Themis: advancing precision oncology through comprehensive molecular subtyping and optimization.

Recent advances in tumor molecular subtyping have revolutionized precision oncology, offering novel avenues for patient-specific treatment strategies. However, a comprehensive and independent comparison of these subtyping methodologies remains unexplored. This study introduces 'Themis' (Tumor HEterogeneity analysis on Molecular subtypIng System), an evaluation platform that encapsulates a few representative tumor molecular subtyping methods, including Stemness, Anoikis, Metabolism, and pathway-based classifications, utilizing 38 test datasets curated from The Cancer Genome Atlas (TCGA) and significant studies. Our self-designed quantitative analysis uncovers the relative strengths, limitations, and applicability of each method in different clinical contexts. Crucially, Themis serves as a vital tool in identifying the most appropriate subtyping methods for specific clinical scenarios. It also guides fine-tuning existing subtyping methods to achieve more accurate phenotype-associated results. To demonstrate the practical utility, we apply Themis to a breast cancer dataset, showcasing its efficacy in selecting the most suitable subtyping methods for personalized medicine in various clinical scenarios. This study bridges a crucial gap in cancer research and lays a foundation for future advancements in individualized cancer therapy and patient management.

A spatially localized DNA linear classifier for cancer diagnosis.

Molecular computing is an emerging paradigm that plays an essential role in data storage, bio-computation, and clinical diagnosis with the future trends of more efficient computing scheme, higher modularity with scaled-up circuity and stronger tolerance of corrupted inputs in a complex environment. Towards these goals, we construct a spatially localized, DNA integrated circuits-based classifier (DNA IC-CLA) that can perform neuromorphic architecture-based computation at a molecular level for medical diagnosis. The DNA-based classifier employs a two-dimensional DNA origami as the framework and localized processing modules as the in-frame computing core to execute arithmetic operations (e.g. multiplication, addition, subtraction) for efficient linear classification of complex patterns of miRNA inputs. We demonstrate that the DNA IC-CLA enables accurate cancer diagnosis in a faster (about 3 h) and more effective manner in synthetic and clinical samples compared to those of the traditional freely diffusible DNA circuits. We believe that this all-in-one DNA-based classifier can exhibit more applications in biocomputing in cells and medical diagnostics.

Generalizable transcriptome-based tumor malignant level evaluation and molecular subtyping towards precision oncology.

In cancer treatment, therapeutic strategies that integrate tumor-specific characteristics (i.e., precision oncology) are widely implemented to provide clinical benefits for cancer patients. Here, through in-depth integration of tumor transcriptome and patients' prognoses across cancers, we investigated dysregulated and prognosis-associated genes and catalogued such important genes in a cancer type-dependent manner. Utilizing the expression matrices of these genes, we built models to quantitatively evaluate the malignant levels of tumors across cancers, which could add value to the clinical staging system for improved prediction of patients' survival. Furthermore, we performed a transcriptome-based molecular subtyping on hepatocellular carcinoma, which revealed three subtypes with significantly diversified clinical outcomes, mutation landscapes, immune microenvironment, and dysregulated pathways. As tumor transcriptome was commonly profiled in clinical practice with low experimental complexity and cost, this work proposed easy-to-perform approaches for practical clinical promotion towards better healthcare and precision oncology of cancer patients.

AVBAE-MODFR: A novel deep learning framework of embedding and feature selection on multi-omics data for pan-cancer classification.

Integration analysis of cancer multi-omics data for pan-cancer classification has the potential for clinical applications in various aspects such as tumor diagnosis, analyzing clinically significant features, and providing precision medicine. In these applications, the embedding and feature selection on high-dimensional multi-omics data is clinically necessary. Recently, deep learning algorithms become the most promising cancer multi-omic integration analysis methods, due to the powerful capability of capturing nonlinear relationships. Developing effective deep learning architectures for cancer multi-omics embedding and feature selection remains a challenge for researchers in view of high dimensionality and heterogeneity. In this paper, we propose a novel two-phase deep learning model named AVBAE-MODFR for pan-cancer classification. AVBAE-MODFR achieves embedding by a multi2multi autoencoder based on the adversarial variational Bayes method and further performs feature selection utilizing a dual-net-based feature ranking method. AVBAE-MODFR utilizes AVBAE to pre-train the network parameters, which improves the classification performance and enhances feature ranking stability in MODFR. Firstly, AVBAE learns high-quality representation among multiple omics features for unsupervised pan-cancer classification. We design an efficient discriminator architecture to distinguish the latent distributions for updating forward variational parameters. Secondly, we propose MODFR to simultaneously evaluate multi-omics feature importance for feature selection by training a designed multi2one selector network, where the efficient evaluation approach based on the average gradient of random mask subsets can avoid bias caused by input feature drift. We conduct experiments on the TCGA pan-cancer dataset and compare it with four state-of-the-art methods for each phase. The results show the superiority of AVBAE-MODFR over SOTA methods.

