[Multivariate alternative classification--an attempt to overcome some of the disadvantages of the Bayes classification].
Explore the source record for details and available documents.
Classification↗
SEARCH · PubMed Health
Results for “Classification”
Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
[Concepts and classification of hyperlipidemia and hyperlipoproteinemia with special reference to the classifications according to Frederickson and WHO].
Explore the source record for details and available documents.
Cholesterol↗
[Tentative classification of nursing based on the library classification systems].
Explore the source record for details and available documents.
Health Occupations↗
A unified benchmark of supervised and retrieval-based methods for viral genomic sequence classification.
The rapid growth of genomic sequencing demands fast, accurate, and scalable analysis methods. In viral genomic classification, expanding labeled reference collections can make supervised models costly to update and dependent on fixed label sets, motivating retrieval-based genomic classification as a simpler, more flexible alternative. We present a unified benchmark of supervised and retrieval-based methods for viral genomic sequence classification across three viral classification tasks: hepatitis C virus (HCV) genotyping, COVID-19 discrimination, and human papillomavirus (HPV) genotyping. We compare standard sequence encodings (one-hot, k-mers, FCGR) with dense embeddings (dna2vec, DNABERT). For each representation, we evaluate supervised classifiers (Random Forest, Decision Tree, XGBoost) and retrieval-based classification, where sequence vectors are indexed with FAISS and labels are assigned via similarity-weighted k-NN. Furthermore, we benchmark multiple FAISS index types (Flat, IVF, HNSW, IVFPQ, OPQ) to characterize accuracy-speed-memory trade-offs at scale. The results show that XGBoost and retrieval using Flat or IVF indexes achieve strong classification performance under different computational profiles. Compressed indexes such as IVFPQ and OPQ substantially reduce memory usage, although their accuracy loss depends on the dataset and representation. Overall, supervised XGBoost provides a favorable accuracy-size trade-off, while retrieval-based classification remains competitive and allows labeled reference sequences to be incorporated without retraining a global classifier. This benchmark provides practical guidance for selecting sequence representations, classifiers, and vector-search indexes under different accuracy, memory, and update requirements.
Genome, Viral↗
Automated Classification of Lymphoma Subtypes From Histopathological Images Using a U-Net Deep Learning Model: Comparative Evaluation Study.
BACKGROUND: Accurate classification and grading of lymphoma subtypes are essential for treatment planning. Traditional diagnostic methods face challenges of subjectivity and inefficiency, highlighting the need for automated solutions based on deep learning techniques. OBJECTIVE: This study aimed to investigate the application of deep learning technology, specifically the U-Net model, in classifying and grading lymphoma subtypes to enhance diagnostic precision and efficiency. METHODS: In this study, the U-Net model was used as the primary tool for image segmentation integrated with attention mechanisms and residual networks for feature extraction and classification. A total of 620 high-quality histopathological images representing 3 major lymphoma subtypes were collected from The Cancer Genome Atlas and the Cancer Imaging Archive. All images underwent standardized preprocessing, including Gaussian filtering for noise reduction, histogram equalization, and normalization. Data augmentation techniques such as rotation, flipping, and scaling were applied to improve the model's generalization capability. The dataset was divided into training (70%), validation (15%), and test (15%) subsets. Five-fold cross-validation was used to assess model robustness. Performance was benchmarked against mainstream convolutional neural network architectures, including fully convolutional network, SegNet, and DeepLabv3+. RESULTS: The U-Net model achieved high segmentation accuracy, effectively delineating lesion regions and improving the quality of input for classification and grading. The incorporation of attention mechanisms further improved the model's ability to extract key features, whereas the residual structure of the residual network enhanced classification accuracy for complex images. In the test set (N=1250), the proposed fusion model achieved an accuracy of 92% (1150/1250), a sensitivity of 91.04% (1138/1250), a specificity of 89.04% (1113/1250), and an F1-score of 90% (1125/1250) for the classification of the 3 lymphoma subtypes, with an area under the receiver operating characteristic curve of 0.95 (95% CI 0.93-0.97). The high sensitivity and specificity of the model indicate strong clinical applicability, particularly as an assistive diagnostic tool. CONCLUSIONS: Deep learning techniques based on the U-Net architecture offer considerable advantages in the automated classification and grading of lymphoma subtypes. The proposed model significantly improved diagnostic accuracy and accelerated pathological evaluation, providing efficient and precise support for clinical decision-making. Future work may focus on enhancing model robustness through integration with advanced algorithms and validating performance across multicenter clinical datasets. The model also holds promise for deployment in digital pathology platforms and artificial intelligence-assisted diagnostic workflows, improving screening efficiency and promoting consistency in pathological classification.
