基于卷积神经网络的大肠杆菌启动子预测

目的 基于位点特异性打分矩阵（position-specific scoring matrices,PSSM）的预测模型已经取得了良好的效果,基于PSSM的各种优化方法也在不断发展,但准确率相对较低,为了进一步提高预测准确率,本文基于卷积神经网络（convolutional neural networks,CNN）算法做了进一步研究。方法 采用PSSM将启动子序列处理成数值矩阵,通过CNN算法进行分类。大肠杆菌K-12（Escherichia coli K-12,E.coli K-12,下文简称大肠杆菌）的Sigma38、Sigma54和Sigma70 3种启动子序列被作为正集,编码（Coding）区和非编码（Non-coding）区的序列为负集。结果 在预测大肠杆菌启动子的二分类中,准确率达到99%,启动子预测的成功率接近100%;在对Sigma38、Sigma54、Sigma70 3种启动子的三分类中,预测准确率为98%,并且针对每一种序列的预测准确率均可以达到98%以上。最后,本文以Sigma38、Sigma54、Sigma70 3种启动子分别和Coding区或者Non-coding区序列做四分类,预测得到的准确性为0.98,对3种Sigma启动子均衡样本的十交叉检验预测精度均可以达到0.95以上,海明距离为0.016,Kappa系数为0.97。结论 相较于支持向量机（support vector machine,SVM）等其他分类算法,CNN分类算法更具优势,并且基于CNN的分类优势,编码方式亦可以得到简化。     

基于双层BiGRU网络的哺乳动物组织m6A甲基化位点预测

目的 N⁶-甲基化腺苷（N⁶-methyladenosine，m⁶A）是RNA中最常见、最丰富的化学修饰，在很多生物过程中发挥着重要作用。目前已经发展了一些预测m⁶A甲基化位点的计算方法。然而，这些方法在针对不同物种或不同组织时，缺乏稳健性。为了提升对不同组织中m⁶A甲基化位点预测的稳健性，本文提出一种能结合序列反向信息来提取数据更高级特征的双层双向门控循环单元（bidirectional gated recurrent unit，BiGRU）网络模型。方法 本文选取具有代表性的哺乳动物组织m⁶A甲基化位点数据集作为训练数据，通过对模型网络、网络结构、层数和优化器等进行搭配，构建双层BiGRU网络。结果 将模型应用于人类、小鼠和大鼠共11个组织的m⁶A甲基化位点预测上，并与其他方法在这11个组织上的预测能力进行了全面的比较。结果表明，本文构建的模型平均预测接受者操作特征曲线下面积（area under the receiver operating characteristic curve，AUC）达到93.72%，与目前最好的预测方法持平，而预测准确率（accuracy，ACC）、敏感性（sensitivity，SN）、特异性（specificity，SP）和马修斯相关系数（Matthews correlation coefficient，MCC）分别为90.07%、90.30%、89.84%和80.17%，均高于目前的m⁶A甲基化位点预测方法。结论 和已有研究方法相比，本文方法对11个哺乳动物组织的m⁶A甲基化位点的预测准确性均达到最高，说明本文方法具有较好的泛化能力。     

