cAMP/PKA signaling regulates TDP-43 aggregation and mislocalization.

Cytoplasmic mislocalization and aggregation of TDP-43 protein are hallmarks of amyotrophic lateral sclerosis (ALS) and are observed in the vast majority of both familial and sporadic cases. How these two interconnected processes are regulated on a molecular level, however, remains enigmatic. Genome-wide screens for modifiers of the ALS-associated genes TDP-43 and FUS have identified the phospholipase D (Pld) pathway as a key regulator of ALS-related phenotypes in the fruit fly Drosophila melanogaster [M. W. Kankel et al., Genetics 215, 747-766 (2020)]. Here, we report the results of our search for downstream targets of the enzymatic product of Pld, phosphatidic acid. We identify two conserved negative regulators of the cAMP/PKA signaling pathway, the phosphodiesterase dunce and the inhibitory subunit PKA-R2, as modifiers of pathogenic phenotypes resulting from overexpression of the Drosophila TDP-43 ortholog TBPH. We show that knockdown of either of these genes results in a mitigation of both TBPH aggregation and mislocalization in larval motor neuron cell bodies, as well as an amelioration of adult-onset motor defects and shortened lifespan induced by TBPH. We determine that PKA kinase activity is downstream of both TBPH and Pld and that overexpression of the PKA target CrebA can rescue TBPH mislocalization. These findings suggest a model whereby increasing cAMP/PKA signaling can ameliorate the molecular and functional effects of pathological TDP-43.

The elicitor VP2 from Verticillium dahliae triggers defence response in cotton.

Verticillium dahliae is a widespread and destructive soilborne vascular pathogenic fungus that causes serious diseases in dicot plants. Here, comparative transcriptome analysis showed that the number of genes upregulated in defoliating pathotype V991 was significantly higher than in the non-defoliating pathotype 1cd3-2 during the early response of cotton. Combined with analysis of the secretome during the V991-cotton interaction, an elicitor VP2 was identified, which was highly upregulated at the early stage of V991 invasion, but was barely expressed during the 1cd3-2-cotton interaction. Full-length VP2 could induce cell death in several plant species, and which was dependent on NbBAK1 but not on NbSOBIR1 in N. benthamiana. Knock-out of VP2 attenuated the pathogenicity of V991. Furthermore, overexpression of VP2 in cotton enhanced resistance to V. dahliae without causing abnormal plant growth and development. Several genes involved in JA, SA and lignin synthesis were significantly upregulated in VP2-overexpressing cotton. The contents of JA, SA, and lignin were also significantly higher than in the wild-type control. In summary, the identified elicitor VP2, recognized by the receptor in the plant membrane, triggers the cotton immune response and enhances disease resistance.

Artificial intelligence-based digital scores of stromal tumour-infiltrating lymphocytes and tumour-associated stroma predict disease-specific survival in triple-negative breast cancer.

Triple-negative breast cancer (TNBC) is known to have a relatively poor outcome with variable prognoses, raising the need for more informative risk stratification. We investigated a set of digital, artificial intelligence (AI)-based spatial tumour microenvironment (sTME) features and explored their prognostic value in TNBC. After performing tissue classification on digitised haematoxylin and eosin (H&E) slides of TNBC cases, we employed a deep learning-based algorithm to segment tissue regions into tumour, stroma, and lymphocytes in order to compute quantitative features concerning the spatial relationship of tumour with lymphocytes and stroma. The prognostic value of the digital features was explored using survival analysis with Cox proportional hazard models in a cross-validation setting on two independent international multi-centric TNBC cohorts: The Australian Breast Cancer Tissue Bank (AUBC) cohort (n = 318) and The Cancer Genome Atlas Breast Cancer (TCGA) cohort (n = 111). The proposed digital stromal tumour-infiltrating lymphocytes (Digi-sTILs) score and the digital tumour-associated stroma (Digi-TAS) score were found to carry strong prognostic value for disease-specific survival, with the Digi-sTILs and Digi-TAS scores giving C-index values of 0.65 (p = 0.0189) and 0.60 (p = 0.0437), respectively, on the TCGA cohort as a validation set. Combining the Digi-sTILs feature with the patient's positivity status for axillary lymph nodes yielded a C-index of 0.76 on unseen validation cohorts. We surmise that the proposed digital features could potentially be used for better risk stratification and management of TNBC patients. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

