Clustering Algorithm Research Articles

ScHNTL: single-cell RNA-seq data clustering augmented by high-order neighbors and triplet loss.

The rapid development of single-cell RNA sequencing (scRNA-seq) has significantly advanced biomedical research. Clustering analysis, crucial for scRNA-seq data, faces challenges including data sparsity, high dimensionality, and variable gene expressions. Better low-dimensional embeddings for these complex data should maintain intrinsic information while making similar data close and dissimilar data distant. However, existing methods utilizing neural networks typically focus on minimizing reconstruction loss and maintaining similarity in embeddings of directly related cells, but fail to consider dissimilarity, thus lacking separability and limiting the performance of clustering. We propose a novel clustering algorithm, called scHNTL (scRNA-seq data clustering augmented by high-order neighbors and triplet loss). It first constructs an auxiliary similarity graph and uses a Graph Attentional Autoencoder to learn initial embeddings of cells. Then it identifies similar and dissimilar cells by exploring high-order structures of the similarity graph and exploits a triplet loss of contrastive learning, to improve the embeddings in preserving structural information by separating dissimilar pairs. Finally, this improvement for embedding and the target of clustering are fused in a self-optimizing clustering framework to obtain the clusters. Experimental evaluations on 16 real-world datasets demonstrate the superiority of scHNTL in clustering over the state-of-the-arts single-cell clustering algorithms. Python implementation of scHNTL is available at Figshare (https://doi.org/10.6084/m9.figshare.27001090) and Github (https://github.com/SWJTU-ML/scHNTL-code). Supplementary data are available at Bioinformatics online.

Detecting noncredible symptomology in ADHD evaluations using machine learning

ABSTRACT Introduction Diagnostic evaluations for attention-deficit/hyperactivity disorder (ADHD) are becoming increasingly complicated by the number of adults who fabricate or exaggerate symptoms. Novel methods are needed to improve the assessment process required to detect these noncredible symptoms. The present study investigated whether unsupervised machine learning (ML) could serve as one such method, and detect noncredible symptom reporting in adults undergoing ADHD evaluations. Method Participants were 623 adults who underwent outpatient ADHD evaluations. Patients’ scores from symptom validity tests embedded in two self-report questionnaires were examined in an unsupervised ML model. The model, called “sidClustering,” is based on a clustering and random forest algorithm. The model synthesized the raw scores (without cutoffs) from the symptom validity tests into an unspecified number of groups. The groups were then compared to predetermined ratings of credible versus noncredible symptom reporting. The noncredible symptom ratings were defined by either two or three or more symptom validity test elevations. Results The model identified two groups that were significantly (p < .001) and meaningfully associated with the predetermined ratings of credible or noncredible symptom reporting, regardless of the number of elevations used to define noncredible reporting. The validity test assessing overreporting of various types of psychiatric symptoms was most influential in determining group membership; but symptom validity tests regarding ADHD-specific symptoms were also contributory. Conclusion These findings suggest that unsupervised ML can effectively identify noncredible symptom reporting using scores from multiple symptom validity tests without predetermined cutoffs. The ML-derived groups also support the use of two validity test elevations to identify noncredible symptom reporting. Collectively, these findings serve as a proof of concept that unsupervised ML can improve the process of detecting noncredible symptoms during ADHD evaluations. With additional research, unsupervised ML may become a useful supplementary tool for quickly and accurately detecting noncredible symptoms during these evaluations.

Development of a CT radiomics prognostic model for post renal tumor resection overall survival based on transformer enhanced K-means clustering.

