Ensuring that online patient education materials are written at an appropriate reading grade level would be expected to improve physician-patient communication.
Graph convolutional neural networks (GCNN) have become an increasingly active field of research. It models the spatial dependencies of nodes in a graph with a pre-defined Laplacian matrix based on node distances. However, in many application scenarios, spatial dependencies change over time, and the use of fixed Laplacian matrix cannot capture the change. To track the spatial dependencies among traffic data, we propose a dynamic spatio-temporal GCNN for accurate traffic forecasting. The core of our deep learning framework is the finding of the change of Laplacian matrix with a dynamic Laplacian matrix estimator. To enable timely learning with a low complexity, we creatively incorporate tensor decomposition into the deep learning framework, where real-time traffic data are decomposed into a global component that is stable and depends on long-term temporal-spatial traffic relationship and a local component that captures the traffic fluctuations. We propose a novel design to estimate the dynamic Laplacian matrix of the graph with above two components based on our theoretical derivation, and introduce our design basis. The forecasting performance is evaluated with two realtime traffic datasets. Experiment results demonstrate that our network can achieve up to 25% accuracy improvement.
Despite advances in DNA methylome analyses of cells and tissues, current techniques for genome-scale profiling of DNA methylation in circulating cell-free DNA (ccfDNA) remain limited. Here we describe a methylated CpG tandems amplification and sequencing (MCTA-Seq) method that can detect thousands of hypermethylated CpG islands simultaneously in ccfDNA. This highly sensitive technique can work with genomic DNA as little as 7.5 pg, which is equivalent to 2.5 copies of the haploid genome. We have analyzed a cohort of tissue and plasma samples (n = 151) of hepatocellular carcinoma (HCC) patients and control subjects, identifying dozens of high-performance markers in blood for detecting small HCC (≤ 3 cm). Among these markers, 4 (RGS10, ST8SIA6, RUNX2 and VIM) are mostly specific for cancer detection, while the other 15, classified as a novel set, are already hypermethylated in the normal liver tissues. Two corresponding classifiers have been established, combination of which achieves a sensitivity of 94% with a specificity of 89% for the plasma samples from HCC patients (n = 36) and control subjects including cirrhosis patients (n = 17) and normal individuals (n = 38). Notably, all 15 alpha-fetoprotein-negative HCC patients were successfully identified. Comparison between matched plasma and tissue samples indicates that both the cancer and noncancerous tissues contribute to elevation of the methylation markers in plasma. MCTA-Seq will facilitate the development of ccfDNA methylation biomarkers and contribute to the improvement of cancer detection in a clinical setting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.