RESUMEN
Background: Prostate cancer (PCa) is among the most common cancers in men and its diagnosis requires the histopathological evaluation of biopsies by human experts. While several recent artificial intelligence-based (AI) approaches have reached human expert-level PCa grading, they often display significantly reduced performance on external datasets. This reduced performance can be caused by variations in sample preparation, for instance the staining protocol, section thickness, or scanner used. Another limiting factor of contemporary AI-based PCa grading is the prediction of ISUP grades, which leads to the perpetuation of human annotation errors. Methods: We developed the prostate cancer aggressiveness index (PCAI), an AI-based PCa detection and grading framework that is trained on objective patient outcome, rather than subjective ISUP grades. We designed PCAI as a clinical application, containing algorithmic modules that offer robustness to data variation, medical interpretability, and a measure of prediction confidence. To train and evaluate PCAI, we generated a multicentric, retrospective, observational trial consisting of six cohorts with 25,591 patients, 83,864 images, and 5 years of median follow-up from 5 different centers and 3 countries. This includes a high-variance dataset of 8,157 patients and 28,236 images with variations in sample thickness, staining protocol, and scanner, allowing for the systematic evaluation and optimization of model robustness to data variation. The performance of PCAI was assessed on three external test cohorts from two countries, comprising 2,255 patients and 9,437 images. Findings: Using our high-variance datasets, we show how differences in sample processing, particularly slide thickness and staining time, significantly reduce the performance of AI-based PCa grading by up to 6.2 percentage points in the concordance index (C-index). We show how a select set of algorithmic improvements, including domain adversarial training, conferred robustness to data variation, interpretability, and a measure of credibility to PCAI. These changes lead to significant prediction improvement across two biopsy cohorts and one TMA cohort, systematically exceeding expert ISUP grading in C-index and AUROC by up to 22 percentage points. Interpretation: Data variation poses serious risks for AI-based histopathological PCa grading, even when models are trained on large datasets. Algorithmic improvements for model robustness, interpretability, credibility, and training on high-variance data as well as outcome-based severity prediction gives rise to robust models with above ISUP-level PCa grading performance.
RESUMEN
Amyotrophic lateral sclerosis (ALS) is a debilitating motor neuron disease and lacks effective disease-modifying treatments. This study utilizes a comprehensive multiomic approach to investigate the early and sex-specific molecular mechanisms underlying ALS. By analyzing the prefrontal cortex of 51 patients with sporadic ALS and 50 control subjects, alongside four transgenic mouse models (C9orf72-, SOD1-, TDP-43-, and FUS-ALS), we have uncovered significant molecular alterations associated with the disease. Here, we show that males exhibit more pronounced changes in molecular pathways compared to females. Our integrated analysis of transcriptomes, (phospho)proteomes, and miRNAomes also identified distinct ALS subclusters in humans, characterized by variations in immune response, extracellular matrix composition, mitochondrial function, and RNA processing. The molecular signatures of human subclusters were reflected in specific mouse models. Our study highlighted the mitogen-activated protein kinase (MAPK) pathway as an early disease mechanism. We further demonstrate that trametinib, a MAPK inhibitor, has potential therapeutic benefits in vitro and in vivo, particularly in females, suggesting a direction for developing targeted ALS treatments.
Asunto(s)
Esclerosis Amiotrófica Lateral , Modelos Animales de Enfermedad , Sistema de Señalización de MAP Quinasas , Ratones Transgénicos , Esclerosis Amiotrófica Lateral/genética , Esclerosis Amiotrófica Lateral/tratamiento farmacológico , Esclerosis Amiotrófica Lateral/metabolismo , Humanos , Femenino , Animales , Masculino , Ratones , Sistema de Señalización de MAP Quinasas/efectos de los fármacos , Piridonas/farmacología , Piridonas/uso terapéutico , Proteína FUS de Unión a ARN/metabolismo , Proteína FUS de Unión a ARN/genética , Corteza Prefrontal/metabolismo , Transcriptoma , Superóxido Dismutasa-1/genética , Superóxido Dismutasa-1/metabolismo , Proteínas de Unión al ADN/metabolismo , Proteínas de Unión al ADN/genética , Persona de Mediana Edad , MicroARNs/genética , MicroARNs/metabolismo , Proteína C9orf72/genética , Proteína C9orf72/metabolismo , Caracteres Sexuales , Anciano , Factores Sexuales , PirimidinonasRESUMEN
Neural-tumor interactions drive glioma growth as evidenced in preclinical models, but clinical validation is limited. We present an epigenetically defined neural signature of glioblastoma that independently predicts patients' survival. We use reference signatures of neural cells to deconvolve tumor DNA and classify samples into low- or high-neural tumors. High-neural glioblastomas exhibit hypomethylated CpG sites and upregulation of genes associated with synaptic integration. Single-cell transcriptomic analysis reveals a high abundance of malignant stemcell-like cells in high-neural glioblastoma, primarily of the neural lineage. These cells are further classified as neural-progenitor-cell-like, astrocyte-like and oligodendrocyte-progenitor-like, alongside oligodendrocytes and excitatory neurons. In line with these findings, high-neural glioblastoma cells engender neuron-to-glioma synapse formation in vitro and in vivo and show an unfavorable survival after xenografting. In patients, a high-neural signature is associated with decreased overall and progression-free survival. High-neural tumors also exhibit increased functional connectivity in magnetencephalography and resting-state magnet resonance imaging and can be detected via DNA analytes and brain-derived neurotrophic factor in patients' plasma. The prognostic importance of the neural signature was further validated in patients diagnosed with diffuse midline glioma. Our study presents an epigenetically defined malignant neural signature in high-grade gliomas that is prognostically relevant. High-neural gliomas likely require a maximized surgical resection approach for improved outcomes.
