admetSAR网站更新:以药物代谢酶转运体及肝毒性为例
详细信息 查看官网全文
- 英文论文题名：admetSAR update:using DMETs and liver toxicity as a case
- 论文作者：李杰 ; 杨弘宾 ; 吴曾睿 ; 蔡迎春 ; 唐赟
- 英文论文作者：Jie Li ; Hongbin Yang ; Zengrui Wu ; Yingchun Cai ; Yun Tang ; Shanghai Key Laboratory of New Drug Design ; School of Pharmacy ; East China University of Science and Technology
- 年：2016
- 作者机构：华东理工大学药学院上海市新药设计重点实验室;
- 论文关键词：ADMET ; 化合物安全性评估 ; 子结构分析 ; 网站更新
- 会议召开时间：2016-07-01
- 会议录名称：中国化学会第30届学术年会摘要集-第二十五分会：化学信息学与化学计量学
- 语种：中文
- 分类号：R96
- 学会代码：ZGHY
- 会议名称：中国化学会第30届学术年会-第二十五分会 ; 化学信息学与化学计量学
- 会议地点：中国辽宁大连
- 主办单位：中国化学会
- 学会名称：中国化学会
- 页数：1
- 文件大小：344k
- 原文格式：D
- 会议级别：全国
摘要
计算预测化合物吸收、分布、代谢、排泄和毒性(ADMET)对于早期发现不良性质,避免安全性问题带来的研发成本损耗具有重要意义~([2])。admetSAR是我们实验室前期开发的用于综合评估化合物安全性的网站服务,已被超过60多所国内外科研院所使用,访问逾3万人次(截至2016年3月末)~([3])。近年来,包括计算系统毒理学在内的相关领域快速发展~([4]),我们实验室也构建了一系列新模型~([5-7]),因此对网站进行了升级更新。目前,admetSARV2.0已收录报道数据25万多条,预测模型增至56个,同时我们对相关数据进行分析,得到5242个重要子结构。为了更方便整合多分类模型、应用域及预测结果可视化等新特征,网站采用PHP框架构建。admetSAR V2.0将在后期公布于http://lmmd.ecust.edu.cn/admetsarv2/。为了更好诠释admetSAR V2.0的新特征,我们以化合物代谢酶转运体(DMETs)和肝毒性为例。我们对ChEMBL、BindingDB和文献收集的DMETs蛋白亚型数据,采用机器学习算法构建了多靶标QSAR预测模型(AUC 0.817~0.908),发现化合物对DMETs具有抑制杂泛性。进一步,我们对3709个肝毒性数据进行子结构分析,得到217个致肝毒性警示子,DMETs统计和对接分析解释了部分警示子的作用机制,提高了模型的可解释性。
In silico prediction of drug absorption,distribution,metabolism,excretion,and toxicity(ADMET) attracts great attentions in early drug discovery and design~([2]).Our admetSAR webserver~([3]) has become a useful tool in this area,which has been used by >30,000 visitors and more than 60 research institutions.Recently,we have updated admetSAR for the rapid development of computational systems toxicology~([4]) and computational models~([5-7]).admetSAR V2.0 has included more than 250,000 records,56 predictive models and 5242 substructures,which will be available late on http://lmmd.ecust.edu.cn/admetsarv2/.To display the new features of our admetSAR V2.0,the drug metabolism enzymes and transporters(DMETs)and liver toxicity were exemplified here.The multi-target QSAR models(AUC 0.817~0.908) helped to find the inhibition promiscuity of DMETs ligands.Further,217 substructural alerts were obtained from 3709 chemicals in liver toxicity dataset,which were also significant in DMETs mechanisms.Collectively,this will help to improve the interpretability of our predictive models.
In silico prediction of drug absorption,distribution,metabolism,excretion,and toxicity(ADMET) attracts great attentions in early drug discovery and design~([2]).Our admetSAR webserver~([3]) has become a useful tool in this area,which has been used by >30,000 visitors and more than 60 research institutions.Recently,we have updated admetSAR for the rapid development of computational systems toxicology~([4]) and computational models~([5-7]).admetSAR V2.0 has included more than 250,000 records,56 predictive models and 5242 substructures,which will be available late on http://lmmd.ecust.edu.cn/admetsarv2/.To display the new features of our admetSAR V2.0,the drug metabolism enzymes and transporters(DMETs)and liver toxicity were exemplified here.The multi-target QSAR models(AUC 0.817~0.908) helped to find the inhibition promiscuity of DMETs ligands.Further,217 substructural alerts were obtained from 3709 chemicals in liver toxicity dataset,which were also significant in DMETs mechanisms.Collectively,this will help to improve the interpretability of our predictive models.
引文
[1]Li,J.;Cheng,F.;Wu,Z.;Liu,G.;et al.in preparation,2016.
[2]Cheng,F.;Li,W.;Liu,G.;Tang,Y.Curr.Top.Med.Chem.,2013,13(11):1273-1289.
[3]Cheng,F.;Li,W.;Zhou,Y.;Shen,J.;et al.J Chem.Inf.Model.,2012,52(11):3099-3105.
[4]李杰,李珂佳,张臣,彭邱鹏,唐赟.科学通报,2015:60:1-11.
[5]Li,X.;Chen,L.;Cheng,F.;Bian,H.;et al.J.Chem.Inf.Model.,2014,54(4):1061-1069.
[6]Zhang,C.;Cheng,F.;Sun,L.;Zhuang,S.;et al.Chemosphere,2015,122:280-287.
[7]Sun,L.;Zhang,C.;Chen,Y.;Li,X.;et al.Toxicol.Res.,2015,4:452-463.
[2]Cheng,F.;Li,W.;Liu,G.;Tang,Y.Curr.Top.Med.Chem.,2013,13(11):1273-1289.
[3]Cheng,F.;Li,W.;Zhou,Y.;Shen,J.;et al.J Chem.Inf.Model.,2012,52(11):3099-3105.
[4]李杰,李珂佳,张臣,彭邱鹏,唐赟.科学通报,2015:60:1-11.
[5]Li,X.;Chen,L.;Cheng,F.;Bian,H.;et al.J.Chem.Inf.Model.,2014,54(4):1061-1069.
[6]Zhang,C.;Cheng,F.;Sun,L.;Zhuang,S.;et al.Chemosphere,2015,122:280-287.
[7]Sun,L.;Zhang,C.;Chen,Y.;Li,X.;et al.Toxicol.Res.,2015,4:452-463.