Kidney tumors, common in the urinary system, have widely varying survival rates post-surgery. Current prognostic methods rely on invasive biopsies, highlighting the need for non-invasive, accurate prediction models to assist in clinical decision-making. This study aimed to construct a K-means clustering algorithm enhanced by Transformer-based feature transformation to predict the overall survival rate of patients after kidney tumor resection and provide an interpretability analysis of the model to assist in clinical decision-making. This study was based on a publicly available C4KC-KiTS-2019 dataset from the TCIA database, including preoperative computed tomography (CT) images and survival time data of 210 patients. Initially, the radiomics features of the kidney tumor area were extracted using the 3D slicer software. Feature selection was then conducted using ICC, mRMR algorithms, and LASSO regression to calculate radiomics scores. Subsequently, the selected features were input into a pre-trained Transformer model for feature transformation to obtain a higher-dimensional feature set. Then, K-means clustering was performed using this feature set, and the model was evaluated using receiver operating characteristic (ROC) and Kaplan-Meier curves. Finally, the SHAP interpretability algorithm was used for the feature importance analysis of the K-means clustering results. Eleven important features were selected from 851 radiomics features. The K-means clustering model after Transformer feature transformation showed AUCs of 0.889, 0.841, and 0.926 for predicting 1-, 3-, and 5-year overall survival rates, respectively, thereby outperforming both the K-means model with original feature inputs and the radiomics score method. A clustering analysis revealed survival prognosis differences among different patient groups, and a SHAP analysis provided insights into the features that had the most significant impacts on the model predictions. The K-means clustering algorithm enhanced by the Transformer feature transformation proposed in this study demonstrates promising accuracy and interpretability in predicting the overall survival rate after kidney tumor resection. This method provides a valuable tool for clinical decision-making and contributes to improved management and treatment strategies for patients with kidney tumors.

Super Partition: fast, flexible, and interpretable large-scale data reduction in R

Motivation As data sets increase in size and complexity with advancing technology, flexible and interpretable data reduction methods that quantify information preservation become increasingly important. Results Super Partition is a large-scale approximation of the original Partition data reduction algorithm that allows the user to flexibly specify the minimum amount of information captured for each input feature. In an initial step, Genie, a fast, hierarchical clustering algorithm, forms a super-partition, thereby increasing the computational tractability by allowing Partition to be applied to the subsets. Applications to high dimensional data sets show scalability to hundreds of thousands of features with reasonable computation times. Availability and implementation Super Partition is a new function within the partition R package, available on the CRAN repository (https://cran.r-project.org/web/packages/partition/index.html).

Generation of Personalized Urban Public Space Color Design Scheme Assisted by Artificial Intelligence

This research focuses on the generation of urban public space color design schemes using Artificial Intelligence (AI). The designed AI-based system predicts colors for the environment, culture, and users and designs a color palette for smart cities. Neural networks and clustering algorithms are used to determine the best hues and shades, depending on the input parameters like climate, architectural style, and general looks in a specific region. It evokes sophisticated colors in varied urban contexts, URBAN FABRICS proposes a specific color answer to the aesthetic and performative beautification of the public realm. In addition to adopting elements of AI binding into the design principles, the system enables dynamic colors to adapt to the changing needs and external conditions. Testing the model in multiple cities demonstrated its ability to generate unique, context-sensitive designs, improving both aesthetic value and user satisfaction. This research highlights the role of AI in modern urban planning, presenting an innovative approach to color design that balances artistic creativity with data-driven insights. The findings offer practical implications for architects, urban planners, and designers seeking to enhance urban public spaces through personalized, AI-assisted color schemes.

A Clustering Algorithm Based on Local Relative Density

DBSCAN and DPC are typical density-based clustering algorithms. These two algorithms have their drawbacks, such as difficulty in clustering when there are significant differences in density between clusters. This study proposes a clustering algorithm, RDBSCAN, which is based on local relative density, drawing on the extension strategy of DBSCAN and the allocation mechanism of DPC. The algorithm first uses k-nearest neighbors to calculate the original local density, then sorts the points in descending order of this density. It then selects the point with the highest original local density from the unprocessed points as the local center of the next cluster. Based on this local center, RDBSCAN calculates the local relative density, determines the core objects, and performs cluster expansion. Drawing on the allocation mechanism of DPC, the algorithm performs a secondary allocation for points in clusters that are too small to complete the final clustering. Comparative experiments using RDBSCAN and eight other clustering algorithms were conducted, and the test results show that RDBSCAN ranks first in clustering performance metrics among all algorithms on synthetic datasets and second on real-world datasets.

