver of tumorigenesis by inducing impaired repair of double-stranded DNA breaks. Although HRD possibly triggers the production of numerous tumor neoantigens that sufficiently stimulate and activate various tumor-immune responses, a comprehensive understanding of the HRD-associated tumor microenvironment is elusive. To investigate the effect of HRD on the selective enrichment of transcriptomic signatures, 294 cases from The Cancer Genome Atlas-Ovarian Cancer project with both RNA-sequencing and SNP array data are analyzed. Differentially expressed gene analysis and network analysis are performed to identify HRD-specific signatures. Gene-sets associated with mitochondrial activation, including enhanced oxidative phosphorylation (OxPhos), are significantly enriched in the HRD-high group. Furthermore, a wide range of immune cell activation signatures is enriched in HRD-high cases of high-grade serous ovarian cancer (HGSOC). On further cell-type-specific analysis, M1-like macrophage genes are significantly enriched in HRD-high HGSOC cases, whereas M2-macrophage-related genes are not. The immune-response-associated genomic features, including tumor mutation rate, neoantigens, and tumor mutation burdens, correlated with HRD scores. In conclusion, the results of this study highlight the biological properties of HRD, including enhanced energy metabolism, increased tumor neoantigens and tumor mutation burdens, and consequent exacerbation of immune responses, particularly the enrichment of M1-like macrophages in HGSOC cases.

A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization

Inspired by the great success of machine learning (ML), researchers have applied ML techniques to visualizations to achieve a better design, development, and evaluation of visualizations. This branch of studies, known as ML4VIS, is gaining increasing research attention in recent years. To successfully adapt ML techniques for visualizations, a structured understanding of the integration of ML4VIS is needed. In this article, we systematically survey 88 ML4VIS studies, aiming to answer two motivating questions: "what visualization processes can be assisted by ML?" and "how ML techniques can be used to solve visualization problems? "This survey reveals seven main processes where the employment of ML techniques can benefit visualizations: Data Processing4VIS, Data-VIS Mapping, Insight Communication, Style Imitation, VIS Interaction, VIS Reading, and User Profiling. The seven processes are related to existing visualization theoretical models in an ML4VIS pipeline, aiming to illuminate the role of ML-assisted visualization in general visualizations. Meanwhile, the seven processes are mapped into main learning tasks in ML to align the capabilities of ML with the needs in visualization. Current practices and future opportunities of ML4VIS are discussed in the context of the ML4VIS pipeline and the ML-VIS mapping. While more studies are still needed in the area of ML4VIS, we hope this article can provide a stepping-stone for future exploration. A web-based interactive browser of this survey is available at https://ml4vis.github.io.

Principal component analysis of photoplethysmography signals for improved gesture recognition

In recent years, researchers have begun to introduce photoplethysmography (PPG) signal into the field of gesture recognition to achieve human-computer interaction on wearable device. Unlike the signals used for traditional neural interface such as electromyography (EMG) and electroencephalograph (EEG), PPG signals are readily available in current commercial wearable devices, which makes it possible to realize practical gesture-based human-computer interaction applications. In the process of gesture execution, the signal collected by PPG sensor usually contains a lot of noise irrelevant to gesture pattern and not conducive to gesture recognition. Toward improving gesture recognition performance based on PPG signals, the main contribution of this study is that it explores the feasibility of using principal component analysis (PCA) decomposition algorithm to separate gesture pattern-related signals from noise, and then proposes a PPG signal processing scheme based on normalization and reconstruction of principal components. For 14 wrist and finger-related gestures, PPG data of three wavelengths of light (green, red, and infrared) are collected from 14 subjects in four motion states (sitting, walking, jogging, and running). The gesture recognition is carried out with Support Vector Machine (SVM) classifier and K-Nearest Neighbor (KNN) classifier. The experimental results verify that PCA decomposition can effectively separate gesture-pattern-related signals from irrelevant noise, and the proposed PCA-based PPG processing scheme can improve the average accuracies of gesture recognition by 2.35∼9.19%. In particular, the improvement is found to be more evident for finger-related (improved by 6.25∼12.13%) than wrist-related gestures (improved by 1.93∼5.25%). This study provides a novel idea for implementing high-precision PPG gesture recognition technology.

