Cluster-based radiomics reveal spatial heterogeneity of bevacizumab response for treatment of radiotherapy-induced cerebral necrosis

Background

Bevacizumab is used in the treatment of radiation necrosis (RN), which is a debilitating toxicity following head and neck radiotherapy. However, there is no biomarker to predict if a patient would respond to bevacizumab.

Purpose

We aimed to develop a cluster-based radiomics approach to characterize the spatial heterogeneity of RN and map their responses to bevacizumab.

Methods

118 consecutive nasopharyngeal carcinoma patients diagnosed with RN were enrolled. We divided 152 lesions from the patients into 101 for training, and 51 for validation. We extracted voxel-level radiomics features from each lesion segmented on T1-weighted+contrast and T2 FLAIR sequences of pre- and post-bevacizumab magnetic resonance images, followed by a three-step analysis involving individual- and population-level clustering, before delta-radiomics to derive five radiomics clusters within the lesions. We tested the association of each cluster with response to bevacizumab and developed a clinico-radiomics model using clinical predictors and cluster-specific features.

Results

71 (70.3%) and 34 (66.7%) lesions had responded to bevacizumab in the training and validation datasets, respectively. Two radiomics clusters were spatially mapped to the edema region, and the volume changes were significantly associated with bevacizumab response (OR:11.12 [95% CI: 2.54-73.47], P = 0.004; and 1.63[1.07-2.78], P = 0.042). The combined clinico-radiomics model based on textural features extracted from the most significant cluster improved the prediction of bevacizumab response, compared with a clinical-only model (AUC:0.755 [0.645-0.865] to 0.852 [0.764-0.940], training; 0.708 [0.554-0.861] to 0.816 [0.699-0.933], validation).

Conclusion

Our radiomics approach yielded intralesional resolution, enabling a more refined feature selection for predicting bevacizumab efficacy in the treatment of RN.

DWSSA: Alleviating over-smoothness for deep Graph Neural Networks

Graph Neural Networks (GNNs) have demonstrated great potential in achieving outstanding performance in various graph-related tasks, e.g., graph classification and link prediction. However, most of them suffer from the following issue: shallow networks capture very limited knowledge. Prior works design deep GNNs with more layers to solve the issue, which however introduces a new challenge, i.e., the infamous over-smoothness. Graph representation over emphasizes node features but only considers the static graph structure with a uniform weight are the key reasons for the over-smoothness issue. To alleviate the issue, this paper proposes a Dynamic Weighting Strategy (DWS) for addressing over-smoothness. We first employ Fuzzy C-Means (FCM) to cluster all nodes into several groups and get each node's fuzzy assignment, based on which a novel metric function is devised for dynamically adjusting the aggregation weights. This dynamic weighting strategy not only enables the intra-cluster interactions, but also inter-cluster aggregations, which well addresses undifferentiated aggregation caused by uniform weights. Based on DWS, we further design a Structure Augmentation (SA) step for addressing the issue of underutilizing the graph structure, where some potentially meaningful connections (i.e., edges) are added to the original graph structure via a parallelable KNN algorithm. In general, the optimized Dynamic Weighting Strategy with Structure Augmentation (DWSSA) alleviates over-smoothness by reducing noisy aggregations and utilizing topological knowledge. Extensive experiments on eleven homophilous or heterophilous graph benchmarks demonstrate the effectiveness of our proposed method DWSSA in alleviating over-smoothness and enhancing deep GNNs performance.

Region partitioning of articular cartilage with streaming-potential-based parameters and indentation maps

Articular cartilage exhibits site-specific tissue inhomogeneity, for which the tissue properties may continuously vary across the articular surface. To facilitate practical applications such as studying site-specific cartilage degeneration, the inhomogeneity may be approximated with several distinct region-wise variations, with one set of tissue properties for one region. A clustering method was previously developed to partition such regions using cartilage indentation-relaxation and thickness mapping instead of simply using surface geometry. In the present study, a quantitative parameter based on streaming potential measurement was introduced as an additional feature to assess the applicability of the methodology with independent datasets. Experimental data were collected from 24 sets of femoral condyles, extracted from fresh porcine stifle joints, through streaming potential mapping, automated indentation, and needle penetration tests. K-means clustering and Elbow method were used to find optimal region partitions. Consistent with previous findings, three regions were suggested for either lateral or medial condyle regardless of left or right joint. The region shapes were approximately triangular or trapezoidal, which was similar to what was found previously. Streaming potentials were confirmed to be region-dependent, but not significantly different among joints. The cartilage was significantly thicker in the medial than lateral condyles. The region areas were consistent among joints, and comparable to that found in a previous study. The present study demonstrated the capability of region partitioning methods with different variables, which may facilitate new applications whenever site-specific tissue properties must be considered.

Identifying unique subgroups in suicide risks among psychiatric outpatients

BACKGROUND

The presence of psychiatric disorders is widely recognized as one of the primary risk factors for suicide. A significant proportion of individuals receiving outpatient psychiatric treatment exhibit varying degrees of suicidal behaviors, which may range from mild suicidal ideations to overt suicide attempts. This study aims to elucidate the transdiagnostic symptom dimensions and associated suicidal features among psychiatric outpatients.

METHODS

The study enrolled patients who attended the psychiatry outpatient clinic at a tertiary hospital in South Korea (n = 1, 849, age range = 18-81; 61% women). A data-driven classification methodology was employed, incorporating a broad spectrum of clinical symptoms, to delineate distinctive subgroups among psychiatric outpatients exhibiting suicidality (n = 1189). A reference group of patients without suicidality (n = 660) was included for comparative purposes to ascertain cluster-specific sociodemographic, suicide-related, and psychiatric characteristics.

RESULTS

Psychiatric outpatients with suicidality (n = 1189) were subdivided into three distinctive clusters: the low-suicide risk cluster (Cluster 1), the high-suicide risk externalizing cluster (Cluster 2), and the high-suicide risk internalizing cluster (Cluster 3). Relative to the reference group (n = 660), each cluster exhibited distinct attributes pertaining to suicide-related characteristics and clinical symptoms, covering domains such as anxiety, externalizing and internalizing behaviors, and feelings of hopelessness. Cluster 1, identified as the low-suicide risk group, exhibited less frequent suicidal ideation, planning, and multiple attempts. In the high-suicide risk groups, Cluster 2 displayed pronounced externalizing symptoms, whereas Cluster 3 was primarily defined by internalizing and hopelessness symptoms. Bipolar disorders were most common in Cluster 2, while depressive disorders were predominant in Cluster 3.

DISCUSSION

Our findings suggest the possibility of differentiating psychiatric outpatients into distinct, clinically relevant subgroups predicated on their suicide risk. This research potentially paves the way for personalizing interventions and preventive strategies that address cluster-specific characteristics, thereby mitigating suicide-related mortality among psychiatric outpatients.

Semi-supervised ensemble learning for human activity recognition in casas Kyoto dataset

-The automatic identification of human physical activities, commonly referred to as Human Activity Recognition (HAR), has garnered significant interest and application across various sectors, including entertainment, sports, and notably health. Within the realm of health, a myriad of applications exists, contingent upon the nature of experimentation, the activities under scrutiny, and the methodology employed for data and information acquisition. This diversity opens doors to multifaceted applications, including support for the well-being and safeguarding of elderly individuals afflicted with neurodegenerative diseases, especially in the context of smart homes. Within the existing literature, a multitude of datasets from both indoor and outdoor environments have surfaced, significantly contributing to the activity identification processes. One prominent dataset, the CASAS project developed by Washington State University (WSU) University, encompasses experiments conducted in indoor settings. This dataset facilitates the identification of a range of activities, such as cleaning, cooking, eating, washing hands, and even making phone calls. This article introduces a model founded on the principles of Semi-supervised Ensemble Learning, enabling the harnessing of the potential inherent in distance-based clustering analysis. This technique aids in the identification of distinct clusters, each encapsulating unique activity characteristics. These clusters serve as pivotal inputs for the subsequent classification process, which leverages supervised techniques. The outcomes of this approach exhibit great promise, as evidenced by the quality metrics' analysis, showcasing favorable results compared to the existing state-of-the-art methods. This integrated framework not only contributes to the field of HAR but also holds immense potential for enhancing the capabilities of smart homes and related applications.

Multimorbidity in middle-aged women and COVID-19: binary data clustering for unsupervised binning of rare multimorbidity features and predictive modeling

BACKGROUND

Multimorbidity is typically associated with deficient health-related quality of life in mid-life, and the likelihood of developing multimorbidity in women is elevated. We address the issue of data sparsity in non-prevalent features by clustering the binary data of various rare medical conditions in a cohort of middle-aged women. This study aims to enhance understanding of how multimorbidity affects COVID-19 severity by clustering rare medical conditions and combining them with prevalent features for predictive modeling. The insights gained can guide the development of targeted interventions and improved management strategies for individuals with multiple health conditions.

METHODS

The study focuses on a cohort of 4477 female patients, (aged 45-60) in Piedmont, Italy, and utilizes their multimorbidity data prior to the COVID-19 pandemic from their medical history from 2015 to 2019. The COVID-19 severity is determined by the hospitalization status of the patients from February to May 2020. Each patient profile in the dataset is depicted as a binary vector, where each feature denotes the presence or absence of a specific multimorbidity condition. By clustering the sparse medical data, newly engineered features are generated as a bin of features, and they are combined with the prevalent features for COVID-19 severity predictive modeling.