Identifying time patterns in Huntington’s disease trajectories using dynamic time warping-based clustering on multi-modal data

One of the principal goals of Precision Medicine is to stratify patients by accounting for individual variability. However, extracting meaningful information from Real-World Data, such as Electronic Health Records, still remains challenging due to methodological and computational issues. A Dynamic Time Warping-based unsupervised-clustering methodology is presented in this paper for the clustering of patient trajectories of multi-modal health data on the basis of shared temporal characteristics. Building on an earlier methodology, a new dimension of time-varying clinical and imaging features is incorporated, through an adapted cost-minimization algorithm for clustering on different, possibly overlapping, feature subsets. The model disease chosen is Huntington’s disease (HD), characterized by progressive neurodegeneration. From a wide range of examined user-defined parameters, four case examples are highlighted to demonstrate the identified temporal patterns in multi-modal HD trajectories and to study how these differ due to the combined effects of feature weights and granularity threshold. For each identified cluster, polynomial fits that describe the time behavior of the assessed features are provided for an informative comparison, together with their averaged values. The proposed data-mining methodology permits the stratification of distinct time patterns of multi-modal health data in individuals that share a diagnosis, by employing user-customized criteria beyond the current clinical practice. Overall, this work bears implications for better analysis of individual variability in disease progression, opening doors to personalized preventative, diagnostic and therapeutic strategies.

AoI-Minimal Task Assignment and Trajectory Optimization in Multi-UAV-Assisted Wireless Powered IoT Networks

This paper investigates the energy transfer and data collection problem of multiple unmanned aerial vehicle (UAV)-assisted wireless-powered Internet of Things (IoT) networks. To ensure information freshness for IoT devices and reduce UAVs’ energy consumption, we minimize the average Age of Information (AoI) of IoT devices by jointly optimizing the energy harvesting (EH) and data collection time for IoT devices, the selection of data collection points (DCPs), DCP-IoT associations, and task assignment, flight speed, and trajectories of UAVs, subject to the limited endurance of UAVs. As this problem is nonconvex, we propose a novel DCP association and trajectory-planning scheme that seeks age-optimal solutions through an iterative three-step process. First, we calculate the EH and data collection time for IoT devices using Karush–Kuhn–Tucker (KKT) conditions. Then, we introduce an optimal hovering time allocation-based affinity propagation (OHTAP) clustering algorithm to determine optimal DCP locations and establish DCP-IoT associations. Finally, we develop two algorithms to optimize UAVs’ trajectories: an improved partheno-genetic algorithm with enhancement mechanisms (EIPGA) and a hybrid algorithm that combines improved MinMax k-means clustering with EIPGA. Numerical results confirm that our scheme consistently outperforms benchmark schemes in AoI performance and solution stability across diverse scenarios.

PRRSV-2 variant classification: a dynamic nomenclature for enhanced monitoring and surveillance.

Existing genetic classification systems for porcine reproductive and respiratory syndrome virus type 2 (PRRSV-2), such as restriction fragment length polymorphisms and sub-lineages, are unreliable indicators of close genetic relatedness or lack sufficient resolution for epidemiological monitoring routinely conducted by veterinarians. Here, we outline a fine-scale classification system for PRRSV-2 genetic variants in the United States. Based on >25,000 U.S. open reading frame 5 (ORF5) sequences, sub-lineages were divided into genetic variants using a clustering algorithm. Through classifying new sequences every 3 months and systematically identifying new variants across 8 years, we demonstrated that prospective implementation of the variant classification system produced robust, reproducible results across time and can dynamically accommodate new genetic diversity arising from virus evolution. From 2015 to 2023, 118 variants were identified, with ~48 active variants per year, of which 26 were common (detected >50 times). Mean within-variant genetic distance was 2.4% (max: 4.8%). The mean distance to the closest related variant was 4.9%. A routinely updated webtool (https://stemma.shinyapps.io/PRRSLoom-variants/) was developed and is publicly available for end users to assign newly generated sequences to a variant ID. This classification system relies on U.S. sequences from 2015 onward; further efforts are required to extend this system to older or international sequences. Finally, we demonstrate how variant classification can better discriminate between previous and new strains on a farm, determine possible sources of new introductions into a farm/system, and track emerging variants regionally. Adoption of this classification system will enhance PRRSV-2 epidemiological monitoring, research, and communication, and improve industry responses to emerging genetic variants.IMPORTANCEThe development and implementation of a fine-scale classification system for PRRSV-2 genetic variants represent a significant advancement for monitoring PRRSV-2 occurrence in the swine industry. Based on systematically applied criteria for variant identification using national-scale sequence data, this system addresses the shortcomings of existing classification methods by offering higher resolution and adaptability to capture emerging variants. This system provides a stable and reproducible method for classifying PRRSV-2 variants, facilitated by a freely available and regularly updated webtool for use by veterinarians and diagnostic labs. Although currently based on U.S. PRRSV-2 ORF5 sequences, this system can be expanded to include sequences from other countries, paving the way for a standardized global classification system. By enabling accurate and improved discrimination of PRRSV-2 genetic variants, this classification system significantly enhances the ability to monitor, research, and respond to PRRSV-2 outbreaks, ultimately supporting better management and control strategies in the swine industry.

