UNASSIGNED: The clinical presentation of Community-acquired pneumonia (CAP) in hospitalized patients exhibits heterogeneity. Inflammation and immune responses play significant roles in CAP development. However, research on immunophenotypes in CAP patients is limited, with few machine learning (ML) models analyzing immune indicators.
UNASSIGNED: A retrospective cohort study was conducted at Xinhua Hospital, affiliated with Shanghai Jiaotong University. Patients meeting predefined criteria were included and unsupervised clustering was used to identify phenotypes. Patients with distinct phenotypes were also compared in different outcomes. By machine learning methods, we comprehensively assess the disease severity of CAP patients.
UNASSIGNED: A total of 1156 CAP patients were included in this research. In the training cohort (n=809), we identified three immune phenotypes among patients: Phenotype A (42.0%), Phenotype B (40.2%), and Phenotype C (17.8%), with Phenotype C corresponding to more severe disease. Similar results can be observed in the validation cohort. The optimal prognostic model, SuperPC, achieved the highest average C-index of 0.859. For predicting CAP severity, the random forest model was highly accurate, with C-index of 0.998 and 0.794 in training and validation cohorts, respectively.
UNASSIGNED: CAP patients can be categorized into three distinct immune phenotypes, each with prognostic relevance. Machine learning exhibits potential in predicting mortality and disease severity in CAP patients by leveraging clinical immunological data. Further external validation studies are crucial to confirm applicability.

Complex systems are typically characterized by intricate internal dynamics that are often hard to elucidate. Ideally, this requires methods that allow to detect and classify in an unsupervised way the microscopic dynamical events occurring in the system. However, decoupling statistically relevant fluctuations from the internal noise remains most often nontrivial. Here, we describe \"Onion Clustering\": a simple, iterative unsupervised clustering method that efficiently detects and classifies statistically relevant fluctuations in noisy time-series data. We demonstrate its efficiency by analyzing simulation and experimental trajectories of various systems with complex internal dynamics, ranging from the atomic- to the microscopic-scale, in- and out-of-equilibrium. The method is based on an iterative detect-classify-archive approach. In a similar way as peeling the external (evident) layer of an onion reveals the internal hidden ones, the method performs a first detection/classification of the most populated dynamical environment in the system and of its characteristic noise. The signal of such dynamical cluster is then removed from the time-series data and the remaining part, cleared-out from its noise, is analyzed again. At every iteration, the detection of hidden dynamical subdomains is facilitated by an increasing (and adaptive) relevance-to-noise ratio. The process iterates until no new dynamical domains can be uncovered, revealing, as an output, the number of clusters that can be effectively distinguished/classified in a statistically robust way as a function of the time-resolution of the analysis. Onion Clustering is general and benefits from clear-cut physical interpretability. We expect that it will help analyzing a variety of complex dynamical systems and time-series data.

We consider unsupervised classification by means of a latent multinomial variable which categorizes a scalar response into one of the L components of a mixture model which incorporates scalar and functional covariates. This process can be thought as a hierarchical model with the first level modelling a scalar response according to a mixture of parametric distributions and the second level modelling the mixture probabilities by means of a generalized linear model with functional and scalar covariates. The traditional approach of treating functional covariates as vectors not only suffers from the curse of dimensionality, since functional covariates can be measured at very small intervals leading to a highly parametrized model, but also does not take into account the nature of the data. We use basis expansions to reduce the dimensionality and a Bayesian approach for estimating the parameters while providing predictions of the latent classification vector. The method is motivated by two data examples that are not easily handled by existing methods. The first example concerns identifying placebo responders on a clinical trial (normal mixture model) and the other predicting illness for milking cows (zero-inflated mixture of the Poisson model).

Single-cell RNA-sequencing (scRNA-seq) is a powerful technology that allows researchers to study gene expression heterogeneity within a tissue or cell population. One of the major advantages of scRNA-seq is that it allows researchers to identify and characterize novel cell types or subpopulations within a tissue that may be missed by traditional bulk RNA-sequencing methods. Although many existing methods have been developed to recognize known cell types, inferring novel cells may still be challenging in routine scRNA-seq analysis. Here we describe three lines of methods for inferring novel cells: unsupervised and outlier-detection-based methods, supervised and semi-supervised methods, and copy number variation (CNV)-based methods, as well as the corresponding situations that each method applies. We also provide implementation code and example usages to illustrate the available methods.

