The drug development process takes a long time since it requires sorting through a large number of inactive compounds from a large collection of compounds chosen for study and choosing just the most pertinent compound...The drug development process takes a long time since it requires sorting through a large number of inactive compounds from a large collection of compounds chosen for study and choosing just the most pertinent compounds that can bind to a disease protein.The use of virtual screening in pharmaceutical research is growing in popularity.During the early phases of medication research and development,it is crucial.Chemical compound searches are nowmore narrowly targeted.Because the databases containmore andmore ligands,thismethod needs to be quick and exact.Neural network fingerprints were created more effectively than the well-known Extended Connectivity Fingerprint(ECFP).Only the largest sub-graph is taken into consideration to learn the representation,despite the fact that the conventional graph network generates a better-encoded fingerprint.When using the average or maximum pooling layer,it also contains unrelated data.This article suggested the Graph Convolutional Attention Network(GCAN),a graph neural network with an attention mechanism,to address these problems.Additionally,it makes the nodes or sub-graphs that are used to create the molecular fingerprint more significant.The generated fingerprint is used to classify drugs using ensemble learning.As base classifiers,ensemble stacking is applied to Support Vector Machines(SVM),Random Forest,Nave Bayes,Decision Trees,AdaBoost,and Gradient Boosting.When compared to existing models,the proposed GCAN fingerprint with an ensemble model achieves relatively high accuracy,sensitivity,specificity,and area under the curve.Additionally,it is revealed that our ensemble learning with generated molecular fingerprint yields 91%accuracy,outperforming earlier approaches.展开更多
Computer-aided drug design (CADD) is an interdisciplinary subject, playing a pivotal role during new drug research and development, especially the discovery and optimization of lead compounds. Traditional Chinese Medi...Computer-aided drug design (CADD) is an interdisciplinary subject, playing a pivotal role during new drug research and development, especially the discovery and optimization of lead compounds. Traditional Chinese Medicine (TCM) modernization is the only way of TCM development and also an effective approach to the development of new drugs and the discovery of potential drug targets (PDTs). Discovery and validation of PTDs has become the “bottle-neck” restricted new drug research and development and is urgently solved. Innovative drug research is of great significance and bright prospects. This paper mainly discusses the “druggability” and specificity of PTDs, the “druglikeness” of drug candidates, the methods and technologies of the discovery and validation of PTDs and their application. It is very important to achieve the invention and innovation strategy “from gene to drug”. In virtue of modern high-new technology, especially CADD, combined with TCM theory, research and develop TCM and initiate an innovating way fitting our country progress. This paper mainly discusses CADD and their application to drug research, especially TCM modernization.展开更多
Since December 2019,severe acute respiratory syndrome coronavirus 2 has been found to be the culprit in the coronavirus disease 2019(COVID-19),causing a global pandemic.Despite the existence of many vaccine programs,t...Since December 2019,severe acute respiratory syndrome coronavirus 2 has been found to be the culprit in the coronavirus disease 2019(COVID-19),causing a global pandemic.Despite the existence of many vaccine programs,the number of confirmed cases and fatalities due to COVID-19 is still increasing.Furthermore,a number of variants have been reported.Because of the absence of approved anticoronavirus drugs,the treatment and management of COVID-19 has become a global challenge.Under these circumstances,drug repurposing is an effective method to identify candidate drugs with a shorter cycle of clinical trials.Here,we summarize the current status of the application of drug repurposing in COVID-19,including drug repurposing based on virtual computer screening,network pharmacology,and bioactivity,which may be a beneficial COVID-19 treatment.展开更多