Long-term creep life prediction of P91 steel using domain knowledge and back propagation artificial neural network

ABSTRACT In this work, the long-term creep life of P91 steels with the limited experiment data was predicted using the domain knowledge and back propagation artificial neural networks (BP-ANN). Based on the traditional creep life models of Larson-Miller (L-M) parameter and θ projection, the domain knowledge was incorporated to expand the creep dataset. Then, the fuzzy C-means (FCM) clustering algorithm was introduced for training data collection. Consequently, the creep life prediction was conducted with the corresponding dataset and BP-ANN. The obtained results demonstrated that in contrast to the conventional prediction models of creep life, the prediction accuracy for long-term creep life of P91 steels can be improved significantly by the present model. For instance, the predicted creep lives 200,000 h exhibit the average errors of 6.0%. In addition, the present study offers a convenient tool to solve the issue of limited experiment data, particularly the long-term creep of P91 steels.

Accurate LAI estimation of soybean plants in the field using deep learning and clustering algorithms

The leaf area index (LAI) is a critical parameter for characterizing plant foliage abundance, canopy structure changes, and vegetation productivity in ecosystems. Traditional phenological measurements are often destructive, time-consuming, and labor-intensive. This paper proposes a high-throughput 3D point cloud data processing pipeline to segment field soybean plants and estimate their LAI. The 3D point cloud data is obtained from a UAV equipped with a LiDAR camera. First, The PointNet++ model was applied to simplify the segmentation process by isolating field soybean plants from their surroundings and eliminating environmental complexities. Subsequently, individual segmentation was achieved using the Watershed approach and k-means clustering algorithms, segmenting the field soybeans into individual plants. Finally, the LAI of soybean plant was estimated using a machine learning method and validated against measured values. The PointNet++ model improved segmentation accuracy by 6.73%, and the watershed algorithm achieved F1 scores of 0.89–0.90, outperforming k-means in complex adhesion cases. For LAI estimation, the SVM model showed the highest accuracy (R² = 0.79, RMSE = 0.47), with RF and XGBoost also performing well (R² &amp;gt; 0.69, RMSE&amp;lt; 0.65). This indicates that the individual segmentation algorithm, Watershed-based approach combined with PointNet++, can serve as a crucial foundation for extracting high-throughput plant phenotypic data. The experimental results confirm that the proposed method can rapidly calculate the morphological parameters of each soybean plant, making it suitable for high-throughput soybean phenotyping.

Deep Multi-View Clustering Optimized by Long Short-Term Memory Network

Long short-term memory (LSTM) networks have shown great promise in sequential data analysis, especially in time-series and natural language processing. However, their potential for multi-view clustering has been largely underexplored. In this paper, we introduce a novel approach called deep multi-view clustering optimized by long short-term memory network (DMVC-LSTM), which leverages the sequential modeling capability of LSTM to effectively integrate multi-view data. By capturing complex interdependencies and nonlinear relationships between views, DMVC-LSTM improves clustering accuracy and robustness. The method includes three feature fusion techniques—concatenation, averaging, and attention-based fusion—with concatenation as the primary method. Notably, DMVC-LSTM is well suited for datasets that exhibit symmetry, as it can effectively handle symmetrical relationships between views while preserving the underlying structures. Extensive experiments demonstrate that DMVC-LSTM outperforms existing multi-view clustering algorithms, particularly in high-dimensional and complex datasets, achieving superior performance in datasets like 20 Newsgroups and Wikipedia Articles. This paper presents the first application of LSTM in multi-view clustering, marking a significant step forward in both clustering performance and the application of LSTM in multi-view data analysis.