RESULTS

From sparse data consisting of 174 input features, we have created a low-dimensional feature matrix of 17 features. Machine Learning algorithms are applied to the reduced sparsity-free data to predict the Covid-19 hospital admission outcome. The performance obtained for the corresponding models are as follows: Logistic Regression (accuracy 0.72, AUC 0.77, F1-score 0.69), Linear Discriminant Analysis (accuracy 0.7, AUC 0.77, F1-score 0.67), and Ada Boost (accuracy 0.7, AUC 0.77, F1-score 0.68).

CONCLUSION

Mapping higher-dimensional data to a low-dimensional space can result in information loss, but reducing sparsity can be beneficial for Machine Learning modeling due to improved predictive ability. In this study, we addressed the issue of data sparsity in electronic health records and created a model that incorporates both prevalent and rare medical conditions, leading to more accurate and effective predictive modeling. The identification of complex associations between multimorbidity and the severity of COVID-19 highlights potential areas of focus for future research, including long COVID and intervention efforts.

Dravet syndrome seizure frequency and clustering: Placebo-treated patients in clinical trials

OBJECTIVE

Dravet syndrome is a rare developmental epilepsy syndrome associated with severe, treatment-resistant seizures. Since seizures and seizure clusters are linked to morbidity, reduced quality of life, and premature mortality, a greater understanding of these outcomes could improve trial designs. This analysis explored seizure types, seizure clusters, and factors affecting seizure cluster variability in Dravet syndrome patients.

METHODS

Pooled post-hoc analyses were performed on data from placebo-treated patients in GWPCARE 1B and GWPCARE 2 randomized controlled phase III trials comparing cannabidiol and placebo in Dravet syndrome patients aged 2-18 years. Multivariate stepwise analysis of covariance of log-transformed convulsive seizure cluster frequency was performed, body weight and body mass index z-scores were calculated, and incidence of adverse events was assessed. Data were summarized in three age groups.

RESULTS

We analyzed 124 placebo-treated patients across both studies (2-5 years: n = 35; 6-12 years: n = 52; 13-18 years: n = 37). Generalized tonic-clonic seizures followed by myoclonic seizures were the most frequent seizure types. Mean and median convulsive seizure cluster frequency overall decreased between baseline and maintenance period but did not change significantly during the latter; variation in convulsive seizure cluster frequency was observed across age groups. Multivariate analysis suggested correlations between convulsive seizure cluster frequency and age (positive), and body mass index (BMI) (negative).

INTERPRETATION

Post-hoc analyses suggested that potential relationships could exist between BMI, age and convulsive seizure cluster variation. Results suggested that seizure cluster frequency may be a valuable outcome in future trials. Further research is needed to confirm our findings.

Autonomous fetal morphology scan: deep learning + clustering merger - the second pair of eyes behind the doctor

The main cause of fetal death, of infant morbidity or mortality during childhood years is attributed to congenital anomalies. They can be detected through a fetal morphology scan. An experienced sonographer (with more than 2000 performed scans) has the detection rate of congenital anomalies around 52%. The rates go down in the case of a junior sonographer, that has the detection rate of 32.5%. One viable solution to improve these performances is to use Artificial Intelligence. The first step in a fetal morphology scan is represented by the differentiation process between the view planes of the fetus, followed by a segmentation of the internal organs in each view plane. This study presents an Artificial Intelligence empowered decision support system that can label anatomical organs using a merger between deep learning and clustering techniques, followed by an organ segmentation with YOLO8. Our framework was tested on a fetal morphology image dataset that regards the fetal abdomen. The experimental results show that the system can correctly label the view plane and the corresponding organs on real-time ultrasound movies.Trial registrationThe study is registered under the name "Pattern recognition and Anomaly Detection in fetal morphology using Deep Learning and Statistical Learning (PARADISE)", project number 101PCE/2022, project code PN-III-P4-PCE-2021-0057. Trial registration: ClinicalTrials.gov, unique identifying number NCT05738954, date of registration 02.11.2023.

Clusters of 24-hour movement behavior and diet and their relationship with health indicators among youth: a systematic review

Movement-related behaviors (physical activity [PA], sedentary behavior [SB], and sleep) and diet interact with each other and play important roles in health indicators in youth. This systematic review aimed to investigate how PA, SB, sleep, and diet cluster in youth by biological sex; and to examine which cluster are associated with health indicators. This study was registered in PROSPERO (number: CRD42018094826). Five electronic databases were assessed. Eligibility criteria allowed studies that included youth (aged 19 years and younger), and only the four behaviors {PA, SB, sleep, and diet (ultra-processed foods [UPF]; fruits and vegetables [FV])} analyzed by applying data-based cluster procedures. From 12,719 articles screened; 23 were included. Of these, four investigated children, and ten identified clusters by biological sex. Sixty-six mixed cluster were identified including, 34 in mixed-sex samples, 10 in boys and 11 in girls. The most frequent clusters in mixed-sex samples were "High SB UPF Low Sleep", "Low PA High SB Satisfactory Sleep", and "High PA". The main difference in profiles according to sex was that girls' clusters were characterized by high sleep duration, whereas boys' clusters by high PA. There were a few associations found between cluster types and health indicators, highlighting that youth assigned to cluster types with low PA exhibited higher adiposity. In conclusion, the youth presented a range of clusters of behaviors, typically exhibiting at least one unhealthy behavior. Similar patterns were observed in both sexes with the biggest difference in time of sleep for girls and PA for boys. These findings underscore the importance of intervention strategies targeting multiple behaviors simultaneously to enhance health risk profiles and indicators in children and adolescents.

Delineating morbidity patterns in preterm infants at near-term age using a data-driven approach

BACKGROUND

Long-term survival after premature birth is significantly determined by development of morbidities, primarily affecting the cardio-respiratory or central nervous system. Existing studies are limited to pairwise morbidity associations, thereby lacking a holistic understanding of morbidity co-occurrence and respective risk profiles.

METHODS

Our study, for the first time, aimed at delineating and characterizing morbidity profiles at near-term age and investigated the most prevalent morbidities in preterm infants: bronchopulmonary dysplasia (BPD), pulmonary hypertension (PH), mild cardiac defects, perinatal brain pathology and retinopathy of prematurity (ROP). For analysis, we employed two independent, prospective cohorts, comprising a total of 530 very preterm infants: AIRR ("Attention to Infants at Respiratory Risks") and NEuroSIS ("Neonatal European Study of Inhaled Steroids"). Using a data-driven strategy, we successfully characterized morbidity profiles of preterm infants in a stepwise approach and (1) quantified pairwise morbidity correlations, (2) assessed the discriminatory power of BPD (complemented by imaging-based structural and functional lung phenotyping) in relation to these morbidities, (3) investigated collective co-occurrence patterns, and (4) identified infant subgroups who share similar morbidity profiles using machine learning techniques.

RESULTS

First, we showed that, in line with pathophysiologic understanding, BPD and ROP have the highest pairwise correlation, followed by BPD and PH as well as BPD and mild cardiac defects. Second, we revealed that BPD exhibits only limited capacity in discriminating morbidity occurrence, despite its prevalence and clinical indication as a driver of comorbidities. Further, we demonstrated that structural and functional lung phenotyping did not exhibit higher association with morbidity severity than BPD. Lastly, we identified patient clusters that share similar morbidity patterns using machine learning in AIRR (n=6 clusters) and NEuroSIS (n=8 clusters).

CONCLUSIONS

By capturing correlations as well as more complex morbidity relations, we provided a comprehensive characterization of morbidity profiles at discharge, linked to shared disease pathophysiology. Future studies could benefit from identifying risk profiles to thereby develop personalized monitoring strategies.

TRIAL REGISTRATION

AIRR: DRKS.de, DRKS00004600, 28/01/2013. NEuroSIS: ClinicalTrials.gov, NCT01035190, 18/12/2009.

Development of a basin-scale total nitrogen prediction model by integrating clustering and regression methods

Nutrient runoff into rivers caused by human activity has led to global eutrophication issues. The Nakdong River in South Korea is currently facing significant challenges related to eutrophication and harmful algal blooms, underscoring the critical importance of managing total nitrogen (T-N) levels. However, traditional methods of indoor analysis, which depend on sampling, are labor-intensive and face limitations in collecting high-frequency data. Despite advancements in sensor allowing for the measurement of various parameters, sensors still cannot directly measure T-N, necessitating surrogate regression methods. Therefore, we conducted T-N predictions using a water quality dataset collected from 2018 to 2022 at 157 observatories within the Nakdong River basin. To account for the water quality characteristics of each location, we employed a clustering technique to divide the basin and compared a Gaussian mixture model with K-means clustering. Moreover, optimal regressor for each cluster was selected by comparing multiple linear regression (MLR), random forest, and XGBoost. The results showed that forming four clusters via K-means clustering was the most suitable approach and MLR was reasonably accurate for all clusters. Subsequently, recursive feature elimination cross-validation was used to identify suitable parameters for T-N prediction, thus leading to the construction of high-accuracy T-N prediction models. Clustering was useful not only for improving the regressors but also for spatially analyzing the water quality characteristics of the Nakdong River. The MLR model can reveal causal relationships and thus is useful for decision-making. The results of this study revealed that the combination of a simple linear regression model and clustering method can be applied to a wide watershed. The clustering-based regression model showed potential for accurately predicting T-N at the basin level and is expected to contribute to nationwide water quality management through future applications in various fields.

