Summary DeepKG is an end-to-end deep learning-based workflow that helps researchers automatically mine valuable knowledge in biomedical literature. Users can utilize it to establish customized knowledge graphs in specified domains, thus facilitating in-depth understanding on disease mechanisms and applications on drug repurposing and clinical research. To improve the performance of DeepKG, a cascaded hybrid information extraction framework is developed for training model of 3-tuple extraction, and a novel AutoML-based knowledge representation algorithm (AutoTransX) is proposed for knowledge representation and inference. The system has been deployed in dozens of hospitals and extensive experiments strongly evidence the effectiveness. In the context of 144 900 COVID-19 scholarly full-text literature, DeepKG generates a high-quality knowledge graph with 7980 entities and 43 760 3-tuples, a candidate drug list, and relevant animal experimental studies are being carried out. To accelerate more studies, we make DeepKG publicly available and provide an online tool including the data of 3-tuples, potential drug list, question answering system, visualization platform. Availability and implementation All the results are publicly available at the website (http://covidkg.ai/). Supplementary information Supplementary data are available at Bioinformatics online.

Objective To examine the clinical characteristics of patients with asymptomatic novel coronavirus disease 2019 (COVID-19) and compare them with those of patients with mild disease. Design A retrospective cohort study. Setting Multiple medical centers in Wuhan, Hubei, China. Participants A total of 3,263 patients with laboratory-confirmed severe acute respiratory syndrome coronavirus 2 (SARS-Cov-2) infection between February 4, 2020, and April 15, 2020. Main outcome measures Patient demographic characteristics, medical history, vital signs, and laboratory and chest computed tomography (CT) findings. Results A total of 3,173 and 90 patients with mild and moderate, and asymptomatic COVID-19, respectively, were included. A total of 575 (18.2%) symptomatic patients and 4 (4.4%) asymptomatic patients developed the severe illness. All asymptomatic patients recovered; no deaths were observed in this group. The median duration of viral shedding in asymptomatic patients was 17 (interquartile range, 9.25–25) days. Patients with higher levels of ultrasensitive C-reactive protein (odds ratio [OR] = 1.025, 95% confidence interval [CI], 1.01–1.04), lower red blood cell volume distribution width (OR = 0.68, 95% CI 0.51–0.88), lower creatine kinase Isoenzyme(0.94, 0.89–0.98) levels, or lower lesion ratio (OR = 0.01, 95% CI 0.00–0.33) at admission were more likely than their counterparts to have asymptomatic disease. Conclusions Patients with younger ages and fewer comorbidities are more likely to be asymptomatic. Asymptomatic patients had similar laboratory characteristics and longer virus shedding time than symptomatic patients; screen and isolation during their infection were helpful to reduce the risk of SARS-CoV-2 transmission.