A digital score of tumour-associated stroma infiltrating lymphocytes predicts survival in head and neck squamous cell carcinoma.

The infiltration of T-lymphocytes in the stroma and tumour is an indication of an effective immune response against the tumour, resulting in better survival. In this study, our aim was to explore the prognostic significance of tumour-associated stroma infiltrating lymphocytes (TASILs) in head and neck squamous cell carcinoma (HNSCC) through an AI-based automated method. A deep learning-based automated method was employed to segment tumour, tumour-associated stroma, and lymphocytes in digitally scanned whole slide images of HNSCC tissue slides. The spatial patterns of lymphocytes and tumour-associated stroma were digitally quantified to compute the tumour-associated stroma infiltrating lymphocytes score (TASIL-score). Finally, the prognostic significance of the TASIL-score for disease-specific and disease-free survival was investigated using the Cox proportional hazard analysis. Three different cohorts of haematoxylin and eosin (H&E)-stained tissue slides of HNSCC cases (n = 537 in total) were studied, including publicly available TCGA head and neck cancer cases. The TASIL-score carries prognostic significance (p = 0.002) for disease-specific survival of HNSCC patients. The TASIL-score also shows a better separation between low- and high-risk patients compared with the manual tumour-infiltrating lymphocytes (TILs) scoring by pathologists for both disease-specific and disease-free survival. A positive correlation of TASIL-score with molecular estimates of CD8+ T cells was also found, which is in line with existing findings. To the best of our knowledge, this is the first study to automate the quantification of TASILs from routine H&E slides of head and neck cancer. Our TASIL-score-based findings are aligned with the clinical knowledge, with the added advantages of objectivity, reproducibility, and strong prognostic value. Although we validated our method on three different cohorts (n = 537 cases in total), a comprehensive evaluation on large multicentric cohorts is required before the proposed digital score can be adopted in clinical practice. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Artificial Intelligence-based methods in head and neck cancer diagnosis: an overview.

BACKGROUND: This paper reviews recent literature employing Artificial Intelligence/Machine Learning (AI/ML) methods for diagnostic evaluation of head and neck cancers (HNC) using automated image analysis. METHODS: Electronic database searches using MEDLINE via OVID, EMBASE and Google Scholar were conducted to retrieve articles using AI/ML for diagnostic evaluation of HNC (2009-2020). No restrictions were placed on the AI/ML method or imaging modality used. RESULTS: In total, 32 articles were identified. HNC sites included oral cavity (n = 16), nasopharynx (n = 3), oropharynx (n = 3), larynx (n = 2), salivary glands (n = 2), sinonasal (n = 1) and in five studies multiple sites were studied. Imaging modalities included histological (n = 9), radiological (n = 8), hyperspectral (n = 6), endoscopic/clinical (n = 5), infrared thermal (n = 1) and optical (n = 1). Clinicopathologic/genomic data were used in two studies. Traditional ML methods were employed in 22 studies (69%), deep learning (DL) in eight studies (25%) and a combination of these methods in two studies (6%). CONCLUSIONS: There is an increasing volume of studies exploring the role of AI/ML to aid HNC detection using a range of imaging modalities. These methods can achieve high degrees of accuracy that can exceed the abilities of human judgement in making data predictions. Large-scale multi-centric prospective studies are required to aid deployment into clinical practice.

Deep learning based digital cell profiles for risk stratification of urine cytology images.