Experimental validation and comprehensive analysis of m6A methylation regulators in intervertebral disc degeneration subpopulation classification

Intervertebral disc degeneration (IVDD) is one of the most prevalent causes of chronic low back pain. The role of m6A methylation modification in disc degeneration (IVDD) remains unclear. We investigated immune-related m6A methylation regulators as IVDD biomarkers through comprehensive analysis and experimental validation of m6A methylation regulators in disc degeneration. The training dataset was downloaded from the GEO database and analysed for differentially expressed m6A methylation regulators and immunological features, the differentially regulators were subsequently validated by a rat IVDD model and RT-qPCR. Further screening of key m6A methylation regulators based on machine learning and LASSO regression analysis. Thereafter, a predictive model based on key m6A methylation regulators was constructed for training sets, which was validated by validation set. IVDD patients were then clustered based on the expression of key m6A regulators, and the expression of key m6A regulators and immune infiltrates between clusters was investigated to determine immune markers in IVDD. Finally, we investigated the potential role of the immune marker in IVDD through enrichment analysis, protein-to-protein network analysis, and molecular prediction. By analysising of the training set, we revealed significant differences in gene expression of five methylation regulators including RBM15, YTHDC1, YTHDF3, HNRNPA2B1 and ALKBH5, while finding characteristic immune infiltration of differentially expressed genes, the result was validated by PCR. We then screen the differential m6A regulators in the training set and identified RBM15 and YTHDC1 as key m6A regulators. We then used RBM15 and YTHDC1 to construct a predictive model for IVDD and successfully validated it in the training set. Next, we clustered IVDD patients based on the expression of RBM15 and YTHDC1 and explored the immune infiltration characteristics between clusters as well as the expression of RBM15 and YTHDC1 in the clusters. YTHDC1 was finally identified as an immune biomarker for IVDD. We finally found that YTHDC1 may influence the immune microenvironment of IVDD through ABL1 and TXK. In summary, our results suggest that YTHDC1 is a potential biomarker for the development of IVDD and may provide new insights for the precise prevention and treatment of IVDD.

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 ).

Symptom-based drug prediction of lifestyle-related chronic diseases using unsupervised machine learning techniques

BACKGROUND AND OBJECTIVES

Lifestyle-related diseases (LSDs) impose a substantial economic burden on patients and health care services. LSDs are chronic in nature and can directly affect the heart and lungs. Therapeutic interventions only based on symptoms can be crucial for prompt treatment initiation in LSDs, as symptoms are the first information available to clinicians. So, this work aims to apply unsupervised machine learning (ML) techniques for developing models to predict drugs from symptoms for LSDs, with a specific focus on pulmonary and heart diseases.

METHODS

The drug-disease and disease-symptom associations of 143 LSDs, 1271 drugs, and 305 symptoms were used to compute direct associations between drugs and symptoms. ML models with four different algorithms - K-Means, Bisecting K-Means, Mean Shift, and Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) - were developed to cluster the drugs using symptoms as features. The optimal model was saved in a server for the development of a web application. A web application was developed to perform the prediction based on the optimal model.

RESULTS

The Bisecting K-means model showed the best performance with a silhouette coefficient of 0.647 and generated 138 drug clusters. The drugs within the optimal clusters showed good similarity based on i) gene ontology annotations of the gene targets, ii) chemical ontology annotations, and iii) maximum common substructure of the drugs. In the web application, the model also provides a confidence score for each predicted drug while predicting from a new set of input symptoms.

CONCLUSION

In summary, direct associations between drugs and symptoms were computed, and those were used to develop a symptom-based drug prediction tool for LSDs with unsupervised ML models. The ML-based prediction can provide a second opinion to clinicians to aid their decision-making for early treatment of LSD patients. The web application (URL - http://bicresources.jcbose.ac.in/ssaha4/sdldpred) can provide a simple interface for all end-users to perform the ML-based prediction.

Blurred streamlines: A novel representation to reduce redundancy in tractography

Tractography is a powerful tool to study brain connectivity in vivo, but it is well known to suffer from an intrinsic trade-off between sensitivity and specificity. A critical - but usually underrated - parameter to choose that can heavily impact the quality of the estimates is the number of streamlines to be reconstructed for a given data set. In fact, sensitivity can be improved by generating more and more streamlines, as all real anatomical connections are likely reconstructed, but lots of false positives are inevitably introduced, too. Consequently, so-called tractography filtering techniques have become increasingly popular to get rid of these false positives and improve specificity. However, increasing number of streamlines introduces redundancy in tractography reconstructions, which may negatively impact the performance of filtering algorithms, especially those based on linear formulations. To address this problem, we introduce a novel streamlines representation, called "blurred streamlines", which drastically reduces the redundancy among streamlines by (i) clustering similar trajectories and (ii) spatially blurring the corresponding signal contributions. We tested the effectiveness of the blurred streamlines both on synthetic and in vivo data. Our results clearly show that this new representation is as accurate as state-of-the-art methods despite using only 5% of the input streamlines, thus significantly decreasing the computational complexity of filtering algorithms as well as storage requirements of the resulting reconstructions.

MBAN: multi-branch attention network for small object detection

Recent years small object detection has seen remarkable advancement. However, small objects are difficult to accurately detect in complex scenes due to their low resolution. The downsampling operation inevitably leads to the loss of information for small objects. In order to solve these issues, this article proposes a novel Multi-branch Attention Network (MBAN) to improve the detection performance of small objects. Firstly, an innovative Multi-branch Attention Module (MBAM) is proposed, which consists of two parts, i.e. Multi-branch structure consisting of convolution and maxpooling, and the parameter-free SimAM attention mechanism. By combining these two parts, the number of network parameters is reduced, the information loss of small objects is reduced, and the representation of small object features is enhanced. Furthermore, to systematically solve the problem of small object localization, a pre-processing method called Adaptive Clustering Relocation (ACR) is proposed. To validate our network, we conducted extensive experiments on two benchmark datasets, i.e. NWPU VHR-10 and PASCAL VOC. The findings from the experiment demonstrates the significant performance gains of MBAN over most existing algorithms, the mAP of MBAN achieved 96.55% and 84.96% on NWPU VHR-10 and PASCAL VOC datasets, respectively, which proves that MBAN has significant performance in small object detection.

Feature extraction of particle morphologies of pharmaceutical excipients from scanning electron microscope images using convolutional neural networks

Scanning electron microscopy (SEM) images are the most widely used tool for evaluating particle morphology; however, quantitative evaluation using SEM images is time-consuming and often neglected. In this study, we aimed to extract features related to particle morphology of pharmaceutical excipients from SEM images using a convolutional neural network (CNN). SEM images of 67 excipients were acquired and used as models. A classification CNN model of the excipients was constructed based on the SEM images. Further, features were extracted from the middle layer of this CNN model, and the data was compressed to two dimensions using uniform manifold approximation and projection. Lastly, hierarchical clustering analysis (HCA) was performed to categorize the excipients into several clusters and identify similarities among the samples. The classification CNN model showed high accuracy, allowing each excipient to be identified with a high degree of accuracy. HCA revealed that the 67 excipients were classified into seven clusters. Additionally, the particle morphologies of excipients belonging to the same cluster were found to be very similar. These results suggest that CNN models are useful tools for extracting information and identifying similarities among the particle morphologies of excipients.

Screening for drought tolerance and genetic diversity of wheat varieties using agronomic and molecular markers

BACKGROUND

The future predictions for frequent and severe droughts will represent a significant threat to wheat yield and food security. In this context, breeding has proven to be the most efficient approach to enhance wheat productivity in dry environments.

METHODS AND RESULTS

In this study, both agronomic and molecular-based approaches were used to evaluate the response of twenty-eight Tunisian wheat varieties to drought stress. The primary objective was to screen these varieties for drought tolerance using molecular and agro-morphological markers. All varieties were significantly affected by drought stress regarding various traits including total dry matter, straw length, flag leaf area, number of senescent leaves, SPAD value, grain yield and grain number. Furthermore, substantial variability in drought-stress tolerance was observed among wheat genotypes. The cluster analysis and principal component analyses confirmed the existence of genotypic variation in growth and yield impairments induced by drought. The stress susceptibility index (SSI) and tolerance index (TOL) proved to be the most effective indices and were strongly correlated with the varying levels of genotypic tolerance. The genotyping evaluation resulted in the amplification of 101 alleles using highly polymorphic 12 SSR markers, showed an average polymorphism of 74%.

CONCLUSIONS

Taken together, the combination of agronomic and molecular approaches revealed that Karim, Td7, D117 and Utique are the most drought-tolerant wheat varieties. These varieties are particularly promising candidates for genetic improvements and can be utilized as potential genitors for future breeding programs in arid and semi-arid regions.