Motif clustering and digital biomarker extraction for free-living physical activity analysis

BackgroundAnalyzing free-living physical activity (PA) data presents challenges due to variability in daily routines and the lack of activity labels. Traditional approaches often rely on summary statistics, which may not capture the nuances of individual activity patterns. To address these limitations and advance our understanding of the relationship between PA patterns and health outcomes, we propose a novel motif clustering algorithm that identifies and characterizes specific PA patterns.MethodsThis paper proposes an elastic distance-based motif clustering algorithm for identifying specific PA patterns (motifs) in free-living PA data. The algorithm segments long-term PA curves into short-term segments and utilizes elastic shape analysis to measure the similarity between activity segments. This enables the discovery of recurring motifs through pattern clustering. Then, functional principal component analysis (FPCA) is then used to extract digital biomarkers from each motif. These digital biomarkers can subsequently be used to explore the relationship between PA and health outcomes of interest.ResultsWe demonstrate the efficacy of our method through three real-world applications. Results show that digital biomarkers derived from these motifs effectively capture the association between PA patterns and disease outcomes, improving the accuracy of patient classification.ConclusionsThis study introduced a novel approach to analyzing free-living PA data by identifying and characterizing specific activity patterns (motifs). The derived digital biomarkers provide a more nuanced understanding of PA and its impact on health, with potential applications in personalized health assessment and disease detection, offering a promising future for healthcare.

A multitasking ant system for multi-depot pick-up and delivery location routing problem with time window

Instant delivery service has brought great convenience to our modern life. In order to improve its efficiency, multi-depot pick-up-and-delivery location routing problem with time windows (MDPDLRPTW) is proposed in this paper. Existing works related to MDPDLRPTW focus on obtaining a depot location scheme by clustering and perform route planning on it through single-task optimization. They are powerless to simultaneously explore the solution spaces of multiple routing tasks under different location schemes. Furthermore, ignoring the potential general knowledge among different schemes leads to redundant optimization. In this work, MDPDLRPTW is modeled as a multi-transformation optimization (MTFO) problem and a novel two-stage algorithm based on multitasking ant system (MTAS) is designed to solve it. In the first stage, a clustering algorithm based on spatio-temporal feature is used to group similar customer pairs, and the clustering centers are set as warehouses. Afterward, multiple localization schemes are selected through non-dominated sorting based on spatio-temporal density. In the second stage, MTAS concurrently optimizes multiple routing tasks based on these location schemes, each task is assigned to an ant system solver. Furthermore, MTAS achieves knowledge sharing among all routing tasks through adaptive similarity measurement and cross-task pheromone fusion strategy. The former can dynamically capture the relationship between tasks to adjust the transfer strength of task pairs, and the latter realizes adaptive knowledge transfer by pheromone-matrix mixing. Experimental results show that MTAS can efficiently utilize the common knowledge to achieve competitive performance.

P1207 Therapy goals and Quality of Life among older patients with Inflammatory Bowel Disease: results of an international EFCCA survey