Urine cytology is a test for the detection of high-grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of atypical and malignant cells in urine cytology is a challenging task and is an essential part of identifying different diagnosis with low-risk and high-risk malignancy. Computer-assisted identification of malignancy in urine cytology can be complementary to the clinicians for treatment management and in providing advice for carrying out further tests. In this study, we presented a method for identifying atypical and malignant cells followed by their profiling to predict the risk of diagnosis automatically. For cell detection and classification, we employed two different deep learning-based approaches. Based on the best performing network predictions at the cell level, we identified low-risk and high-risk cases using the count of atypical cells and the total count of atypical and malignant cells. The area under the receiver operating characteristic (ROC) curve shows that a total count of atypical and malignant cells is comparably better at diagnosis as compared to the count of malignant cells only. We obtained area under the ROC curve with the count of malignant cells and the total count of atypical and malignant cells as 0.81 and 0.83, respectively. Our experiments also demonstrate that the digital risk could be a better predictor of the final histopathology-based diagnosis. We also analyzed the variability in annotations at both cell and whole slide image level and also explored the possible inherent rationales behind this variability.

Suppression of tryptophan synthase activates cotton immunity by triggering cell death via promoting SA synthesis.

Primary metabolism plays an important role in plant growth and development, however the relationship between primary metabolism and the adaptive immune response is largely unknown. Here, we employed RNA interference (RNAi), virus-induced gene silencing (VIGS) technology, phytohormone profiling, genetic studies, and transcriptome and metabolome analysis to investigate the function of the tryptophan synthesis pathway in the resistance of cotton to V. dahliae. We found that knock-down of GbTSA1 (Tryptophan Synthase α) and GbTSB1 (tryptophan synthase ß) induced a spontaneous cell death phenotype in a salicylic acid (SA)-dependent manner and enhanced resistance to V. dahliae in cotton plants. Metabolome analysis showed that indole and indolic metabolites were highly accumulated in GbTSA1- or GbTSB1-silenced plants. Transcriptomic analysis showed that exogenous indole promotes the expression levels of genes involved in SA synthesis and the defense response. Similarly, indole application strongly enhanced cotton resistance to V. dahliae. These results suggested that metabolic intermediates in the Trp synthesis pathway may be a signal to activate SA synthesis. These results also provided a strategy to elicit plant defense responses by the application of indole.

High day and night temperatures distinctively disrupt fatty acid and jasmonic acid metabolism, inducing male sterility in cotton.

High temperature stress is an inevitable environmental factor in certain geographical regions. To study the effect of day and night high temperature stress on male reproduction, the heat-sensitive cotton line H05 was subjected to high temperature stress. High day/normal night (HN) and normal day/high night (NH) temperature treatments were compared with normal day/normal night (NN) temperature as a control. At the anther dehiscence stage, significant differences were observed, with a reduction in flower size and filament length, and sterility in pollen, seen in NH more than in HN. A total of 36 806 differentially expressed genes were screened, which were mainly associated with fatty acid and jasmonic acid (JA) metabolic pathways. Fatty acid and JA contents were reduced more in NH than HN. Under NH, ACYL-COA OXIDASE 2 (ACO2), a JA biosynthesis gene, was down-regulated. Interestingly, aco2 CRISPR-Cas9 mutants showed male sterility under the NN condition. The exogenous application of methyl jasmonate to early-stage buds of mutants rescued the sterile pollen and indehiscent anther phenotypes at the late stage. These data show that high temperature at night may affect fatty acid and JA metabolism in anthers by suppressing GhACO2 and generate male sterility more strongly than high day temperature.

GbSOBIR1 confers Verticillium wilt resistance by phosphorylating the transcriptional factor GbbHLH171 in Gossypium barbadense.