Enhancing subcellular protein localization mapping analysis using Sc2promap utilizing attention mechanisms

BACKGROUND

Aberrant protein localization is a prominent feature in many human diseases and can have detrimental effects on the function of specific tissues and organs. High-throughput technologies, which continue to advance with iterations of automated equipment and the development of bioinformatics, enable the acquisition of large-scale data that are more pattern-rich, allowing for the use of a wider range of methods to extract useful patterns and knowledge from them.

METHODS

The proposed sc2promap (Spatial and Channel for SubCellular Protein Localization Mapping) model, designed to proficiently extract meaningful features from a vast repository of single-channel grayscale protein images for the purposes of protein localization analysis and clustering. Sc2promap incorporates a prediction head component enriched with supplementary protein annotations, along with the integration of a spatial-channel attention mechanism within the encoder to enables the generation of high-resolution protein localization maps that encapsulate the fundamental characteristics of cells, including elemental cellular localizations such as nuclear and non-nuclear domains.

RESULTS

Qualitative and quantitative comparisons were conducted across internal and external clustering evaluation metrics, as well as various facets of the clustering results. The study also explored different components of the model. The research outcomes conclusively indicate that, in comparison to previous methods, Sc2promap exhibits superior performance.

CONCLUSIONS

The amalgamation of the attention mechanism and prediction head components has led the model to excel in protein localization clustering and analysis tasks.

GENERAL SIGNIFICANCE

The model effectively enhances the capability to extract features and knowledge from protein fluorescence images.

Sequencing hour-level temporal patterns of polysubstance use among persons who use cocaine, alcohol, and cannabis: A back-translational approach

BACKGROUND

Polysubstance use is highly prevalent among persons who use cocaine; however, little is known about how alcohol and cannabis are used with cocaine. We identified temporal patterns of cocaine+alcohol and cocaine+cannabis polysubstance use to inform more translationally relevant preclinical models.

METHODS

Participants who used cocaine plus alcohol and/or cannabis at least once in the past 30 days (n=148) were interviewed using the computerized Substance Abuse Module and the newer Polysubstance Use-Temporal Patterns Section. For each day in the past 30 days, participants reported whether they had used cocaine, alcohol, and cannabis; if any combinations of use were endorsed, participants described detailed hourly use of each substance on the most "typical day" for the combination. Sequence analysis and hierarchical clustering were applied to identify patterns of timing of drug intake on typical days of cocaine polysubstance use.

RESULTS

We identified five temporal patterns among the 180 sequences of reported cocaine polysubstance use: 1) limited cocaine/cocaine+alcohol use (53%); 2) extensive cannabis then cocaine+alcohol+cannabis use (22%); 3) limited alcohol/cannabis then cocaine+alcohol use (13%); 4) extensive cocaine+cannabis then cocaine+alcohol+cannabis use (4%); and 5) extensive cocaine then cocaine+alcohol use (8%). While drug intake patterns differed, prevalence of use disorders did not.

CONCLUSIONS

Patterns were characterized by cocaine, alcohol, and cannabis polysubstance use and by the timing, order, duration, and quantity of episode-level substance use. The identification of real-world patterns of cocaine polysubstance use represents an important step toward developing laboratory models that accurately reflect human behavior.

An analysis of the CIBERESUCICOVID Cohort

BACKGROUND

Acute respiratory distress syndrome (ARDS) can be classified into sub-phenotypes according to different inflammatory/clinical status. Prognostic enrichment was achieved by grouping patients into hypoinflammatory or hyperinflammatory sub-phenotypes, even though the time of analysis may change the classification according to treatment response or disease evolution. We aimed to evaluate when patients can be clustered in more than 1 group, and how they may change the clustering of patients using data of baseline or day 3, and the prognosis of patients according to their evolution by changing or not the cluster.

METHODS

Multicenter, observational prospective, and retrospective study of patients admitted due to ARDS related to COVID-19 infection in Spain. Patients were grouped according to a clustering mixed-type data algorithm (k-prototypes) using continuous and categorical readily available variables at baseline and day 3.

RESULTS

Of 6205 patients, 3743 (60%) were included in the study. According to silhouette analysis, patients were grouped in two clusters. At baseline, 1402 (37%) patients were included in cluster 1 and 2341(63%) in cluster 2. On day 3, 1557(42%) patients were included in cluster 1 and 2086 (57%) in cluster 2. The patients included in cluster 2 were older and more frequently hypertensive and had a higher prevalence of shock, organ dysfunction, inflammatory biomarkers, and worst respiratory indexes at both time points. The 90-day mortality was higher in cluster 2 at both clustering processes (43.8% [n = 1025] versus 27.3% [n = 383] at baseline, and 49% [n = 1023] versus 20.6% [n = 321] on day 3). Four hundred and fifty-eight (33%) patients clustered in the first group were clustered in the second group on day 3. In contrast, 638 (27%) patients clustered in the second group were clustered in the first group on day 3.

CONCLUSIONS

During the first days, patients can be clustered into two groups and the process of clustering patients may change as they continue to evolve. This means that despite a vast majority of patients remaining in the same cluster, a minority reaching 33% of patients analyzed may be re-categorized into different clusters based on their progress. Such changes can significantly impact their prognosis.

Comparative study on chromatin loop callers using Hi-C data reveals their effectiveness

BACKGROUND

Chromosome is one of the most fundamental part of cell biology where DNA holds the hierarchical information. DNA compacts its size by forming loops, and these regions house various protein particles, including CTCF, SMC3, H3 histone. Numerous sequencing methods, such as Hi-C, ChIP-seq, and Micro-C, have been developed to investigate these properties. Utilizing these data, scientists have developed a variety of loop prediction techniques that have greatly improved their methods for characterizing loop prediction and related aspects.

RESULTS

In this study, we categorized 22 loop calling methods and conducted a comprehensive study of 11 of them. Additionally, we have provided detailed insights into the methodologies underlying these algorithms for loop detection, categorizing them into five distinct groups based on their fundamental approaches. Furthermore, we have included critical information such as resolution, input and output formats, and parameters. For this analysis, we utilized the GM12878 Hi-C datasets at 5 KB, 10 KB, 100 KB and 250 KB resolutions. Our evaluation criteria encompassed various factors, including memory usages, running time, sequencing depth, and recovery of protein-specific sites such as CTCF, H3K27ac, and RNAPII.

CONCLUSION

This analysis offers insights into the loop detection processes of each method, along with the strengths and weaknesses of each, enabling readers to effectively choose suitable methods for their datasets. We evaluate the capabilities of these tools and introduce a novel Biological, Consistency, and Computational robustness score ( B C C score ) to measure their overall robustness ensuring a comprehensive evaluation of their performance.

DANCE: a deep learning library and benchmark platform for single-cell analysis

DANCE is the first standard, generic, and extensible benchmark platform for accessing and evaluating computational methods across the spectrum of benchmark datasets for numerous single-cell analysis tasks. Currently, DANCE supports 3 modules and 8 popular tasks with 32 state-of-art methods on 21 benchmark datasets. People can easily reproduce the results of supported algorithms across major benchmark datasets via minimal efforts, such as using only one command line. In addition, DANCE provides an ecosystem of deep learning architectures and tools for researchers to facilitate their own model development. DANCE is an open-source Python package that welcomes all kinds of contributions.

Patient characteristics correlate with diagnostic performance of photodynamic diagnostic assisted transurethral resection of bladder tumors: A retrospective, single-center study

BACKGROUND

Identification of patient subclasses that correlate with the diagnostic performance of photodynamic diagnostic (PDD)-assisted transurethral resection of bladder tumors (TURBT) may improve outcomes.

METHODS

Data were extracted from patients that underwent PDD-assisted TURBT at the University of Tsukuba Hospital between 2018 and 2023. Sensitivity and specificity were evaluated based on PDD findings (excluding WL findings) and pathology results. Cluster analysis using uniform manifold approximation and projection and k-means methods was performed, focusing on patients with malignant lesions.

RESULTS

A total of 267 patients and 2082 specimens were extracted. Sensitivity was lowest with regard to BCG treatment (53.7 %), followed by flat lesions (57.2 %), urine cytology class ≥ III (62.9 %), and recurrent tumors (64.5 %). In the cluster analysis of 231 patients with malignant lesions, two showed lower sensitivity: Cluster 3 (62.4 %), consisting of patients with recurrent tumors and post-BCG treatment, and Cluster 4 (55.7 %), consisting of patients with primary tumors and urine cytology class ≥ III. Clusters 1 and 2, consisting of patients without BCG treatment and patients with lower urine cytology classes, exhibited higher sensitivities (94.4 % and 87.7 %). Among all clusters, Cluster 4 had the highest proportion of specimens which were negative for both PDD and white light (WL) findings but actually had malignant lesions (20.8 %).

CONCLUSIONS

PDD-assisted TURBT sensitivity was lower in subclasses after BCG treatment or with cytology class III or higher. Random biopsy for PDD/WL double-negative lesions may improve diagnostic accuracy in these subclasses.

K-Means Clustering Identifies Diverse Clinical Phenotypes in COVID-19 Patients: Implications for Mortality Risks and Remdesivir Impact

INTRODUCTION

The impact of remdesivir on mortality in patients with COVID-19 is still controversial. We aimed to identify clinical phenotype clusters of COVID-19 hospitalized patients with highest benefit from remdesivir use and validate these findings in an external cohort.