不同城市居民头发中氧、氢稳定同位素检验和特征初探

目的 人体组织的稳定同位素组成与其生长期间的个体饮食情况、所处环境及代谢状况有关。人头发一经长出便不再与身体进行物质交换，化学性质稳定，易于采集，是研究人体组织稳定同位素组成的良好对象。构成人体的氧、氢元素主要来自于所摄入的水和食物，其中氧、氢稳定同位素组成会通过角蛋白的形式被记录于头发当中。不同地区居民头发中氧、氢稳定同位素组成差异可被用于推断人的饮食情况、生活地域和活动轨迹信息，在法庭科学等研究领域具有重要意义。方法 本研究利用元素分析仪-稳定同位素比质谱仪（EA-IRMS）对国内不同地区常住居民头发样本进行氧、氢稳定同位素比值检测和分析。结果 部分城市间居民头发δ¹⁸O和δ²H存在显著性差异，整体δ¹⁸O和δ²H存在显著正相关性。对所得稳定同位素数据进行判别分析推断头发的地域来源，其交互验证整体判别准确率为63.9%，结合碳、氮稳定同位素数据后，其判别准确率大幅提升，交互验证的整体判别准确率达到76.0%。随着判别分析中使用的稳定同位素种类的增加，判别函数模型的判别能力明显增强。结论 利用4种元素稳定同位素数据建立的多层感知器神经网络模型的整体判别准确率为82.8%，径向基函数神经网络模型整体判别准确率为78.8%，3种溯源推断数学模型中，多层感知器神经网络模型的判别准确率最高。     

北京三级医院医院内部绩效考核与薪酬分配机制期望意向比较研究

目的 了解北京三级医院内部绩效考核与薪酬分配机制的期望意向。方法 用内容分析法与描述性统计分析方法,比较医院内部绩效考核与薪酬分配机制期望意向。结果 两者具有内在的有机联系,具体表现在考核内容和依据、考核机制、原则及方式方法等4个方面。结论 了解期望意向是设计构建医院绩效评价系统的基础性工作,能够为医院绩效管理实务提供参考。     

研究报告: 基于Ser-SELEX技术的结肠癌血清适配体的筛选及其应用研究

目的 为了解决癌症早期诊断困难的问题，实现结肠癌的早期检测。方法 采用Ser-SELEX技术筛选了结肠癌血清的特异性适配体。通过前期结肠癌血清正筛-正常人血清反筛步骤和后期结肠癌血清正筛-其他癌症血清反筛步骤循环的方式，经过16轮筛选流程，共选取4条候选适配体，并对其进行序列分析、二级结构和三级结构模拟、特异性分析等。结果 候选适配体主要形成的结构是茎环和假结两种，qPCR法测试亲和力，K_d约为10 nmol/L，适配体与结肠癌患者血清特异性结合情况分析表明，候选适配体APT-2具有良好特异性，且此种方法检出率约为 82.5%。结论 适配体（APT-2）应用于结肠癌早期诊断具有良好的发展前景。     

三级医院管理人员职业规划现状分析和对策研究

目的 通过对上海市部分三级医院管理人员职业规划现状的调查、分析,探寻管理人员职业规划的适宜方法,并提出应对举措和政策支持,为推进公立医院持续发展助力。方法 研究选取上海市5家三级综合性医院、1家三级专科医院和1家中医类三级医院抽样,采用问卷形式对抽样人群进行基本情况、职业状态和职业规划现状的调查。结果 医院管理人员职业规划滞后,职业发展途径不畅,部分管理者晋升受阻。自身性格特质和学历、月薪收入成为影响职业规划与职业状态满意度的重要因素。结论 公立医院管理人员梯队建设不容忽视,引导管理人员进行职业规划、畅通职称晋升途径、提高职业归属感是保障公立医院持续发展的重要一环。     

基于质量功能展开的产科顾客非技术质量服务需求研究

目的 探讨产科顾客对非技术质量服务的需求。方法 按照预先设计的调查问卷从2010年3—5月对广东省某三级医院妇产科的产妇及其家属进行随机抽样调查并运用质量功能展开进行分析。结果 100﹪的产妇及家属对医院仪器设备的需求情况是需要的，其余需求均在90﹪以上。结论 医院应以顾客需求为导向，努力改善非技术质量服务，满足顾客需求，提高医疗服务质量。     