A survey of urban visual analytics: Advances and future directions

Developing effective visual analytics systems demands care in characterization of domain problems and integration of visualization techniques and computational models. Urban visual analytics has already achieved remarkable success in tackling urban problems and providing fundamental services for smart cities. To promote further academic research and assist the development of industrial urban analytics systems, we comprehensively review urban visual analytics studies from four perspectives. In particular, we identify 8 urban domains and 22 types of popular visualization, analyze 7 types of computational method, and categorize existing systems into 4 types based on their integration of visualization techniques and computational models. We conclude with potential research directions and opportunities.

Developing an Artificial Intelligence Tool to Predict Vocal Cord Pathology in Primary Care Settings

OBJECTIVES

Diagnostic tools for voice disorders are lacking for primary care physicians. Artificial intelligence (AI) tools may add to the armamentarium for physicians, decreasing the time to diagnosis and limiting the burden of dysphonia.

METHODS

Voice recordings of patients were collected from 2019 to 2021 using smartphones. The Saarbruecken dataset was included for comparison. Audio files were converted to mel-spectrograms using TensorFlow. Diagnostic categories were created to group pathology, including neurological and muscular disorders, inflammatory, mass lesions, and normal. The samples were further separated into sustained/a/and the rainbow passage.

RESULTS

Two hundred three prospective samples and 1131 samples were used from the Saarbruecken database. The AI detected abnormal pathology with an F1-score of 98%. The artificial neural network (ANN) differentiated key pathologies, including unilateral paralysis, laryngitis, adductor spasmodic dysphonia (ADSD), mass lesions, and normal samples with 39%-87% F-1 scores. The Calgary database models had higher F-1 scores in a head-to-head comparison to the Saarbruecken and combined datasets (87% vs. 58% and 50%). The AI outperformed otolaryngologists using a standardized test set of recordings (83% compared to 55% ± 15%).

CONCLUSION

An AI tool was created to differentiate pathology by individual or categorical diagnosis with high evaluation metrics. Prospective data should be collected in a controlled fashion to reduce intrinsic variability between recordings. Multi-center data collaborations are imperative to increase the prediction capability of AI tools for detecting vocal cord pathology. We provide proof-of-concept for an AI tool to assist primary care physicians in managing dysphonic patients.

LEVEL OF EVIDENCE

3 Laryngoscope, 2022.

Using SincNet for Learning Pathological Voice Disorders

Deep learning techniques such as convolutional neural networks (CNN) have been successfully applied to identify pathological voices. However, the major disadvantage of using these advanced models is the lack of interpretability in explaining the predicted outcomes. This drawback further introduces a bottleneck for promoting the classification or detection of voice-disorder systems, especially in this pandemic period. In this paper, we proposed using a series of learnable sinc functions to replace the very first layer of a commonly used CNN to develop an explainable SincNet system for classifying or detecting pathological voices. The applied sinc filters, a front-end signal processor in SincNet, are critical for constructing the meaningful layer and are directly used to extract the acoustic features for following networks to generate high-level voice information. We conducted our tests on three different Far Eastern Memorial Hospital voice datasets. From our evaluations, the proposed approach achieves the highest 7%-accuracy and 9%-sensitivity improvements from conventional methods and thus demonstrates superior performance in predicting input pathological waveforms of the SincNet system. More importantly, we intended to give possible explanations between the system output and the first-layer extracted speech features based on our evaluated results.

