基于神经网络技术自动筛选Monastrol抑制剂的算法研究

带自动荧光显微镜的HCS（high content screening）系统是一种新兴的显微摄影、筛选和处理系统.HCS系统在摄影过程中会产生大量数据,人工筛选和识别费时费力.本文为了进行Monastrol抑制剂的筛选,基于前馈式神经网络技术研究了一种对HCS系统摄影的大量细胞同时进行特征提取和细胞显型识别的自动算法.在得到各个通道分离的图像后,对不同通道图像进行并行预处理,并采用神经网络和逻辑运算相结合的算法进行处理.我们将该方法运用于Monastrol抑制剂的筛选中,并将结果与人工识别结果进行分析比较.相比较前人提出的multi-phenotypic mitotic analysis（MMA）算法自动识别的正确率得以提高,可更好评估抗癌药剂效用.     

基于异构数据库银行业绩考核系统的构建

针对从异种操作系统平台事后下载、解压、提取当日银行业务报表数据,采用Visual FoxPro数据库语言进行银行业绩考核统计应用程序设计中涉及的异种数据库数据格式转换、数据筛选等几个难点问题进行分析,提出采用基于中间数据格式转换的方法,有效地解决了Informix 数据、FoxPro 数据格式转换问题,使该程序得以成功开发和应用.     

浅谈加强工程建设领域招标投标活动管理的方法

文章针对目前工程建设领域招标投标活动中招标代理机构市场行为、评标专家评标活动和评标方法存在的问题,提出了加强工程建设领域招标投标活动管理的方法.     

基于深度贝叶斯网络学习的不确定性建模方法

战场态势评估涉及很多不确定因素,对不确定性进行仿真建模能够提高态势评估的能力。针对参战对象多元、不确定性增多导致的无法全面准确表达不确定性问题,提出了基于记忆模块和变分自编码器的深度贝叶斯网络模型。采用生成模型设计了基于深度贝叶斯网络学习的态势评估模型;阐述了融合记忆模块的深度生成模型原理和模型的学习与推理过程;以某空袭行动为例构建贝叶斯网络,对所提方法进行了验证。结果表明:深度神经网络能够逼近隐变量的非线性变换,设计的记忆模块能存储深度神经网络提取的大量局部特征,通过学习自动得到了贝叶斯网络条件概率,增强了不确定性建模能力。     

New Lyapunov-Krasovskii Functional for Stability Analysis of Linear Systems with Time-Varying Delay

This paper focuses on the problem of delay-dependent stability of linear systems with time-varying delay. A new delay-product-type augmented Lyapunov-Krasovskii functional(LKF) is constructed. Based on the LKF and by employing a generalized free-matrix-based integral inequality,less conservative delay-dependent stability criteria are obtained. Finally, two well-known numerical examples are used to confirm the effectiveness and the superiority of the presented stability criteria.     

Germline-specific dgcr8 knockout in zebrafish using a BACK approach

Zebrafish is an important model to study developmental biology and human diseases. However, an effective approach to achieve spatial and temporal gene knockout in zebrafish has not been well established. In this study, we have developed a new approach, namely bacterial artificial chromosome-rescue-based knockout (BACK), to achieve conditional gene knockout in zebrafish using the Cre/loxP system. We have successfully deleted the DiGeorge syndrome critical region gene 8 (dgcr8) in zebrafish germ line and demonstrated that the maternal-zygotic dgcr8 (MZdgcr8) embryos exhibit MZdicer-like phenotypes with morphological defects which could be rescued by miR-430, indicating that canonical microRNAs play critical role in early development. Our findings establish that Cre/loxP-mediated tissue-specific gene knockout could be achieved using this BACK strategy and that canonical microRNAs play important roles in early embryonic development in zebrafish.     

Overactive bone morphogenetic protein signaling in heterotopic ossification and Duchenne muscular dystrophy

Bone morphogenetic proteins (BMPs) are important extracellular cytokines that play critical roles in embryogenesis and tissue homeostasis. BMPs signal via transmembrane type I and type II serine/threonine kinase receptors and intracellular Smad effector proteins. BMP signaling is precisely regulated and perturbation of BMP signaling is connected to multiple diseases, including musculoskeletal diseases. In this review, we will summarize the recent progress in elucidation of BMP signal transduction, how overactive BMP signaling is involved in the pathogenesis of heterotopic ossification and Duchenne muscular dystrophy, and discuss possible therapeutic strategies for treatment of these diseases.