Receptor-like kinases (RLKs) are important components of plant innate immunity. Although recent studies have revealed that the RLK suppressor of BIR1-1 (SOBIR1) can interact with multiple receptor-like proteins and is required for resistance against fungal pathogens, how the signal is transduced and triggers immune responses remains enigmatic. In this study, we identified a defence-related RLK from Gossypium barbadense (designated GbSOBIR1) and investigated its functional mechanism. Expression of the GbSOBIR1 gene is ubiquitous in cotton plants and is induced by Verticillium dahliae inoculation. Knock-down of GbSOBIR1 by virus-induced gene silencing resulted in attenuated resistance of cotton plants to V. dahliae, while heterologous overexpression of GbSOBIR1 in Arabidopsis improves resistance. We also found that the kinase region of GbSOBIR1 interacts with a basic helix-loop-helix (bHLH) transcription factor identified as GbbHLH171 in a yeast-two-hybrid screen. GbbHLH171 could interact with and be phosphorylated by GbSOBIR1 in vitro and in vivo and contributes positively to the resistance of cotton against V. dahliae. Furthermore, we found that this phosphorylation is essential to the transcriptional activity and functional role of GbbHLH171. We also show by spectrometric analysis and site-directed mutagenesis that Ser413 is the GbSOBIR1-mediated phosphorylation site of GbbHLH171. These results demonstrate that GbSOBIR1 interacts with GbbHLH171 and plays a critical role in cotton resistance to V. dahliae.

Microbiome Diversity in Cotton Rhizosphere Under Normal and Drought Conditions.

Climate change contributes to drought stress and subsequently affects crop growth, development, and yield. The microbial community, such as fungi and bacteria in the rhizosphere, is of special importance to plant productivity. In this study, soil collected from a cotton research field was used to grow cotton plants (Gossypium hirsutum cv. Jin668) under controlled environment conditions. Drought stress was applied at flowering stage, while control plants were regularly watered. At the same time, the soil without plants was also subjected to drought, while control pots were regularly watered. The soil was collected in sterilized tubes and microbial DNA was isolated and high-throughput sequencing of 16S rRNA genes was carried out. The alpha diversity of bacteria community significantly increased in the soil with cotton plants compared to the soil without cotton plants. Taxonomic analysis revealed that the bacterial community structure of the cotton rhizosphere predominantly consisted of the phyla Proteobacteria (31.7%), Actinobacteria (29.6%), Gemmatimonadetes (9.8%), Chloroflexi (9%), Cyanobacteria (5.6%), and Acidobacteria. In the drought-treated rhizosphere, Chloroflexi and Gemmatimonadetes were the dominant phyla. This study reveals that the cotton rhizosphere has a rich pool of bacterial communities even under drought stress, and which may improve drought tolerance in plants. These data will underpin future improvement of drought tolerance of cotton via the soil microbial community.

Genome-wide identification of lipoxygenase gene family in cotton and functional characterization in response to abiotic stresses.

BACKGROUND: Plant lipoxygenase (LOX) genes are members of the non-haeme iron-containing dioxygenase family that catalyze the oxidation of polyunsaturated fatty acids into functionally diverse oxylipins. The LOX family genes have been extensively studied under biotic and abiotic stresses, both in model and non-model plant species; however, information on their roles in cotton is still limited. RESULTS: A total of 64 putative LOX genes were identified in four cotton species (Gossypium (G. hirsutum, G. barbadense, G. arboreum, and G. raimondii)). In the phylogenetic tree, these genes were clustered into three categories (9-LOX, 13-LOX type I, and 13-LOX type II). Segmental duplication of putative LOX genes was observed between homologues from A2 to At and D5 to Dt hinting at allopolyploidy in cultivated tetraploid species (G. hirsutum and G. barbadense). The structure and motif composition of GhLOX genes appears to be relatively conserved among the subfamilies. Moreover, many cis-acting elements related to growth, stresses, and phytohormone signaling were found in the promoter regions of GhLOX genes. Gene expression analysis revealed that all GhLOX genes were induced in at least two tissues and the majority of GhLOX genes were up-regulated in response to heat and salinity stress. Specific expressions of some genes in response to exogenous phytohormones suggest their potential roles in regulating growth and stress responses. In addition, functional characterization of two candidate genes (GhLOX12 and GhLOX13) using virus induced gene silencing (VIGS) approach revealed their increased sensitivity to salinity stress in target gene-silenced cotton. Compared with controls, target gene-silenced plants showed significantly higher chlorophyll degradation, higher H2O2, malondialdehyde (MDA) and proline accumulation but significantly reduced superoxide dismutase (SOD) activity, suggesting their reduced ability to effectively degrade accumulated reactive oxygen species (ROS). CONCLUSION: This genome-wide study provides a systematic analysis of the cotton LOX gene family using bioinformatics tools. Differential expression patterns of cotton LOX genes in different tissues and under various abiotic stress conditions provide insights towards understanding the potential functions of candidate genes. Beyond the findings reported here, our study provides a basis for further uncovering the biological roles of LOX genes in cotton development and adaptation to stress conditions.