马钱子致大鼠体内毒性的研究*——“装袋”算法和16S rRNA基因测序技术在毒理学研究中的应用

目的 中药马钱子（Strychnos nux-vomica L.,SN）在临床上具有消肿止痛的功效,然而,由于含有生物碱类成分,马钱子具有一定毒性。人们对马钱子毒性所引起的大鼠内源性代谢变化及其对肠道微生物群代谢失调的潜在影响知之甚少,因此,马钱子的毒理学研究对其安全性评价具有重要意义。本研究将代谢组学和16S rRNA基因测序技术相结合来探索马钱子的致毒机制。方法 通过急性、蓄积性和亚急性毒性试验,分别确定马钱子的中毒剂量、毒性强度和毒性靶器官。超高效液相色谱-质谱联用技术用于分析大鼠灌胃马钱子后的血清、肝脏和肾脏样本。利用基于装袋算法的决策树和K最近邻（K nearest neighbor,KNN）模型对组学数据进行分类。从大鼠粪便中提取样本后,使用高通量测序平台对细菌的16s rRNA V3-V4区域进行分析。结果 装袋算法提高了样本分类的准确率。共鉴定出12个生物标志物,这些生物标志物的代谢失调可能是马钱子致体内毒性的原因。拟杆菌、粪厌氧棒菌、颤螺菌、双茎体菌等与肾肝功能的生理指标密切相关,这表明马钱子引起的肝肾损害可能与这些肠道细菌的代谢紊乱有关。结论 本文揭示了马钱子的体内致毒机制,为马钱子临床上的安全合理使用提供了科学依据。     

对北京市新农合定点三级医院监管现状的分析与思考

目的 为加强北京市定点三级医院监管提出合理化建议,保障新农合基金安全。方法 选取北京市7个区县与6个三甲医院,收集相关数据,与区县卫生局与医院相关人员进行定性访谈,了解北京市新农合三级医院监管现状及存在的问题。结果 目前各区县新农合管理机构对定点三级医院均无相应的管理措施,发生在三级医院的资金长期处于无人监管的状态,新农合基金的安全性受到了严重威胁。结论 必须从市卫生局和三级医院两方面入手,通过制定相应政策与新农合管理部门改革等方式,加强新农合定点三级医院监管。     

政府补偿与监管机制改革对公立医疗卫生机构收支状况的影响分析

目的 分析政府补偿与监管机制改革前后闵行区公立医疗卫生机构的收支及结构变化,并与上海市同期平均水平进行比较,探索研究政府补偿与监管机制改革对公立医疗卫生机构收支状况的影响。方法 进行问卷调查和二手数据分析。结果 改革后,闵行区公立医疗卫生机构的医疗与药品收入比例趋于合理,医疗费用得到控制,但政府财政补助水平仍有待提高。结论 政府应确保公立医院财政投入水平,落实取消药品加成后的相应补偿。     

Analysis of distance-based protein structure prediction by deep learning in CASP13

This paper reports the CASP13 results of distance-based contact prediction, threading, and folding methods implemented in three RaptorX servers, which are built upon the powerful deep convolutional residual neural network (ResNet) method initiated by us for contact prediction in CASP12. On the 32 CASP13 FM (free-modeling) targets with a median multiple sequence alignment (MSA) depth of 36, RaptorX yielded the best contact prediction among 46 groups and almost the best 3D structure modeling among all server groups without time-consuming conformation sampling. In particular, RaptorX achieved top L/5, L/2, and L long-range contact precision of 70%, 58%, and 45%, respectively, and predicted correct folds (TMscore > 0.5) for 18 of 32 targets. Further, RaptorX predicted correct folds for all FM targets with >300 residues (T0950-D1, T0969-D1, and T1000-D2) and generated the best 3D models for T0950-D1 and T0969-D1 among all groups. This CASP13 test confirms our previous findings: (a) predicted distance is more useful than contacts for both template-based and free modeling; and (b) structure modeling may be improved by integrating template and coevolutionary information via deep learning. This paper will discuss progress we have made since CASP12, the strength and weakness of our methods, and why deep learning performed much better in CASP13.     

