共查询到20条相似文献,搜索用时 62 毫秒
1.
定量构效关系(QSAR)是化学品安全评价中有用的工具之一。本文叙述它的应用背景、基本原理、学科历史进展、概念模型、数学模型和算法,着重介绍作者开发的实用量子化学计算程序包,用以产生分子结构参数,所建立的化学物质毒性数据库可用来获取大量生物活性数据,还可用模式识别程序包构筑构效定量关系。本文对其研究前景也作了叙述。 相似文献
2.
3.
分子扩散系数(D)是获得污染物与环境介质之间的平衡分配系数(K)的重要前提,然而通过实验测定获取污染物的扩散系数的过程过于繁琐,因此需开发一种更为简单、高效、准确的预测模型来定量预测扩散系数.为此,本文搜集了一些多环芳香烃(PAHs)和多氯联苯(PCBs)在低密度聚乙烯膜(LDPE)上扩散系数(log D)的实测值,基于定量结构-活性关系(QSAR),利用逐步多元线性回归(MLR)构建了预测D值的模型.模型的决定系数Radj2为0.941,交叉验证系数QLOO2为0.934,外部系数Qext2为0.895.结果表明,该QSAR模型具有良好的拟合优度、稳健性和预测能力,其可用来预测应用域内有机污染物在LDPE膜上的扩散系数. 相似文献
4.
基于定量构效关系(QSAR),运用线性(逐步多元回归MLR)和非线性(支持向量机SVM)两种计算方法开发了两种可靠且高效预测聚苯乙烯二乙烯基苯树脂(XAD)和空气之间分配系数(KXAD-A)的模型.构建模型的数据包含醇类(Alcohols),苯类(Benzenes),多氯联苯(PCBs)和多环芳香烃(PAHs)等,共计70种有机污染物.两个模型的决定系数R2adj和外部验证系数Q2ext均在0.930以上,同时所有物质均在定义的应用域内,结果表明两种QSAR模型有较高的拟合度、稳健性和较为优秀的预测能力,且非线性(SVM)模型比线性(MLR)模型的拟合效果更好. 相似文献
5.
苯胺类化合物在不同pH值下对大型蚤的急性毒性及QSAR研究 总被引:6,自引:0,他引:6
测定了13种苯胺类化合物在不同pH下(6.0,7.8,9.0)对大型蚤(Daphnia magna)的24h半数活动抑制浓度24h-1C50,应用三种理化参数logP,TSA和pKa,对毒性数据进行了定量构效关系(QSARs)研究,并在此基础上初步探讨了苯胺类化合物的毒性机制。 相似文献
6.
硝基苯类化合物的结构/毒性定量构效关系研究 总被引:6,自引:0,他引:6
为了定量结构/毒性相关性研究提取了拓扑指数Am,分子连接性指数^mXt量子化学参数及分子体积等,同时运用最佳变量子集算法(Leaps and Bounds)进行了变量的压缩和选择,进而实施了多元间归分析,并由所得结果进行了硝基苯类化合物结构与毒性关系的理论解释,同时还进行了人工神经网络法对于该类化合物毒性的预测,其结果明显好于多元回归法。 相似文献
7.
取代苯类有机物拓扑指数与酵母菌毒性的人工神经网络 总被引:1,自引:0,他引:1
以酿酒酵母菌作为指示生物,对78种取代苯类有机物开展了定量构效关系研究。采用人工神经网络(ANN)建模方法,以酵母菌的1g(1/Cmlz)为活性参数,点价自相关拓扑指数(A、B、C和D值)为分子结构参数,建立了取代苯类有机物定量构效关系神经网络模型;从24种点价自相关拓扑指数中在线筛选出A[0]、A[1]、C[3]、C[5]和D[3]等5种主要结构参数作为ANN的输入节点,并讨论了它们对酵母菌毒性的影响。将模型用于23种取代苯类有机物的生物毒性预测,结果满意。建立了Cmlz与LC50之间线性关系良好的相关性数学模型。 相似文献
8.
9.
10.
《环境科学与技术》2021,44(3):135-140
该文在化合物二维结构基础上,对48个酯类化合物结构进行了表征,进而建立了化合物结构与水生毒性关系模型,模型的相关系数(R~2)分别为0.926 6和0.917 4,标准偏差(SD)分别为0.257 6和0.255 8。采用留一法交互检验评价了模型的稳定性,得到模型交互检验的相关系数(RCV~2)分别为0.885 6和0.799 2,标准偏差(SD_(CV))分别为0.255 8和0.294 5。运用外部样本检验了模型的预测能力,得到外部预测的相关系数(Rtest2)分别为0.991 0和0.952 3,标准偏差(SD_(test))分别为0.079 3和0.182 9。分子结构描述符能较好地表现化合物结构特征,所建模型拟合效果好、稳定性强、预测准确性高。对于环境中有毒化合物的结构-毒性关系研究具有较好的参考价值。 相似文献
11.
12.
应用自适应分子结构描述符生成方法和神经网络数值模式,研究62种烹调食品过程中产生的杂环芳胺结构与致变活性间的关系。该模式预报结果与实验测定结果符合良好;致变剂、非致变剂和勉强有致变活性剂三类间正确分类率超过90%。通过6次自适应分子结构描述符选择迭代,得到5种特征分子描述符为:芳环碳原子取代甲基数、芳环氮原子取代甲基数、母体共轭环数、端环增活结构数和端环抑活结构数。其中,增活结构为具有共轭烯烃碎片结构;抑活结构具有短共轭烯烃结构或不具有共轭烯烃结构。最后,对该构效关系的起因进行了定性解释。 相似文献
13.
