基于反向传播算法神经网络的信用评分系统预测力研究

为了提高信用评分系统的预测准确性和稳定性，建立了基于反向传播（BP）算法神经网络的信用评分系统，并提出信用评分系统预测力和预测稳定性验证的新方法．结合信用评分问题的实际特点建立了模型并确定了参数，然后采用一种正向选入法确定输入变量，进行模型训练，并通过引入接收器操作特征曲线的分析理论、曲线面积（AUC）值及信息理论等评价方式，对所构造的神经网络信用评分系统预测力进行评价，最后利用自抽样法构造出多个验证样本来评估信用评分系统的稳定性．与传统的逻辑信用评分系统的比较结果表明，BP神经网络信用评分系统具有更高的预测准确性和稳定性，其AUC值平均提高0．0367，AUC值的标准误差平均降低0．005．     

基于DNA结合特异性权重矩阵的TAL效应物靶标预测

计算预测出TAL效应物的候选靶标有助于高效地确定TAL效应物的靶基因,进而阐明TAL效应物的生物学功能,但是目前在TAL效应物靶标计算预测方面的研究仍然很少.为了设计出预测TAL效应物靶标的有效算法,基于TAL效应物的已知靶标数据,构建了TAL效应物靶点的RVD-核苷酸关联矩阵,并将RVD-核苷酸关联矩阵归一化成RVD特异性概率矩阵,为靶标预测构造新的打分函数.实验结果表明,改进的TAL效应物靶标预测算法对大部分已知靶标预测的打分排名比已有算法更靠前,并且结合基因表达数据可以预测出TAL效应物的新的候选靶标.     

Inhibitor docking screened by the modified SAFE_p scoring function: application to cyclic urea HIV-1 PR inhibitors

Our laboratory has in the past developed a method for the prediction of ligand binding free energies to proteins, referred to as SAFE_p (Solvent free energy predictor). Previously, we have applied this protocol for the prediction of the binding free energy of peptidic and cyclic urea HIV-1 PR inhibitors, whose X-ray structures bound to enzyme are known. In this work, we present the first account of a docking simulation, where the ligand conformations were screened and inhibitor ranking was predicted on the basis of a modified SAFE_p approach, for a set of cyclic urea-HIV-1 PR complexes whose structures are not known. We show that the optimal dielectric constant for docking is rather high, in line with the values needed to reproduce some protein residue properties, like pKa's. Our protocol is able to reproduce most of the observed binding ranking, even in the case that the components of the equation are not fitted to experimental data. Partition of the binding free energy into pocket and residue contributions sheds light into the importance of the inhibitor's fragments and on the prediction of "hot spots" for resistance mutations.     

A large decoy set of protein–protein complexes produced by flexible docking

Computational methods are needed to help characterize the structure and function of protein–protein complexes. To develop and improve such methods, standard test problems are essential. One important test is to identify experimental structures from among large sets of decoys. Here, a flexible docking procedure was used to produce such a large ensemble of decoy complexes. In addition to their use for structure prediction, they can serve as a proxy for the nonspecific, protein–protein complexes that occur transiently in the cell, which are hard to characterize experimentally, yet biochemically important. For 202 homodimers and 41 heterodimers with known X‐ray structures, we produced an average of 1217 decoys each. The structures were characterized in detail. The decoys have rather large protein–protein interfaces, with at least 45 residue–residue contacts for every 100 contacts found in the experimental complex. They have limited intramonomer deformation and limited intermonomer steric conflicts. The decoys thoroughly sample each monomer's surface, with all the surface amino acids being part of at least one decoy interface. The decoys with the lowest intramonomer deformation were analyzed separately, as proxies for nonspecific protein–protein complexes. Their interfaces are less hydrophobic than the experimental ones, with an amino acid composition similar to the overall surface composition. They have a poorer shape complementarity and a weaker association energy, but are no more fragmented than the experimental interfaces, with 2.1 distinct patches of interacting residues on average, compared to 2.6 for the experimental interfaces. The decoys should be useful for testing and parameterizing docking methods and scoring functions; they are freely available as PDB files at http://biology.polytechnique.fr/decoys . © 2010 Wiley Periodicals, Inc. J Comput Chem, 2010     