Improving accuracy of protein contact prediction using balanced network deconvolution

Residue contact map is essential for protein three‐dimensional structure determination. But most of the current contact prediction methods based on residue co‐evolution suffer from high false‐positives as introduced by indirect and transitive contacts (i.e., residues A–B and B–C are in contact, but A–C are not). Built on the work by Feizi et al. (Nat Biotechnol 2013; 31:726–733), which demonstrated a general network model to distinguish direct dependencies by network deconvolution, this study presents a new balanced network deconvolution (BND) algorithm to identify optimized dependency matrix without limit on the eigenvalue range in the applied network systems. The algorithm was used to filter contact predictions of five widely used co‐evolution methods. On the test of proteins from three benchmark datasets of the 9th critical assessment of protein structure prediction (CASP9), CASP10, and PSICOV (precise structural contact prediction using sparse inverse covariance estimation) database experiments, the BND can improve the medium‐ and long‐range contact predictions at the L/5 cutoff by 55.59% and 47.68%, respectively, without additional central processing unit cost. The improvement is statistically significant, with a P‐value < 5.93 × 10^?3 in the Student's t‐test. A further comparison with the ab initio structure predictions in CASPs showed that the usefulness of the current co‐evolution‐based contact prediction to the three‐dimensional structure modeling relies on the number of homologous sequences existing in the sequence databases. BND can be used as a general contact refinement method, which is freely available at: http://www.csbio.sjtu.edu.cn/bioinf/BND/ . Proteins 2015; 83:485–496. © 2014 Wiley Periodicals, Inc.     

Predicting loop–helix tertiary structural contacts in RNA pseudoknots

Tertiary interactions between loops and helical stems play critical roles in the biological function of many RNA pseudoknots. However, quantitative predictions for RNA tertiary interactions remain elusive. Here we report a statistical mechanical model for the prediction of noncanonical loop–stem base-pairing interactions in RNA pseudoknots. Central to the model is the evaluation of the conformational entropy for the pseudoknotted folds with defined loop–stem tertiary structural contacts. We develop an RNA virtual bond-based conformational model (Vfold model), which permits a rigorous computation of the conformational entropy for a given fold that contains loop–stem tertiary contacts. With the entropy parameters predicted from the Vfold model and the energy parameters for the tertiary contacts as inserted parameters, we can then predict the RNA folding thermodynamics, from which we can extract the tertiary contact thermodynamic parameters from theory–experimental comparisons. These comparisons reveal a contact enthalpy (ΔH) of −14 kcal/mol and a contact entropy (ΔS) of −38 cal/mol/K for a protonated C⁺•(G–C) base triple at pH 7.0, and (ΔH = −7 kcal/mol, ΔS = −19 cal/mol/K) for an unprotonated base triple. Tests of the model for a series of pseudoknots show good theory–experiment agreement. Based on the extracted energy parameters for the tertiary structural contacts, the model enables predictions for the structure, stability, and folding pathways for RNA pseudoknots with known or postulated loop–stem tertiary contacts from the nucleotide sequence alone.     

CoCoNet—boosting RNA contact prediction by convolutional neural networks

Co-evolutionary models such as direct coupling analysis (DCA) in combination with machine learning (ML) techniques based on deep neural networks are able to predict accurate protein contact or distance maps. Such information can be used as constraints in structure prediction and massively increase prediction accuracy. Unfortunately, the same ML methods cannot readily be applied to RNA as they rely on large structural datasets only available for proteins. Here, we demonstrate how the available smaller data for RNA can be used to improve prediction of RNA contact maps. We introduce an algorithm called CoCoNet that is based on a combination of a Coevolutionary model and a shallow Convolutional Neural Network. Despite its simplicity and the small number of trained parameters, the method boosts the positive predictive value (PPV) of predicted contacts by about 70% with respect to DCA as tested by cross-validation of about eighty RNA structures. However, the direct inclusion of the CoCoNet contacts in 3D modeling tools does not result in a proportional increase of the 3D RNA structure prediction accuracy. Therefore, we suggest that the field develops, in addition to contact PPV, metrics which estimate the expected impact for 3D structure modeling tools better. CoCoNet is freely available and can be found at https://github.com/KIT-MBS/coconet.     