METHODS

We included consecutive patients hospitalized between February 2020 and February 2021 for COVID-19. The derivation cohort comprised subjects admitted to Hospital Clinic of Barcelona. The validation cohort included patients from Hospital Universitari Mutua de Terrassa (Terrassa) and Hospital Universitari La Fe (Valencia), all tertiary centers in Spain. We employed K-means clustering to group patients according to reverse transcription polymerase chain reaction (rRT-PCR) cycle threshold (Ct) values and lymphocyte counts at diagnosis, and pre-test symptom duration. The impact of remdesivir on 60-day mortality in each cluster was assessed.

RESULTS

A total of 1160 patients (median age 66, interquartile range (IQR) 55-78) were included. We identified five clusters, with mortality rates ranging from 0 to 36.7%. Highest mortality rate was observed in the cluster including patients with shorter pre-test symptom duration, lower lymphocyte counts, and lower Ct values at diagnosis. The absence of remdesivir administration was associated with worse outcome in the high-mortality cluster (10.5% vs. 36.7%; p < 0.001), comprising subjects with higher viral loads. These results were validated in an external multicenter cohort of 981 patients.

CONCLUSIONS

Patients with COVID-19 exhibit varying mortality rates across different clinical phenotypes. K-means clustering aids in identifying patients who derive the greatest mortality benefit from remdesivir use.

SMART (Splitting-Merging Assisted Reliable) Independent Component Analysis for Extracting Accurate Brain Functional Networks

Functional networks (FNs) hold significant promise in understanding brain function. Independent component analysis (ICA) has been applied in estimating FNs from functional magnetic resonance imaging (fMRI). However, determining an optimal model order for ICA remains challenging, leading to criticism about the reliability of FN estimation. Here, we propose a SMART (splitting-merging assisted reliable) ICA method that automatically extracts reliable FNs by clustering independent components (ICs) obtained from multi-model-order ICA using a simplified graph while providing linkages among FNs deduced from different-model orders. We extend SMART ICA to multi-subject fMRI analysis, validating its effectiveness using simulated and real fMRI data. Based on simulated data, the method accurately estimates both group-common and group-unique components and demonstrates robustness to parameters. Using two age-matched cohorts of resting fMRI data comprising 1,950 healthy subjects, the resulting reliable group-level FNs are greatly similar between the two cohorts, and interestingly the subject-specific FNs show progressive changes while age increases. Furthermore, both small-scale and large-scale brain FN templates are provided as benchmarks for future studies. Taken together, SMART ICA can automatically obtain reliable FNs in analyzing multi-subject fMRI data, while also providing linkages between different FNs.

Deep learning of movement behavior profiles and their association with markers of cardiometabolic health

BACKGROUND

Traditionally, existing studies assessing the health associations of accelerometer-measured movement behaviors have been performed with few averaged values, mainly representing the duration of physical activities and sedentary behaviors. Such averaged values cannot naturally capture the complex interplay between the duration, timing, and patterns of accumulation of movement behaviors, that altogether may be codependently related to health outcomes in adults. In this study, we introduce a novel approach to visually represent recorded movement behaviors as images using original accelerometer outputs. Subsequently, we utilize these images for cluster analysis employing deep convolutional autoencoders.

METHODS

Our method involves converting minute-by-minute accelerometer outputs (activity counts) into a 2D image format, capturing the entire spectrum of movement behaviors performed by each participant. By utilizing convolutional autoencoders, we enable the learning of these image-based representations. Subsequently, we apply the K-means algorithm to cluster these learned representations. We used data from 1812 adult (20-65 years) participants in the National Health and Nutrition Examination Survey (NHANES, 2003-2006 cycles) study who worn a hip-worn accelerometer for 7 seven consecutive days and provided valid accelerometer data.

RESULTS

Deep convolutional autoencoders were able to learn the image representation, encompassing the entire spectrum of movement behaviors. The images were encoded into 32 latent variables, and cluster analysis based on these learned representations for the movement behavior images resulted in the identification of four distinct movement behavior profiles characterized by varying levels, timing, and patterns of accumulation of movement behaviors. After adjusting for potential covariates, the movement behavior profile characterized as "Early-morning movers" and the profile characterized as "Highest activity" both had lower levels of insulin (P < 0.01 for both), triglycerides (P < 0.05 and P < 0.01, respectively), HOMA-IR (P < 0.01 for both), and plasma glucose (P < 0.05 and P < 0.1, respectively) compared to the "Lowest activity" profile. No significant differences were observed for the "Least sedentary movers" profile compared to the "Lowest activity" profile.

CONCLUSIONS

Deep learning of movement behavior profiles revealed that, in addition to duration and patterns of movement behaviors, the timing of physical activity may also be crucial for gaining additional health benefits.

FlowSOM clustering - A novel pattern recognition approach for water research: Application to a hyper-arid coastal aquifer system

Monitoring and understanding of water resources have become essential in designing effective and sustainable management strategies to overcome the growing water quality challenges. In this context, the utilization of unsupervised learning techniques for evaluating environmental tracers has facilitated the exploration of sources and dynamics of groundwater systems through pattern recognition. However, conventional techniques may overlook spatial and temporal non-linearities present in water research data. This paper introduces the adaptation of FlowSOM, a pioneering approach that combines self-organizing maps (SOM) and minimal spanning trees (MST), with the fast-greedy network clustering algorithm to unravel intricate relationships within multivariate water quality datasets. By capturing connections within the data, this ensemble tool enhances clustering and pattern recognition. Applied to the complex water quality context of the hyper-arid transboundary Caplina/Concordia coastal aquifer system (Peru/Chile), the FlowSOM network and clustering yielded compelling results in pattern recognition of the aquifer salinization. Analyzing 143 groundwater samples across eight variables, including major ions, the approach supports the identification of distinct clusters and connections between them. Three primary sources of salinization were identified: river percolation, slow lateral aquitard recharge, and seawater intrusion. The analysis demonstrated the superiority of FlowSOM clustering over traditional techniques in the case study, producing clusters that align more closely with the actual hydrogeochemical pattern. The outcomes broaden the utilization of multivariate analysis in water research, presenting a comprehensive approach to support the understanding of groundwater systems.

Comparison of the clinical characteristics in parents and their children in a series of family clustered Mycoplasma pneumoniae infections

BACKGROUND

Mycoplasma pneumoniae infections have increased in China recently, causing some evidence of familial clustering. The purpose of this study was to compare the clinical features of parents and children in cases of familial clustering of Mycoplasma pneumoniae infection.

METHODS

A retrospective analysis was performed on the cases of familial clustering of Mycoplasma pneumoniae infection, and the clinical characteristics of parents and children were compared.

RESULTS

We identified 63 families, of these, 57 (65.5%) adults and 65 (94.2%) children required hospitalization. Fifty-seven adults (mean age 35.1 ± 4.6 years, 80.7% female) and 55 children (mean age 6.3 ± 3.9 years, 54.5% female) were included in the analysis. The incidence of mycoplasma infection in adults had increased gradually over the past year, while the rate in children had spiked sharply since June 2023. The clinical symptoms were similar in the two groups, mainly fever and cough. The peak temperature of children was higher than that of adults (39.1 ± 0.7℃ vs 38.6 ± 0.7℃, p = 0.004). Elevated lactate dehydrogenase was more common in children than in adults (77.8% vs 11.3%, p < 0.001). Bronchial pneumonia and bilateral involvement were more common in children, while adults usually had unilateral involvement. Three (60%) adults and 21 (52.5%) children were macrolide-resistant Mycoplasma pneumoniae infected. Children were more likely to be co-infected (65.5% vs 22.8%, p < .001). Macrolides were used in most children and quinolones were used in most adults. Ten (18.2%) children were diagnosed with severe Mycoplasma pneumoniae pneumonia, whereas all adults had mild disease. Children had a significantly longer fever duration than adults ((5.6 ± 2.2) days vs (4.1 ± 2.2) days, p = 0.002). No patient required mechanical ventilation or died.

CONCLUSIONS

Mycoplasma pneumoniae infection shows a familial clustering epidemic trend at the turn of summer and autumn, with different clinical characteristics between parents and children.

BSXplorer: analytical framework for exploratory analysis of BS-seq data

BACKGROUND

Bisulfite sequencing detects and quantifies DNA methylation patterns, contributing to our understanding of gene expression regulation, genome stability maintenance, conservation of epigenetic mechanisms across divergent taxa, epigenetic inheritance and, eventually, phenotypic variation. Graphical representation of methylation data is crucial in exploring epigenetic regulation on a genome-wide scale in both plants and animals. This is especially relevant for non-model organisms with poorly annotated genomes and/or organisms where genome sequences are not yet assembled on chromosome level. Despite being a technology of choice to profile DNA methylation for many years now there are surprisingly few lightweight and robust standalone tools available for efficient graphical analysis of data in non-model systems. This significantly limits evolutionary studies and agrigenomics research. BSXplorer is a tool specifically developed to fill this gap and assist researchers in explorative data analysis and in visualising and interpreting bisulfite sequencing data more easily.

RESULTS

BSXplorer provides in-depth graphical analysis of sequencing data encompassing (a) profiling of methylation levels in metagenes or in user-defined regions using line plots and heatmaps, generation of summary statistics charts, (b) enabling comparative analyses of methylation patterns across experimental samples, methylation contexts and species, and (c) identification of modules sharing similar methylation signatures at functional genomic elements. The tool processes methylation data quickly and offers API and CLI capabilities, along with the ability to create high-quality figures suitable for publication.