Elucidating Cancer Subtypes by Using the Relationship between DNA Methylation and Gene Expression.

Advancements in the field of next generation sequencing (NGS) have generated vast amounts of data for the same set of subjects. The challenge that arises is how to combine and reconcile results from different omics studies, such as epigenome and transcriptome, to improve the classification of disease subtypes. In this study, we introduce sCClust (sparse canonical correlation analysis with clustering), a technique to combine high-dimensional omics data using sparse canonical correlation analysis (sCCA), such that the correlation between datasets is maximized. This stage is followed by clustering the integrated data in a lower-dimensional space. We apply sCClust to gene expression and DNA methylation data for three cancer genomics datasets from the Cancer Genome Atlas (TCGA) to distinguish between underlying subtypes. We evaluate the identified subtypes using Kaplan-Meier plots and hazard ratio analysis on the three types of cancer-GBM (glioblastoma multiform), lung cancer and colon cancer. Comparison with subtypes identified by both single- and multi-omics studies implies improved clinical association. We also perform pathway over-representation analysis in order to identify up-regulated and down-regulated genes as tentative drug targets. The main goal of the paper is twofold: the integration of epigenomic and transcriptomic datasets followed by elucidating subtypes in the latent space. The significance of this study lies in the enhanced categorization of cancer data, which is crucial to precision medicine.

Classification performance assessment for imbalanced multiclass data.

The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or F ß -score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction-an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality.

Vislocas: Vision transformers for identifying protein subcellular mis-localization signatures of different cancer subtypes from immunohistochemistry images.

Proteins must be sorted to specific subcellular compartments to perform their functions. Abnormal protein subcellular localizations are related to many diseases. Although many efforts have been made in predicting protein subcellular localization from various static information, including sequences, structures and interactions, such static information cannot predict protein mis-localization events in diseases. On the contrary, the IHC (immunohistochemistry) images, which have been widely applied in clinical diagnosis, contains information that can be used to find protein mis-localization events in disease states. In this study, we create the Vislocas method, which is capable of finding mis-localized proteins from IHC images as markers of cancer subtypes. By combining CNNs and vision transformer encoders, Vislocas can automatically extract image features at both global and local level. Vislocas can be trained with full-sized IHC images from scratch. It is the first attempt to create an end-to-end IHC image-based protein subcellular location predictor. Vislocas achieved comparable or better performances than state-of-the-art methods. We applied Vislocas to find significant protein mis-localization events in different subtypes of glioma, melanoma and skin cancer. The mis-localized proteins, which were found purely from IHC images by Vislocas, are in consistency with clinical or experimental results in literatures. All codes of Vislocas have been deposited in a Github repository (https://github.com/JingwenWen99/Vislocas). All datasets of Vislocas have been deposited in Zenodo (https://zenodo.org/records/10632698).

A multi-instance tumor subtype classification method for small PET datasets using RA-DL attention module guided deep feature extraction with radiomics features.

