基于文本挖掘和生物医学数据库的新型冠状病毒肺炎药物发现

目的 基于文本挖掘技术和生物医学数据库对新型冠状病毒肺炎（COVID-19）相关文献进行数据挖掘分析，探究COVID-19及其主要症状发热、咳嗽、呼吸障碍相关基因靶点，筛选潜在有效的化学药和中药。方法 使用GenCLiP 3网站获取COVID-19和其主要症状咳嗽、发热、呼吸障碍共4个关键词的共有靶点，在METASCAPE数据库中对其进行基因本体（GO）和通路富集分析，再利用String数据库和Cytoscape软件构建共有靶点的蛋白质相互作用网络，筛选获得核心基因，运用DGIdb数据库、SymMap数据库针对核心基因进行中西医治疗药物预测。结果 获得COVID-19及其主要症状共有基因靶点28个，其中有IL2、IL1B、CCL2等核心基因16个，使用DGIdb数据库筛选获得与16个关键靶点相互作用的化学药包括沙利度胺、来氟米特、环孢素等28种，中药包括虎杖、黄芪、芦荟等70味。结论 COVID-19及其主要症状的病理机制可能和CD4、KNG1、VEGFA等28个共有基因相关，可能通过介导TNF、IL-17等信号通路参与COVID-19病理过程。潜在有效药物可能通过作用相关靶点通路起到治疗COVID-19的作用。     

嘌呤能受体X1与肺腺癌预后及免疫细胞浸润的相关性研究

目的：探索嘌呤能受体X1(purinergic receptor，P2RX1)与肺腺癌(LUAD)患者预后及免疫细胞浸润的相关性。方法：利用生物信息学技术分析非小细胞肺癌中P2RX1的表达及其甲基化与患者预后的关系，对P2RX1共表达基因进行富集分析并筛选核心基因。利用TIMER 2.0数据库、R软件等分析P2RX1与免疫细胞、免疫检查点、免疫基质评分等的相关性。结果：P2RX1在LUAD中表达下调，低表达P2RX1的患者预后较差(P<0.05)，且P2RX1与肿瘤纯度、分期等临床病理因素有关(P<0.05)。P2RX1的表达与肺鳞癌患者预后无明显相关。Cg06475633等P2RX1 CpG位点甲基化与患者预后相关。P2RX1共表达基因主要富集于免疫细胞活化、分化等通路和生物学进程，核心基因主要包括BTK、IKZF1等。P2RX1的表达与B细胞浸润、免疫/基质评分、PD-1、CTLA-4等多个免疫检查点显著相关(P<0.05)。结论：P2RX1有望成为LUAD诊断和免疫治疗的新靶点。     

Computer-generated vegan menus: The importance of food composition database choice

Precise data on food chemical composition is crucial for any quantitative nutrition research and indispensable for evaluation and planning of computer-based menus. Moreover, exact food chemical composition is of the utmost importance in composing specific diets that may be low in certain essential nutrients. Therefore, this research evaluated a weekly vegan menu using three different food composition databases (FCDB): the Croatian, the official Danish Food Composition Database and the United States Department of Agriculture (USDA) – National Nutrient Database for Standard Reference. Significant differences (p < 0.05) were determined in evaluated and optimised offers for the same menu when using different FCDBs. Furthermore, in these menus quantities of some nutrients have not reached official daily recommendations needed for prevention of non-communicable diseases. In this research, new vegan menus that can provide adequate quantity of essential nutrients, regardless of FCDB utilized, were created with linear optimisation (LO). This resulted in high quality daily menu offers. However, depending on the FCDB that was used, optimal menus differed in daily meal combinations, and the effectiveness of the optimisation in the minimisation of differences caused by differences of data in FCDBs was tested. Linear optimisation has been proved to be an effective tool in planning of specific diets, such as vegan diets. Nonetheless, the quality of computer-planned menus depends heavily on the quality of FCDB used.     