Abstract Background The number of older patients with Inflammatory Bowel Disease (IBD) is rapidly growing, however they are underrepresented in research. To enhance more personalized and patient-centered care, it is important to study the disease burden and therapy goals of this population. Therefore, the aim of this study was to explore prioritized therapy goals, clusters of therapy goals and determinants of quality of life (QoL) in older patients with IBD. Methods This was an international, anonymous, online survey in older patients (age ≥ 60 years) with IBD, proposed and conducted by the European Federation of Crohn’s and Ulcerative Colitis Associations (EFCCA), between May 2023 and November 2023. Patients were asked to select three out of twelve pre-specified therapy goals. A cluster analysis was performed to identify patterns or combinations of therapy goals that were reported together, using a binary distance and an agglomerative clustering algorithm. QoL was assessed by one question about general well-being (five-point Likert scale). We assessed the influence of the therapy goal clusters on QoL by an ordinal regression model adjusting for common confounders. Results Of 1997 included respondents from 34 countries, with a median age of 66 years (IQR 63-71), 297 (14.8%) reported poor-terrible QoL. Older patients with IBD most often prioritized therapy goals related to decreasing fatigue (56%), preserving/restoring a good mood (43%) and decrease diarrhea/incontinence (32%). Six clusters of therapy goals were identified and labelled: 1 - Inflammation control, 2 - IBD-symptom control, 3 - Mobility capacity, 4 - Bodily perception, 5 - Mood and energy, 6 - Activity engagement. The proportion of patients with very well QoL was highest in cluster 6 (60%) and the lowest in cluster 2 (17%). Low QoL was independently associated with therapy goal clusters related to Inflammation control (adjusted Odds Ratio (aOR) 1.86 95% confidence interval (95%CI): 1.24-2.77), IBD-symptom control (aOR: 3.19, 95%CI: 2.13-4.79), Mobility capacity (aOR: 2.14, 95%CI: 1.41-3.24) and Mood and energy (aOR: 1.82, 95%CI: 1.19-2.78), compared to the Activity engagement cluster. Conclusion Older patients with IBD prioritize therapy goals focused on reducing fatigue, improving mood and decreasing diarrhea/incontinence. Low QoL was significantly associated with therapy goal clusters emphasizing inflammation control, IBD symptoms, mobility, and mood/energy. These results are indicative for the need to evaluate the QoL in older patients with IBD in the context of their therapy goals.

Toward the fabric of the Milky Way. I. The density of disk streams from a local 250^3 pc^3 volume

We studied 12 disk streams found in a 250^3 pc^3 volume in the solar neighborhood, which we define as coeval and comoving stellar structures with aspect ratios greater than 3:1. Using Gaia Data Release 3 data and the advanced clustering algorithms SigMA and Uncover we identified and characterized these streams beyond the search volume, doubling, on average, their known populations. We estimate the number density of disk streams to be ≈ 820 objects,/,kpc^3 (for $|Z| &lt; 100$,pc), or surface densities of ≈ 160 objects,/,kpc^2. These estimates surpass N-body estimates by one to two orders of magnitude and challenge the prevailing understanding of their destruction mechanisms. Our analysis reveals that these 12 disk streams are dynamically cold with 3D velocity dispersions between 2 and 5,km,s^-1, exhibit narrow sequences in the Hertzsprung-Russell diagram, and are highly elongated with average aspect ratios of 7:1, extending up to several hundred parsecs. We find evidence suggesting that one of the disk streams, currently embedded in the Scorpius-Centaurus association, is experiencing disruption, likely due to the primordial gas mass of the association.

MutaSwarmClus: enhancing data clustering efficiency with mutation-enhanced swarm algorithm

Data clustering is a fundamental technique in data mining, pivotal for various applications such as statistical analysis and data compression. Traditional clustering algorithms often struggle with noisy or high-dimensional datasets, hindering their efficacy in addressing real-world challenges. In response, this research introduces MutaSwarmClus, a novel hybrid metaheuristic algorithm that combines Mouth Brooding Fish (MBF), Ant Colony Optimization (ACO), and mutation operators to enhance clustering quality. MutaSwarmClus intends to adaptively control the exploration and exploitation phases of the solution space, solve issues with local optima and changes in the distribution of available data. Moreover, it incorporates an Iterated Local Search (ILS) to refine solutions and avoiding getting stuck in local optima. MutaSwarmClus therefore increases the robustness of the clustering process by incorporating controlled randomness through mutation operators in order to handle noisy and outlier data points well. According to the contributions analysis, the proposed algorithm improves the clustering solution with the combined system of MBF, ACO, and mutation operators, which enables the mechanism of exploration and exploitation in the process of information search. As shown through the results of experimental studies, MutaSwarmClus has high performance when used with various benchmarks, and outperforms or performs as well as or better than compared to other clustering algorithms such as K-means, ALO, Hybrid ALO, and MBF. It achieves an average error rate of only 10%, underscoring its accuracy in clustering tasks. The utilization of MutaSwarmClus offers a solution to the existing problems in clustering large datasets in terms of scalability, efficiency and accuracy. Possible directions for future work can continue to optimize the model parameters of the algorithm and study its adaptability in dynamic conditions and with large amounts of data.

