Predicting gastric cancer tumor mutational burden from histopathological images using multimodal deep learning.

Tumor mutational burden (TMB) is a significant predictive biomarker for selecting patients that may benefit from immune checkpoint inhibitor therapy. Whole exome sequencing is a common method for measuring TMB; however, its clinical application is limited by the high cost and time-consuming wet-laboratory experiments and bioinformatics analysis. To address this challenge, we downloaded multimodal data of 326 gastric cancer patients from The Cancer Genome Atlas, including histopathological images, clinical data and various molecular data. Using these data, we conducted a comprehensive analysis to investigate the relationship between TMB, clinical factors, gene expression and image features extracted from hematoxylin and eosin images. We further explored the feasibility of predicting TMB levels, i.e. high and low TMB, by utilizing a residual network (Resnet)-based deep learning algorithm for histopathological image analysis. Moreover, we developed a multimodal fusion deep learning model that combines histopathological images with omics data to predict TMB levels. We evaluated the performance of our models against various state-of-the-art methods using different TMB thresholds and obtained promising results. Specifically, our histopathological image analysis model achieved an area under curve (AUC) of 0.749. Notably, the multimodal fusion model significantly outperformed the model that relied only on histopathological images, with the highest AUC of 0.971. Our findings suggest that histopathological images could be used with reasonable accuracy to predict TMB levels in gastric cancer patients, while multimodal deep learning could achieve even higher levels of accuracy. This study sheds new light on predicting TMB in gastric cancer patients.

Genetics and Epigenetics of Glioblastoma: Applications and Overall Incidence of IDH1 Mutation.

Glioblastoma is the most fatal brain cancer found in humans. Patients suffering from glioblastoma have a dismal prognosis, with a median survival of 15 months. The tumor may develop rapidly de novo in older patients or through progression from anaplastic astrocytomas in younger patients if glioblastoma is primary or secondary, respectively. During the past decade, significant advances have been made in the understanding of processes leading to glioblastoma, and several important genetic defects that appear to be important for the development and progression of this tumor have been identified. Particularly, the discovery of recurrent mutations in the isocitrate dehydrogenase 1 (IDH1) gene has shed new light on the molecular landscape in glioblastoma. Indeed, emerging research on the consequences of mutant IDH1 protein expression suggests that its neomorphic enzymatic activity catalyzing the production of the oncometabolite 2-hydroxyglutarate influences a range of cellular programs that affect the epigenome and contribute to glioblastoma development. One of the exciting observations is the presence of IDH1 mutation in the vast majority of secondary glioblastoma, while it is almost absent in primary glioblastoma. Growing data indicate that this particular mutation has clinical and prognostic importance and will become a critical early distinction in diagnosis of glioblastoma.

Enhanced susceptibility to immune nephritis in DBA/1 mice is contingent upon IL-1 expression.

The DBA/1 mouse strain is particularly sensitive to experimental immune-mediated nephritis. Previous studies have indicated that various chemokines/cytokines are elevated in strains of mice susceptible to immune-mediated glomerulonephritis. One of the many elevated cytokines is IL-1. This study was designed to determine if IL-1 is essential for the development of immune-mediated nephritis in the DBA/1 mouse strain that is particularly sensitive to this disease. Both male and female DBA/1 mice and DBA/1.IL-1R1(-/-) mice were challenged with anti-GBM sera. We then compared DBA/1 mice to DBA/1.IL-1R1(-/-) mice to determine the influence of IL-1 on immune-mediated nephritis. Compared to DBA/1 mice, DBA/1.IL-1R1(-/-) mice excreted significantly less protein post anti-GBM serum challenge. None of the DBA/1.IL-1R1(-/-) mice, male or female, had a BUN higher than 22 mg/dl post-challenge whereas wild-type DBA/1 mice had significantly elevated BUN. Wild-type DBA/1 mice exhibited pronounced glomerulonephritis, with crescent formation, as well as tubulo-interstitial disease compared to DBA/1.IL1R1(-/-) mice. These findings indicate that IL-1 is necessary for the development of nephritis in DBA/1 mice and suggest that the elevated IL-1 levels in these mice may be one reason why the DBA/1 strain is particularly sensitive to multiple end organ diseases.