Morphological predictors for microsatellite instability in urothelial carcinoma

Introduction Microsatellite instability occurs due to a series of mutations in the DNA pairing error repair (Mismatch repair; MMR) genes, which can affect germ cells as occurs in Lynch syndrome, whose patients are at high risk of developing multiple cancers. The loss of MMR protein is commonly determined by immunohistochemical studies. Although the relation between microsatellite instability and urothelial carcinomas has been widely studied, its evaluation is not currently performed in the analysis of urothelial carcinomas. Methods In this study, the microsatellite status of 139 urothelial carcinomas was analyzed and their clinicopathological characteristics were evaluated. We identified that 10.3% (13 patients) of urothelial carcinomas had loss of MMR protein expression (9 MLH1; 5 MSH2; 2 PMS2; 2 PSH6; n = 139). Results Results suggest that these tumors occur more frequently in males, are more frequently located in the bladder or ureters, and present a high tumor grade with a papillary histological pattern that does not infiltrate the lamina propria or, in the case of infiltrating tumors, that grows into perivesical tissues. Conclusions We identified patients with the aforementioned tumor characteristics as patients with a high probability of presenting loss of MMR protein expression, and consider that only these patients should undergo further immunohistochemical and molecular techniques for proper diagnosis. Therefore, we propose that the clinicopathological characteristics found in the present study could become possible markers to determine which cases should undergo additional tests.

Morphological predictors for microsatellite instability in urothelial carcinoma

IntroductionMicrosatellite instability occurs due to a series of mutations in the DNA pairing error repair (Mismatch repair; MMR) genes, which can affect germ cells as occurs in Lynch syndrome, whose patients are at high risk of developing multiple cancers. The loss of MMR protein is commonly determined by immunohistochemical studies. Although the relation between microsatellite instability and urothelial carcinomas has been widely studied, its evaluation is not currently performed in the analysis of urothelial carcinomas.Methods In this study, the microsatellite status of 139 urothelial carcinomas was analyzed and their clinicopathological characteristics were evaluated. We identified that 10.3% (13 patients) of urothelial carcinomas had loss of MMR protein expression (9 MLH1; 5 MSH2; 2 PMS2; 2 PSH6; n = 139). ResultsResults suggest that these tumors occur more frequently in males, are more frequently located in the bladder or ureters, and present a high tumor grade with a papillary histological pattern that does not infiltrate the lamina propria or, in the case of infiltrating tumors, that grows into perivesical tissues.ConclusionsWe identified patients with the aforementioned tumor characteristics as patients with a high probability of presenting microsatellite instability, and consider that only these patients should undergo further immunohistochemical and molecular techniques for proper diagnosis. Therefore, we propose that the clinicopathological characteristics found in the present study could become possible markers to determine which cases should undergo additional tests.

Deep Reinforcement Learning for Syntactic Error Repair in Student Programs

Novice programmers often struggle with the formal syntax of programming languages. In the traditional classroom setting, they can make progress with the help of real time feedback from their instructors which is often impossible to get in the massive open online course (MOOC) setting. Syntactic error repair techniques have huge potential to assist them at scale. Towards this, we design a novel programming language correction framework amenable to reinforcement learning. The framework allows an agent to mimic human actions for text navigation and editing. We demonstrate that the agent can be trained through self-exploration directly from the raw input, that is, program text itself, without either supervision or any prior knowledge of the formal syntax of the programming language. We evaluate our technique on a publicly available dataset containing 6975 erroneous C programs with typographic errors, written by students during an introductory programming course. Our technique fixes 1699 (24.4%) programs completely and 1310 (18.8%) program partially, outperforming DeepFix, a state-of-the-art syntactic error repair technique, which uses a fully supervised neural machine translation approach.