A DNA microarray for the versatile diagnosis of infectious diarrhea

Several bacteria, viruses, and parasites cause diarrhea as coinfecting pathogens. We designed a DNA microarray comprising 60‐bp probes spotted 194 times for the multiplex detection of 33 enteropathogenic bacteria and seven enteropathogenic viruses, and the archaeon Methanobrevibacter smithii was used as an internal positive control. Nine pathogen‐free stool specimens were used as negative controls. One of these control specimens was further spiked with Salmonella enterica as a positive control. The microarray was then tested with 40 pathological stool specimens, comprising S. enterica (n = 30), Campylobacter jejuni (n = 4), pathogenic Escherichia coli (n = 2), and adenovirus (n = 4). M. smithii was detected in 47/49 (95.9%) specimens, no pathogen was detected in negative controls and S. enterica was identified in the S. enterica‐spiked positive control. The overall specificity was 100% and the overall sensitivity was 97.5% because one S. enterica sample was missed by the microarray. The multiplexed detection of C. jejuni spiked into an adenovirus‐positive stool sample gave positive results, with fluorescence values of 14.3 and 9.1, respectively. These data indicate that using the protocol developed in this article, the DNA array allows for the multiplexed detection of some enteropathogens in stool samples.     

A novel ensemble machine learning for robust microarray data classification

Microarray data analysis and classification has demonstrated convincingly that it provides an effective methodology for the effective diagnosis of diseases and cancers. Although much research has been performed on applying machine learning techniques for microarray data classification during the past years, it has been shown that conventional machine learning techniques have intrinsic drawbacks in achieving accurate and robust classifications. This paper presents a novel ensemble machine learning approach for the development of robust microarray data classification. Different from the conventional ensemble learning techniques, the approach presented begins with generating a pool of candidate base classifiers based on the gene sub-sampling and then the selection of a sub-set of appropriate base classifiers to construct the classification committee based on classifier clustering. Experimental results have demonstrated that the classifiers constructed by the proposed method outperforms not only the classifiers generated by the conventional machine learning but also the classifiers generated by two widely used conventional ensemble learning methods (bagging and boosting).     

单增李斯特菌检测基因芯片的研制与评价

目的 研制快速、特异、灵敏的检测单增李斯特菌的基因芯片.方法 选择gyrB、ISR、16S rRNA、23S rRNA、hlyA、iap和prfA作为单增李斯特菌的检测靶基因,研制一种Oligo探针基因芯片,对18个不同种属来源的已知参考生物样品进行检测和鉴定,并且采用对比试验、重复性试验、灵敏度试验和特异性试验对该芯片进行验证评估.结果 通过对比发现IDT合成的70 mer Oligo芯片探针在芯片打印与芯片检测两个方面较优.比较10、40和80 μmol/L 3个Oligo探针点样浓度,结果 显示10 μmol/L的探针点样浓度已能获得很好的芯片检测结果.单增李斯特菌检测芯片具有较好的重复性;样品检测绝对量下限为0.9 ng DNA左右.结论 Oligo基因芯片可以快速准确地检测单增李斯特菌.     

DNA微阵列的数字图像处理

从微阵列图像中提取基因表达和识别基因，并进一步测定基因的功能是DNA微阵列研究的主要目标，而微阵列图像处理通过定位和提取每个cDNA靶点上探针的信号强度，并通过计算平均灰度值和分析强度比率等为生物学家进行更高层的基因分析提供必要条件，本文介绍采用红绿双色荧光标记杂交实验进行微阵列图像处理几个关键步骤；微阵列靶区的分割，背景强度的提取，靶点检测，靶点灰度提取、靶点表达程度分析。     

缺失型α地中海贫血的基因芯片检测

目的 探讨基因芯片诊断地中海贫血的方法。方法 共测定了50份已知基因分型的血液样品。抽提基因组DNA，经聚合酶链反应后。进行荧光标记及杂交，扫描芯片荧光信号图像，并将分析的结果与原基因类型进行对照。结果 10例正常个体及40例缺失型。地中海贫血患者被诊断，其中-SEA型29例，占72.5％；-α^3.7型6例，占15.0％；-α^4.2型12.5例，占7％。结果均与原诊断相符。结论 基因芯片法可快速、准确地筛查缺失型α地中海贫血。     

基因芯片数据的聚类分析

基因芯片技术是后基因组时代功能基因组研究的主要工具。由于采用了高效的并行DNA杂交技术,每次实验可以得到大量丰富的数据,因此其结果分析成为一项很有挑战性而且具有重要意义的工作。聚类分析是基因芯片数据分析中使用广泛的一类方法。基因芯片实验得到的大量数据通过聚类分析,可以得到很多有用的信息,其成功应用已广泛涉及到生物医学研究中的各个领域。本文介绍了基因芯片数据的聚类分析方法及其重要应用。     