Humans↗
IASLC Update on Classification of Pulmonary Neuroendocrine Neoplasms.
Since the publication of the 2021 WHO classification of thoracic tumors, our knowledge of pulmonary neuroendocrine neoplasms (NENs) has expanded significantly, particularly through the elucidation of molecular pathways and proposals to refine histopathologic classification. This expanded knowledge across all aspects of pulmonary NENs holds promise for more precise stratification of neuroendocrine tumors (NETs) and the potential development of novel, subtype-specific therapeutic strategies for all NENs. Based on our comprehensive review of the current pulmonary NEN landscape, our multidisciplinary expert panel has deliberated on the modification and updating of the 2021 classification, resulting in the proposal of a new pulmonary carcinoid/NET classification presented in this position paper, which incorporates the following three major points: (1) The proposed framework continues the shift from the traditional carcinoid terminology toward broader adoption of the "NET" nomenclature as found in other organ systems while retaining the term "carcinoid" as the primary diagnostic term to ensure clear communication with thoracic clinical providers. (2) Ki-67 has been incorporated as a diagnostic criterion, aligning with practices in other NET classifications. (3) There is formal recognition of the concept of "carcinoid/NET G3," a rare subset of lung carcinoids characterized by increased proliferative activity but with molecular features more aligned with pulmonary NETs than with high-grade neuroendocrine carcinomas. This position paper on the current knowledge of pulmonary NENs, including the proposed carcinoid/NET classification, will aid in accurate tumor categorization and guide treatment strategies.
Carcinoid tumor↗
A module-based approach for post-omics, post-GWAS network-based gene classification.
MOTIVATION: Complex traits and diseases are highly polygenic and understanding the full set of genes involved is a central challenge in biomedicine. However, due to sample size limitations and noise (technical and biological), experimental approaches for disease-gene discovery such as transcriptomics and GWAS result in long, noisy, heterogeneous gene lists, which may be trimmed to a subset of likely relevant genes while leaving several false negatives. Computational gene classification approaches, especially those using genome-scale molecular interaction networks, are promising avenues for complementing such experimental findings by analytically expanding observed gene lists based on the functional relatedness between genes. We previously introduced the network-based gene classification approach, GenePlexus, which was rigorously benchmarked to show state-of-the-art performance, especially for predicting novel genes associated with biological processes and fine-grained phenotypes. Network-based gene classification performance,however, declines for diseases, especially when the inputs are omics and GWAS-based long gene lists. RESULTS: Here, we show that these disease gene lists span multiple biological processes spread across the molecular network, and we propose ModGenePlexus, a new network-based gene classification method that takes a two-stage approach. First, clustering and semi-supervised learning decomposes the input gene list into coherent, denoised network gene modules. Then, ModGenePlexus trains supervised (GenePlexus) classifiers for each module and aggregates predictions to return genome-wide rankings. We benchmarked ModGenePlexus across simulated data, transcriptomic signatures, and GWAS datasets (together spanning hundreds of diseases), showing improved recovery of known disease genes compared to GenePlexus. Beyond improved classification, the results of enrichment analysis of ModGenePlexus outputs are much more interpretable by virtue of revealing nuanced biological processes. Together, these results establish ModGenePlexus as a scalable, interpretable tool for gene classification of GWAS- and omics-derived gene lists across diverse biological contexts. AVAILABILITY AND IMPLEMENTATION: ModGenePlexus is freely available on GitHub at https://github.com/krishnanlab/ModGenePlexus, and the full source code and results supporting this study are available on Zenodo at https://zenodo.org/records/19857910.
Genome-Wide Association Study↗
Gastric carcinoma classification in the WHO 6th edition (2026): Updated framework and emerging entities.