GhUMC1, a blue copper-binding protein, regulates lignin synthesis and cotton immune response.

Verticillium wilt caused by the soil-borne fungus Verticillium dahliae is a serious problem for the sustainable production of cotton. The mechanism of cotton resistance to V. dahliae is unclear, which makes it is difficult to improve cotton resistance breeding. In this study, we characterized an umecyanin-like gene GhUMC1 in cotton, which is homologous to the AtBCB gene in Arabidopsis. It is predominantly expressed in roots and responds to pathogen infection. Knock-down of GhUMC1 increases plant susceptibility to V. dahliae. Expression levels of genes in the JA and SA signaling pathways in roots were down-regulated in GhUMC1-silenced plants. The transcripts of lignin synthesis genes, such as C4H, HCT, CCoAOMT and CAD, were also decreased in GhUMC1 knock-down seedlings, as was lignin content. Interestingly, knock-down of the GhUMC1 also decreased the contents of H202 compared with the control. Our results suggest that GhUMC1 is involved in cotton resistance to V. dahliae by the regulation of the JA signaling pathway and lignin metabolism.

A comparative genomics approach revealed evolutionary dynamics of microsatellite imperfection and conservation in genus Gossypium.

BACKGROUND: Ongoing molecular processes in a cell could target microsatellites, a kind of repetitive DNA, owing to length variations and motif imperfection. Mutational mechanisms underlying such kind of genetic variations have been extensively investigated in diverse organisms. However, obscure impact of ploidization, an evolutionary process of genome content duplication prevails mostly in plants, on non-coding DNA is poorly understood. RESULTS: Genome sequences of diversely originated plant species were examined for genome-wide motif imperfection pattern, and various analytical tools were employed to canvass characteristic relationships among repeat density, imperfection and length of microsatellites. Moreover, comparative genomics approach aided in exploration of microsatellites conservation footprints in Gossypium evolution. Based on our results, motif imperfection in repeat length was found intricately related to genomic abundance of imperfect microsatellites among 13 genomes. Microsatellite decay estimation depicted slower decay of long motif repeats which led to predominant abundance of 5-nt repeat motif in Gossypium species. Short motif repeats exhibited rapid decay through the evolution of Gossypium lineage ensuing drastic decrease of 2-nt repeats, of which, "AT" motif type dilapidated in cultivated tetraploids of cotton. CONCLUSION: The outcome could be a directive to explore comparative evolutionary footprints of simple non-coding genetic elements i.e., repeat elements, through the evolution of genus-specific characteristics in cotton genomes.

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer.

Importance: Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Objective: Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting. Design, Setting, and Participants: Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Exposures: Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. Main Outcomes and Measures: The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. Results: The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC). Conclusions and Relevance: In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

Functional characterization of cotton genes responsive to Verticillium dahliae through bioinformatics and reverse genetics strategies.