A neural network-based biomarker association information extraction approach for cancer classification

A number of different approaches based on high-throughput data have been developed for cancer classification. However, these methods often ignore the underlying correlation between the expression levels of different biomarkers which are related to cancer. From a biological viewpoint, the modeling of these abnormal associations between biomarkers will play an important role in cancer classification. In this paper, we propose an approach based on the concept of Biomarker Association Networks (BAN) for cancer classification. The BAN is modeled as a neural network, which can capture the associations between the biomarkers by minimizing an energy function. Based on the BAN, a new cancer classification approach is developed. We validate the proposed approach on four publicly available biomarker expression datasets. The derived Biomarker Association Networks are observed to be significantly different for different cancer classes, which help reveal the underlying deviant biomarker association patterns responsible for different cancer types. Extensive comparisons show the superior performance of the BAN-based classification approach over several conventional classification methods.     

微阵列数据中常用的分类分析方法

微阵列技术的出现改变了生物医学研究的前景。微阵列技术产生的大量数据是限制其发展的一个主要瓶颈,为提取其中所隐含的有价值的信息,在微阵列数据分析的复杂计算工具和方法方面都有很多尝试。本文对基因表达模式识别中的分类方法进行了综述。     

Use of neural networks as medical diagnosis expert systems

A major bottleneck in building expert systems is the process of acquiring the required knowledge in the form of production rules. A novel class of neural networks is proposed to articulate the knowledge it learned from a set of examples. It provides an appealing solution to the problem of knowledge acquisition. After training, the knowledge embedded in the numerical weights of trained neural networks can be easily extracted and represented in the form of production rules. The approach is demonstrated by an example of a hypothesis regarding the pathophysiology of diabetes.     

DNA芯片检测乙型肝炎病毒基因多态性

目的　建立DNA芯片检测乙型肝炎病毒 (hepatitisBvirus,HBV)基因多态性的研究方法并对实验条件进行优化。方法　设计多条寡核苷酸探针 ,在硅烷化芯片的特定位置上 ,用点样仪将探针固定 ,并与PCR扩增的HBV基因相应区段杂交 ,杂交结果影印至硝酸纤维素膜 ,经BCIP NBT避光显色 ,用放大镜观察杂交信号呈暗紫色圆点 ,根据特定位置上杂交信号的有无和与之相应的探针序列来判定基因突变的类型。结果　通过 1次杂交反应可检测HBV前C C区 (nt 1896 1814 )、BCP区 (nt1762 1764)和P区 (nt 52 8 552 )等多个位点的变异 ,与测序分析结果完全一致 ,具有较好的检测灵敏度和重复性。结论　DNA芯片检测HBV基因常见突变位点多态性 ,操作简便易行 ,技术要求不高 ,具有临床推广应用价值 ,而且可以方便地通过向寡核苷酸探针阵列中添加相应探针 ,扩大基因芯片的检测应用范围 ,为临床检测提供了新的方法     

Cancer adjuvant chemotherapy strategic classification by artificial neural network with gene expression data: An example for non-small cell lung cancer

PurposeAdjuvant chemotherapy (ACT) is used after surgery to prevent recurrence or metastases. However, ACT for non-small cell lung cancer (NSCLC) is still controversial. This study aimed to develop prediction models to distinguish who is suitable for ACT (ACT-benefit) and who should avoid ACT (ACT-futile) in NSCLC.MethodsWe identified the ACT correlated gene signatures and performed several types of ANN algorithms to construct the optimal ANN architecture for ACT benefit classification. Reliability was assessed by cross-data set validation.ResultsWe obtained 2 probes (2 genes) with T-stage clinical data combination can get good prediction result. These genes included 208893_s_at (DUSP6) and 204891_s_at (LCK). The 10-fold cross validation classification accuracy was 65.71%. The best result of ANN models is MLP14-8-2 with logistic activation function.ConclusionsUsing gene signature profiles to predict ACT benefit in NSCLC is feasible. The key to this analysis was identifying the pertinent genes and classification. This study maybe helps reduce the ineffective medical practices to avoid the waste of medical resources.     

