A combination of modified particle swarm optimization algorithm and support vector machine for gene selection and tumor classification

In the analysis of gene expression profiles, the number of tissue samples with genes expression levels available is usually small compared with the number of genes. This can lead either to possible overfitting or even to a complete failure in analysis of microarray data. The selection of genes that are really indicative of the tissue classification concerned is becoming one of the key steps in microarray studies. In the present paper, we have combined the modified discrete particle swarm optimization (PSO) and support vector machines (SVM) for tumor classification. The modified discrete PSO is applied to select genes, while SVM is used as the classifier or the evaluator. The proposed approach is used to the microarray data of 22 normal and 40 colon tumor tissues and showed good prediction performance. It has been demonstrated that the modified PSO is a useful tool for gene selection and mining high dimension data.     

Thermally Induced Intra‐Carboxyl Proton Shuttle in a Molecular Rack‐and‐Pinion Cascade Achieving Macroscopic Crystal Deformation

Proton transport via dynamic molecules is ubiquitous in chemistry and biology. However, its use as a switching mechanism for properties in functional molecular assemblies is far less common. In this study, we demonstrate how an intra‐carboxyl proton shuttle can be generated in a molecular assembly akin to a rack‐and‐pinion cascade via a thermally induced single‐crystal‐to‐single‐crystal phase transition. In a triply interpenetrated supramolecular organic framework (SOF), a 4,4′‐azopyridine (azpy) molecule connects to two biphenyl‐3,3′,5,5′‐tetracarboxylic acid (H₄BPTC) molecules to form a functional molecular system with switchable mechanical properties. A temperature change reversibly triggers a molecular movement akin to a rack‐and‐pinion cascade, which mainly involves 1) an intra‐carboxyl proton shuttle coupled with tilting of the azo molecules and azo pedal motion and 2) H₄BPTC translation. Moreover, both the molecular motions are collective, and being propagated across the entire framework, leading to a macroscopic crystal expansion and contraction.     

基于SVR和k-近邻群的组合预测在QSAR中的应用

为提高定量构效关系(QSAR)研究的预测精度,发展了一种新的基于支持向量机回归(SVR)非线性筛选分子结构描述符、基于k-近邻群的非线性组合预测方法.首先以均方误差(MSE)最小为原则,以留一法通过多轮末尾淘汰实施分子结构描述符的非线性SVR汰选并给出最优核函数和相应保留描述符;其次基于待测样本与训练样本保留描述符向量的欧氏距离,以不同k-近邻群子模型双重留一法预测值反映样本集的异质性;然后基于MSE最小,以留一法通过多轮末尾淘汰实施近邻群子模型的非线性SVR汰选并给出最优核函数和相应保留子模型;最后基于保留子模型以双重留一法实施组合预测.以取代苯胺和苯酚类化合物对大型溞的QSAR实例验证表明:新方法在所有参比模型中预测精度最高,且能更精细地反映描述符与化合物毒性间的非线性关系,具结构风险最小、非线性、适于小样本,能有效克服过拟合、维数灾和局极小,非线性筛选描述符和子模型,非线性组合预测,自动选择最优核函数及其相应参数,泛化推广能力优异、预测精度高等诸多优点,在QSAR研究中有广泛应用前景.     

烷基苯酚类化合物的气相色谱保留值与其结构参数的定量关系

计算了44个烷基苯酚类化合物的组成、拓扑、几何、静电和量子化学等结构参数,运用启发式方法对这些结构参数进行筛选,得到了含3个变量的化合物的定量结构与色谱保留值的线性关系模型,同时以这3个变量作为支持向量机模型的输入变量建立非线性回归模型。两种方法的相关系数(R2 )分别为0.98和0.92,相应的均方根误差分别是0.99和2.77。通过对两种模型的稳定性和预测能力的比较,发现线性模型能够更好地反映烷基苯酚的气相色谱保留值与其结构参数之间的定量关系。在已知烷基苯酚类化合物结构参数的情况下,线性回归模型更有助于它们的色谱分析。     

共轴双脉冲激光诱导击穿光谱和最小二乘支持向量机法定量分析植物油中铬

利用共轴双脉冲激光诱导击穿光谱( DP-LIBS)技术对植物油(大豆油、花生油和玉米油)中的重金属铬( Cr)含量进行定量分析。采用Ava-Spec双通道高精度光谱仪采集样品的LIBS光谱,然后通过其LIBS谱线图确定了CN分子谱线(421.49 nm)、Ca原子谱线(422.64 nm)及Cr的3条原子谱线(425.39、427.43和428.87 nm),根据上述谱线建立了Cr元素的单变量定标模型和最小二乘支持向量机(LS-SVM)校正模型,并用验证样品对它们进行检验。研究结果表明,对于单变量定标法,大豆油、花生油及玉米油验证样品的平均预测相对误差(PRE)分别为12.57%,12.11%和13.72%;对于三变量LS-SVM法,其定标样品真实值与预测值之间的拟合度 R2分别为0.9785,0.9792和0.9654,验证样品的平均 PRE 分别为8.92%,8.33%和10.98%;对于五变量LS-SVM法(增加两基体元素谱线变量),其定标样品真实值与预测值之间的拟合度R2分别为0.9895,0.9901和0.9855,验证样品的平均PRE分别为7.46%,8.96%和8.95%。由此可知,LS-SVM校正模型性能优于单变量定标法,且五变量LS-SVM校正模型性能优于三变量LS-SVM校正模型;采用LS-SVM法及引入合适的基体元素谱线( CN、Ca)能有效减小定量分析误差,提高LIBS技术对植物油中Cr含量预测的精度。     

Neural network and ReaxFF comparison for Au properties

We have studied how ReaxFF and Behler–Parrinello neural network (BPNN) atomistic potentials should be trained to be accurate and tractable across multiple structural regimes of Au as a representative example of a single‐component material. We trained these potentials using subsets of 9,972 Kohn‐Sham density functional theory calculations and then validated their predictions against the untrained data. Our best ReaxFF potential was trained from 848 data points and could reliably predict surface and bulk data; however, it was substantially less accurate for molecular clusters of 126 atoms or fewer. Training the ReaxFF potential to more data also resulted in overfitting and lower accuracy. In contrast, BPNN could be fit to 9,734 calculations, and this potential performed comparably or better than ReaxFF across all regimes. However, the BPNN potential in this implementation brings significantly higher computational cost. © 2016 Wiley Periodicals, Inc.     

摩擦磨损试验机模拟活塞环-缸套摩擦行为的功能开发

参考活塞环-缸套的实际运行条件,结合SRV-4摩擦磨损试验机自身的性能特点和工作原理,通过开发设计,增加合理的硬件及软件测试条件,实现摩擦磨损试验机模拟活塞环-缸套摩擦行为的功能.系统测试结果表明：功能开发后的摩擦磨损试验机可在较短时间内获得活塞环-缸套摩擦副性能优劣的试验数据,满足快速、直观评价活塞环-缸套的摩擦磨损性能的需要,在活塞环-缸套摩擦副研究中具有重要的应用价值.     

从电子工业“脊梁”到全面开花的镓元素

镓是第一个根据化学元素周期律预言并在自然界中证实的元素，是室温下电导率和热导率均为最大的液态物质，镓在电子工业中得到了广泛应用，被誉为电子工业“脊梁”。近十几年来，镓的更多应用潜力被发掘出来，在电子工业、散热、增材制造、柔性机器、生物医学等领域均有重要的应用前景。