Cerebral cortex layer segmentation using diffusion magnetic resonance imaging in vivo with applications to laminar connections and working memory analysis

Understanding the laminar brain structure is of great help in further developing our knowledge of the functions of the brain. However, since most layer segmentation methods are invasive, it is difficult to apply them to the human brain in vivo. To systematically explore the human brain's laminar structure noninvasively, the K-means clustering algorithm was used to automatically segment the left hemisphere into two layers, the superficial and deep layers, using a 7 Tesla (T) diffusion magnetic resonance imaging (dMRI)open dataset. The obtained layer thickness was then compared with the layer thickness of the BigBrain reference dataset, which segmented the neocortex into six layers based on the von Economo atlas. The results show a significant correlation not only between our automatically segmented superficial layer thickness and the thickness of layers 1-3 from the reference histological data, but also between our automatically segmented deep layer thickness and the thickness of layers 4-6 from the reference histological data. Second, we constructed the laminar connections between two pairs of unidirectional connected regions, which is consistent with prior research. Finally, we conducted the laminar analysis of the working memory, which was challenging to do in the past, and explained the conclusions of the functional analysis. Our work successfully demonstrates that it is possible to segment the human cortex noninvasively into layers using dMRI data and further explores the mechanisms of the human brain.

A Visual Analytics Approach for Hardware System Monitoring with Streaming Functional Data Analysis

Many real-world applications involve analyzing time-dependent phenomena, which are intrinsically functional, consisting of curves varying over a continuum (e.g., time). When analyzing continuous data, functional data analysis (FDA) provides substantial benefits, such as the ability to study the derivatives and to restrict the ordering of data. However, continuous data inherently has infinite dimensions, and for a long time series, FDA methods often suffer from high computational costs. The analysis problem becomes even more challenging when updating the FDA results for continuously arriving data. In this paper, we present a visual analytics approach for monitoring and reviewing time series data streamed from a hardware system with a focus on identifying outliers by using FDA. To perform FDA while addressing the computational problem, we introduce new incremental and progressive algorithms that promptly generate the magnitude-shape (MS) plot, which conveys both the functional magnitude and shape outlyingness of time series data. In addition, by using an MS plot in conjunction with an FDA version of principal component analysis, we enhance the analyst's ability to investigate the visually-identified outliers. We illustrate the effectiveness of our approach with two use scenarios using real-world datasets. The resulting tool is evaluated by industry experts using real-world streaming datasets.

DGCyTOF: Deep learning with graphic cluster visualization to predict cell types of single cell mass cytometry data

Single-cell mass cytometry, also known as cytometry by time of flight (CyTOF) is a powerful high-throughput technology that allows analysis of up to 50 protein markers per cell for the quantification and classification of single cells. Traditional manual gating utilized to identify new cell populations has been inadequate, inefficient, unreliable, and difficult to use, and no algorithms to identify both calibration and new cell populations has been well established. A deep learning with graphic cluster (DGCyTOF) visualization is developed as a new integrated embedding visualization approach in identifying canonical and new cell types. The DGCyTOF combines deep-learning classification and hierarchical stable-clustering methods to sequentially build a tri-layer construct for known cell types and the identification of new cell types. First, deep classification learning is constructed to distinguish calibration cell populations from all cells by softmax classification assignment under a probability threshold, and graph embedding clustering is then used to identify new cell populations sequentially. In the middle of two-layer, cell labels are automatically adjusted between new and unknown cell populations via a feedback loop using an iteration calibration system to reduce the rate of error in the identification of cell types, and a 3-dimensional (3D) visualization platform is finally developed to display the cell clusters with all cell-population types annotated. Utilizing two benchmark CyTOF databases comprising up to 43 million cells, we compared accuracy and speed in the identification of cell types among DGCyTOF, DeepCyTOF, and other technologies including dimension reduction with clustering, including Principal Component Analysis (PCA), Factor Analysis (FA), Independent Component Analysis (ICA), Isometric Feature Mapping (Isomap), t-distributed Stochastic Neighbor Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP) with k-means clustering and Gaussian mixture clustering. We observed the DGCyTOF represents a robust complete learning system with high accuracy, speed and visualization by eight measurement criteria. The DGCyTOF displayed F-scores of 0.9921 for CyTOF1 and 0.9992 for CyTOF2 datasets, whereas those scores were only 0.507 and 0.529 for the t-SNE+k-means; 0.565 and 0.59, for UMAP+ k-means. Comparison of DGCyTOF with t-SNE and UMAP visualization in accuracy demonstrated its approximately 35% superiority in predicting cell types. In addition, observation of cell-population distribution was more intuitive in the 3D visualization in DGCyTOF than t-SNE and UMAP visualization. The DGCyTOF model can automatically assign known labels to single cells with high accuracy using deep-learning classification assembling with traditional graph-clustering and dimension-reduction strategies. Guided by a calibration system, the model seeks optimal accuracy balance among calibration cell populations and unknown cell types, yielding a complete and robust learning system that is highly accurate in the identification of cell populations compared to results using other methods in the analysis of single-cell CyTOF data. Application of the DGCyTOF method to identify cell populations could be extended to the analysis of single-cell RNASeq data and other omics data.