Colorectal cancer (CRC) is a prevalent and aggressive malignancy characterized by a complex tumor microenvironment (TME). Given the variations in the level of adipocyte infiltration in TME, the prognosis may differ among CRC patients. Thus, there is an urgent need to establish a reliable method for identifying adipocyte subtypes in CRC in order to elucidate the impact of adipocyte infiltration on CRC treatment and prognosis. Herein, 144 adipocyte-infiltration-related genes (AIRGs) were identified as predictive markers for the immune-associated features and prognosis of CRC patients. Based on the 144 genes, the unsupervised clustering algorithm identified two distinct clusters of CRC patients with variations in molecular and signaling pathways, clinicopathological characteristics and responses to CRC chemotherapy and immunotherapy. Furthermore, an AIRG prognostic signature was constructed and validated in independent datasets. Overall, this study developed a prognostic signature based on AIRGs in CRC, which may contribute to the development of personalized treatment strategies and enhance prognostic prediction for CRC patients.

Classifications of forest vegetation types and characterization of related species assemblages are important analytical tools for mapping and diversity monitoring of forest communities. The discrimination of forest communities is often based on β-diversity, which can be quantified via numerous indices to derive compositional dissimilarity between samples. This study aims to evaluate the applicability of unsupervised classification for National Forest Inventory data from Georgia by comparing two cluster hierarchies. We calculated the mean basal area per hectare for each woody species across 1059 plot observations and quantified interspecies distances for all 87 species. Following an unspuervised cluster analysis, we compared the results derived from the species-neutral dissimilarity (Bray-Curtis) with those based on the Discriminating Avalanche dissimilarity, which incorporates interspecies phylogenetic variation. Incorporating genetic variation in the dissimilarity quantification resulted in a more nuanced discrimination of woody species assemblages and increased cluster coherence. Favorable statistics include the total number of clusters (23 vs. 20), mean distance within clusters (0.773 vs. 0.343), and within sum of squares (344.13 vs. 112.92). Clusters derived from dissimilarities that account for genetic variation showed a more robust alignment with biogeographical units, such as elevation and known habitats. We demonstrate that the applicability of unsupervised classification of species assemblages to large-scale forest inventory data strongly depends on the underlying quantification of dissimilarity. Our results indicate that by incorporating phylogenetic variation, a more precise classification aligned with biogeographic units is attained. This supports the concept that the genetic signal of species assemblages reflects biogeographical patterns and facilitates more precise analyses for mapping, monitoring, and management of forest diversity.
ტყის მცენარეულობის ტიპების კლასიფიკაცია და მონათესავე სახეობათა შეკრების დახასიათება მნიშვნელოვანი ანალიტიკური ინსტრუმენტებია ტყის ტიპების აღწერისა და მრავალფეროვნების მონიტორინგისთვის. ტყის ტიპების განსხვავება ხშირად ემყარება β‐მრავალფეროვნებას, რომლის რაოდენობრივი დადგენა შესაძლებელია მრავალი ინდექსის მეშვეობით ნიმუშებს შორის კომპოზიციური განსხვავებულობის გამოსათვლელად. ეს კვლევა მიზნად ისახავს შეაფასოს საქართველოს ეროვნული ტყის ინვენტარიზაციის ზედამხედველობის გარეშე კლასიფიკაციის გამოყენებადობა ორი კლასტერული იერარქიის შედარების გზით. ჩვენ გამოვთვალეთ საშუალო ბაზალური ფართობი ჰექტარზე თითოეული მერქნიანი სახეობისთვის 1059 ნაკვეთზე დაკვირვებით და რაოდენობრივად დავადგინეთ სახეობათაშორისი მანძილი 87‐ვე სახეობისთვის. ჩვენ შევადარეთ სახეობების ნეიტრალური განსხვავებულობიდან მიღებული შედეგები (ბრეი‐კურტისი) ზვავის დისკრიმინაციული განსხვავებულობის საფუძველზე, რომელიც აერთიანებს სახეობათაშორის ფილოგენეტიკურ ვარიაციებს. გენეტიკური ცვალებადობის ჩართვამ განსხვავებულობის რაოდენობრივ განსაზღვრებაში გამოიწვია მერქნიანი სახეობების შეკრების უფრო ნიუანსური განსხვავება და გაზრდილი კლასტერული თანმიმდევრულობა. ხელსაყრელი სტატისტიკა მოიცავს მტევანთა საერთო რაოდენობას (23 v. 20), საშუალო მანძილს მტევნის შიგნით (0.773 vs. 0.343) და კვადრატების ჯამის ფარგლებში (344.13 vs. 112.92). განსხვავებებიდან მიღებული კლასტერებმა, რომლებიც ითვალისწინებენ გენეტიკურ ვარიაციებს, აჩვენეს უფრო მძლავრი გასწორება ბიოგეოგრაფიულ ერთეულებთან, როგორიცაა სიმაღლე და ცნობილი ჰაბიტატები. ჩვენ ვაჩვენებთ, რომ სახეობების შეკრების უკონტროლო კლასიფიკაციის გამოყენებადობა ფართომასშტაბიანი ტყის ინვენტარიზაციის მონაცემებზე მტკიცედ არის დამოკიდებული განსხვავებულობის ფუძემდებლური რაოდენობრივი განსაზღვრაზე. ჩვენი შედეგები მიუთითებს, რომ ფილოგენეტიკური ვარიაციით, უფრო ზუსტი კლასიფიკაციაა შესაძლებელი, რომელიც შეესაბამება ბიოგეოგრაფიულ ერთეულებს. ეს ამტიცებს კონცეფციას, რომ სახეობათა შეკრების გენეტიკური სიგნალი ასახავს ბიოგეოგრაფიულ ნიმუშებს და ხელს უწყობს ტყის მრავალფეროვნების აღწერას მონიტორინგისა და მართვის უფრო ზუსტ ანალიზს.