Asunto(s)
Neoplasias Encefálicas , Epigénesis Genética , Glioma , Humanos , Pronóstico , Glioma/genética , Glioma/patología , Neoplasias Encefálicas/genética , Neoplasias Encefálicas/patología , Metilación de ADN/genética , Animales , Ratones , Masculino , Femenino , Regulación Neoplásica de la Expresión Génica , Glioblastoma/genética , Glioblastoma/patología , Persona de Mediana Edad , Neuronas/patología , Neuronas/metabolismo , Adulto , Análisis de la Célula Individual , Línea Celular Tumoral , Transcriptoma , Clasificación del TumorRESUMEN
Cell deconvolution is the estimation of cell type fractions and cell type-specific gene expression from mixed data. An unmet challenge in cell deconvolution is the scarcity of realistic training data and the domain shift often observed in synthetic training data. Here, we show that two novel deep neural networks with simultaneous consistency regularization of the target and training domains significantly improve deconvolution performance. Our algorithm, DISSECT, outperforms competing algorithms in cell fraction and gene expression estimation by up to 14 percentage points. DISSECT can be easily adapted to other biomedical data types, as exemplified by our proteomic deconvolution experiments.
Asunto(s)
Algoritmos , Humanos , Proteómica/métodos , Perfilación de la Expresión Génica/métodos , Aprendizaje Profundo , Redes Neurales de la ComputaciónRESUMEN
The longitudinal transition of phenotypes is pivotal in glioblastoma treatment resistance and DNA methylation emerged as an important tool for classifying glioblastoma phenotypes. We aimed to characterize DNA methylation subclass heterogeneity during progression and assess its clinical impact. Matched tissues from 47 glioblastoma patients were subjected to DNA methylation profiling, including CpG-site alterations, tissue and serum deconvolution, mass spectrometry, and immunoassay. Effects of clinical characteristics on temporal changes and outcomes were studied. Among 47 patients, 8 (17.0%) had non-matching classifications at recurrence. In the remaining 39 cases, 28.2% showed dominant DNA methylation subclass transitions, with 72.7% being a mesenchymal subclass. In general, glioblastomas with a subclass transition showed upregulated metabolic processes. Newly diagnosed glioblastomas with mesenchymal transition displayed increased stem cell-like states and decreased immune components at diagnosis and exhibited elevated immune signatures and cytokine levels in serum. In contrast, tissue of recurrent glioblastomas with mesenchymal transition showed increased immune components but decreased stem cell-like states. Survival analyses revealed comparable outcomes for patients with and without subclass transitions. This study demonstrates a temporal heterogeneity of DNA methylation subclasses in 28.2% of glioblastomas, not impacting patient survival. Changes in cell state composition associated with subclass transition may be crucial for recurrent glioblastoma targeted therapies.
Asunto(s)
Neoplasias Encefálicas , Glioblastoma , Humanos , Glioblastoma/genética , Glioblastoma/terapia , Metilación de ADN , Recurrencia Local de Neoplasia/genética , Análisis de SupervivenciaRESUMEN
Background: 5-aminolevulinic acid (5-ALA) fluorescence-guided resection increases the percentage of complete CNS tumor resections and improves the progression-free survival of IDH-wildtype glioblastoma patients. A small subset of IDH-wildtype glioblastoma shows no 5-ALA fluorescence. An explanation for these cases is missing. In this study, we used DNA methylation profiling to further characterize non-fluorescent glioblastomas. Methods: Patients with newly diagnosed and recurrent IDH-wildtype glioblastoma that underwent surgery were analyzed. The intensity of intraoperative 5-ALA fluorescence was categorized as non-visible or visible. DNA was extracted from tumors and genome-wide DNA methylation patterns were analyzed using Illumina EPIC (850k) arrays. Furthermore, 5-ALA intensity was measured by flow cytometry on human gliomasphere lines (BT112 and BT145). Results: Of 74 included patients, 12 (16.2%) patients had a non-fluorescent glioblastoma, which were compared to 62 glioblastomas with 5-ALA fluorescence. Clinical characteristics were equally distributed between both groups. We did not find significant differences between DNA methylation subclasses and 5-ALA fluorescence (P = .24). The distribution of cells of the tumor microenvironment was not significantly different between the non-fluorescent and fluorescent tumors. Copy number variations in EGFR and simultaneous EGFRvIII expression were strongly associated with 5-ALA fluorescence since all non-fluorescent glioblastomas were EGFR-amplified (P < .01). This finding was also demonstrated in recurrent tumors. Similarly, EGFR-amplified glioblastoma cell lines showed no 5-ALA fluorescence after 24 h of incubation. Conclusions: Our study demonstrates an association between non-fluorescent IDH-wildtype glioblastomas and EGFR gene amplification which should be taken into consideration for recurrent surgery and future studies investigating EGFR-amplified gliomas.