The sixth edition of the WHO Classification of Digestive System Tumours (2026) represents an important step in the continuing evolution of gastric carcinoma classification. While preserving morphology as the foundation of diagnosis, it incorporates advances in molecular pathology, genotype-phenotype correlations, tumour evolution, and predictive biomarker assessment. This review summarizes the development of the WHO classification from the third edition (2000) to the sixth edition (2026) and highlights its relationship with other major classification systems, including those of Laurén, Nakamura, and the Japanese Gastric Carcinoma Association (JGCA). Major histological categories remain largely unchanged; however, several important conceptual and diagnostic refinements have been introduced. These include recognition of crawling-type adenocarcinoma as a distinctive variant of tubular adenocarcinoma, subclassification of poorly cohesive carcinoma into signet-ring cell and non-signet-ring cell subtypes, introduction of the concept of pure signet-ring cell carcinoma, and increased emphasis on tumour evolution. The sixth edition also expands and refines the spectrum of uncommon gastric carcinoma subtypes, including gastric carcinoma with lymphoid stroma, AFP-producing carcinoma, micropapillary adenocarcinoma, gastric adenocarcinoma of fundic-gland type, and gastric sarcomatoid carcinoma. Crucially, molecular subgroups originally proposed by The Cancer Genome Atlas (TCGA) and actionable biomarkers-including HER2 (ERBB2), Claudin 18.2, mismatch repair deficiency/microsatellite instability (dMMR/MSI), and programmed death-ligand 1 (PD-L1)-have transitioned from research-based categories into essential tools for precision oncology. Rather than providing exhaustive diagnostic criteria, this review offers a conceptual framework and encourages consultation of the original WHO text for full details. These advances illustrate the transition of gastric carcinoma classification from a predominantly morphology-based system toward an integrated histomolecular framework that more closely links pathological diagnosis with tumour biology, prognostication, and therapeutic stratification.
Crawling-type adenocarcinoma↗
A nonlinear multi-omics data integration and classification model based on pathway self-attention and graph convolutional networks.
The abundance of omics data has significantly advanced the development of multi-omics data integration techniques. Non-linear embedding approaches for data integration have gradually become the mainstream in multi-omics research, as these approaches can substantially improve cancer analysis by enhancing the quality of the embeddings. However, current multi-omics data integration methods are typically confined to omics measurements, neglecting domain-specific prior knowledge encompassing biological pathways. In this study, we proposed a multi-omics integrated classification model, PathTransGCN, based on pathway self-attention and graph convolutional networks (GCN). The model integrated biological pathway information into multi-omics data analysis with the aim of enhancing the accuracy of cancer classification. Multi-omics data for breast cancer (BRCA), non-small cell lung cancer (NSCLC), and low-grade glioma (LGG) were obtained from The Cancer Genome Atlas (TCGA) and UCSC Xena databases. These data included gene mutations, DNA methylation, copy number variations, and gene expression, and were used to assess the model's generalizability across different cancers. First, PathTransGCN employed a pathway self-attention module to learn latent representations of samples across different pathways, thereby obtaining multi-omics integration vectors. Concurrently, a patient similarity network (PSN) was constructed using the similarity network fusion (SNF) approach. Second, the integrated vectors and the PSN were jointly fed into a GCN for end-to-end training, enabling precise classification of cancer subtypes. Through multi-omics data analysis of the BRCA dataset, PathTransGCN outperformed several popular algorithms (such as MoGCN and DeePathNet) in the five-class classification of cancer subtypes, achieving an accuracy rate of 87.6% and an F1 score of 86.4%. Moreover, the model demonstrated robust generalization capabilities across both NSCLC and LGG datasets, while effectively identifying key disease-associated biomarkers at the pathway level. Experimental results demonstrate that PathTransGCN exhibits outstanding performance in integrating omics data and delivering interpretable classification outcomes, presenting significant potential for clinical applications.
Humans↗
Proceedings: Prognosis of non-Hodgkin's lymphomas with special emphasis on the staging classification.