UNASSIGNED: Accumulating evidence reveals mitochondrial dysfunction exacerbates intestinal barrier dysfunction and inflammation. Despite the growing knowledge of mitochondrial dysfunction and ulcerative colitis (UC), the mechanism of mitochondrial dysfunction in UC remains to be fully explored.
UNASSIGNED: We integrated 1137 UC colon mucosal samples from 12 multicenter cohorts worldwide to create a normalized compendium. Differentially expressed mitochondria-related genes (DE-MiRGs) in individuals with UC were identified using the \"Limma\" R package. Unsupervised consensus clustering was utilized to determine the intrinsic subtypes of UC driven by DE-MiRGs. Weighted gene co-expression network analysis was employed to investigate module genes related to UC. Four machine learning algorithms were utilized for screening DE-MiRGs in UC and construct MiRGs diagnostic models. The models were developed utilizing the over-sampled training cohort, followed by validation in both the internal test cohort and the external validation cohort. Immune cell infiltration was assessed using the Xcell and CIBERSORT algorithms, while potential biological mechanisms were explored through GSVA and GSEA algorithms. Hub genes were selected using the PPI network.
UNASSIGNED: The study identified 108 DE-MiRGs in the colonic mucosa of patients with UC compared to healthy controls, showing significant enrichment in pathways associated with mitochondrial metabolism and inflammation. The MiRGs diagnostic models for UC were constructed based on 17 signature genes identified through various machine learning algorithms, demonstrated excellent predictive capabilities. Utilizing the identified DE-MiRGs from the normalized compendium, 941 patients with UC were stratified into three subtypes characterized by distinct cellular and molecular profiles. Specifically, the metabolic subtype demonstrated enrichment in epithelial cells, the immune-inflamed subtype displayed high enrichment in antigen-presenting cells and pathways related to pro-inflammatory activation, and the transitional subtype exhibited moderate activation across all signaling pathways. Importantly, the immune-inflamed subtype exhibited a stronger correlation with superior response to four biologics: infliximab, ustekinumab, vedolizumab, and golimumab compared to the metabolic subtype.
UNASSIGNED: This analysis unveils the interplay between mitochondrial dysfunction and the immune microenvironment in UC, thereby offering novel perspectives on the potential pathogenesis of UC and precision treatment of UC patients, and identifying new therapeutic targets.