Better prediction of protein contact number using a support vector regression analysis of amino acid sequence

Background  

Protein tertiary structure can be partly characterized via each amino acid's contact number measuring how residues are spatially arranged. The contact number of a residue in a folded protein is a measure of its exposure to the local environment, and is defined as the number of C _β atoms in other residues within a sphere around the C _β atom of the residue of interest. Contact number is partly conserved between protein folds and thus is useful for protein fold and structure prediction. In turn, each residue's contact number can be partially predicted from primary amino acid sequence, assisting tertiary fold analysis from sequence data. In this study, we provide a more accurate contact number prediction method from protein primary sequence.     

The Genetic Algorithm and the Conformational Search of Polypeptides and Proteins

Abstract

The genetic algorithm is a technique of function optimization derived from the principles of evolutionary theory. We have adapted it to perform conformational search on polypeptides and proteins. The algorithm was first tested on several small polypeptides and the 46 amino acid protein crambin under the AMBER potential energy function. The probable global minimum conformations of the polypeptides were located 90% of the time and a non-native conformation of crambin was located that was 150kcal/mol lower in potential energy than the minimized crystal structure conformation. Next, we used a knowledge-based potential function to predict the structures of melittin, pancreatic polypeptide, and crambin. A 2.31 Å ΔRMS conformation of melittin and a 5.33 Å ΔRMS conformation of pancreatic polypeptide were located by genetic algorithm-based conformational search under the knowledge-based potential function. Although the ΔRMS of pancreatic polypeptide was somewhat high, most of the secondary structure was correct. The secondary structure of crambin was predicted correctly, but the potential failed to promote packing interactions. Finally, we tested the packing aspects of our potential function by attempting to predict the tertiary structure of cytochrome b ₅₆₂ given correct secondary structure as a constraint. The final predicted conformation of cytochrome b ₅₆₂ was an almost completely extended continuous helix which indicated that the knowledge-based potential was useless for tertiary structure prediction. This work serves as a warning against testing potential functions designed for tertiary structure prediction on small proteins.     

Finding recurrent RNA structural networks with fast maximal common subgraphs of edge-colored graphs

RNA tertiary structure is crucial to its many non-coding molecular functions. RNA architecture is shaped by its secondary structure composed of stems, stacked canonical base pairs, enclosing loops. While stems are precisely captured by free-energy models, loops composed of non-canonical base pairs are not. Nor are distant interactions linking together those secondary structure elements (SSEs). Databases of conserved 3D geometries (a.k.a. modules) not captured by energetic models are leveraged for structure prediction and design, but the computational complexity has limited their study to local elements, loops. Representing the RNA structure as a graph has recently allowed to expend this work to pairs of SSEs, uncovering a hierarchical organization of these 3D modules, at great computational cost. Systematically capturing recurrent patterns on a large scale is a main challenge in the study of RNA structures. In this paper, we present an efficient algorithm to compute maximal isomorphisms in edge colored graphs. We extend this algorithm to a framework well suited to identify RNA modules, and fast enough to considerably generalize previous approaches. To exhibit the versatility of our framework, we first reproduce results identifying all common modules spanning more than 2 SSEs, in a few hours instead of weeks. The efficiency of our new algorithm is demonstrated by computing the maximal modules between any pair of entire RNA in the non-redundant corpus of known RNA 3D structures. We observe that the biggest modules our method uncovers compose large shared sub-structure spanning hundreds of nucleotides and base pairs between the ribosomes of Thermus thermophilus, Escherichia Coli, and Pseudomonas aeruginosa.     

