在为用户选择并组合其满意的Web服务时,预测Web服务缺失的服务质量(quality of service,QoS)值是必要的。为解决该问题,提出一种R-SRec模型,加入用户地理位置信息和服务的反向预测,提高预测精准度。在基于用户的协同过滤算法中融入用户...在为用户选择并组合其满意的Web服务时,预测Web服务缺失的服务质量(quality of service,QoS)值是必要的。为解决该问题,提出一种R-SRec模型,加入用户地理位置信息和服务的反向预测,提高预测精准度。在基于用户的协同过滤算法中融入用户地理位置信息,提高参与预测数据的空间相关度;在基于服务的协同过滤算法中加入Web服务反向预测,缓解数据稀疏问题;根据不同的置信度融合两种算法,对缺失的QoS值进行预测。使用真实的数据集与其它3类常用的算法进行比较,实验结果表明,该方法的预测结果精确度更高。展开更多
The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown adv...The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown advantage for the latter in different domains of application. However, some difficulties still deteriorate the performance of the support vector machines. The main one is related to the setting of the hyperparameters involved in their training. Techniques based on meta-heuristics have been employed to determine appropriate values for those hyperparameters. However, because of the high noneonvexity of this estimation problem, which makes the search for a good solution very hard, an approach based on Bayesian inference, called relevance vector machine, has been proposed more recently. The present paper aims at investigating the suitability of this new approach to the short-term load forecasting problem.展开更多
采用反向预测和分子对接技术,评价鄂西香茶菜甲素成为抗肿瘤先导物的可行性。在反向预测的基础上,利用网络药理学技术构建"疾病-化合物-靶点-通路"网络。结果显示,鄂西香茶菜甲素预测靶点中有39个与肿瘤密切相关,参与调节细...采用反向预测和分子对接技术,评价鄂西香茶菜甲素成为抗肿瘤先导物的可行性。在反向预测的基础上,利用网络药理学技术构建"疾病-化合物-靶点-通路"网络。结果显示,鄂西香茶菜甲素预测靶点中有39个与肿瘤密切相关,参与调节细胞凋亡、细胞周期、肿瘤转移等多种细胞活动,并可调节雌激素信号转导途径和炎症应答。采用Discovery Studio 2020软件进行分子对接及TOPKAT毒性预测;鄂西香茶菜甲素与肿瘤相关靶点ABL1、ESR1、SRC、BCL-XL的结合亲和力均强于冬凌草甲素,且其致突变性、啮齿动物致癌性、大鼠口服LD50毒性均小于冬凌草甲素;进而,采用体外实验证实了鄂西香茶菜甲素的抗肿瘤活性,并初步探讨了其作用机制。结果显示,鄂西香茶菜甲素在细胞毒、抑制细胞集落形成和诱导凋亡方面均优于冬凌草甲素。鄂西香茶菜甲素有望成为新的抗肿瘤先导物,具有较大的研究前景。且鄂西香茶菜素对雌激素信号转导通路调节作用的预测结果值得进行深入研究,为其抗肿瘤作用机制的研究提供新视角。展开更多
As a powerful tool for target prediction,reverse docking remains largely unexplored.The objective evaluation of reverse docking software can help us know better about the strength and weakness of these tools,hence gui...As a powerful tool for target prediction,reverse docking remains largely unexplored.The objective evaluation of reverse docking software can help us know better about the strength and weakness of these tools,hence guiding us in target prediction.In the present study,we evaluated the target prediction power of Glide(SP)against general inhibitors and selective inhibitors.The results showed that the scoring tendency could be different for each ligand,and overall scoring sampling was necessary for a better understanding of the docking score for a certain protein-ligand pair.Besides,the input conformation of the binding pocket could affect the docking result.Glide(SP)showed a preferable performance on the target prediction of the general inhibitors.However,the accuracy of the target prediction of the selective inhibitors was relatively low,indicating that Glide(SP)might not be capable for this task.The case study about COVID-19 proved that coagulation factor Xa might be a potential target of chloroquine.Therefore,we recommend the further development of reverse docking tools and rectification of inter-target scoring bias.展开更多