Fingerprints of Element Concentrations in Infective Endocarditis Obtained by Mass Spectrometric Imaging and t-Distributed Stochastic Neighbor Embedding

Staphylococcus aureus-induced infective endocarditis (IE) is a life-threatening disease. Differences in virulence between distinct S. aureus strains, which are partly based on the molecular mechanisms during bacterial adhesion, are not fully understood. Yet, distinct molecular or elemental patterns, occurring during specific steps in the adhesion process, may help to identify novel targets for accelerated diagnosis or improved treatment. Here, we use laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS) of post-mortem tissue slices of an established mouse model of IE to obtain fingerprints of element distributions in infected aortic valve tissue. Three S. aureus strains with different virulence due to deficiency in distinct adhesion molecules (fibronectin-binding protein A and staphylococcal protein A) were used to assess strain-specific patterns. Data analysis was performed by t-distributed stochastic neighbor embedding (t-SNE) of mass spectrometry imaging data, using manual reference tissue classification in histological specimens. This procedure allowed for obtaining distinct element patterns in infected tissue for all three bacterial strains and for comparing those to patterns observed in healthy mice or after sterile inflammation of the valve. In tissue from infected mice, increased concentrations of calcium, zinc, and magnesium were observed compared to noninfected mice. Between S. aureus strains, pronounced variations were observed for manganese. The presented approach is sensitive for detection of S. aureus infection. For strain-specific tissue characterization, however, further improvements such as establishing a database with elemental fingerprints may be required.

Deep Recursive Embedding for High-Dimensional Data

Embedding high-dimensional data onto a low-dimensional manifold is of both theoretical and practical value. In this article, we propose to combine deep neural networks (DNN) with mathematics-guided embedding rules for high-dimensional data embedding. We introduce a generic deep embedding network (DEN) framework, which is able to learn a parametric mapping from high-dimensional space to low-dimensional space, guided by well-established objectives such as Kullback-Leibler (KL) divergence minimization. We further propose a recursive strategy, called deep recursive embedding (DRE), to make use of the latent data representations for boosted embedding performance. We exemplify the flexibility of DRE by different architectures and loss functions, and benchmarked our method against the two most popular embedding methods, namely, t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP). The proposed DRE method can map out-of-sample data and scale to extremely large datasets. Experiments on a range of public datasets demonstrated improved embedding performance in terms of local and global structure preservation, compared with other state-of-the-art embedding methods. Code is available at https://github.com/tao-aimi/DeepRecursiveEmbedding.