The prognosis of the non-Hodgkin's lymphomas is determined by 1. the pattern of origin and spread which can be demonstrated in a staging classification, 2, the histopathological type, and 3. the effectiveness and scope of the treatment methods, particularly radio- and chemo-therapy. In the following paper the Ann Arbor Classification, which was originally conceived of for both disease groups (Hodgkin's and non-Hodgkin's lymphomas), is discussed particularly with respect to the applicability and prognostic evaluation for the non-Hodgkin's lymphomas. The Ann Arbor Classification may in essence reflect the oncological characteristics of the non-Hodgkin's accurately; there are, however, a number of findings with qualitative and quantitative differences which defy integration into the Ann Arbor Classification. The qualitative differences consist of the differing lymphatic and extralymphatic origins and their consequence for spread and prognosis. The quantitative differences refer to the varying patterns of distribution of the different stages of spreading, whereby the dissemination stages in the non-Hodgkin's lymphomas are more dependent on the histological form than is the case with the Hodgkin's lymphomas, and thus must play a greater role in the prognostic evaluation and indication for treatment. Suggestions have been made for a modification of the Ann Arbor Staging Classification for the non-Hodgkin's lymphomas.
Humans↗
MegaPlantTF: a machine learning framework for comprehensive identification and classification of plant transcription factors.
MOTIVATION: Understanding the role of transcription factors (TFs) in plants is essential for the study of gene regulation and various biological processes. However, both TF detection and classification remain challenging due to the great diversity and complexity of these proteins. Conventional approaches, such as BLAST, often suffer from high computational complexity and limited performance on less common TF families. RESULTS: We introduce MegaPlantTF, the first comprehensive machine learning and deep learning framework for the prediction (TF versus non-TF) and classification (family-level) of plant TFs. Our method employs k-mer-based protein representations and a two-stage architecture combining a deep feed-forward neural network with a stacking ensemble classifier. To ensure robust performance assessment, we report micro-, macro-, and weighted-average performance metrics, providing a holistic evaluation of both frequent and underrepresented TF families. Additionally, we employ threshold-based evaluation to calibrate confidence in TF detection. The results show that MegaPlantTF achieves strong accuracy and precision, particularly with a k-mer size of 3 and a classification threshold of 0.5, and maintains stable performance even under stringent thresholds. In addition to the standard cross-validation tests, a use case study on Sorghum bicolor confirms that our method performs strongly in the genome-wide analysis, making it highly suitable for large-scale TF identification and classification tasks. MegaPlantTF represents a novel contribution by integrating k-mer encoding, binary family-specific classifiers, and a two-stage stacking ensemble into a unified, reproducible framework for large-scale plant TF identification and classification. AVAILABILITY AND IMPLEMENTATION: MegaPlantTF is freely accessible through a public web server available at https://bioinformatics.um6p.ma/MegaPlantTF. The complete source code, including pretrained models and example datasets, is available at https://github.com/Bioinformatics-UM6P/MegaPlantTF.
Transcription Factors↗
Advances in the diagnosis and classification of B-ALL: comparative insights from updated guidelines.
Accurate molecular classification is essential for diagnosis, risk stratification, and treatment selection in B-cell lymphoblastic leukemia (B-ALL). In this study, we performed a comprehensive, real-world reclassification of 1015 consecutively diagnosed B-ALL patients using the fifth edition of the World Health Organization Classification of Haematolymphoid Tumours (WHO-HAEM5) and the International Consensus Classification (ICC). An integrative genomic strategy that combined whole transcriptome sequencing, fusion detection, mutational analysis, and cytogenetics enabled reclassification according to both the WHO-HAEM5 and ICC frameworks, thereby substantially reducing the proportion of unclassifiable B-ALL from 41.9% (2016 WHO revision [WHO-HAEM4R]) to 15.9% (WHO-HAEM5) and 11.9% (ICC). Distinct clinical and prognostic features were identified across newly defined subtypes. Multivariable analysis confirmed that this genomic classification is a robust, independent predictor of survival after adjusting for age, minimal residual disease status, and transplant intervention. Specifically, HLF-rearranged and MEF2D-rearranged B-ALL conferred a persistently poor prognosis across all age groups despite allogeneic hematopoietic stem cell transplantation, highlighting an urgent need for novel therapeutic strategies. Gene expression profiling resolved cryptic subtypes, including ETV6::RUNX1-like, ZNF384-rearranged-like, and BCR::ABL1-like B-ALL, and uncovered diagnostic ambiguity in patients with concurrent lesions. In addition, we report emerging high-risk groups, including IDH1/2- and ZEB2 Q1072-mutated B-ALL, that may warrant recognition as distinct molecular entities. Our findings demonstrate the clinical use of integrative transcriptomic profiling in refining B-ALL taxonomy in guiding risk-adapted therapies and informing future revisions of diagnostic standards. This study supports the incorporation of high-throughput molecular diagnostics into routine leukemia classification and precision treatment planning.
