RESUMO
Clear cell renal cell carcinoma (ccRCC) is molecularly heterogeneous, immune infiltrated, and selectively sensitive to immune checkpoint inhibition (ICI). However, the joint tumor-immune states that mediate ICI response remain elusive. We develop spatially aware deep-learning models of tumor and immune features to learn representations of ccRCC tumors using diagnostic whole-slide images (WSIs) in untreated and treated contexts (n = 1,102 patients). We identify patterns of grade heterogeneity in WSIs not achievable through human pathologist analysis, and these graph-based "microheterogeneity" structures associate with PBRM1 loss of function and with patient outcomes. Joint analysis of tumor phenotypes and immune infiltration identifies a subpopulation of highly infiltrated, microheterogeneous tumors responsive to ICI. In paired multiplex immunofluorescence images of ccRCC, microheterogeneity associates with greater PD1 activation in CD8+ lymphocytes and increased tumor-immune interactions. Our work reveals spatially interacting tumor-immune structures underlying ccRCC biology that may also inform selective response to ICI.
Assuntos
Carcinoma de Células Renais , Carcinoma , Aprendizado Profundo , Neoplasias Renais , Humanos , Carcinoma de Células Renais/genética , FenótipoRESUMO
Clear cell renal cell carcinoma (ccRCC) is molecularly heterogeneous, immune infiltrated, and selectively sensitive to immune checkpoint inhibition (ICI). Established histopathology paradigms like nuclear grade have baseline prognostic relevance for ccRCC, although whether existing or novel histologic features encode additional heterogeneous biological and clinical states in ccRCC is uncertain. Here, we developed spatially aware deep learning models of tumor- and immune-related features to learn representations of ccRCC tumors using diagnostic whole-slide images (WSI) in untreated and treated contexts (n = 1102 patients). We discovered patterns of nuclear grade heterogeneity in WSI not achievable through human pathologist analysis, and these graph-based "microheterogeneity" structures associated with PBRM1 loss of function, adverse clinical factors, and selective patient response to ICI. Joint computer vision analysis of tumor phenotypes with inferred tumor infiltrating lymphocyte density identified a further subpopulation of highly infiltrated, microheterogeneous tumors responsive to ICI. In paired multiplex immunofluorescence images of ccRCC, microheterogeneity associated with greater PD1 activation in CD8+ lymphocytes and increased tumor-immune interactions. Thus, our work reveals novel spatially interacting tumor-immune structures underlying ccRCC biology that can also inform selective response to ICI.
RESUMO
Medical artificial intelligence (AI) has tremendous potential to advance healthcare by supporting and contributing to the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving both healthcare provider and patient experience. Unlocking this potential requires systematic, quantitative evaluation of the performance of medical AI models on large-scale, heterogeneous data capturing diverse patient populations. Here, to meet this need, we introduce MedPerf, an open platform for benchmarking AI models in the medical domain. MedPerf focuses on enabling federated evaluation of AI models, by securely distributing them to different facilities, such as healthcare organizations. This process of bringing the model to the data empowers each facility to assess and verify the performance of AI models in an efficient and human-supervised process, while prioritizing privacy. We describe the current challenges healthcare and AI communities face, the need for an open platform, the design philosophy of MedPerf, its current implementation status and real-world deployment, our roadmap and, importantly, the use of MedPerf with multiple international institutions within cloud-based technology and on-premises scenarios. Finally, we welcome new contributions by researchers and organizations to further strengthen MedPerf as an open benchmarking platform.
RESUMO
Imaging datasets in cancer research are growing exponentially in both quantity and information density. These massive datasets may enable derivation of insights for cancer research and clinical care, but only if researchers are equipped with the tools to leverage advanced computational analysis approaches such as machine learning and artificial intelligence. In this work, we highlight three themes to guide development of such computational tools: scalability, standardization, and ease of use. We then apply these principles to develop PathML, a general-purpose research toolkit for computational pathology. We describe the design of the PathML framework and demonstrate applications in diverse use cases. PathML is publicly available at www.pathml.com.