Vec2image: an explainable artificial intelligence model for the feature representation and classification of high-dimensional biological data by vector-to-image conversion

Feature representation and discriminative learning are proven models and technologies in artificial intelligence fields; however, major challenges for machine learning on large biological datasets are learning an effective model with mechanistical explanation on the model determination and prediction. To satisfy such demands, we developed Vec2image, an explainable convolutional neural network framework for characterizing the feature engineering, feature selection and classifier training that is mainly based on the collaboration of principal component coordinate conversion, deep residual neural networks and embedded k-nearest neighbor representation on pseudo images of high-dimensional biological data, where the pseudo images represent feature measurements and feature associations simultaneously. Vec2image has achieved better performance compared with other popular methods and illustrated its efficiency on feature selection in cell marker identification from tissue-specific single-cell datasets. In particular, in a case study on type 2 diabetes (T2D) by multiple human islet scRNA-seq datasets, Vec2image first displayed robust performance on T2D classification model building across different datasets, then a specific Vec2image model was trained to accurately recognize the cell state and efficiently rank feature genes relevant to T2D which uncovered potential T2D cellular pathogenesis; and next the cell activity changes, cell composition imbalances and cell–cell communication dysfunctions were associated to our finding T2D feature genes from both population-shared and individual-specific perspectives. Collectively, Vec2image is a new and efficient explainable artificial intelligence methodology that can be widely applied in human-readable classification and prediction on the basis of pseudo image representation of biological deep sequencing data.

An Efficient Dual-Hierarchy t-SNE Minimization

t-distributed Stochastic Neighbour Embedding (t-SNE) has become a standard for exploratory data analysis, as it is capable of revealing clusters even in complex data while requiring minimal user input. While its run-time complexity limited it to small datasets in the past, recent efforts improved upon the expensive similarity computations and the previously quadratic minimization. Nevertheless, t-SNE still has high runtime and memory costs when operating on millions of points. We present a novel method for executing the t-SNE minimization. While our method overall retains a linear runtime complexity, we obtain a significant performance increase in the most expensive part of the minimization. We achieve a significant improvement without a noticeable decrease in accuracy even when targeting a 3D embedding. Our method constructs a pair of spatial hierarchies over the embedding, which are simultaneously traversed to approximate many N-body interactions at once. We demonstrate an efficient GPGPU implementation and evaluate its performance against state-of-the-art methods on a variety of datasets.

Pyramid-based Scatterplots Sampling for Progressive and Streaming Data Visualization

We present a pyramid-based scatterplot sampling technique to avoid overplotting and enable progressive and streaming visualization of large data. Our technique is based on a multiresolution pyramid-based decomposition of the underlying density map and makes use of the density values in the pyramid to guide the sampling at each scale for preserving the relative data densities and outliers. We show that our technique is competitive in quality with state-of-the-art methods and runs faster by about an order of magnitude. Also, we have adapted it to deliver progressive and streaming data visualization by processing the data in chunks and updating the scatterplot areas with visible changes in the density map. A quantitative evaluation shows that our approach generates stable and faithful progressive samples that are comparable to the state-of-the-art method in preserving relative densities and superior to it in keeping outliers and stability when switching frames. We present two case studies that demonstrate the effectiveness of our approach for exploring large data.

Joint t-SNE for Comparable Projections of Multiple High-Dimensional Datasets

We present Joint t-Stochastic Neighbor Embedding (Joint t-SNE), a technique to generate comparable projections of multiple high-dimensional datasets. Although t-SNE has been widely employed to visualize high-dimensional datasets from various domains, it is limited to projecting a single dataset. When a series of high-dimensional datasets, such as datasets changing over time, is projected independently using t-SNE, misaligned layouts are obtained. Even items with identical features across datasets are projected to different locations, making the technique unsuitable for comparison tasks. To tackle this problem, we introduce edge similarity, which captures the similarities between two adjacent time frames based on the Graphlet Frequency Distribution (GFD). We then integrate a novel loss term into the t-SNE loss function, which we call vector constraints, to preserve the vectors between projected points across the projections, allowing these points to serve as visual landmarks for direct comparisons between projections. Using synthetic datasets whose ground-truth structures are known, we show that Joint t-SNE outperforms existing techniques, including Dynamic t-SNE, in terms of local coherence error, Kullback-Leibler divergence, and neighborhood preservation. We also showcase a real-world use case to visualize and compare the activation of different layers of a neural network.