Humans↗
[Classification and diagnosis of ankle injuries].
A new method for the classification of the injuries of the ankle is recommended by the author. The main types according to his classifixation are the following: pronation-flexion, pronation-extension, supination-extension, supination-flexion and supination-extension types. His classification is compared with Lauge-Hansen's and Weber's classification. Critical analysis of these two last classifications is given. The aim of the author's classification is to render help to the doctors for their every-days' curative work. The characteristic symptoms of the pronation and supination, resp., injuries are described. Attention is drawn to "Weber's lace"--this denomination is proposed by the author, since the first description is due to Weber. On the basis of the author's examinations described in his candidate's dissertation "syndesmolysis trigonum"--pathognostic for syndesmolysis--is dealt with. The "reclined" roentgenograms are dealt with. The so-called pronation reclined roentgenogram visualize the rupture of the deltoid ligament and the syndesmolysis in the same time. The sagittal reclined roentgenogram is dealth with separately, by means of which the "table-drawer" symptom may be produced.
Ankle Injuries↗
[TNM-classification of oral cavity neoplasms the value of clinically measurable factors (TN)].
Problems associated with the classification of cavum oris and labial carcinomata were discussed with particular reference to patients admitted to and treated in seven different clinical hospitals where identical methods of diagnosis and case history evaluation had been used. Using electronic data processing and biostatistical methods it was possible to study the effects of two clinically detectable factors (growth of primary tumor and degree of regional metastasizing) on both the prognosis and classification according to UICC rules. It was possible to show that a determination of the size of primary tumor (T) alone was not sufficient for three homogeneous, prognostically different collectives of tumors to be satisfactorily classified by the new UICC rules. It has been shown that a classification of three collectives of tumors (new classification according to UICC rules), especially as regards the proportion of N3 metastases within the collectives of tumors, was made possible. Therefore, it will be necessary to study the prognostic influences of additional clinically determinable factors with a view to arriving at a useful and practicable classification of oral cavity carcinomata.
Aged↗
Hierarchical Multi-Label Classification With Gene-Environment Interactions in Disease Modeling.
In biomedical studies, gene-environment (G-E) interactions have been demonstrated to have important implications for analyzing disease outcomes beyond the main G and main E effects. Many approaches have been developed for G-E interaction analysis, yielding important findings. However, hierarchical multi-label classification, which provides insightful information on disease outcomes, remains unexplored in G-E analysis literature. Moreover, unlabeled data are commonly observed in practical settings but omitted by many existing methods of hierarchical multi-label classification. In this study, we consider a semi-supervised scenario and develop a novel approach for the two-layer hierarchical response with G-E interactions. A two-step penalized estimation is then proposed using an efficient expectation-maximization (EM) algorithm. Simulation shows that it has superior performance in classification and feature selection. The analysis of The Cancer Genome Atlas (TCGA) data on lung cancer demonstrates the practical utility of the proposed method. Overall, this study can fill the important knowledge gap in G-E interaction analysis by providing a widely applicable framework for hierarchical multi-label classification of complex disease outcomes.
Humans↗
Discrepancies in CPAK classification between CT and long-leg radiography: a systematic review and meta-analysis.
OBJECTIVE: To determine whether substantial differences in coronal plane alignment of the knee phenotype distribution, as well as systematic angular measurement discrepancies, exist between CT and long-leg radiography. MATERIALS AND METHODS: From February 2021 to April 2025, we searched PubMed, Embase, and the Cochrane Central Register of Controlled Trials for studies comparing CT- and long-leg radiography-derived coronal plane alignment classifications of the knee in patients with osteoarthritis. The primary outcome was distribution of coronal plane alignment phenotypes. Secondary outcomes included differences in medial proximal tibial angle, lateral distal femoral angle, arithmetic hip-knee-ankle angle, and joint line obliquity. RESULTS: Four studies (1,134 knees) were included. Compared with long-leg radiography-derived classification, CT-derived classification increased type I phenotypes (risk difference: 0.10; 95% confidence interval: 0.01-0.20; P = 0.040) and decreased type III (risk difference: -0.04; 95% confidence interval: -0.07 to -0.01; P = 0.020) and type V phenotypes (risk difference: -0.04; 95% confidence interval: -0.07 to -0.01; P = 0.004). CT yielded significantly lower medial proximal tibial angle (weighted mean difference: - 1.18°; P < 0.001), arithmetic hip-knee-ankle angle (weighted mean difference: - 0.95°; P < 0.001), and joint line obliquity (weighted mean difference: - 1.40°; P < 0.001) than long-leg radiography. Heterogeneity was high for type I phenotype (I2 = 81%), lateral distal femoral angle (I2 = 70%), and joint line obliquity (I2 = 69%). CONCLUSION: Discrepancies between CT-based software-generated and long-leg radiography-derived measurements substantially affect coronal plane alignment classification and angular parameters. Surgeons should consider these modality-specific variations and employ compensatory verification strategies to ensure optimal alignment.