BACKGROUND: Positron emission tomography (PET) is extensively employed for diagnosing and staging various tumors, including liver cancer, lung cancer, and lymphoma. Accurate subtype classification of tumors plays a crucial role in formulating effective treatment plans for patients. Notably, lymphoma comprises subtypes like diffuse large B-cell lymphoma and Hodgkin's lymphoma, while lung cancer encompasses adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. Similarly, liver cancer consists of subtypes such as cholangiocarcinoma and hepatocellular carcinoma. Consequently, the subtype classification of tumors based on PET images holds immense clinical significance. However, in clinical practice, the number of cases available for each subtype is often limited and imbalanced. Therefore, the primary challenge lies in achieving precise subtype classification using a small dataset. METHOD: This paper presents a novel approach for tumor subtype classification in small datasets using RA-DL (Radiomics-DeepLearning) attention. To address the limited sample size, Support Vector Machines (SVM) is employed as the classifier for tumor subtypes instead of deep learning methods. Emphasizing the importance of texture information in tumor subtype recognition, radiomics features are extracted from the tumor regions during the feature extraction stage. These features are compressed using an autoencoder to reduce redundancy. In addition to radiomics features, deep features are also extracted from the tumors to leverage the feature extraction capabilities of deep learning. In contrast to existing methods, our proposed approach utilizes the RA-DL-Attention mechanism to guide the deep network in extracting complementary deep features that enhance the expressive capacity of the final features while minimizing redundancy. To address the challenges of limited and imbalanced data, our method avoids using classification labels during deep feature extraction and instead incorporates 2D Region of Interest (ROI) segmentation and image reconstruction as auxiliary tasks. Subsequently, all lesion features of a single patient are aggregated into a feature vector using a multi-instance aggregation layer. RESULT: Validation experiments were conducted on three PET datasets, specifically the liver cancer dataset, lung cancer dataset, and lymphoma dataset. In the context of lung cancer, our proposed method achieved impressive performance with Area Under Curve (AUC) values of 0.82, 0.84, and 0.83 for the three-classification task. For the binary classification task of lymphoma, our method demonstrated notable results with AUC values of 0.95 and 0.75. Moreover, in the binary classification task of liver tumor, our method exhibited promising performance with AUC values of 0.84 and 0.86. CONCLUSION: The experimental results clearly indicate that our proposed method outperforms alternative approaches significantly. Through the extraction of complementary radiomics features and deep features, our method achieves a substantial improvement in tumor subtype classification performance using small PET datasets.

Determination of Nursing Care Times Based on the Perroca Patient Classification Instrument in the Inpatient Oncology Unit: A Mixed Method Study.

OBJECTIVES: The aim of this study was to determine the daily nursing care times of hospitalized inpatient oncology unit patients according to degree of acuity using the Perroca Patient Classification tool. DATA SOURCES: This study used a mixed method sequential explanatory design. The "Nursing Activity Record Form" and "Perroca Patient Classification Instrument" were used for quantitative data collection, and direct observation was performed for 175 hours via time-motion study. Descriptive statistics, between-group comparison, and correlation analysis were used for data analysis. Using a semistructured questionnaire, qualitative data were collected from individual in-depth interviews with seven nurses who participated in the quantitative part of the study. Qualitative data were analyzed by thematic analysis. The reporting of this study followed GRAMMS checklist. CONCLUSIONS: As a result of the integration of quantitative and qualitative data, daily nursing care duration was determined as 2 to 2.5 hours for Type 1 patients, 2.6 to 3.5 hours for Type 2 patients, 3.6 to 4.75 hours for Type 3 patients, and 4.76 to 5.5 hours for Type 4 patients. The findings showed that in an inpatient oncology unit, nursing care hours increased as patients' Perroca Patient Classification Instrument acuity grade increased; thus, the instrument was discriminative in determining patients' degree of acuity. IMPLICATIONS FOR NURSING PRACTICE: Nurse managers can utilize this study's results to plan daily assignments that are sensitive to patient care needs. The results can also help nurse managers to identify relationships between nurse staffing and patient outcomes at the unit level, as well as to develop ways to analyze such relationships.

Actualización de los tumores cartilaginosos según la clasificación de la OMS de 2020 / Update of cartilaginous tumours according to the WHO classification 2020

Los tumores cartilaginosos son un grupo amplio y heterogéneo de neoplasias caracterizadas por la presencia de una matriz condroide que presenta crecimiento lobular y patrones de calcificación en arcos y anillos o en palomitas de maíz. En RM destaca su hiperintensidad en las secuencias potenciadas en T2, y en las imágenes poscontraste, un relace lobulado o septal. En la clasificación de 2020 de la OMS, los tumores de estirpe condral se clasifican en benignos, intermedios o malignos. A pesar de los avances tecnológicos, siguen suponiendo un reto tanto para el radiólogo como para el patólogo, siendo la principal dificultad la diferenciación entre los tumores benignos y malignos, razón por la que requieren un abordaje multidisciplinar. Este trabajo recoge los principales cambios introducidos en la actualización de 2020, describe las características de imagen de los principales tumores cartilaginosos y proporciona las claves radiológicas para diferenciar entre tumores benignos y malignos.(AU)