Characterizing the Core Internal Gene Pool of H9N2 Responsible for Continuous Reassortment With Other Influenza A Viruses

Reassortment among avian influenza viruses is the main source of novel avian influenza virus subtypes. Studies have shown that the H9N2 virus often donates internal segments to generate novel reassortant avian influenza viruses, acting as a reassortment template. However, the characteristics of the internal pattern of reassortment remain unclear. In this article, we first defined the core gene pool of the internal segments of the H9N2 virus that provide templates for reassortment. We used genetic distance and sequence similarity to define typical clusters in the core gene pool. Then, we analyzed the phylogenetic relationships, feature vector distances, geographic distributions and mutation sites of strains related to the core gene pool. Strains in the same typical clusters have close phylogenetic relationships and feature vector distances. We also found that these typical clusters can be divided into three categories according to their main geographic distribution area. Furthermore, typical clusters in the same geographic area contain some common mutation patterns. Our results suggest that typical clusters in the core gene pool affect the reassortment events of the H9N2 virus in many respects, such as geographic distribution and amino acid mutation sites.

Stochastic neighbor embedding as a tool for visualizing the encoding capability of magnetic resonance fingerprinting dictionaries

Objective

To visualize the encoding capability of magnetic resonance fingerprinting (MRF) dictionaries.

Materials and methods

High-dimensional MRF dictionaries were simulated and embedded into a lower-dimensional space using t-distributed stochastic neighbor embedding (t-SNE). The embeddings were visualized via colors as a surrogate for location in low-dimensional space. First, we illustrate this technique on three different MRF sequences. We then compare the resulting embeddings and the color-coded dictionary maps to these obtained with a singular value decomposition (SVD) dimensionality reduction technique. We validate the t-SNE approach with measures based on existing quantitative measures of encoding capability using the Euclidean distance. Finally, we use t-SNE to visualize MRF sequences resulting from an MRF sequence optimization algorithm.

Results

t-SNE was able to show clear differences between the color-coded dictionary maps of three MRF sequences. SVD showed smaller differences between different sequences. These findings were confirmed by quantitative measures of encoding. t-SNE was also able to visualize differences in encoding capability between subsequent iterations of an MRF sequence optimization algorithm.

Discussion

This visualization approach enables comparison of the encoding capability of different MRF sequences. This technique can be used as a confirmation tool in MRF sequence optimization.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10334-021-00963-8.

Landscape of Bone Marrow Metastasis in Human Neuroblastoma Unraveled by Transcriptomics and Deep Multiplex Imaging

While the bone marrow attracts tumor cells in many solid cancers leading to poor outcome in affected patients, comprehensive analyses of bone marrow metastases have not been performed on a single-cell level. We here set out to capture tumor heterogeneity and unravel microenvironmental changes in neuroblastoma, a solid cancer with bone marrow involvement. To this end, we employed a multi-omics data mining approach to define a multiplex imaging panel and developed DeepFLEX, a pipeline for subsequent multiplex image analysis, whereby we constructed a single-cell atlas of over 35,000 disseminated tumor cells (DTCs) and cells of their microenvironment in the metastatic bone marrow niche. Further, we independently profiled the transcriptome of a cohort of 38 patients with and without bone marrow metastasis. Our results revealed vast diversity among DTCs and suggest that FAIM2 can act as a complementary marker to capture DTC heterogeneity. Importantly, we demonstrate that malignant bone marrow infiltration is associated with an inflammatory response and at the same time the presence of immuno-suppressive cell types, most prominently an immature neutrophil/granulocytic myeloid-derived suppressor-like cell type. The presented findings indicate that metastatic tumor cells shape the bone marrow microenvironment, warranting deeper investigations of spatio-temporal dynamics at the single-cell level and their clinical relevance.