Humans↗
MWENA: a novel sample re-weighting-based algorithm for disease classification and data interpretation using extracellular vesicles omics data.
BACKGROUND AND OBJECTIVE: Extracellular vesicles (EVs), considered as a form of liquid biopsy, have gained significant attention in recent years due to their stability and the preservation of disease markers. Research studies underscore the clinical significance of molecules found in EVs, highlighting their role as communicative mediators between cells. However, analyzing this data is challenging due to noisy measurements, having far more variables than samples, and some groups (e.g., disease subtypes or experimental conditions) having much less data than others. We therefore develop an algorithm to address aforementioned challenges for the classification of imbalanced EVs omics data. METHODS AND RESULTS: We propose the EV Meta-Weight Elastic Net Algorithm (MWENA), which utilizes logistic regression with elastic net regularization for the classification and identification of EV signatures, effectively addressing the challenges posed by high-dimensional small sample sizes. To mitigate issues related to class imbalance and high noise levels, MWENA incorporates an automatic sample re-weighting function, which uses a meta-net to adaptively learn generalizable patterns directly from the data itself. We validate the MWENA algorithm on both simulated data and EVs omics data, covering six classification tasks that involve four different types of diseases (pancreatic ductal adenocarcinoma, interstitial lung diseases, colorectal cancer, and ovarian cancer) and three clinical scenarios (disease diagnosis, disease-stage screening, and disease-subtype classification). Compared to other machine learning methods, MWENA demonstrates superiority in identifying small class samples and achieves the highest scores in both sensitivity and G-means. Biological analysis is also performed to further explore the significance of selected signatures as biological markers and their roles in disease mechanisms. CONCLUSIONS: We anticipate that our proposed approach will take a modest step in harnessing EV omics data to discover biomarkers, aiding researchers in gaining a comprehensive understanding of biological processes.
Extracellular Vesicles↗
Perseus: Lineage-Aware Refinement of Kraken2 Taxonomic Classification for Long Read Metagenomes.
MOTIVATION: Long-read metagenomic sequencing improves assembly contiguity and enables genome-resolved analysis of complex microbial communities, but accurate taxonomic classification of long reads and assembled contigs remains challenging. Highly scalable k-mer-based classifiers such as Kraken2 frequently over-assign fine-rank taxonomic labels when applied to long-read data, producing high false positive classification rates driven by sparse or localized k-mer matches, particularly in microbiomes with extensive taxonomic novelty. RESULTS: We present Perseus, a lineage-aware confidence estimation framework for taxonomic classification that models the spatial distribution and hierarchical consistency of k-mer evidence along sequences. This formulation reframes taxonomic classification as a hierarchical confidence estimation problem rather than a single-rank prediction task. Perseus refines k-mer-level taxonomic signals from Kraken2 using a multi-headed convolutional neural network that estimates calibrated confidence scores for taxonomic correctness at each canonical rank. Using these estimates, Perseus confirms assignments, backs off to higher taxonomic ranks, or abstains when evidence is insufficient, prioritizing correctness and lineage consistency over overly specific assignments. Across simulations of taxonomic novelty and real-world metagenomic datasets, Perseus consistently and substantially reduces the false assignment rate while improving precision and lineage-consistent accuracy. These improvements are most pronounced for long reads and assembled contigs, where spatial context enables reliable discrimination between consistent taxonomic signal and spurious matches. AVAILABILITY AND IMPLEMENTATION: Perseus integrates with existing Kraken2 workflows and is available at https://github.com/matnguyen/perseus.
Journal Article↗