Cartilaginous tumours are a large and heterogeneous group of neoplasms characterised by the presence of a chondroid matrix, with lobular growth and arcuate, ring-like or popcorn-like calcification patterns. MRI shows hyperintensity in T2-weighted sequences and a lobulated or septal relief in postcontrast images. In the WHO 2020 classification, chondral tumours are classified as benign, intermediate or malignant. Despite technological advances, they continue to pose a challenge for both the radiologist and the pathologist, being the main difficulty the differentiation between benign and malignant tumours, which is why they require a multidisciplinary approach. This paper describes the main changes introduced in the 2020 update, describes the imaging characteristics of the main cartilaginous tumours and provides the radiological keys to differentiate between benign and malignant tumours.(AU)

Demoralization in cancer survivors: an updated systematic review and meta-analysis for quantitative studies.

BACKGROUND: Demoralization can cause impairments across all life aspects of cancer patients. Cancer patients are also vulnerable during their survivorship. The purpose of this review is to examine the risk of demoralization and associated risk factors among cancer survivors who have completed their primary anti-cancer treatment or time since diagnosis ≥5 years without recurrence. METHODS: We searched databases of PubMed, Cochrane, Embase, PsycINFO and ClinicalTrial.gov to identify eligible studies which reported the demoralization level among cancer survivors. A random-effect meta-analysis model was used for calculating mean demoralization level. Heterogeneity was evaluated by I2 statistics. Funnel plots and Egger's regression tests were performed for checking publication bias. We used one-study-removed method for sensitivity analysis. Subgroup analysis was also done to examine the difference of demoralization level between cancer types. Meta-regression was performed to reveal risk factors of demoralization. RESULTS: A meta-analysis of 12 articles involving 2902 cancer survivors was conducted. The mean demoralization score among cancer survivors was 25.98 (95% CI: 23.53-28.43). Higher demoralization level was seen in participants with older age, higher female ratio, higher married/living together status ratio and higher patient health questionnaire-9 score. The literature review revealed correlations between demoralization and suicide risk, anxiety and quality of life. No consistent correlation between demoralization and post-traumatic stress symptoms could be seen. CONCLUSIONS: High demoralization level is noticed among cancer survivors. Risks for females, elder patients or breast cancer survivors are identified. More longitudinal or interventional studies for cancer survivors' demoralization are expected in the future.

Epigenetic regulation during cancer transitions across 11 tumour types.

Chromatin accessibility is essential in regulating gene expression and cellular identity, and alterations in accessibility have been implicated in driving cancer initiation, progression and metastasis1-4. Although the genetic contributions to oncogenic transitions have been investigated, epigenetic drivers remain less understood. Here we constructed a pan-cancer epigenetic and transcriptomic atlas using single-nucleus chromatin accessibility data (using single-nucleus assay for transposase-accessible chromatin) from 225 samples and matched single-cell or single-nucleus RNA-sequencing expression data from 206 samples. With over 1 million cells from each platform analysed through the enrichment of accessible chromatin regions, transcription factor motifs and regulons, we identified epigenetic drivers associated with cancer transitions. Some epigenetic drivers appeared in multiple cancers (for example, regulatory regions of ABCC1 and VEGFA; GATA6 and FOX-family motifs), whereas others were cancer specific (for example, regulatory regions of FGF19, ASAP2 and EN1, and the PBX3 motif). Among epigenetically altered pathways, TP53, hypoxia and TNF signalling were linked to cancer initiation, whereas oestrogen response, epithelial-mesenchymal transition and apical junction were tied to metastatic transition. Furthermore, we revealed a marked correlation between enhancer accessibility and gene expression and uncovered cooperation between epigenetic and genetic drivers. This atlas provides a foundation for further investigation of epigenetic dynamics in cancer transitions.

A Comprehensive Landscape of De Novo Malignancy After Double Lung Transplantation.