A Non-Contact Fault Diagnosis Method for Bearings and Gears Based on Generalized Matrix Norm Sparse Filtering

Fault diagnosis of mechanical equipment is mainly based on the contact measurement and analysis of vibration signals. In some special working conditions, the non-contact fault diagnosis method represented by the measurement of acoustic signals can make up for the lack of contact testing. However, its engineering application value is greatly restricted due to the low signal-to-noise ratio (SNR) of the acoustic signal. To solve this deficiency, a novel fault diagnosis method based on the generalized matrix norm sparse filtering (GMNSF) is proposed in this paper. Specially, the generalized matrix norm is introduced into the sparse filtering to seek the optimal sparse feature distribution to overcome the defect of low SNR of acoustic signals. Firstly, the collected acoustic signals are randomly overlapped to form the sample fragment data set. Then, three constraints are imposed on the multi-period data set by the GMNSF model to extract the sparse features in the sample. Finally, softmax is used to as a classifier to categorize different fault types. The diagnostic performance of the proposed method is verified by the bearing and planetary gear datasets. Results show that the GMNSF model has good feature extraction ability performance and anti-noise ability than other traditional methods.

Morphing projections: a new visual technique for fast and interactive large-scale analysis of biomedical datasets

MOTIVATION

Biomedical research entails analyzing high dimensional records of biomedical features with hundreds or thousands of samples each. This often involves using also complementary clinical metadata, as well as a broad user domain knowledge. Common data analytics software makes use of machine learning algorithms or data visualization tools. However, they are frequently one-way analyses, providing little room for the user to reconfigure the steps in light of the observed results. In other cases, reconfigurations involve large latencies, requiring a retraining of algorithms or a large pipeline of actions. The complex and multiway nature of the problem, nonetheless, suggests that user interaction feedback is a key element to boost the cognitive process of analysis, and must be both broad and fluid.

RESULTS

In this article, we present a technique for biomedical data analytics, based on blending meaningful views in an efficient manner, allowing to provide a natural smooth way to transition among different but complementary representations of data and knowledge. Our hypothesis is that the confluence of diverse complementary information from different domains on a highly interactive interface allows the user to discover relevant relationships or generate new hypotheses to be investigated by other means. We illustrate the potential of this approach with three case studies involving gene expression data and clinical metadata, as representative examples of high dimensional, multidomain, biomedical data.

AVAILABILITY AND IMPLEMENTATION

Code and demo app to reproduce the results available at https://gitlab.com/idiazblanco/morphing-projections-demo-and-dataset-preparation.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

ProReveal: Progressive Visual Analytics With Safeguards

We present a new visual exploration concept-Progressive Visual Analytics with Safeguards-that helps people manage the uncertainty arising from progressive data exploration. Despite its potential benefits, intermediate knowledge from progressive analytics can be incorrect due to various machine and human factors, such as a sampling bias or misinterpretation of uncertainty. To alleviate this problem, we introduce PVA-Guards, safeguards people can leave on uncertain intermediate knowledge that needs to be verified, and derive seven PVA-Guards based on previous visualization task taxonomies. PVA-Guards provide a means of ensuring the correctness of the conclusion and understanding the reason when intermediate knowledge becomes invalid. We also present ProReveal, a proof-of-concept system designed and developed to integrate the seven safeguards into progressive data exploration. Finally, we report a user study with 14 participants, which shows people voluntarily employed PVA-Guards to safeguard their findings and ProReveal's PVA-Guard view provides an overview of uncertain intermediate knowledge. We believe our new concept can also offer better consistency in progressive data exploration, alleviating people's heterogeneous interpretation of uncertainty.