Machine learning models for Parkinson’s disease detection and stage classification based on spatial-temporal gait parameters

BackgroundParkinson’s disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up.Research questionThis article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry.MethodsGait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments.ResultsIn the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability.SignificanceThe results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters.     

Registries,Databases and Repositories for Developing Artificial Intelligence in Cancer Care

Modern artificial intelligence techniques have solved some previously intractable problems and produced impressive results in selected medical domains. One of their drawbacks is that they often need very large amounts of data. Pre-existing datasets in the form of national cancer registries, image/genetic depositories and clinical datasets already exist and have been used for research. In theory, the combination of healthcare Big Data with modern, data-hungry artificial intelligence techniques should offer significant opportunities for artificial intelligence development, but this has not yet happened. Here we discuss some of the structural reasons for this, barriers preventing artificial intelligence from making full use of existing datasets, and make suggestions as to enable progress. To do this, we use the framework of the 6Vs of Big Data and the FAIR criteria for data sharing and availability (Findability, Accessibility, Interoperability, and Reuse). We share our experience in navigating these barriers through The Brain Tumour Data Accelerator, a Brain Tumour Charity-supported initiative to integrate fragmented patient data into an enriched dataset. We conclude with some comments as to the limits of such approaches.     

基于肿瘤影像学异质性分析CT在诊断十二指肠恶性肿瘤的价值

目的 探讨十二指肠肿瘤血流量存在的异质性及容积灌注CT成像对降低肿瘤异质性的影响。方法 纳入我院2013年1月至2014年11月十二指肠结节病例的132例,其中腺癌48例,间质瘤52例,淋巴瘤32例。所有的病例均行单层面灌注CT和容积灌注CT成像扫描,比较两者对十二指肠恶性肿瘤的诊断效能,采用变异系数评价两者在影像学异质性的差异,评价肿瘤影像学异质性对十二指肠恶性肿瘤的影响。结果 容积灌注CT成像与单层面灌注CT诊断恶性结节的效能其敏感性、特异性、准确性、阴性预测值、阳性预测值比较均无明显差别(P0.05);中高分化组及低分化组两个亚组的容积灌注CT成像的变异系数也均小于单层面灌注CT的变异系数,组间相比具有统计学差异(P0.05);血流量差异性的大小相比具有统计学差异(P0.05)。结论 容积灌注CT成像与单层面灌注CT检查在诊断效能上无明显差异,稳定性好,肿瘤影像学异质性对评价十二指肠肿瘤血流量有着一定影响,容积灌注CT成像能够降低肿瘤异质性的影响。     

基于TCGA数据初步探查肝内胆管癌预后相关基因

目的 分析tCGA数据库中肝内胆管癌（ICC）高通量测序数据，寻找其预后相关基因，构建风险模型，并研究其在ICC组织中表达及作用通路。方法 下载tCGA数据库中33例ICC组织和8例癌旁组织中的RNA-seq表达矩阵数据和患者临床资料信息，利用edgeR软件包进行基因差异表达分析，通过单因素Cox回归分析筛选出预后相关差异基因，对差异基因绘制生存曲线，筛选出具有临床意义的基因，经多因素Cox回归分析并构建风险模型，通过京都基因与基因组百科全书（KEGG）通路富集分析了解预后相关基因的作用通路。结果 通过edgeR分析后得到6 617个差异基因（筛选标准为|log2 Fold Change|＞1，P＜0.05），其中高表达组4 094个，低表达组2 523个。通过功能富集发现，这些基因主要集中在化学物致癌作用、药物代谢-细胞色素P450系统、细胞色素P450对异生物质的代谢影响以及视黄醇代谢通路。经单因素Cox回归、R软件“survival”包生存曲线分析显示，UCN2、CST1、PROS1、SLC35E4、PEMT五个基因对ICC患者预后存在显著性影响。通过多因素Cox回归分析，CST1、PEMT、PROS1构建的风险模型对ICC患者预后具有判断作用。结论 UCN2、CST1、PROS1、SLC35E4、PEMT基因可能成为ICC预后判断指标，为后续临床试验提供数据支持。