Although the association between post-transplant malignancy (PTM) and immunosuppressive therapy after organ transplantation has been studied, an integrated review of PTM after lung transplantation is lacking. We investigated the incidence and types of de novo PTM and its impact on survival following double lung transplantation (DLT). The incidence and type of PTM as well as the annual and cumulative risks of each malignancy after DLT were analyzed. The overall survival (OS) of recipients with or without PTM was compared by the Kaplan-Meier survival method and landmark analysis. There were 5,629 cases (23.52%) with 27 types of PTMs and incidences and OS varied according to the types of PTMs. The recipients with PTM showed a significantly longer OS than those without PTM (p < 0.001). However, while the recipients with PTM showed significantly better OS at 3, and 5 years (p < 0.001, p = 0.007), it was worse at the 10-year landmark time (p = 0.013). And the single PTM group showed a worse OS rate than the multiple PTM group (p < 0.001). This comprehensive report on PTM following DLT can help understand the risks and timing of PTM to improve the implementation of screening and treatment.

Supervivencia de los pacientes con cáncer en Navarra y comparación con España / Survival of cancer patients in Navarre and comparison with Spain

Fundamento: Analizar la supervivencia de pacientes adultosdiagnosticados de cáncer en Navarra, describir su tendencia ycompararla con la supervivencia en España. Métodos: Los casos de personas adultas diagnosticadas decáncer en los periodos 1999-2007 y 2008-2016 fueron seleccionados del registro poblacional de cáncer de Navarra; su esta-do vital se había actualizado hasta 2020. La supervivencia observada, la supervivencia neta (SN) y la SN estandarizada poredad (SNe) a cinco años, junto con sus intervalos de confianzaal 95%, fueron estimados globalmente y para veintinueve grupos de cáncer. Resultados. Se analizaron 57.564 casos. La SNe de los hombresy mujeres diagnosticados en 2008-2016 fue 59,9% (59,1-60,8) y63,8% (62,8-64,7), respectivamente. En hombres varió desde13,4% (10,4-17,4) en cáncer de páncreas hasta 94,0% (88,1-100) en el de tiroides, y en mujeres desde 11,9% (7,2-19,7) enel cáncer de hígado hasta 95,6% (92,6-98,6) en el de tiroides. Encomparación con los casos diagnosticados en 1999-2007, la SNeaumentó en diez grupos de cáncer, resultando un incrementoglobal de 5,1 (4,1-6,0) puntos porcentuales. La SNe en Navarrafue 2,7 (1,9-3,4) puntos porcentuales mayor que la descrita enEspaña en 2008-2013. Conclusiones: En Navarra la supervivencia de pacientes diagnosticados de cáncer en el periodo 2008-2016 mejoró significativamente respecto al periodo 1999-2007. Esta mejora obedece probablemente a múltiples factores, incluyendo diagnósticos mástempranos, opciones terapéuticas más efectivas y mejora delproceso asistencial. La supervivencia global fue mayor en las mujeres que en los hombres. Además, los resultados sugieren unasupervivencia más alta en Navarra en comparación con España.(AU)

Background: To analyze the survival of adult cancer patients inNavarre, describe its trend, and compare the data for this Spanish Autonomous Community against that reported for Spain. Methods: Records of adult cancer patients were retrieved fromthe Navarre’s population-based cancer registry for two periods(1999-2007 and 2008-2016). The vital status had been updated to2020. Observed survival, net survival and age-standardized netsurvival at five years with 95% confidence intervals were estimated overall and for twenty-nine cancer groups. Results: We analyzed 57,564 cases. Age-standardized net survival was 59.9% (59.1-60.8) and 63.8% (62.8-64.7) for males and females diagnosed with cancer during the 2008-2016 period,respectively. Age-standardized net survival ranged from 13.4%(10.4-17.4) for pancreatic cancer to 94.0% (88.1-100) for thyroidcancer in male patients, and from 11.9% (7.2-19.7) for livercancer to 95.6% (92.6-98.6-%) for thyroid cancer in female patients. Compared with cases diagnosed in the 1999-2007 period,age-standardized net survival increased in 10 cancer groups, resulting in an overall increase of 5.1 (4.1-6.0) percentage points.The age-standardized net survival in Navarre was 2.7 (1.9-3.4)percentage points higher than that described for Spain for the2008-2013 period. Conclusions: In Navarre, the survival of cancer patients diagnosed during the 2008-2016 period improved significantlyin comparison to the 1999-2007 period. Different factors mayexplain this improvement, including earlier diagnoses, moreeffective treatment options, and better healthcare processes.Overall, survival was higher in women than in men. Our resultssuggest a higher survival rate in Navarre than in Spain.(AU)

Hallmarks of transcriptional intratumour heterogeneity across a thousand tumours.