CONCLUSIONS

BSXplorer facilitates efficient methylation data mining, contrasting and visualization, making it an easy-to-use package that is highly useful for epigenetic research.

State-transition dynamics of resting-state functional magnetic resonance imaging data: model comparison and test-to-retest analysis

Electroencephalogram (EEG) microstate analysis entails finding dynamics of quasi-stable and generally recurrent discrete states in multichannel EEG time series data and relating properties of the estimated state-transition dynamics to observables such as cognition and behavior. While microstate analysis has been widely employed to analyze EEG data, its use remains less prevalent in functional magnetic resonance imaging (fMRI) data, largely due to the slower timescale of such data. In the present study, we extend various data clustering methods used in EEG microstate analysis to resting-state fMRI data from healthy humans to extract their state-transition dynamics. We show that the quality of clustering is on par with that for various microstate analyses of EEG data. We then develop a method for examining test-retest reliability of the discrete-state transition dynamics between fMRI sessions and show that the within-participant test-retest reliability is higher than between-participant test-retest reliability for different indices of state-transition dynamics, different networks, and different data sets. This result suggests that state-transition dynamics analysis of fMRI data could discriminate between different individuals and is a promising tool for performing fingerprinting analysis of individuals.

CDSKNNXMBD: a novel clustering framework for large-scale single-cell data based on a stable graph structure

BACKGROUND

Accurate and efficient cell grouping is essential for analyzing single-cell transcriptome sequencing (scRNA-seq) data. However, the existing clustering techniques often struggle to provide timely and accurate cell type groupings when dealing with datasets with large-scale or imbalanced cell types. Therefore, there is a need for improved methods that can handle the increasing size of scRNA-seq datasets while maintaining high accuracy and efficiency.

METHODS

We propose CDSKNNXMBD (Community Detection based on a Stable K-Nearest Neighbor Graph Structure), a novel single-cell clustering framework integrating partition clustering algorithm and community detection algorithm, which achieves accurate and fast cell type grouping by finding a stable graph structure.

RESULTS

We evaluated the effectiveness of our approach by analyzing 15 tissues from the human fetal atlas. Compared to existing methods, CDSKNN effectively counteracts the high imbalance in single-cell data, enabling effective clustering. Furthermore, we conducted comparisons across multiple single-cell datasets from different studies and sequencing techniques. CDSKNN is of high applicability and robustness, and capable of balancing the complexities of across diverse types of data. Most importantly, CDSKNN exhibits higher operational efficiency on datasets at the million-cell scale, requiring an average of only 6.33 min for clustering 1.46 million single cells, saving 33.3% to 99% of running time compared to those of existing methods.

CONCLUSIONS

The CDSKNN is a flexible, resilient, and promising clustering tool that is particularly suitable for clustering imbalanced data and demonstrates high efficiency on large-scale scRNA-seq datasets.

Absorption function loss due to the history of previous ankle sprain explored by unsupervised machine learning

BACKGROUND

Ankle sprains are common and cause persistent ankle function reduction. To biomechanically evaluate the ankle function after ankle sprains, the ground reaction force (GRF) measurement during the single-legged landing had been used. However, previous studies focused on discrete features of vertical GRF (vGRF), which largely ignored vGRF waveform features that could better identify the ankle function.

PURPOSE

To identify how the history of ankle sprain affect the vGRF waveform during the single-legged landing with unsupervised machine learning considering the time-series information of vGRF.

METHODS

Eighty-seven currently healthy basketball athletes (12 athletes without ankle sprain, 49 athletes with bilateral, and 26 athletes with unilateral ankle sprain more than 6 months before the test day) performed single-legged landings from a 20 centimeters (cm) high box onto the force platform. Totally 518 trials vGRF data were collected from 87 athletes of 174 ankles, including 259 ankle sprain trials (from previous sprain ankles) and 259 non-ankle sprain trials (from without sprain ankles). The first 100 milliseconds (ms) vGRF waveforms after landing were extracted. Principal component analysis (PCA) was applied to the vGRF data, selecting 8 principal components (PCs) representing 96% of the information. Based on these 8 PCs, k-means method (k = 3) clustered the 518 trials into three clusters. Chi-square test assessed significant differences (p < 0.01) in the distribution of ankle sprain and non-ankle sprain trials among clusters.

FINDINGS

The ankle sprain trials accounted for a significantly larger percentage (63.9%) in Cluster 3, which exhibited rapidly increased impulse vGRF waveforms with larger peaks in a short time.

SIGNIFICANCE

PCA and k-means method for vGRF waveforms during single-legged landing identified that the history of previous ankle sprains caused a loss of ankle absorption ability lasting at least 6 months from an ankle sprain.

Subpopulations of children with multiple chronic health outcomes in relation to chemical exposures in the ECHO-PATHWAYS consortium

A multimorbidity-focused approach may reflect common etiologic mechanisms and lead to better targeting of etiologic agents for broadly impactful public health interventions. Our aim was to identify clusters of chronic obesity-related, neurodevelopmental, and respiratory outcomes in children, and to examine associations between cluster membership and widely prevalent chemical exposures to demonstrate our epidemiologic approach. Early to middle childhood outcome data collected 2011-2022 for 1092 children were harmonized across the ECHO-PATHWAYS consortium of 3 prospective pregnancy cohorts in six U.S. cities. 15 outcomes included age 4-9 BMI, cognitive and behavioral assessment scores, speech problems, and learning disabilities, asthma, wheeze, and rhinitis. To form generalizable clusters across study sites, we performed k-means clustering on scaled residuals of each variable regressed on study site. Outcomes and demographic variables were summarized between resulting clusters. Logistic weighted quantile sum regressions with permutation test p-values associated odds of cluster membership with a mixture of 15 prenatal urinary phthalate metabolites in full-sample and sex-stratified models. Three clusters emerged, including a healthier Cluster 1 (n = 734) with low morbidity across outcomes; Cluster 2 (n = 192) with low IQ and higher levels of all outcomes, especially 0.4-1.8-standard deviation higher mean neurobehavioral outcomes; and Cluster 3 (n = 179) with the highest asthma (92 %), wheeze (53 %), and rhinitis (57 %) frequencies. We observed a significant positive, male-specific stratified association (odds ratio = 1.6; p = 0.01) between a phthalate mixture with high weights for MEP and MHPP and odds of membership in Cluster 3 versus Cluster 1. These results identified subpopulations of children with co-occurring elevated levels of BMI, neurodevelopmental, and respiratory outcomes that may reflect shared etiologic pathways. The observed association between phthalates and respiratory outcome cluster membership could inform policy efforts towards children with respiratory disease. Similar cluster-based epidemiology may identify environmental factors that impact multi-outcome prevalence and efficiently direct public policy efforts.

Clustering the cortical laminae: in vivo parcellation

The laminar microstructure of the cerebral cortex has distinct anatomical characteristics of the development, function, connectivity, and even various pathologies of the brain. In recent years, multiple neuroimaging studies have utilized magnetic resonance imaging (MRI) relaxometry to visualize and explore this intricate microstructure, successfully delineating the cortical laminar components. Despite this progress, T1 is still primarily considered a direct measure of myeloarchitecture (myelin content), rather than a probe of tissue cytoarchitecture (cellular composition). This study aims to offer a robust, whole-brain validation of T1 imaging as a practical and effective tool for exploring the laminar composition of the cortex. To do so, we cluster complex microstructural cortical datasets of both human (N = 30) and macaque (N = 1) brains using an adaptation of an algorithm for clustering cell omics profiles. The resulting cluster patterns are then compared to established atlases of cytoarchitectonic features, exhibiting significant correspondence in both species. Lastly, we demonstrate the expanded applicability of T1 imaging by exploring some of the cytoarchitectonic features behind various unique skillsets, such as musicality and athleticism.

SARS-CoV-2 NSP14 governs mutational instability and assists in making new SARS-CoV-2 variants

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the rapidly evolving RNA virus behind the COVID-19 pandemic, has spawned numerous variants since its 2019 emergence. The multifunctional Nonstructural protein 14 (NSP14) enzyme, possessing exonuclease and messenger RNA (mRNA) capping capabilities, serves as a key player. Notably, single and co-occurring mutations within NSP14 significantly influence replication fidelity and drive variant diversification. This study comprehensively examines 120 co-mutations, 68 unique mutations, and 160 conserved residues across NSP14 homologs, shedding light on their implications for phylogenetic patterns, pathogenicity, and residue interactions. Quantitative physicochemical analysis categorizes 3953 NSP14 variants into three clusters, revealing genetic diversity. This research underscoresthe dynamic nature of SARS-CoV-2 evolution, primarily governed by NSP14 mutations. Understanding these genetic dynamics provides valuable insights for therapeutic and vaccine development.