Objective:To select potential molecules that can target viral spike proteins,which may potentially interrupt the interaction between the human angiotension-converting enzyme 2(ACE2)receptor and viral spike protein by ...Objective:To select potential molecules that can target viral spike proteins,which may potentially interrupt the interaction between the human angiotension-converting enzyme 2(ACE2)receptor and viral spike protein by virtual screening.Methods:The three-dimensional(3D)-coordinate file of the receptor-binding domain(RBD)-ACE2 complex for searching a suitable docking pocket was firstly downloaded and prepared.Secondly,approximately 15,000 molecular candidates were prepared,including US Food and Drug Administration(FDA)-approved drngs from DrugBank and natural compounds from Traditional Chinese Medicine Systems Pharmacology(TCMSP),for the docking process.Then,virtual screening was performed and the binding energy in Autodock Vina was calculated.Finally,the top 20 molecules with high binding energy and their Chinese medicine(CM)herb sources were listed in this paper.Results:It was found that digitoxin,a cardiac glycoside in DrugBank and bisindigotin in TCMSP had the highest docking scores.Interestingly,two of the CM herbs containing the natural compounds that had relatively high binding scores,Forsyfh/ae frucft/s and/saf/d/s racWx,are components of Lianhua Qingwen(莲花清痕),a CM formula reportedly exerting activity against severe acute respiratory syndrome(SARS)-Cov-2.Moreover,raltegravir,an HIV integrase inhibitor,was found to have a relatively high binding score.Conclusions:A class of compounds,which are from FDA-approved drugs and CM natural compounds,that had high binding energy with RBD of the viral spike protein.Our work provides potential candidates for other researchers to identify inhibitors to prevent SARS-CoV-2 infection,and highlights the importance of CM and integrative application of CM and Western medicine on treating COVID-19.展开更多
近10年来,随着X-射线晶体学和高通量测序等技术的不断发展,越来越多的蛋白晶体结构得到确证,其相应的基因信息也随之公布。蛋白质等生物大分子结构和功能信息的"井喷",产生了愈来愈多的药物靶标,加之计算科学的蓬勃发展亦极...近10年来,随着X-射线晶体学和高通量测序等技术的不断发展,越来越多的蛋白晶体结构得到确证,其相应的基因信息也随之公布。蛋白质等生物大分子结构和功能信息的"井喷",产生了愈来愈多的药物靶标,加之计算科学的蓬勃发展亦极大地促进了分子对接和虚拟筛选技术在药物设计领域的应用推广。如今,计算技术已成为药物设计领域的重要手段之一,通过计算机模拟的分子对接运算,研究人员能快速准确地描述药物与靶标间的相互作用,从而缩短了药物研发周期。本文简要介绍了分子对接化学机理、分子表征方法以及3种分子对接机制。同时着重介绍了一些在药物设计中广泛使用的分子对接软件,包括Auto Dock、SLIDE、DOCK以及Auto Dock Vina。这些软件分别采用不同的搜索算法以及打分函数,但其功能较为相似且囊括了分子对接领域的最近研究进展。为了使分子对接过程更为方便快捷,研究者们不断更新计算技术,推出各种图形分析工具。最后,以G蛋白偶联受体和蛋白激酶为例,简要说明分子对接及虚拟筛选领域的部分研究成果。展开更多
文摘The drug development process takes a long time since it requires sorting through a large number of inactive compounds from a large collection of compounds chosen for study and choosing just the most pertinent compounds that can bind to a disease protein.The use of virtual screening in pharmaceutical research is growing in popularity.During the early phases of medication research and development,it is crucial.Chemical compound searches are nowmore narrowly targeted.Because the databases containmore andmore ligands,thismethod needs to be quick and exact.Neural network fingerprints were created more effectively than the well-known Extended Connectivity Fingerprint(ECFP).Only the largest sub-graph is taken into consideration to learn the representation,despite the fact that the conventional graph network generates a better-encoded fingerprint.When using the average or maximum pooling layer,it also contains unrelated data.This article suggested the Graph Convolutional Attention Network(GCAN),a graph neural network with an attention mechanism,to address these problems.Additionally,it makes the nodes or sub-graphs that are used to create the molecular fingerprint more significant.The generated fingerprint is used to classify drugs using ensemble learning.As base classifiers,ensemble stacking is applied to Support Vector Machines(SVM),Random Forest,Nave Bayes,Decision Trees,AdaBoost,and Gradient Boosting.When compared to existing models,the proposed GCAN fingerprint with an ensemble model achieves relatively high accuracy,sensitivity,specificity,and area under the curve.Additionally,it is revealed that our ensemble learning with generated molecular fingerprint yields 91%accuracy,outperforming earlier approaches.
基金This work was supported by the National Science and Technology Major Project(2022ZD0115003)the National Natural Science Foundation of China(No.92053202,No.92353304,No.22050003,No.21821004,No.21927901).
文摘Computer-aided drug design (CADD) is an interdisciplinary subject, playing a pivotal role during new drug research and development, especially the discovery and optimization of lead compounds. Traditional Chinese Medicine (TCM) modernization is the only way of TCM development and also an effective approach to the development of new drugs and the discovery of potential drug targets (PDTs). Discovery and validation of PTDs has become the “bottle-neck” restricted new drug research and development and is urgently solved. Innovative drug research is of great significance and bright prospects. This paper mainly discusses the “druggability” and specificity of PTDs, the “druglikeness” of drug candidates, the methods and technologies of the discovery and validation of PTDs and their application. It is very important to achieve the invention and innovation strategy “from gene to drug”. In virtue of modern high-new technology, especially CADD, combined with TCM theory, research and develop TCM and initiate an innovating way fitting our country progress. This paper mainly discusses CADD and their application to drug research, especially TCM modernization.