RESUMEN
BACKGROUND: Single-cell sequencing provides detailed insights into biological processes including cell differentiation and identity. While providing deep cell-specific information, the method suffers from technical constraints, most notably a limited number of expressed genes per cell, which leads to suboptimal clustering and cell type identification. RESULTS: Here, we present DISCERN, a novel deep generative network that precisely reconstructs missing single-cell gene expression using a reference dataset. DISCERN outperforms competing algorithms in expression inference resulting in greatly improved cell clustering, cell type and activity detection, and insights into the cellular regulation of disease. We show that DISCERN is robust against differences between batches and is able to keep biological differences between batches, which is a common problem for imputation and batch correction algorithms. We use DISCERN to detect two unseen COVID-19-associated T cell types, cytotoxic CD4+ and CD8+ Tc2 T helper cells, with a potential role in adverse disease outcome. We utilize T cell fraction information of patient blood to classify mild or severe COVID-19 with an AUROC of 80% that can serve as a biomarker of disease stage. DISCERN can be easily integrated into existing single-cell sequencing workflow. CONCLUSIONS: Thus, DISCERN is a flexible tool for reconstructing missing single-cell gene expression using a reference dataset and can easily be applied to a variety of data sets yielding novel insights, e.g., into disease mechanisms.
Asunto(s)
COVID-19 , Humanos , COVID-19/genética , Algoritmos , Ciclo Celular , Diferenciación Celular , Análisis por ConglomeradosRESUMEN
Neural-tumor interactions drive glioma growth as evidenced in preclinical models, but clinical validation is nascent. We present an epigenetically defined neural signature of glioblastoma that independently affects patients' survival. We use reference signatures of neural cells to deconvolve tumor DNA and classify samples into low- or high-neural tumors. High-neural glioblastomas exhibit hypomethylated CpG sites and upregulation of genes associated with synaptic integration. Single-cell transcriptomic analysis reveals high abundance of stem cell-like malignant cells classified as oligodendrocyte precursor and neural precursor cell-like in high-neural glioblastoma. High-neural glioblastoma cells engender neuron-to-glioma synapse formation in vitro and in vivo and show an unfavorable survival after xenografting. In patients, a high-neural signature associates with decreased survival as well as increased functional connectivity and can be detected via DNA analytes and brain-derived neurotrophic factor in plasma. Our study presents an epigenetically defined malignant neural signature in high-grade gliomas that is prognostically relevant.
Asunto(s)
Neoplasias Encefálicas , Glioblastoma , Glioma , Humanos , Glioblastoma/tratamiento farmacológico , Glioblastoma/genética , Metilación de ADN , Glioma/genética , Neoplasias Encefálicas/tratamiento farmacológico , Neoplasias Encefálicas/genética , Isocitrato Deshidrogenasa/genética , MutaciónRESUMEN
Differences in immune response between men and women may influence the outcome of infectious diseases. Intestinal infection with Entamoeba histolytica leads to hepatic amebiasis, which is more common in males. Previously, we reported that innate immune cells contribute to liver damage in males in the murine model for hepatic amebiasis. Here, we focused on the influences of sex and androgens on neutrophils in particular. Infection associated with neutrophil accumulation in the liver was higher in male than in female mice and further increased after testosterone treatment in both sexes. Compared with female neutrophils, male neutrophils exhibit a more immature and less activated status, as evidenced by a lower proinflammatory N1-like phenotype and deconvolution, decreased gene expression of type I and type II interferon stimulated genes (ISGs) as well as downregulation of signaling pathways related to neutrophil activation. Neutrophils from females showed higher protein expression of the type I ISG viperin/RSAD2 during infection, which decreased by testosterone substitution. Moreover, ex vivo stimulation of human neutrophils revealed lower production of RSAD2 in neutrophils from men compared with women. These findings indicate that sex-specific effects on neutrophil physiology associated with maturation and type I IFN responsiveness might be important in the outcome of hepatic amebiasis.