Integrative analysis of RNA expression data unveils distinct cancer types through machine learning techniques

Cancer is a highly complex and heterogeneous disease. Traditional methods of cancer classification based on histopathology have limitations in guiding personalized prognosis and therapy. Gene expression profiling provides a powerful approach to unraveling molecular intricacies and better-stratifying cancer subtypes. In this study, we performed an integrative analysis of RNA sequencing data from five cancer types - BRCA, KIRC, COAD, LUAD, and PRAD. A machine learning workflow consisting of dataset identification, normalization, feature selection, dimensionality reduction, clustering, and classification was implemented. The k-means algorithm was applied to categorize samples into distinct clusters based solely on gene expression patterns. Five unique clusters emerged from the unsupervised machine learning based analysis, significantly correlating with the known cancer types. BRCA aligned predominantly with one cluster, while COAD spanned three clusters. KIRC was represented within two main clusters. LUAD is associated strongly with a single cluster and PRAD with another cluster. This demonstrates the ability of machine learning approaches to unravel complex signatures within transcriptomic profiles that can delineate cancer subtypes. The proposed study highlights the potential of integrative analytics to derive meaningful biological insights from high-dimensional omics datasets. Molecular subtyping through machine learning clustering enhances our understanding of the intrinsic heterogeneities and pathways dysregulated in different cancers. Overall, this study exemplifies a powerful computational framework to classify gene expressions of patients having different types of cancers and guide personalized therapeutic decisions. Finally, Wide Neural Network demonstrates a significantly higher accuracy, achieving 99.834% on the validation set and an even more impressive 99.995% on the test set.

GAUDIE: Development, validation, and exploration of a naturalistic German AUDItory Emotional database

Since thoroughly validated naturalistic affective German speech stimulus databases are rare, we present here a novel validated database of speech sequences assembled with the purpose of emotion induction. The database comprises 37 audio speech sequences with a total duration of 92 minutes for the induction of positive, neutral, and negative emotion: comedian shows intending to elicit humorous and amusing feelings, weather forecasts, and arguments between couples and relatives from movies or television series. Multiple continuous and discrete ratings are used to validate the database to capture the time course and variabilities of valence and arousal. We analyse and quantify how well the audio sequences fulfil quality criteria of differentiation, salience/strength, and generalizability across participants. Hence, we provide a validated speech database of naturalistic scenarios suitable to investigate emotion processing and its time course with German-speaking participants. Information on using the stimulus database for research purposes can be found at the OSF project repository GAUDIE: https://osf.io/xyr6j/ .

DEPICTER: Deep representation clustering for histology annotation

Automatic segmentation of histopathology whole-slide images (WSI) usually involves supervised training of deep learning models with pixel-level labels to classify each pixel of the WSI into tissue regions such as benign or cancerous. However, fully supervised segmentation requires large-scale data manually annotated by experts, which can be expensive and time-consuming to obtain. Non-fully supervised methods, ranging from semi-supervised to unsupervised, have been proposed to address this issue and have been successful in WSI segmentation tasks. But these methods have mainly been focused on technical advancements in algorithmic performance rather than on the development of practical tools that could be used by pathologists or researchers in real-world scenarios. In contrast, we present DEPICTER (Deep rEPresentatIon ClusTERing), an interactive segmentation tool for histopathology annotation that produces a patch-wise dense segmentation map at WSI level. The interactive nature of DEPICTER leverages self- and semi-supervised learning approaches to allow the user to participate in the segmentation producing reliable results while reducing the workload. DEPICTER consists of three steps: first, a pretrained model is used to compute embeddings from image patches. Next, the user selects a number of benign and cancerous patches from the multi-resolution image. Finally, guided by the deep representations, label propagation is achieved using our novel seeded iterative clustering method or by directly interacting with the embedding space via feature space gating. We report both real-time interaction results with three pathologists and evaluate the performance on three public cancer classification dataset benchmarks through simulations. The code and demos of DEPICTER are publicly available at https://github.com/eduardchelebian/depicter.

Feature selection for effective prediction of SARS-COV-2 using machine learning

BACKGROUND

With rise in variants of SARS-CoV-2, it is necessary to classify the emerging SARS-CoV-2 for early detection and thereby reduce human transmission. Genomic and proteomic information have less frequently been used for classifying in a machine learning (ML) approach for detection of SARS-CoV-2.

OBJECTIVE

With this aim we used nucleoprotein and viral proteomic evolutionary information of SARS-CoV-2 along with the charge and basicity distribution of amino acids from various strains of SARS-CoV-2 to generate a disease severity model based on ML.

METHODS

All sequence and clinical data were obtained from GISAID. Proteomic level calculations were added to comprise the dataset. The training set was used for feature selection. Select K- Best feature selection method was employed which was cross validated with testing set and performance evaluated. Delong's test was also done. We also employed BIRCH clustering on SARS-CoV-2 for clustering the strains.

RESULTS

Out of six ML models four were successful in training and testing. Extra Trees algorithm generated a micro-averaged F1-score of 74.2% and a weighted averaged area under the receiver operating characteristic curve (AUC-ROC) score of 73.7% with multi-class option. The feature selection set to 5, enhanced the ROC AUC from 73.7 to 76.4%. Accuracy of the selected model of 86.9% was achieved.

CONCLUSION

The unique features identified in the ML approach was able to classify disease severity into classes and had potential for predicting risk in newer variants.

On the Reliability of the EEG Microstate Approach

EEG microstates represent functional brain networks observable in resting EEG recordings that remain stable for 40-120ms before rapidly switching into another network. It is assumed that microstate characteristics (i.e., durations, occurrences, percentage coverage, and transitions) may serve as neural markers of mental and neurological disorders and psychosocial traits. However, robust data on their retest-reliability are needed to provide the basis for this assumption. Furthermore, researchers currently use different methodological approaches that need to be compared regarding their consistency and suitability to produce reliable results. Based on an extensive dataset largely representative of western societies (2 days with two resting EEG measures each; day one: n = 583; day two: n = 542) we found good to excellent short-term retest-reliability of microstate durations, occurrences, and coverages (average ICCs = 0.874-0.920). There was good overall long-term retest-reliability of these microstate characteristics (average ICCs = 0.671-0.852), even when the interval between measures was longer than half a year, supporting the longstanding notion that microstate durations, occurrences, and coverages represent stable neural traits. Findings were robust across different EEG systems (64 vs. 30 electrodes), recording lengths (3 vs. 2 min), and cognitive states (before vs. after experiment). However, we found poor retest-reliability of transitions. There was good to excellent consistency of microstate characteristics across clustering procedures (except for transitions), and both procedures produced reliable results. Grand-mean fitting yielded more reliable results compared to individual fitting. Overall, these findings provide robust evidence for the reliability of the microstate approach.

Combining Global-Constrained Concept Factorization and a Regularized Gaussian Graphical Model for Clustering Single-Cell RNA-seq Data

Single-cell RNA sequencing technology is one of the most cost-effective ways to uncover transcriptomic heterogeneity. With the rapid rise of this technology, enormous amounts of scRNA-seq data have been produced. Due to the high dimensionality, noise, sparsity and missing features of the available scRNA-seq data, accurately clustering the scRNA-seq data for downstream analysis is a significant challenge. Many computational methods have been designed to address this issue; nevertheless, the efficacy of the available methods is still inadequate. In addition, most similarity-based methods require a number of clusters as input, which is difficult to achieve in real applications. In this study, we developed a novel computational method for clustering scRNA-seq data by considering both global and local information, named GCFG. This method characterizes the global properties of data by applying concept factorization, and the regularized Gaussian graphical model is utilized to evaluate the local embedding relationship of data. To learn the cell-cell similarity matrix, we integrated the two components, and an iterative optimization algorithm was developed. The categorization of single cells is obtained by applying Louvain, a modularity-based community discovery algorithm, to the similarity matrix. The behavior of the GCFG approach is assessed on 14 real scRNA-seq datasets in terms of ACC and ARI, and comparison results with 17 other competitive methods suggest that GCFG is effective and robust.

Finding neural correlates of depersonalisation/derealisation disorder via explainable CNN-based analysis guided by clinical assessment scores

Mental health disorders are typically diagnosed based on subjective reports (e.g., through questionnaires) followed by clinical interviews to evaluate the self-reported symptoms. Therefore, considering the interconnected nature of psychiatric disorders, their accurate diagnosis is a real challenge without indicators of underlying physiological dysfunction. Depersonalisation/derealisation disorder (DPD) is an example of dissociative disorder affecting 1-2 % of the population. DPD is characterised mainly by persistent disembodiment, detachment from surroundings, and feelings of emotional numbness, which can significantly impact patients' quality of life. The underlying neural correlates of DPD have been investigated for years to understand and help with a more accurate and in-time diagnosis of the disorder. However, in terms of EEG studies, which hold great importance due to their convenient and inexpensive nature, the literature has often been based on hypotheses proposed by experts in the field, which require prior knowledge of the disorder. In addition, participants' labelling in research experiments is often derived from the outcome of the Cambridge Depersonalisation Scale (CDS), a subjective assessment to quantify the level of depersonalisation/derealisation, the threshold and reliability of which might be challenged. As a result, we aimed to propose a novel end-to-end EEG processing pipeline based on deep neural networks for DPD biomarker discovery, which requires no prior handcrafted labelled data. Alternatively, it can assimilate knowledge from clinical outcomes like CDS as well as data-driven patterns that differentiate individual brain responses. In addition, the structure of the proposed model targets the uncertainty in CDS scores by using them as prior information only to guide the unsupervised learning task in a multi-task learning scenario. A comprehensive evaluation has been done to confirm the significance of the proposed deep structure, including new ways of network visualisation to investigate spectral, spatial, and temporal information derived in the learning process. We argued that the proposed EEG analytics could also be applied to investigate other psychological and mental disorders currently indicated on the basis of clinical assessment scores. The code to reproduce the results presented in this paper is openly accessible at https://github.com/AbbasSalami/DPD_Analysis.