Polar Gini Curve: A Technique to Discover Gene Expression Spatial Patterns from Single-cell RNA-seq Data

In this work, we describe the development of Polar Gini Curve, a method for characterizing cluster markers by analyzing single-cell RNA sequencing (scRNA-seq) data. Polar Gini Curve combines the gene expression and the 2D coordinates ("spatial") information to detect patterns of uniformity in any clustered cells from scRNA-seq data. We demonstrate that Polar Gini Curve can help users characterize the shape and density distribution of cells in a particular cluster, which can be generated during routine scRNA-seq data analysis. To quantify the extent to which a gene is uniformly distributed in a cell cluster space, we combine two polar Gini curves (PGCs)-one drawn upon the cell-points expressing the gene (the "foreground curve") and the other drawn upon all cell-points in the cluster (the "background curve"). We show that genes with highly dissimilar foreground and background curves tend not to uniformly distributed in the cell cluster-thus having spatially divergent gene expression patterns within the cluster. Genes with similar foreground and background curves tend to uniformly distributed in the cell cluster-thus having uniform gene expression patterns within the cluster. Such quantitative attributes of PGCs can be applied to sensitively discover biomarkers across clusters from scRNA-seq data. We demonstrate the performance of the Polar Gini Curve framework in several simulation case studies. Using this framework to analyze a real-world neonatal mouse heart cell dataset, the detected biomarkers may characterize novel subtypes of cardiac muscle cells. The source code and data for Polar Gini Curve could be found at http://discovery.informatics.uab.edu/PGC/ or https://figshare.com/projects/Polar_Gini_Curve/76749.

Systems analysis and controlled malaria infection in Europeans and Africans elucidate naturally acquired immunity

Controlled human infections provide opportunities to study the interaction between the immune system and malaria parasites, which is essential for vaccine development. Here, we compared immune signatures of malaria-naive Europeans and of Africans with lifelong malaria exposure using mass cytometry, RNA sequencing and data integration, before and 5 and 11 days after venous inoculation with Plasmodium falciparum sporozoites. We observed differences in immune cell populations, antigen-specific responses and gene expression profiles between Europeans and Africans and among Africans with differing degrees of immunity. Before inoculation, an activated/differentiated state of both innate and adaptive cells, including elevated CD161⁺CD4⁺ T cells and interferon-γ production, predicted Africans capable of controlling parasitemia. After inoculation, the rapidity of the transcriptional response and clusters of CD4⁺ T cells, plasmacytoid dendritic cells and innate T cells were among the features distinguishing Africans capable of controlling parasitemia from susceptible individuals. These findings can guide the development of a vaccine effective in malaria-endemic regions.

Single-Cell Transcriptomics: Current Methods and Challenges in Data Acquisition and Analysis

Rapid cost drops and advancements in next-generation sequencing have made profiling of cells at individual level a conventional practice in scientific laboratories worldwide. Single-cell transcriptomics [single-cell RNA sequencing (SC-RNA-seq)] has an immense potential of uncovering the novel basis of human life. The well-known heterogeneity of cells at the individual level can be better studied by single-cell transcriptomics. Proper downstream analysis of this data will provide new insights into the scientific communities. However, due to low starting materials, the SC-RNA-seq data face various computational challenges: normalization, differential gene expression analysis, dimensionality reduction, etc. Additionally, new methods like 10× Chromium can profile millions of cells in parallel, which creates a considerable amount of data. Thus, single-cell data handling is another big challenge. This paper reviews the single-cell sequencing methods, library preparation, and data generation. We highlight some of the main computational challenges that require to be addressed by introducing new bioinformatics algorithms and tools for analysis. We also show single-cell transcriptomics data as a big data problem.

Latent Dirichlet Allocation and t-Distributed Stochastic Neighbor Embedding Enhance Scientific Reading Comprehension of Articles Related to Enterprise Architecture

As the amount of scientific information increases steadily, it is crucial to improve fast-reading comprehension. To grasp many scientific articles in a short period, artificial intelligence becomes essential. This paper aims to apply artificial intelligence methodologies to examine broad topics such as enterprise architecture in scientific articles. Analyzing abstracts with latent dirichlet allocation or inverse document frequency appears to be more beneficial than exploring full texts. Furthermore, we demonstrate that t-distributed stochastic neighbor embedding is well suited to explore the degree of connectivity to neighboring topics, such as complexity theory. Artificial intelligence produces results that are similar to those obtained by manual reading. Our full-text study confirms enterprise architecture trends such as sustainability and modeling languages.