文摘在为用户选择并组合其满意的Web服务时,预测Web服务缺失的服务质量(quality of service,QoS)值是必要的。为解决该问题,提出一种R-SRec模型,加入用户地理位置信息和服务的反向预测,提高预测精准度。在基于用户的协同过滤算法中融入用户地理位置信息,提高参与预测数据的空间相关度;在基于服务的协同过滤算法中加入Web服务反向预测,缓解数据稀疏问题;根据不同的置信度融合两种算法,对缺失的QoS值进行预测。使用真实的数据集与其它3类常用的算法进行比较,实验结果表明,该方法的预测结果精确度更高。
文摘The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown advantage for the latter in different domains of application. However, some difficulties still deteriorate the performance of the support vector machines. The main one is related to the setting of the hyperparameters involved in their training. Techniques based on meta-heuristics have been employed to determine appropriate values for those hyperparameters. However, because of the high noneonvexity of this estimation problem, which makes the search for a good solution very hard, an approach based on Bayesian inference, called relevance vector machine, has been proposed more recently. The present paper aims at investigating the suitability of this new approach to the short-term load forecasting problem.
文摘采用反向预测和分子对接技术,评价鄂西香茶菜甲素成为抗肿瘤先导物的可行性。在反向预测的基础上,利用网络药理学技术构建"疾病-化合物-靶点-通路"网络。结果显示,鄂西香茶菜甲素预测靶点中有39个与肿瘤密切相关,参与调节细胞凋亡、细胞周期、肿瘤转移等多种细胞活动,并可调节雌激素信号转导途径和炎症应答。采用Discovery Studio 2020软件进行分子对接及TOPKAT毒性预测;鄂西香茶菜甲素与肿瘤相关靶点ABL1、ESR1、SRC、BCL-XL的结合亲和力均强于冬凌草甲素,且其致突变性、啮齿动物致癌性、大鼠口服LD50毒性均小于冬凌草甲素;进而,采用体外实验证实了鄂西香茶菜甲素的抗肿瘤活性,并初步探讨了其作用机制。结果显示,鄂西香茶菜甲素在细胞毒、抑制细胞集落形成和诱导凋亡方面均优于冬凌草甲素。鄂西香茶菜甲素有望成为新的抗肿瘤先导物,具有较大的研究前景。且鄂西香茶菜素对雌激素信号转导通路调节作用的预测结果值得进行深入研究,为其抗肿瘤作用机制的研究提供新视角。
基金National Key Research and Development Project(Grant No.2019YFC1708900)the National Natural Science Foundation of China(Grant No.81872730+6 种基金8167327921772005)National Major Scientific and Technological Special Project for Significant New Drugs Development(Grant No.2018ZX09735001-0032019ZX09201005-0012019ZX09204-001)Beijing Natural Science Foundation(Grant No.72020887172118)。
文摘As a powerful tool for target prediction,reverse docking remains largely unexplored.The objective evaluation of reverse docking software can help us know better about the strength and weakness of these tools,hence guiding us in target prediction.In the present study,we evaluated the target prediction power of Glide(SP)against general inhibitors and selective inhibitors.The results showed that the scoring tendency could be different for each ligand,and overall scoring sampling was necessary for a better understanding of the docking score for a certain protein-ligand pair.Besides,the input conformation of the binding pocket could affect the docking result.Glide(SP)showed a preferable performance on the target prediction of the general inhibitors.However,the accuracy of the target prediction of the selective inhibitors was relatively low,indicating that Glide(SP)might not be capable for this task.The case study about COVID-19 proved that coagulation factor Xa might be a potential target of chloroquine.Therefore,we recommend the further development of reverse docking tools and rectification of inter-target scoring bias.