Computational Evaluation of Bioactive Compounds from Dysphania ambrosioides Leaves

Dysphania ambrosioides has been reported to have many medicinal properties, due to its possession of a multitude of biologically active molecules contained in its leaves. However, very few studies have been reported to evaluate their pharmacological properties. Consequently, in the present study, many computational tools have been performed to predict drug similarity and ADMET properties. Besides, the inhibitory potential of D.ambrosioides major compounds against Bacterial, Fungal and cardiovascular main receptor targets has been investigated. This study suggests that Carvone oxide, 5-Isopropenyl-2-Methylenecyclohexanol, and Caryophyllene oxide were the most active molecules belonging to D. ambrosioides Leaves, possessing drug-likeness with satisfactory bioactivity scores, having good pharmacokinetic values. Metabolism and toxicities were further studied using FAME3, GLORY, and pred-hERG. Slight cardiotoxicity and cytotoxicity were predicted, respectively, for Caryophyllene oxide and Carvone oxide, 5-Isopropenyl-2-Methylenecyclohexanol. Good inhibitory activities of the three compounds against Bacterial, Fungal, and Cardiovascular receptor targets. Hence, this is a comprehensive in silico approach to evaluate D.ambrosioides Leaves main phytocompounds in the background of its potential in future drug development.

Association of medication clusters and subsequent labor market marginalization in refugee and Swedish-born young adults with common mental disorders in Sweden

Little is known about the association between common mental disorders (CMD) and labor market integration among refugee and Swedish-born young adults. Socially disadvantaged patients such as refugees are more likely to discontinue their medication use prematurely. This study aimed to identify clusters of individuals with similar psychotropic medication patterns; and examine the relationship between cluster membership with labor market marginalization (LMM) in refugee and Swedish-born young adults with CMD. The study uses a longitudinal matched cohort aged 18-24 years with CMD diagnoses from Swedish registers covering 2006-2016. Dispensed psychotropic medications (antidepressants, antipsychotics, anxiolytics, sedative-hypnotics, mood stabilizers) were collected one year before and after CMD diagnosis. Clusters of patients with similar time courses of prescribed dosages were algorithmically identified. The association of cluster membership with subsequent LMM, (long-term sickness absence, SA, disability pension, DP, or long-term unemployment, UE) was assessed using Cox regression. Among 12,472 young adults with CMD, there were 13.9% with SA, 11.9% with DP, and 13.0% with UE during a mean follow-up of 4.1 years (SD 2.3 years). Six clusters of individuals were identified. A cluster with a sustained increase in all medication types yielded the highest hazard ratio (HR [95% CI]) 1.69 [1.34, 2.13] for SA and 2.63 [2.05, 3.38] for DP. The highest HRs of UE give a cluster with a concentrated peak in antidepressants at CMD diagnosis (HR 1.61[1.18, 2.18]). Refugees and Swedish-born showed similar associations between clusters and LMM. To prevent LMM, targeted support and early assessment of CMD treatment are needed for individuals with a sustained increase in psychotropic medication after CMD diagnosis and for refugees in high-risk clusters for UE characterized by a rapid lowering of treatment dosages, which could be an indicator for premature medication discontinuation.

Attention guided multi-scale cluster refinement with extended field of view for amodal nuclei segmentation

Nuclei segmentation plays a crucial role in disease understanding and diagnosis. In whole slide images, cell nuclei often appear overlapping and densely packed with ambiguous boundaries due to the underlying 3D structure of histopathology samples. Instance segmentation via deep neural networks with object clustering is able to detect individual segments in crowded nuclei but suffers from a limited field of view, and does not support amodal segmentation. In this work, we introduce a dense feature pyramid network with a feature mixing module to increase the field of view of the segmentation model while keeping pixel-level details. We also improve the model output quality by adding a multi-scale self-attention guided refinement module that sequentially adjusts predictions as resolution increases. Finally, we enable clusters to share pixels by separating the instance clustering objective function from other pixel-related tasks, and introduce supervision to occluded areas to guide the learning process. For evaluation of amodal nuclear segmentation, we also update prior metrics used in common modal segmentation to allow the evaluation of overlapping masks and mitigate over-penalization issues via a novel unique matching algorithm. Our experiments demonstrate consistent performance across multiple datasets with significantly improved segmentation quality.

Clustering Analysis of Time Series of Affect in Dyadic Interactions

An important goal when analyzing multivariate time series is the identification of heterogeneity, both within and across individuals over time. This heterogeneity can represent different ways in which psychological processes manifest, either between people or within a person across time. In many instances, those differences can have systematic patterns that can be related to future outcomes. In close relationships, for example, the daily exchange of affect between two individuals in a couple can contain a particular structure that is different across people and can result in varying levels of relationship satisfaction. In this paper we use Louvain, a clustering method, as a tool to characterize heterogeneity in multivariate time series data. Using affect measures from dyadic interactions, we first determine that Louvain is adept at detecting homogeneous patterns that are distinct from one another. Additionally, these homogeneous points are linked, at some level, by time. Thus, we find that clustering via Louvain is useful to find time periods of stable, reoccurring patterns. However, using measures founded on information theory reveals that there is some level of information loss that is inevitable when clustering on levels of variable expression. Finally, we evaluate the predictive validity of the clustering method by examining the relation between the identified clusters of affect and measures outside the time series (i.e., relationship satisfaction and breakup taken one and two years later).

Classification of thermal environment control indicators according to the thermal sensitivity of office occupants

The control that have the greatest influence on comfortable in the office occupants are the heating, ventilation, and air conditioning (HVAC) system operation and the thermal environment. However, comfortable HVAC operation is difficult in the office space characterized by a recommended standard thermal environment or a centralized HVAC system. To consider the occupant's thermal comfort to the greatest possible extent, must establish a method to quantify the variables related to the occupant's thermal comfort. This study aims to group occupants in Thermal sensation vote (TSV) clusters and perform sensitivity analysis (SA) on the relationship between thermal environmental factors in an office building and each cluster's TSV to establish the typology of the control indicators for each cluster. A total of 10 field experiments were conducted in the same office. This field study was carried out 2022. The indoor thermal environmental parameters, the subjective evaluation of the thermal comfort of the resident and the operation pattern of the heating system were monitored at the same time. A total of 4,200 datasets related to indoor thermal environmental parameters and a total of 1,680 datasets related to occupants' thermal comfort were collected and analyzed. The results of this study show that people have different levels of adaptability and sensitivity to a given thermal environment. This study founded distinguishable similarities in their thermal sensation traits and grouped similar TSV values into five clusters that responded differently to the same thermal environment. Each cluster showed different TSV and Thermal comfort vote (TCV) patterns, which allowed us to classify the groups that had sensitive responses to the thermal environment and those that did not. This study was determined different control indicators and guidelines for the divided groups according to thermal sensitivity.

Research on evaluation of university education informatization level based on clustering technique

Today, the utilization of Information Technology tools is considered an inevitable path in the education system. In this regard, assessing the effective integration of Information Technology tools in the educational system holds significant importance. This process can be automated using artificial intelligence techniques, which are the subject of the current study. In this research, initially, a set of 14 indicators related to levels of Education Informatization (EI) in higher education is introduced. Subsequently, a clustering-based strategy is proposed to rank the indicators and determine an optimal subset of these features. Based on this framework, it is demonstrated that using 11 indicators related to educational behaviors can achieve the highest accuracy in evaluating EI levels. The proposed approach employs a group of Support Vector Machines (SVMs) for EI level assessment, where classifier hyperparameters are tuned using reinforcement learning strategy. The performance of the proposed method is evaluated on real-world data and compared with previous works. The results indicate that the proposed method can assess EI levels in universities with an average accuracy of 93.64 %, outperforming compared methods by at least 4.09 %.

Deep learning and predictive modelling for generating normalised muscle function parameters from signal images of mandibular electromyography

Challenges arise in accessing archived signal outputs due to proprietary software limitations. There is a notable lack of exploration in open-source mandibular EMG signal conversion for continuous access and analysis, hindering tasks such as pattern recognition and predictive modelling for temporomandibular joint complex function. To Develop a workflow to extract normalised signal parameters from images of mandibular muscle EMG and identify optimal clustering methods for quantifying signal intensity and activity durations. A workflow utilising OpenCV, variational encoders and Neurokit2 generated and augmented 866 unique EMG signals from jaw movement exercises. k-means, GMM and DBSCAN were employed for normalisation and cluster-centric signal processing. The workflow was validated with data collected from 66 participants, measuring temporalis, masseter and digastric muscles. DBSCAN (0.35 to 0.54) and GMM (0.09 to 0.24) exhibited lower silhouette scores for mouth opening, anterior protrusion and lateral excursions, while K-means performed best (0.10 to 0.11) for temporalis and masseter muscles during chewing activities. The current study successfully developed a deep learning workflow capable of extracting normalised signal data from EMG images and generating quantifiable parameters for muscle activity duration and general functional intensity.