SOPTICS: A modified density-based algorithm for identifying galaxy groups/clusters and brightest cluster galaxies

Abstract A direct approach to studying the galaxy-halo connection is to analyze groups and clusters of galaxies that trace the underlying dark matter halos, emphasizing the importance of identifying galaxy clusters and their associated brightest cluster galaxies (BCGs). In this work, we test and propose a robust density-based clustering algorithm that outperforms the traditional Friends-of-Friends (FoF) algorithm in the currently available galaxy group/cluster catalogs. Our new approach is a modified version of the Ordering Points To Identify the Clustering Structure (OPTICS) algorithm, which accounts for line-of-sight positional uncertainties due to redshift space distortions by incorporating a scaling factor, and is thereby referred to as sOPTICS. When tested on both a galaxy group catalog based on semi-analytic galaxy formation simulations and observational data, our algorithm demonstrated robustness to outliers and relative insensitivity to hyperparameter choices. In total, we compared the results of eight clustering algorithms. The proposed density-based clustering method, sOPTICS, outperforms FoF in accurately identifying giant galaxy clusters and their associated BCGs in various environments with higher purity and recovery rate, also successfully recovering 115 BCGs out of 118 reliable BCGs from a large galaxy sample. Furthermore, when applied to an independent observational catalog without extensive re-tuning, sOPTICS maintains high recovery efficiency, confirming its flexibility and effectiveness for large-scale astronomical surveys.

Functional genomic imaging (FGI), a virtual tool for visualization of functional gene expression modules in heterogeneous tumor samples

Advances in sequencing technologies are reshaping clinical diagnostics, prompting the development of new software tools to decipher big data. To this end, we developed functional genomic imaging (FGI), a visualization tool designed to assist clinicians in interpreting RNA-Seq results from patient samples. FGI uses weighted gene co-expression network analysis (WGCNA), followed by a modified Phenograph clustering algorithm to identify co-expression gene clusters. These gene modules were annotated and projected onto a t-SNE map for visualization. Annotation of FGI gene clusters revealed three categories: tissue-specific, functional, and positional. These clusters may be used to build tumor subtypes with pre-annotated functions. At the multi-cancer cohort level, tissue-specific clusters are enriched, whereas at the single cancer level, such as in lung cancer or ovarian cancer, positional clusters can be more prominent. Moreover, FGI analysis could also reveal molecular tumor subtypes not documented in clinical records and generated a more detailed co-expression gene cluster map. Based on different levels of FGI modeling, each individual tumor sample can be customized to display various types of information such as tissue origin, molecular subtypes, immune activation status, stromal signaling pathways, cell cycle activity, and potential amplicon regions which can aid in diagnosis and guide treatment decisions. Our results highlight the potential of FGI as a robust visualization tool for personalized medicine in molecular diagnosis.

Autoencoder based data clustering for identifying anomalous repetitive hand movements, and behavioral transition patterns in children.

The analysis of repetitive hand movements and behavioral transition patterns holds particular significance in detecting atypical behaviors in early child development. Early recognition of these behaviors holds immense promise for timely interventions, which can profoundly impact a child's well-being and future prospects. However, the scarcity of specialized medical professionals and limited facilities has made detecting these behaviors and unique patterns challenging using traditional manual methods. This highlights the necessity for automated tools to identify anomalous repetitive hand movements and behavioral transition patterns in children. Our study aimed to develop an automated model for the early identification of anomalous repetitive hand movements and the detection of unique behavioral patterns. Utilizing autoencoders, self-similarity matrices, and unsupervised clustering algorithms, we analyzed skeleton and image-based features, repetition count, and frequency of repetitive child hand movements. This approach aimed to distinguish between typical and atypical repetitive hand movements of varying speeds, addressing data limitations through dimension reduction. Additionally, we aimed to categorize behaviors into clusters beyond binary classification. Through experimentation on three datasets (Hand Movements in Wild, Updated Self-Stimulatory Behaviours, Autism Spectrum Disorder), our model effectively differentiated between typical and atypical hand movements, providing insights into behavioral transitional patterns. This aids the medical community in understanding the evolving behaviors in children. In conclusion, our research addresses the need for early detection of atypical behaviors through an automated model capable of discerning repetitive hand movement patterns. This innovation contributes to early intervention strategies for neurological conditions.