Discovering trends and hotspots of biosafety and biosecurity research via machine learning.

Coronavirus disease 2019 (COVID-19) has infected hundreds of millions of people and killed millions of them. As an RNA virus, COVID-19 is more susceptible to variation than other viruses. Many problems involved in this epidemic have made biosafety and biosecurity (hereafter collectively referred to as 'biosafety') a popular and timely topic globally. Biosafety research covers a broad and diverse range of topics, and it is important to quickly identify hotspots and trends in biosafety research through big data analysis. However, the data-driven literature on biosafety research discovery is quite scant. We developed a novel topic model based on latent Dirichlet allocation, affinity propagation clustering and the PageRank algorithm (LDAPR) to extract knowledge from biosafety research publications from 2011 to 2020. Then, we conducted hotspot and trend analysis with LDAPR and carried out further studies, including annual hot topic extraction, a 10-year keyword evolution trend analysis, topic map construction, hot region discovery and fine-grained correlation analysis of interdisciplinary research topic trends. These analyses revealed valuable information that can guide epidemic prevention work: (1) the research enthusiasm over a certain infectious disease not only is related to its epidemic characteristics but also is affected by the progress of research on other diseases, and (2) infectious diseases are not only strongly related to their corresponding microorganisms but also potentially related to other specific microorganisms. The detailed experimental results and our code are available at https://github.com/KEAML-JLU/Biosafety-analysis.

Speech- and language-linked FOXP2 mutation targets protein motors in striatal neurons.

Human speech and language are among the most complex motor and cognitive abilities. The discovery of a mutation in the transcription factor FOXP2 in KE family members with speech disturbances has been a landmark example of the genetic control of vocal communication in humans. Cellular mechanisms underlying this control have remained unclear. By leveraging FOXP2 mutation/deletion mouse models, we found that the KE family FOXP2R553H mutation directly disables intracellular dynein-dynactin 'protein motors' in the striatum by induction of a disruptive high level of dynactin1 that impairs TrkB endosome trafficking, microtubule dynamics, dendritic outgrowth and electrophysiological activity in striatal neurons alongside vocalization deficits. Dynactin1 knockdown in mice carrying FOXP2R553H mutations rescued these cellular abnormalities and improved vocalization. We suggest that FOXP2 controls vocal circuit formation by regulating protein motor homeostasis in striatal neurons, and that its disruption could contribute to the pathophysiology of FOXP2 mutation/deletion-associated speech disorders.

Deep Learning Model for Coronary Angiography.

The visual inspection of coronary artery stenosis is known to be significantly affected by variation, due to the presence of other tissues, camera movements, and uneven illumination. More accurate and intelligent coronary angiography diagnostic models are necessary for improving the above problems. In this study, 2980 medical images from 949 patients are collected and a novel deep learning-based coronary angiography (DLCAG) diagnose system is proposed. Firstly, we design a module of coronary classification. Then, we introduce RetinaNet to balance positive and negative samples and improve the recognition accuracy. Additionally, DLCAG adopts instance segmentation to segment the stenosis of vessels and depict the degree of the stenosis vessels. Our DLCAG is available at http://101.132.120.184:8077/ . When doctors use our system, all they need to do is login to the system, upload the coronary angiography videos. Then, a diagnose report is automatically generated.

Chinese Herbal Medicine Treatment Improves the Overall Survival Rate of Individuals with Hypertension among Type 2 Diabetes Patients and Modulates In Vitro Smooth Muscle Cell Contractility.

Type 2 diabetes (T2D) is a chronic, multifactorial, and metabolic disorder accounting for 90% diabetes cases worldwide. Among them, almost half of T2D have hypertension, which is responsible for cardiovascular disease, morbidity, and mortality in these patients. The Chinese herbal medicine (CHM) prescription patterns of hypertension individuals among T2D patients have yet to be characterized. This study, therefore, aimed to determine their prescription patterns and evaluate the CHM effect. A cohort of one million randomly sampled cases from the National Health Insurance Research Database (NHIRD) was used to investigate the overall survival rate of CHM users, and prescription patterns. After matching CHM and non-CHM users for age, gender and date of diagnosis of hypertension, 980 subjects for each group were selected. The CHM users were characterized with slightly longer duration time from diabetes to hypertension, and more cases for hyperlipidaemia. The cumulative survival probabilities were higher in CHM users than in non-CHM users. Among these top 12 herbs, Liu-Wei-Di-Huang-Wan, Jia-Wei-Xiao-Yao-San, Dan-Shen, and Ge-Gen were the most common herbs and inhibited in vitro smooth muscle cell contractility. Our study also provides a CHM comprehensive list that may be useful in future investigation of the safety and efficacy for individuals with hypertension among type 2 diabetes patients.