Each tumour contains diverse cellular states that underlie intratumour heterogeneity (ITH), a central challenge of cancer therapeutics1. Dozens of recent studies have begun to describe ITH by single-cell RNA sequencing, but each study typically profiled only a small number of tumours and provided a narrow view of transcriptional ITH2. Here we curate, annotate and integrate the data from 77 different studies to reveal the patterns of transcriptional ITH across 1,163 tumour samples covering 24 tumour types. Among the malignant cells, we identify 41 consensus meta-programs, each consisting of dozens of genes that are coordinately upregulated in subpopulations of cells within many tumours. The meta-programs cover diverse cellular processes including both generic (for example, cell cycle and stress) and lineage-specific patterns that we map into 11 hallmarks of transcriptional ITH. Most meta-programs of carcinoma cells are similar to those identified in non-malignant epithelial cells, suggesting that a large fraction of malignant ITH programs are variable even before oncogenesis, reflecting the biology of their cell of origin. We further extended the meta-program analysis to six common non-malignant cell types and utilize these to map cell-cell interactions within the tumour microenvironment. In summary, we have assembled a comprehensive pan-cancer single-cell RNA-sequencing dataset, which is available through the Curated Cancer Cell Atlas website, and leveraged this dataset to carry out a systematic characterization of transcriptional ITH.

Genetic algorithm-based feature selection with manifold learning for cancer classification using microarray data.

BACKGROUND: Microarray data have been widely utilized for cancer classification. The main characteristic of microarray data is "large p and small n" in that data contain a small number of subjects but a large number of genes. It may affect the validity of the classification. Thus, there is a pressing demand of techniques able to select genes relevant to cancer classification. RESULTS: This study proposed a novel feature (gene) selection method, Iso-GA, for cancer classification. Iso-GA hybrids the manifold learning algorithm, Isomap, in the genetic algorithm (GA) to account for the latent nonlinear structure of the gene expression in the microarray data. The Davies-Bouldin index is adopted to evaluate the candidate solutions in Isomap and to avoid the classifier dependency problem. Additionally, a probability-based framework is introduced to reduce the possibility of genes being randomly selected by GA. The performance of Iso-GA was evaluated on eight benchmark microarray datasets of cancers. Iso-GA outperformed other benchmarking gene selection methods, leading to good classification accuracy with fewer critical genes selected. CONCLUSIONS: The proposed Iso-GA method can effectively select fewer but critical genes from microarray data to achieve competitive classification performance.

High-Order Correlation-Guided Slide-Level Histology Retrieval With Self-Supervised Hashing.

Histopathological Whole Slide Images (WSIs) play a crucial role in cancer diagnosis. It is of significant importance for pathologists to search for images sharing similar content with the query WSI, especially in the case-based diagnosis. While slide-level retrieval could be more intuitive and practical in clinical applications, most methods are designed for patch-level retrieval. A few recently unsupervised slide-level methods only focus on integrating patch features directly, without perceiving slide-level information, and thus severely limits the performance of WSI retrieval. To tackle the issue, we propose a High-Order Correlation-Guided Self-Supervised Hashing-Encoding Retrieval (HSHR) method. Specifically, we train an attention-based hash encoder with slide-level representation in a self-supervised manner, enabling it to generate more representative slide-level hash codes of cluster centers and assign weights for each. These optimized and weighted codes are leveraged to establish a similarity-based hypergraph, in which a hypergraph-guided retrieval module is adopted to explore high-order correlations in the multi-pairwise manifold to conduct WSI retrieval. Extensive experiments on multiple TCGA datasets with over 24,000 WSIs spanning 30 cancer subtypes demonstrate that HSHR achieves state-of-the-art performance compared with other unsupervised histology WSI retrieval methods.