Using correlated parameters for improved ranking of protein-protein docking decoys

A successful protein–protein docking study culminates in identification of decoys at top ranks with near‐native quaternary structures. However, this task remains enigmatic because no generalized scoring functions exist that effectively infer decoys according to the similarity to near‐native quaternary structures. Difficulties arise because of the highly irregular nature of the protein surface and the significant variation of the nonbonding and solvation energies based on the chemical composition of the protein–protein interface. In this work, we describe a novel method combining an interface‐size filter, a regression model for geometric compatibility (based on two correlated surface and packing parameters), and normalized interaction energy (calculated from correlated nonbonded and solvation energies), to effectively rank decoys from a set of 10,000 decoys. Tests on 30 unbound binary protein–protein complexes show that in 16 cases we can identify at least one decoy in top three ranks having ≤10 Å backbone root mean square deviation from true binding geometry. Comparisons with other state‐of‐art methods confirm the improved ranking power of our method without the use of any experiment‐guided restraints, evolutionary information, statistical propensities, or modified interaction energy equations. Tests on 118 less‐difficult bound binary protein–protein complexes with ≤35% sequence redundancy at the interface showed that in 77% cases, at least 1 in 10,000 decoys were identified with ≤5Å backbone root mean square deviation from true geometry at first rank. The work will promote the use of new concepts where correlations among parameters provide more robust scoring models. It will facilitate studies involving molecular interactions, including modeling of large macromolecular assemblies and protein structure prediction. © 2010 Wiley Periodicals, Inc. J Comput Chem, 2011.     

基于支持向量机的癌细胞经典分泌蛋白与非经典分泌蛋白识别研究

基于支持向量机算法,本文提出了一种能快速准确区分癌细胞经典分泌蛋白与非经典分泌蛋白的方法.通过严格的特征筛选,氨基酸组成、位置特异性得分矩阵和信号肽组成了最优特征集.测试集检测结果表明,本方法对癌细胞经典分泌蛋白与非经典分泌蛋白具有较强的区分能力,可为寻找到不同种类癌症间通用的生物标志物提供理论参考.     

试卷识别码的集成设计与识别算法

设计一种可简单书写的数码数字,并将其作为学号识别码直接集成在试卷上,有效地实现试卷与学生的一一对应关系.分析纸质扫描试卷识别码的识别算法,处理了识别中可能出现的多种异常情况,并将该设计和算法应用到选择类试题答案的自动识别和批阅中.实测结果表明:所提出的集成设计,具有占用空间小、连写简便、识别快速、识别率高和低成本等特点.     

基于SVM的个人房贷信用评估数据分析

采用SVM的序列最小最优化算法（SMO）作为训练算法对商业银行个人房贷信用评估数据进行分析,着重探讨了在个人房贷信用评估中分别应用径向基核函数参数和SMO训练算法中的参数调整对准确度的影响;通过银行实际数据集将该算法与C4．5和神经网络进行了比较,支持向量机对个人信用评估的总精度高于其他两种算法;支持向量机对实际的住房抵押贷款数据进行信用评估效果较好,且参数调整对试验结果有影响。     

基于综合加权评分法的钒钛磁铁矿高炉渣系优化

在实验室条件下,以国内某钢铁企业提供的钒钛磁铁矿现场高炉渣为基础,利用纯化学试剂调整炉渣成分,采用RTW熔体物性测定仪进行了5因素4水平的正交试验研究,检测了炉渣冶金性能;然后运用综合加权评分法对试验结果进行分析,探索得出高炉冶炼钒钛磁铁矿的适宜渣系:二元碱度R2115,MgO质量分数14%,Al2O3质量分数13%,TiO2质量分数7%,V2O5质量分数020%.对渣系综合指标影响从大到小依次为:V2O5含量,MgO含量,二元碱度R2,TiO2含量,Al2O3含量.     

Scoring indices,top-truncated preferences,and splitting invariance

We present a new characterization of the class of weight-based scoring indices for ranking problems with top-truncated preferences. The main novel axiom is Splitting Invariance: if an alternative is split up into a number of distinct yet unranked alternatives, then the total score of these alternatives should increase by the score of the original alternative, and the scores of the other alternatives should not change.