14.
污水处理厂出水总氮(TN)浓度是评价水处理效果的关键指标之一。建立BP神经网络模型对污水处理厂脱氮工艺进行模拟,引入自回归整合移动平均模型(ARIMA模型)对污水处理厂未来短期出水TN浓度进行预测。结果表明:BP神经网络模型在训练集和测试集模拟结果的平均相对误差分别为15.9%和16.5%,模型预测结果的平稳性较差;ARIMA模型对未来7 d出水TN浓度的时序预测平均误差为4.41%,预测精度较高;2个模型相结合有助于实现污水处理厂快捷和高效的在线检测。 相似文献
15.
Surface monitoring, vertical atmospheric column observation, and simulation using chemical transportation models are three dominant approaches for perception of fine particles with diameters less than 2.5 micrometers (PM2.5) concentration. Here we explored an image-based methodology with a deep learning approach and machine learning approach to extend the ability on PM2.5 perception. Using 6976 images combined with daily weather conditions and hourly time data in Shanghai (2016), trained by hourly surface monitoring concentrations, an end-to-end model consisting of convolutional neural network and gradient boosting machine (GBM) was constructed. The mean absolute error, the root-mean-square error and the R-squared for PM2.5 concentration estimation using our proposed method is 3.56, 10.02, and 0.85 respectively. The transferability analysis showed that networks trained in Shanghai, fine-tuned with only 10% of images in other locations, achieved performances similar to ones from trained on data from target locations themselves. The sensitivity of different regions in the image to PM2.5 concentration was also quantified through the analysis of feature importance in GBM. All the required inputs in this study are commonly available, which greatly improved the accessibility of PM2.5 concentration for placed and period with no surface observation. And this study makes an exploratory attempt on pollution monitoring using graph theory and deep learning approach. 相似文献
16.
The objective of this study was to determine the relationship between PM_(10) and PM_(2.5) levels as related to meteorological conditions and traffic flow using both a linear regression analysis and a path analysis. The Particulate matter(PM) samples were collected from Sukhumvit road, Bangkok, Thailand, at both open(104 samples) and covered(92 samples)areas along the road. Fifteen percent of all samples were separated before the statistical models were run and used for model validation. The results from the path analysis were more elaborate than those from the linear regression, thus indicating that meteorological conditions had a direct effect on the particulate levels and that the effects of traffic flow were more variable in open areas. The model also indicated that meteorological conditions had an indirect effect and that traffic flow had a direct effect on particulate levels in covered areas. The model validation results indicated that for open areas, the R~2 values were not very different between the path analysis and the linear regression model, but that the path analysis was more accurate than the linear regression model at very low PM concentrations. At high PM concentrations, the path analysis model also had a better fit than did the linear regression, so the predictions from the path analysis model were more accurate than those from the linear regression. 相似文献
17.
Using information derived from the voluntary system of notification of congenital malformations in England and Wales, the birth prevalence of anencephaly and spina bifida was estimated to have declined by 80 per cent from 31.5 to 6.2 per 10 000 between 1964–1972 and 1985. Over the same period, notified terminations of pregnancy with a suspected fetal central nervous system abnormality increased from less than 1 per cent to 56 per cent of neural tube defect births and central nervous system terminations combined, accounting for 31 per cent of the decline in births. Routinely collected national statistics provide a method for monitoring the impact of screening for open neural tube defects. However because they are incomplete and lack detail an alternative method of monitoring is needed. This paper includes an outline of such a method, together with the results of a pilot study designed to assess the feasibility of monitoring screening in the Oxford Region. 相似文献
18.
为实现混合底物的高效定向转化,以产絮菌根癌农杆菌(Agrobactrium tumefaciens)F2为研究对象,考察不同单一碳源及不同初始浓度对菌体生长、絮凝效能及絮凝剂产量的变化规律,采用BP算法构建絮凝效能及产量预测神经网络.产絮菌F2利用葡萄糖时的絮凝效能和产量分别为88.98%和2.20 g·L-1,过低的初始浓度将影响产量,不低于7.5 g·L-1为佳.以D-(+)-葡萄糖、D-半乳糖和D-甘露糖3种单糖为混合碳源,构建网络结构为3-5-2的产絮效能及絮凝剂产量预测模型,对两个输出层的预测误差范围均在4%以内,预测葡萄糖、半乳糖、甘露糖浓度的最优解为6.59 g·L-1、1.32 g·L-1、3.57 g·L-1,经验证混合碳源发酵产絮可使絮凝效能和产量比单一葡萄糖发酵时分别提高6.87%和26.82%,本文为产絮菌F2利用含糖有机质废液发酵产絮凝剂提供数据参考. 相似文献
19.
在实际污水处理厂运行过程中,其最终出水水质会受多种因素影响制约,而基于生物反应机理的活性污泥数学模型(ASM)并未将这些生物反应以外的因素考虑在内,由此带来一些不足.对此,本文提出可通过基于数据挖掘技术的黑箱模型对污水厂处理效果进行模拟预测.结合具体实际分析,提出可将BP神经网络与马尔可夫链组合应用于污水处理脱氮效果预测中.首先,通过BP神经网络模型对北京某大型污水处理厂实际进出水数据和工艺参数进行粗略拟合;其次,利用马尔可夫链对拟合结果及误差进行状态划分以进一步提高预测精确度;最后,运用基于BP神经网络与马尔可夫链的组合模型预测分析了该厂的实际出水水质.试验结果表明,BP神经网络适用于污水处理脱氮过程的拟合计算,而通过与马尔可夫链组合,可以提高模拟预测的精度和可靠性. 相似文献