Verticillium wilt causes dramatic cotton yield loss in China. Although some genes or biological processes involved in the interaction between cotton and Verticillium dahliae have been identified, the molecular mechanism of cotton resistance to this disease is still poorly understood. The basic innate immune response for defence is somewhat conserved among plant species to defend themselves in complex environments, which makes it possible to characterize genes involved in cotton immunity based on information from model plants. With the availability of Arabidopsis databases, a data-mining strategy accompanied by virus-induced gene silencing (VIGS) and heterologous expression were adopted in cotton and tobacco, respectively, for global screening and gene function characterization. A total of 232 Arabidopsis genes putatively involved in basic innate immunity were screened as candidate genes, and bioinformatic analysis suggested a role of these genes in the immune response. In total, 38 homologous genes from cotton were singled out to characterize their response to V. dahliae and methyl jasmonate treatment through quantitative real-time PCR. The results revealed that 24 genes were differentially regulated by pathogen inoculation, and most of these genes responded to both Verticillium infection and jasmonic acid stimuli. Furthermore, the efficiency of the strategy was illustrated by the functional identification of six candidate genes via heterologous expression in tobacco or a knock-down approach using VIGS in cotton. Functional categorization of these 24 differentially expressed genes as well as functional analysis suggest that reactive oxygen species, salicylic acid- and jasmonic acid-signalling pathways are involved in the cotton disease resistance response to V. dahliae. Our data demonstrate how information from model plants can allow the rapid translation of information into non-model species without complete genome sequencing, via high-throughput screening and functional identification of target genes based on data-mining and VIGS.

Autophagy: A New Avenue and Biochemical Mechanisms to Mitigate the Climate Change.

Autophagy is a preserved process in eukaryotes that allows large material degeneration and nutrient recovery via vacuoles or lysosomes in cytoplasm. Autophagy starts from the moment of induction during the formation of a phagophore. Degradation may occur in the autophagosomes even without fusion with lysosome or vacuole, particularly in microautophagosomes. This process is arbitrated by the conserved machinery of basic autophagy-related genes (ATGs). In selective autophagy, specific materials are recruited by autophagosomes via receptors. Selective autophagy targets a vast variety of cellular components for degradation, i.e., old or damaged organelles, aggregates, and inactive or misfolded proteins. In optimal conditions, autophagy in plants ensures cellular homeostasis, proper plant growth, and fitness. Moreover, autophagy is essential during stress responses in plants and aids in survival of plants. Several biotic and abiotic stresses, i.e., pathogen infection, nutrient deficiency, plant senescence, heat stress, drought, osmotic stress, and hypoxia induce autophagy in plants. Cell death is not a stress, which induces autophagy but in contrast, sometimes it is a consequence of autophagy. In this way, autophagy plays a vital role in plant survival during harsh environmental conditions by maintaining nutrient concentration through elimination of useless cellular components. This review discussed the recent advances regarding regulatory functions of autophagy under normal and stressful conditions in plants and suggests future prospects in mitigating climate change. Autophagy in plants offers a viable way to increase plant resilience to climate change by increasing stress tolerance and nutrient usage efficiency.

MAPS: pathologist-level cell type annotation from tissue images through machine learning.

Highly multiplexed protein imaging is emerging as a potent technique for analyzing protein distribution within cells and tissues in their native context. However, existing cell annotation methods utilizing high-plex spatial proteomics data are resource intensive and necessitate iterative expert input, thereby constraining their scalability and practicality for extensive datasets. We introduce MAPS (Machine learning for Analysis of Proteomics in Spatial biology), a machine learning approach facilitating rapid and precise cell type identification with human-level accuracy from spatial proteomics data. Validated on multiple in-house and publicly available MIBI and CODEX datasets, MAPS outperforms current annotation techniques in terms of speed and accuracy, achieving pathologist-level precision even for typically challenging cell types, including tumor cells of immune origin. By democratizing rapidly deployable and scalable machine learning annotation, MAPS holds significant potential to expedite advances in tissue biology and disease comprehension.