去甲肾上腺素对血管平滑肌细胞A7r5基因表达谱的影响

目的: 探讨去甲肾上腺素刺激后A7r5血管平滑肌细胞基因表达谱的改变。方法: 应用放射配体结合实验明确A7r5细胞上肾上腺素受体(AR)的表达。采用基因芯片技术观察去甲肾上腺素引起的血管平滑肌细胞基因表达谱的变化。用荧光实时定量PCR验证α_1A－AR,α_1B-AR的mRNA表达变化。结果:A7r5细胞中有α₁-AR和β-AR表达,其最大结合容量(Bmax)分别为(45.0±11.8)fmol／mg蛋白和(17.4±2.5)fmol／mg蛋白。去甲肾上腺素刺激细胞24 h后,有75个基因表达发生明显改变,其中涉及细胞结构、防御、代谢及信号转导等多方面的基因。荧光实时定量PCR结果显示去甲肾上腺素刺激细胞24 h后α_1A－AR和α_1B-AR的mRNA表达增加,与基因芯片的结果一致。结论:去甲肾上腺素激动AR引起A7r5血管平滑肌细胞多种不同功能的基因表达发生改变,提示在血管平滑肌中AR可能通过基因水平的调控而介导多种生物学功能。     

Neural network-based diagnostic and prognostic estimations in breast cancer microscopic instances

This paper deals with breast cancer diagnostic and prognostic estimations employing neural networks over the Wisconsin Breast Cancer datasets, which consist of measurements taken from breast cancer microscopic instances. A probabilistic approach is dedicated to solve the diagnosis problem, detecting malignancy among instances derived from the Fine Needle Aspirate test, while regression algorithms estimate the time interval that possibly correspond to the right end-point of the patients’ disease-free survival time or the time where the tumour recurs (time-to-recur). For the diagnosis problem, the accuracy of the neural network in terms of sensitivity and specificity was measured at 98.6 and 97.5% respectively, using the leave-one-out test method. As far as the prognosis problem is concerned, the accuracy of the neural network was measured through a stratified tenfold cross-validation approach. Sensitivity ranged between 80.5 and 91.8%, while specificity ranged between 91.9 and 97.9%, depending on the tested fold and the partition of the predicted period. The prognostic recurrence predictions were then further evaluated using survival analysis and compared with other techniques found in literature.     

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition

BackgroundPrevious state-of-the-art systems on Drug Name Recognition (DNR) and Clinical Concept Extraction (CCE) have focused on a combination of text “feature engineering” and conventional machine learning algorithms such as conditional random fields and support vector machines. However, developing good features is inherently heavily time-consuming. Conversely, more modern machine learning approaches such as recurrent neural networks (RNNs) have proved capable of automatically learning effective features from either random assignments or automated word “embeddings”.Objectives(i) To create a highly accurate DNR and CCE system that avoids conventional, time-consuming feature engineering. (ii) To create richer, more specialized word embeddings by using health domain datasets such as MIMIC-III. (iii) To evaluate our systems over three contemporary datasets.MethodsTwo deep learning methods, namely the Bidirectional LSTM and the Bidirectional LSTM-CRF, are evaluated. A CRF model is set as the baseline to compare the deep learning systems to a traditional machine learning approach. The same features are used for all the models.ResultsWe have obtained the best results with the Bidirectional LSTM-CRF model, which has outperformed all previously proposed systems. The specialized embeddings have helped to cover unusual words in DrugBank and MedLine, but not in the i2b2/VA dataset.ConclusionsWe present a state-of-the-art system for DNR and CCE. Automated word embeddings has allowed us to avoid costly feature engineering and achieve higher accuracy. Nevertheless, the embeddings need to be retrained over datasets that are adequate for the domain, in order to adequately cover the domain-specific vocabulary.     

Analysis of Mycobacterium leprae gene expression using DNA microarray

Mycobacterium leprae, the causative agent of leprosy, does not grow under in vitro condition, making molecular analysis of this bacterium difficult. For this reason, bacteriological information regarding M. leprae gene function is limited compared with other mycobacterium species. In this study, we performed DNA microarray analysis to clarify the RNA expression profile of the Thai53 strain of M. leprae grown in footpads of hypertensive nude rats (SHR/NCrj-rnu). Of 1605 M. leprae genes, 315 showed signal intensity twofold higher than the median. These genes include Acyl-CoA metabolic enzymes and drug metabolic enzymes, which might be related to the virulence of M. leprae. In addition, consecutive RNA expression profile and in silico analyses enabled identification of possible operons within the M. leprae genome. The present results will shed light on M. leprae gene function and further our understanding of the pathogenesis of leprosy.     

