目前,抗胰腺癌候选药物化合物在药物研发中面临时间和成本等诸多挑战。因此,本文提出一种融合Lasso回归与BP神经网络模型的方法,用于筛选和优化ERα靶向化合物。首先,使用Lasso回归筛选出与生物活性(pIC50)相关的重要分子描述符,并通过...目前,抗胰腺癌候选药物化合物在药物研发中面临时间和成本等诸多挑战。因此,本文提出一种融合Lasso回归与BP神经网络模型的方法,用于筛选和优化ERα靶向化合物。首先,使用Lasso回归筛选出与生物活性(pIC50)相关的重要分子描述符,并通过神经网络进行ADMET分类预测。实验结果表明,该方法能够有效提高药物活性和安全性的预测精度。从Lasso回归中筛选出的前20个重要特征对药物活性有显著影响,构建的随机森林回归模型在测试集上的准确率达到89%。并且筛选的特征在BP神经网络中ADMET分类任务中也表现良好,其中CYP3A4任务的准确率为91%。该方法为ERα拮抗剂的筛选和优化提供了可借鉴的思路。Currently, anti-breast cancer drug candidate compounds are facing many heavy challenges in drug discovery such as time and cost. Therefore, in this paper, we propose an approach that integrates Lasso regression and BP neural network models for screening and optimizing ERα-targeting compounds. First, important molecular descriptors related to biological activity (pIC50) were screened using Lasso regression and predicted by neural network for ADMET classification. The experimental results showed that this method can effectively improve the prediction accuracy of drug activity and safety. The top 20 important features screened from Lasso regression had a significant effect on drug activity, and the accuracy of the constructed random forest regression model reached 89% on the test set. And the screened features also performed well in the ADMET classification task in BP neural network, with an accuracy of 91% in the CYP3A4 task. This method provides a referable idea for the screening and optimization of ERα antagonists.展开更多
随着“互联网+”的持续推进,由互联网技术和传统医药行业融合的医疗电商平台应运而生,为人们带来便利的同时,也面临着一系列挑战。因此,为了规范与完善医疗电商平台,保障人民权益,本文通过设计相关问卷收集数据对医疗电商平台需求及其...随着“互联网+”的持续推进,由互联网技术和传统医药行业融合的医疗电商平台应运而生,为人们带来便利的同时,也面临着一系列挑战。因此,为了规范与完善医疗电商平台,保障人民权益,本文通过设计相关问卷收集数据对医疗电商平台需求及其满意度的影响因素进行分析。根据描述性统计分析,用户对于医疗电商平台的需求大多在于药品的购买,对医疗电商平台附加服务的关注更倾向于运动、饮食方面的建议;利用SEM结构方程模型探究影响医疗电商平台用户购买满意度的因素,结果表明,医疗电商平台的网络安全性、网站设计特色、产品质量保证和购物便利性均对用户购物满意度有正面影响。最后根据本文所得结论,为政府管理部门和企业规范医疗电商平台市场、保障人民权益提供可行性的建议。With the continuous promotion of “Internet+”, medical e-commerce platforms have emerged as a result of the integration of Internet technology and traditional pharmaceutical industry, bringing great convenience to people’s lives while also facing a series of challenges. Therefore, in order to standardize and improve the medical e-commerce platform and protect people’s rights and interests, this paper analyzes the influencing factors of demand and satisfaction of the medical e-commerce platform by designing relevant questionnaires to collect data. According to the descriptive statistics analysis, users’ demand for medical e-commerce platforms mostly lies in the purchase of medicines, and the additional service concerns of medical e-commerce platforms are more inclined to exercise and dietary advice;SEM structural equation modeling is utilized to explore the factors affecting users’ satisfaction with medical e-commerce platforms’ purchases, and the results show that network security, website design features, product quality assurance and shopping convenience of medical e-commerce platforms have a positive impact on users’ shopping satisfaction. Finally, based on the conclusions obtained, feasible suggestions are provided for government management and enterprises to regulate the medical e-commerce platform market and protect people’s rights and interests.展开更多
文摘目前,抗胰腺癌候选药物化合物在药物研发中面临时间和成本等诸多挑战。因此,本文提出一种融合Lasso回归与BP神经网络模型的方法,用于筛选和优化ERα靶向化合物。首先,使用Lasso回归筛选出与生物活性(pIC50)相关的重要分子描述符,并通过神经网络进行ADMET分类预测。实验结果表明,该方法能够有效提高药物活性和安全性的预测精度。从Lasso回归中筛选出的前20个重要特征对药物活性有显著影响,构建的随机森林回归模型在测试集上的准确率达到89%。并且筛选的特征在BP神经网络中ADMET分类任务中也表现良好,其中CYP3A4任务的准确率为91%。该方法为ERα拮抗剂的筛选和优化提供了可借鉴的思路。Currently, anti-breast cancer drug candidate compounds are facing many heavy challenges in drug discovery such as time and cost. Therefore, in this paper, we propose an approach that integrates Lasso regression and BP neural network models for screening and optimizing ERα-targeting compounds. First, important molecular descriptors related to biological activity (pIC50) were screened using Lasso regression and predicted by neural network for ADMET classification. The experimental results showed that this method can effectively improve the prediction accuracy of drug activity and safety. The top 20 important features screened from Lasso regression had a significant effect on drug activity, and the accuracy of the constructed random forest regression model reached 89% on the test set. And the screened features also performed well in the ADMET classification task in BP neural network, with an accuracy of 91% in the CYP3A4 task. This method provides a referable idea for the screening and optimization of ERα antagonists.
文摘随着“互联网+”的持续推进,由互联网技术和传统医药行业融合的医疗电商平台应运而生,为人们带来便利的同时,也面临着一系列挑战。因此,为了规范与完善医疗电商平台,保障人民权益,本文通过设计相关问卷收集数据对医疗电商平台需求及其满意度的影响因素进行分析。根据描述性统计分析,用户对于医疗电商平台的需求大多在于药品的购买,对医疗电商平台附加服务的关注更倾向于运动、饮食方面的建议;利用SEM结构方程模型探究影响医疗电商平台用户购买满意度的因素,结果表明,医疗电商平台的网络安全性、网站设计特色、产品质量保证和购物便利性均对用户购物满意度有正面影响。最后根据本文所得结论,为政府管理部门和企业规范医疗电商平台市场、保障人民权益提供可行性的建议。With the continuous promotion of “Internet+”, medical e-commerce platforms have emerged as a result of the integration of Internet technology and traditional pharmaceutical industry, bringing great convenience to people’s lives while also facing a series of challenges. Therefore, in order to standardize and improve the medical e-commerce platform and protect people’s rights and interests, this paper analyzes the influencing factors of demand and satisfaction of the medical e-commerce platform by designing relevant questionnaires to collect data. According to the descriptive statistics analysis, users’ demand for medical e-commerce platforms mostly lies in the purchase of medicines, and the additional service concerns of medical e-commerce platforms are more inclined to exercise and dietary advice;SEM structural equation modeling is utilized to explore the factors affecting users’ satisfaction with medical e-commerce platforms’ purchases, and the results show that network security, website design features, product quality assurance and shopping convenience of medical e-commerce platforms have a positive impact on users’ shopping satisfaction. Finally, based on the conclusions obtained, feasible suggestions are provided for government management and enterprises to regulate the medical e-commerce platform market and protect people’s rights and interests.