Demographic bias in misdiagnosis by computational pathology models.

Despite increasing numbers of regulatory approvals, deep learning-based computational pathology systems often overlook the impact of demographic factors on performance, potentially leading to biases. This concern is all the more important as computational pathology has leveraged large public datasets that underrepresent certain demographic groups. Using publicly available data from The Cancer Genome Atlas and the EBRAINS brain tumor atlas, as well as internal patient data, we show that whole-slide image classification models display marked performance disparities across different demographic groups when used to subtype breast and lung carcinomas and to predict IDH1 mutations in gliomas. For example, when using common modeling approaches, we observed performance gaps (in area under the receiver operating characteristic curve) between white and Black patients of 3.0% for breast cancer subtyping, 10.9% for lung cancer subtyping and 16.0% for IDH1 mutation prediction in gliomas. We found that richer feature representations obtained from self-supervised vision foundation models reduce performance variations between groups. These representations provide improvements upon weaker models even when those weaker models are combined with state-of-the-art bias mitigation strategies and modeling choices. Nevertheless, self-supervised vision foundation models do not fully eliminate these discrepancies, highlighting the continuing need for bias mitigation efforts in computational pathology. Finally, we demonstrate that our results extend to other demographic factors beyond patient race. Given these findings, we encourage regulatory and policy agencies to integrate demographic-stratified evaluation into their assessment guidelines.

Towards a general-purpose foundation model for computational pathology.

Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks, requiring the objective characterization of histopathological entities from whole-slide images (WSIs). The high resolution of WSIs and the variability of morphological features present significant challenges, complicating the large-scale annotation of data for high-performance applications. To address this challenge, current efforts have proposed the use of pretrained image encoders through transfer learning from natural image datasets or self-supervised learning on publicly available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using more than 100 million images from over 100,000 diagnostic H&E-stained WSIs (>77 TB of data) across 20 major tissue types. The model was evaluated on 34 representative CPath tasks of varying diagnostic difficulty. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient artificial intelligence models that can generalize and transfer to a wide range of diagnostically challenging tasks and clinical workflows in anatomic pathology.

Epstein-Barr Virus Orchestrates Spatial Reorganization and Immunomodulation within the Classic Hodgkin Lymphoma Tumor Microenvironment.

Classic Hodgkin Lymphoma (cHL) is a tumor composed of rare malignant Hodgkin and Reed-Sternberg (HRS) cells nested within a T-cell rich inflammatory immune infiltrate. cHL is associated with Epstein-Barr Virus (EBV) in 25% of cases. The specific contributions of EBV to the pathogenesis of cHL remain largely unknown, in part due to technical barriers in dissecting the tumor microenvironment (TME) in high detail. Herein, we applied multiplexed ion beam imaging (MIBI) spatial pro-teomics on 6 EBV-positive and 14 EBV-negative cHL samples. We identify key TME features that distinguish between EBV-positive and EBV-negative cHL, including the relative predominance of memory CD8 T cells and increased T-cell dysfunction as a function of spatial proximity to HRS cells. Building upon a larger multi-institutional cohort of 22 EBV-positive and 24 EBV-negative cHL samples, we orthogonally validated our findings through a spatial multi-omics approach, coupling whole transcriptome capture with antibody-defined cell types for tu-mor and T-cell populations within the cHL TME. We delineate contrasting transcriptomic immunological signatures between EBV-positive and EBV-negative cases that differently impact HRS cell proliferation, tumor-immune interactions, and mecha-nisms of T-cell dysregulation and dysfunction. Our multi-modal framework enabled a comprehensive dissection of EBV-linked reorganization and immune evasion within the cHL TME, and highlighted the need to elucidate the cellular and molecular fac-tors of virus-associated tumors, with potential for targeted therapeutic strategies.