基金supported by the Ph D Start-up Fund of Guangdong Medical University(Grant No.:B2019016)Administration of Traditional Chinese Medicine of Guangdong Province(Grant No.:20201180)+4 种基金Science and Technology Special Project of Zhanjiang(Project No.:2019A01009)Natural Science Foundation of Guangdong Province(Grant No.:2016B030309002)Basic and Applied Basic Research Program of Guangdong Province(Grant No.:2019A1515110201)Educational Commission of Guangdong Province(Grant No.:4SG20138G)Fund of Southern Marine Science and Engineering Guangdong Laboratory(Zhanjiang)(Grant No.:ZJW-2019-007)。
文摘Since December 2019,severe acute respiratory syndrome coronavirus 2 has been found to be the culprit in the coronavirus disease 2019(COVID-19),causing a global pandemic.Despite the existence of many vaccine programs,the number of confirmed cases and fatalities due to COVID-19 is still increasing.Furthermore,a number of variants have been reported.Because of the absence of approved anticoronavirus drugs,the treatment and management of COVID-19 has become a global challenge.Under these circumstances,drug repurposing is an effective method to identify candidate drugs with a shorter cycle of clinical trials.Here,we summarize the current status of the application of drug repurposing in COVID-19,including drug repurposing based on virtual computer screening,network pharmacology,and bioactivity,which may be a beneficial COVID-19 treatment.
基金National Natural Science Foundation of China(No.61773196)Special Scientific Research Project on COVID-19 Epidemic Prevention and Control in Guangdong Universities(No.2020KZDZX1182)+3 种基金Guangdong Provincial Key Laboratory Funds(Nos.2017B030301018,2019B030301001)Shenzhen Research Funds(No.JCYJ20170817104740861)Shenzhen Peacock Plan(No.KQ TD 2016053117035204)Center for Computational Science and Engineering of Southern University of Science and Technology,China。
文摘Objective:To select potential molecules that can target viral spike proteins,which may potentially interrupt the interaction between the human angiotension-converting enzyme 2(ACE2)receptor and viral spike protein by virtual screening.Methods:The three-dimensional(3D)-coordinate file of the receptor-binding domain(RBD)-ACE2 complex for searching a suitable docking pocket was firstly downloaded and prepared.Secondly,approximately 15,000 molecular candidates were prepared,including US Food and Drug Administration(FDA)-approved drngs from DrugBank and natural compounds from Traditional Chinese Medicine Systems Pharmacology(TCMSP),for the docking process.Then,virtual screening was performed and the binding energy in Autodock Vina was calculated.Finally,the top 20 molecules with high binding energy and their Chinese medicine(CM)herb sources were listed in this paper.Results:It was found that digitoxin,a cardiac glycoside in DrugBank and bisindigotin in TCMSP had the highest docking scores.Interestingly,two of the CM herbs containing the natural compounds that had relatively high binding scores,Forsyfh/ae frucft/s and/saf/d/s racWx,are components of Lianhua Qingwen(莲花清痕),a CM formula reportedly exerting activity against severe acute respiratory syndrome(SARS)-Cov-2.Moreover,raltegravir,an HIV integrase inhibitor,was found to have a relatively high binding score.Conclusions:A class of compounds,which are from FDA-approved drugs and CM natural compounds,that had high binding energy with RBD of the viral spike protein.Our work provides potential candidates for other researchers to identify inhibitors to prevent SARS-CoV-2 infection,and highlights the importance of CM and integrative application of CM and Western medicine on treating COVID-19.
文摘近10年来,随着X-射线晶体学和高通量测序等技术的不断发展,越来越多的蛋白晶体结构得到确证,其相应的基因信息也随之公布。蛋白质等生物大分子结构和功能信息的"井喷",产生了愈来愈多的药物靶标,加之计算科学的蓬勃发展亦极大地促进了分子对接和虚拟筛选技术在药物设计领域的应用推广。如今,计算技术已成为药物设计领域的重要手段之一,通过计算机模拟的分子对接运算,研究人员能快速准确地描述药物与靶标间的相互作用,从而缩短了药物研发周期。本文简要介绍了分子对接化学机理、分子表征方法以及3种分子对接机制。同时着重介绍了一些在药物设计中广泛使用的分子对接软件,包括Auto Dock、SLIDE、DOCK以及Auto Dock Vina。这些软件分别采用不同的搜索算法以及打分函数,但其功能较为相似且囊括了分子对接领域的最近研究进展。为了使分子对接过程更为方便快捷,研究者们不断更新计算技术,推出各种图形分析工具。最后,以G蛋白偶联受体和蛋白激酶为例,简要说明分子对接及虚拟筛选领域的部分研究成果。