This paper presents an innovative technique, Advanced Predictor of Electrical Parameters, based on machine learning methods to predict the degradation of electronic components under the effects of radiation. The term degradation refers to the way in which electrical parameters of the electronic components vary with the irradiation dose. This method consists of two sequential steps defined as \'recognition of degradation patterns in the database\' and \'degradation prediction of new samples without any kind of irradiation\'. The technique can be used under two different approaches called \'pure data driven\' and \'model based\'. In this paper, the use of Advanced Predictor of Electrical Parameters is shown for bipolar transistors, but the methodology is sufficiently general to be applied to any other component.

UNASSIGNED: For Rheumatoid Arthritis (RA), a long-term chronic illness, it is essential to identify and describe patient subtypes with comparable goal status and molecular biomarkers. This study aims to develop and validate a new subtyping scheme that integrates genome-scale transcriptomic profiles of RA peripheral blood genes, providing a fresh perspective for stratified treatments.
UNASSIGNED: We utilized independent microarray datasets of RA peripheral blood mononuclear cells (PBMCs). Up-regulated differentially expressed genes (DEGs) were subjected to functional enrichment analysis. Unsupervised cluster analysis was then employed to identify RA peripheral blood gene expression-driven subtypes. We defined three distinct clustering subtypes based on the identified 404 up-regulated DEGs.
UNASSIGNED: Subtype A, named NE-driving, was enriched in pathways related to neutrophil activation and responses to bacteria. Subtype B, termed interferon-driving (IFN-driving), exhibited abundant B cells and showed increased expression of transcripts involved in IFN signaling and defense responses to viruses. In Subtype C, an enrichment of CD8+ T-cells was found, ultimately defining it as CD8+ T-cells-driving. The RA subtyping scheme was validated using the XGBoost machine learning algorithm. We also evaluated the therapeutic outcomes of biological disease-modifying anti-rheumatic drugs.
UNASSIGNED: The findings provide valuable insights for deep stratification, enabling the design of molecular diagnosis and serving as a reference for stratified therapy in RA patients in the future.

BACKGROUND: Membranoproliferative glomerulonephritis is currently divided into immunoglobulin-mediated glomerulonephritis (IC-MPGN) and C3 glomerulopathy (C3G); however, the patients often overlap with histology, complement, clinical and prognostic factors. Our aim was to investigate if an unsupervised clustering method finds different patient groups in 44 IC-MPGN/C3G patients using only histological and clinical data available in everyday clinical work.
METHODS: Primary IC-MPGN/C3G adult patients were included whose diagnostic (baseline) native biopsy was obtained in 2006-2017. The biopsies were reassessed and the clinical data at baseline and during follow-up were obtained from the medical records. There were 39 baseline histological and clinical variables included in the unsupervised clustering. Follow-up information was combined with the clustering results.
RESULTS: The clustering resulted in two clusters (n = 24 and n = 20 patients for clusters 1-2, respectively), where cluster 1 had a significantly higher baseline plasma creatinine (mean 213 vs. 104, respectively, p value <0.001) and a lower baseline eGFR than cluster 2 (mean 37 vs. 70, respectively, p value <0.001). Regarding histology, chronic changes such as lobulated glomeruli, mesangial matrix expansion, and glomeruli double contours were more prevalent in cluster 1 (p value <0.001). Biopsy morphology was more often crescentic and membranoproliferative in cluster 1 (p value <0.001). Although the differences were insignificant, cluster 1 patients were in dialysis in the last follow-up or had a progressive disease more often than cluster 2 patients (21% vs. 5%, 38% vs. 10%).
CONCLUSIONS: Our results indicate that these patients share greater similarity than the current classification IC-MPGN versus C3G indicates.