Microsatellite instability (MSI) has been approved as a pan-cancer biomarker for immune checkpoint blockade (ICB) therapy. However, current MSI identification methods are not available for all patients. We proposed an ensemble multiple instance deep learning model to predict microsatellite status based on histopathology images, and interpreted the pathomics-based model with multi-omics correlation. Methods: Two cohorts of patients were collected, including 429 from The Cancer Genome Atlas (TCGA-COAD) and 785 from an Asian colorectal cancer (CRC) cohort (Asian-CRC). We established the pathomics model, named Ensembled Patch Likelihood Aggregation (EPLA), based on two consecutive stages: patch-level prediction and WSI-level prediction. The initial model was developed and validated in TCGA-COAD, and then generalized in Asian-CRC through transfer learning. The pathological signatures extracted from the model were analyzed with genomic and transcriptomic profiles for model interpretation. Results: The EPLA model achieved an area-under-the-curve (AUC) of 0.8848 (95% CI: 0.8185-0.9512) in the TCGA-COAD test set and an AUC of 0.8504 (95% CI: 0.7591-0.9323) in the external validation set Asian-CRC after transfer learning. Notably, EPLA captured the relationship between pathological phenotype of poor differentiation and MSI ( P < 0.001). Furthermore, the five pathological imaging signatures identified from the EPLA model were associated with mutation burden and DNA damage repair related genotype in the genomic profiles, and antitumor immunity activated pathway in the transcriptomic profiles. Conclusions: Our pathomics-based deep learning model can effectively predict MSI from histopathology images and is transferable to a new patient cohort. The interpretability of our model by association with pathological, genomic and transcriptomic phenotypes lays the foundation for prospective clinical trials of the application of this artificial intelligence (AI) platform in ICB therapy.

Smoking is a well-known major risk factor in development of esophageal cancer, but few studies have reported the association between smoking status and prognosis of these patients. We conduct the present study to summarize current evidence. A computerized search of the PubMed and EMBASE was performed up to April 30, 2015. Eight studies, containing 4,286 patients, were analyzed. In the grouping analysis, among esophageal squamous-cell carcinoma patients, current and former smokers, compared to those who have never smoked, seemed to have a poorer prognosis (HR = 1.41, 95% CI 1.22–1.64, and HR = 1.35, 95% CI 0.92–1.97, resp.). In the subgroup analysis, adverse effects on current smoker compared with never smoker were also observed in China and the other countries (HR = 1.5, 95% CI 1.18–1.92, and HR = 1.36, 95% CI 1.12–1.65, resp.). In the group that ever smoked, we could not get a similar result. No significantly increased risk was found in esophageal adenocarcinoma patients compared to the squamous-cell histology ones. In the smoking intensity analysis, heavy smoking was associated with poor survival in esophageal squamous-cell carcinoma. Our pooled results supported the existence of harmful effects of smoking on survival after esophagus cancer diagnosis.

Background Non-small cell lung cancer (NSCLC) is a predominant type of lung cancer with a high mortality rate. Objective The aim of this study is to investigate the roles of nuclear casein kinase and cyclin-dependent kinase substrate 1 (NUCKS1) in NSCLC and to identify the potential mechanisms. Materials and Methods The expression of NUCKS1 in several NSCLC cells was detected firstly. Then, NUCKS1 was overexpressed or silenced in both A549 and NCI-H460 cells, where cell proliferation, invasion and migration were, respectively, determined, using CCK-8, colony formation assay, transwell and wound healing assays. Cell cycle analysis was performed, and the expression-associated proteins were detected by Western blotting. Subsequently, NCI-H460 cells with NUCKS1 overexpression for the subsequent tumor-bearing experiment. And the NUCKS1 expression in tumor tissues was measured by means of immunohistochemistry and Western blotting. Additionally, the STRING database predicted that Cyclin-Dependent Kinase 1 (CDK1) would bind to NUSK1, which was verified by the co-immunoprecipitation assay. Then, CDK1 was silenced by transfection with short hairpin RNA (shRNA)-CDK-1 or by exposure to CDK1 inhibitor p2767-00. And the biological characteristics of proliferation, invasion and migration were examined. Results Results indicated that NUCKS1 was overly expressed in NSCLC cells, and its overexpression promoted proliferation, invasion and migration of both A549 and NCI-H460 cells while NUCKS1 knockdown displayed the opposite effects. Moreover, the results of the xenograft experiments revealed that NUCKS1-upregulation promoted the tumor growth. Furthermore, the immunoprecipitation assay verified CDK1’s interaction with NUCKS1, and CDK1 knockdown alleviates the impact of NUCKS1 overexpression on NSCLC cell proliferation, invasion and migration. Conclusion Taken together, these findings demonstrated that NUCKS1 promotes proliferation, invasion and migration of NSCLC by upregulating CDK1, providing a novel putative target for the clinical treatment of NSCLC.