Assuntos
Inteligência Artificial/normas , Aprendizado de Máquina/normas , Neoplasias/patologia , Projetos de Pesquisa/normas , HumanosRESUMO
Gleason score, a measure of prostate tumor differentiation, is the strongest predictor of lethal prostate cancer at the time of diagnosis. Metabolomic profiling of tumor and of patient serum could identify biomarkers of aggressive disease and lead to the development of a less-invasive assay to perform active surveillance monitoring. Metabolomic profiling of prostate tissue and serum samples was performed. Metabolite levels and metabolite sets were compared across Gleason scores. Machine learning algorithms were trained and tuned to predict transformation or differentiation status from metabolite data. A total of 135 metabolites were significantly different (P adjusted < 0.05) in tumor versus normal tissue, and pathway analysis identified one sugar metabolism pathway (P adjusted = 0.03). Machine learning identified profiles that predicted tumor versus normal tissue (AUC of 0.82 ± 0.08). In tumor tissue, 25 metabolites were associated with Gleason score (unadjusted P < 0.05), 4 increased in high grade while the remainder were enriched in low grade. While pyroglutamine and 1,5-anhydroglucitol were correlated (0.73 and 0.72, respectively) between tissue and serum from the same patient, no metabolites were consistently associated with Gleason score in serum. Previously reported as well as novel metabolites with differing abundance were identified across tumor tissue. However, a "metabolite signature" for Gleason score was not obtained. This may be due to study design and analytic challenges that future studies should consider. IMPLICATIONS: Metabolic profiling can distinguish benign and neoplastic tissues. A novel unsupervised machine learning method can be utilized to achieve this distinction.
Assuntos
Aprendizado de Máquina/normas , Metabolômica/métodos , Neoplasias da Próstata/genética , Feminino , Humanos , Masculino , Gradação de TumoresRESUMO
Genes that are inherently subject to strong selective constraints tend to be overretained in duplicate after polyploidy. They also continue to experience similar, but somewhat relaxed, constraints after that polyploidy event. We sought to assess for how long the influence of polyploidy is felt on these genes' selective pressures. We analyzed two nested polyploidy events in Brassicaceae: the At-α genome duplication that is the most recent polyploidy in the model plant Arabidopsis thaliana and a more recent hexaploidy shared by the genus Brassica and its relatives. By comparing the strength and direction of the natural selection acting at the population and at the species level, we find evidence for continued intensified purifying selection acting on retained duplicates from both polyploidies even down to the present. The constraint observed in preferentially retained genes is not a result of the polyploidy event: the orthologs of such genes experience even stronger constraint in nonpolyploid outgroup genomes. In both the Arabidopsis and Brassica lineages, we further find evidence for segregating mildly deleterious variants, confirming that the population-level data uncover patterns not visible with between-species comparisons. Using the A. thaliana metabolic network, we also explored whether network position was correlated with the measured selective constraint. At both the population and species level, nodes/genes tended to show similar constraints to their neighbors. Our results paint a picture of the long-lived effects of polyploidy on plant genomes, suggesting that even yesterday's polyploids still have distinct evolutionary trajectories.
Assuntos
Evolução Molecular , Genoma de Planta/genética , Seleção Genética/genética , Arabidopsis/genética , Brassica/genética , Dosagem de Genes/genética , Duplicação Gênica , Genes de Plantas/genética , Filogenia , PoliploidiaRESUMO
This study was undertaken to test the hypothesis that Sjogren's syndrome Antigen A (SSA)/Ro60-reactive T cells are activated by peptides originating from oral and gut bacteria. T cell hybridomas generated from HLA-DR3 transgenic mice recognized 3 regions on Ro60, with core epitopes mapped to amino acids 228-238, 246-256 and 371-381. BLAST analysis identified several mimicry peptides, originating from human oral, intestinal, skin and vaginal bacteria, as well as environmental bacteria. Amongst these, a peptide from the von Willebrand factor type A domain protein (vWFA) from the oral microbe Capnocytophaga ochracea was the most potent activator. Further, Ro60-reactive T cells were activated by recombinant vWFA protein and whole Escherichia coli expressing this protein. These results demonstrate that peptides derived from normal human microbiota can activate Ro60-reactive T cells. Thus, immune responses to commensal microbiota and opportunistic pathogens should be explored as potential triggers for initiating autoimmunity in SLE and Sjögren's syndrome.