研究报告: 基于遗传算法的计算机辅助策略优化孕酮适配体

目的 本研究致力于优化孕酮（progesterone，P4）适配体的亲和力和选择性。方法 基于遗传算法（genetic algorithm，GA）的计算机辅助优化策略（in silico maturation，ISM），进行了4轮GA操作（含交叉变异、单点突变和双点突变操作），构建了初始文库和G1、G2、G3代ssDNA作为新的候选适配体库，采用分子对接对候选适配体进行筛选和分析，并使用迭代策略不断优化适配体。此外，还提出了一种较为准确预测ssDNA三级结构的方法，首先使用Mfold预测二级结构，继而使用RNAComposer建立与ssDNA相对应的RNA三级结构，输出的PDB文件使用Discovery Studio将RNA修改为DNA，最后使用Molecular Operating Environment对结构进行能量最小化处理。结果 到G2代，在局部搜索空间对P4S-0进行优化，筛选出P4G1-14、P4G2-20、P4G1-6、P4G1-7和P4G2-14这5条适配体作为P4的最佳候选适配体。采用AuNPs比色法初步验证优化后适配体的亲和力，继而构建了基于适配体结构开关的荧光法测定适配体的解离常数（equilibrium dissociation constant，K_D），并以此方法对适配体的选择性（对双酚A、雌二醇、睾酮和皮质醇）进行了评估。结论 通过ISM优化后的适配体，对P4的亲和力较原适配体有了较大提升，仍保留着识别结构类似分子的选择性。     

Comparison of P-RnaPredict and mfold--algorithms for RNA secondary structure prediction

MOTIVATION: Ribonucleic acid is vital in numerous stages of protein synthesis; it also possesses important functional and structural roles within the cell. The function of an RNA molecule within a particular organic system is principally determined by its structure. The current physical methods available for structure determination are time-consuming and expensive. Hence, computational methods for structure prediction are sought after. The energies involved by the formation of secondary structure elements are significantly greater than those of tertiary elements. Therefore, RNA structure prediction focuses on secondary structure. RESULTS: We present P-RnaPredict, a parallel evolutionary algorithm for RNA secondary structure prediction. The speedup provided by parallelization is investigated with five sequences, and a dramatic improvement in speedup is demonstrated, especially with longer sequences. An evaluation of the performance of P-RnaPredict in terms of prediction accuracy is made through comparison with 10 individual known structures from 3 RNA classes (5S rRNA, Group I intron 16S rRNA and 16S rRNA) and the mfold dynamic programming algorithm. P-RnaPredict is able to predict structures with higher true positive base pair counts and lower false positives than mfold on certain sequences. AVAILABILITY: P-RnaPredict is available for non-commercial usage. Interested parties should contact Kay C. Wiese (wiese@cs.sfu.ca).     

Contact prediction for beta and alpha‐beta proteins using integer linear optimization and its impact on the first principles 3D structure prediction method ASTRO‐FOLD

An integer linear optimization model is presented to predict residue contacts in β, α + β, and α/β proteins. The total energy of a protein is expressed as sum of a C^α? C^α distance dependent contact energy contribution and a hydrophobic contribution. The model selects contact that assign lowest energy to the protein structure as satisfying a set of constraints that are included to enforce certain physically observed topological information. A new method based on hydrophobicity is proposed to find the β‐sheet alignments. These β‐sheet alignments are used as constraints for contacts between residues of β‐sheets. This model was tested on three independent protein test sets and CASP8 test proteins consisting of β, α + β, α/β proteins and it was found to perform very well. The average accuracy of the predictions (separated by at least six residues) was ～61%. The average true positive and false positive distances were also calculated for each of the test sets and they are 7.58 Å and 15.88 Å, respectively. Residue contact prediction can be directly used to facilitate the protein tertiary structure prediction. This proposed residue contact prediction model is incorporated into the first principles protein tertiary structure prediction approach, ASTRO‐FOLD. The effectiveness of the contact prediction model was further demonstrated by the improvement in the quality of the protein structure ensemble generated using the predicted residue contacts for a test set of 10 proteins. Proteins 2010. © 2010 Wiley‐Liss, Inc.