Quantitative assessment of RUNX3 methylation in neoplastic and non-neoplastic gastric epithelia using a DNA microarray

Silencing of the RUNX3 gene by hypermethylation of its promoter CpG island plays a major role in gastric carcinogenesis. To quantitatively evaluate RUNX3 methylation, a fiber-type DNA microarray was used on which methylated and unmethylated sequence probes were mounted. After bisulfite modification, a part of the RUNX3 promoter CpG island, at which methylation is critical for gene silencing, was amplified by polymerase chain reaction using a Cy5 end-labeled primer. Methylation rates (MR) were calculated as the ratio of the fluorescence intensity of a methylated sequence probe to the total fluorescence intensity of methylated and unmethylated probes. Five gastric cancer cell lines were analyzed, as well as 26 primary gastric cancers and their corresponding non-neoplastic gastric epithelia. MR in four of the cancer cell lines that lost RUNX3 mRNA ranged from 99.0% to 99.7% (mean, 99.4%), whereas MR in the remaining cell line that expressed RUNX3 mRNA was 0.6%. In primary gastric cancers and their corresponding non-neoplastic gastric epithelia, MR ranged from 0.2% to 76.5% (mean, 22.7%) and from 0.7% to 25.1% (mean, 5.5%). Ten (38.5%) of the 26 gastric cancers and none of their corresponding non-neoplastic gastric epithelia had MR >30%. Most of the samples with MR >10% tested methylation-positive by conventional methylation-specific polymerase chain reaction (MSP). This microarray-based methylation assay is a promising method for the quantitative assessment of gene methylation.     

A hybrid feature selection method for DNA microarray data

Gene expression profiles, which represent the state of a cell at a molecular level, have great potential as a medical diagnosis tool. In cancer classification, available training data sets are generally of a fairly small sample size compared to the number of genes involved. Along with training data limitations, this constitutes a challenge to certain classification methods. Feature (gene) selection can be used to successfully extract those genes that directly influence classification accuracy and to eliminate genes which have no influence on it. This significantly improves calculation performance and classification accuracy. In this paper, correlation-based feature selection (CFS) and the Taguchi-genetic algorithm (TGA) method were combined into a hybrid method, and the K-nearest neighbor (KNN) with the leave-one-out cross-validation (LOOCV) method served as a classifier for eleven classification profiles to calculate the classification accuracy. Experimental results show that the proposed method reduced redundant features effectively and achieved superior classification accuracy. The classification accuracy obtained by the proposed method was higher in ten out of the eleven gene expression data set test problems when compared to other classification methods from the literature.     

Quantitative assessment of gene methylation in neoplastic and non‐neoplastic gastric epithelia using methylation‐specific DNA microarray

A fiber‐type DNA microarray was used to calculate methylation rates (MR) of four tumor suppressor genes, lysyl oxidase (LOX), p16, RUNX3, and tazarotene‐induced gene 1 (TIG1). MR were calculated in 26 primary gastric cancers and corresponding non‐neoplastic gastric epithelia, and the results were compared to those of conventional methylation‐specific polymerase chain reaction (MSP). MR ranged from 0.1% to 69.1% (mean, 18.3%) for LOX, 0.5–74.1% (mean, 15.7%) for p16, 0.2–76.5% (mean, 22.7%) for RUNX3, and 0.6–41.2% (mean, 5.8%) for TIG1 in primary gastric cancers, and from 0.1% to 25.8% (mean, 8.7%) for LOX, 1.0– 23.2% (mean, 10.3%) for p16, 0.7–25.1% (mean, 5.5%) for RUNX3, and 1.8–27.6% (mean, 11.4%) for TIG1 in corresponding non‐neoplastic gastric epithelia. Although MR varied significantly across different samples for both neoplastic and non‐neoplastic gastric epithelia, high‐level methylation (MR >40%) was cancer specific and was observed in 19.2%, 19.2%, 30.8%, and 3.8% of primary gastric cancers for LOX, p16, RUNX3, and TIG1, respectively. All samples with high‐level methylation, as well as some samples with low MR (particularly <10%) were judged to be methylation positive on conventional MSP. Quantitative analysis of gene methylation using methylation‐specific DNA microarray is a promising method for cancer diagnosis.     

APC基因甲基化定量检测芯片的建立

目的 建立抑癌基因APC（adenomatous polyposis coli，APC）启动子1A的甲基化定量芯片检测方法。方法选取一段420bp的APC基因启动子1A CpG密集序列作为靶序列，针对M0、M1、M2、M3、M4 5个CpG靶位点，设计一套检测甲基化与非甲基化的探针。采用脐带血DNA克隆体作为阴性、阳性质控品。结果甲基化阳性、阴性质控的芯片结果与测序吻合。每组探针中荧光强度由强至弱依次为，阳性质控（甲基化）：探针1〉2、3〉4；阴性质控（非甲基化）：探针3〉4、1〉2。5个位点的5条荧光强度标准曲线，尺。范围是0．93～0．99。M0、M1、M2、M3、M4 5个位点甲基化杂合型的检测范围分别为50．0％±3．6％、50．0％±6．9％、50．0％±3．5％、50．0％±8．5％、50．0％±7．3％。结论建立了APC基因启动子5个COG位点的甲基化定量检测芯片。