Extraction and Visualization of Potential Pharmacophore Points Using Support Vector Machines: Application to Ligand-Based Virtual Screening for COX-2 Inhibitors. Franke, L., Byvatov, E., Werz, O., Steinhilber, D., Schneider, P., & Schneider, G. J.~Med.~Chem., 48(22):6997--7004, 2005. doi abstract bibtex Support vector machines (SVM) were trained to predict cyclooxygenase 2 (COX-2) and thrombin inhibitors. The classifiers were obtained using sets of known COX-2 and thrombin inhibitors as "positive examples" and a large collection of screening compounds as "negative examples". Molecules were encoded by topological pharmacophore-point triangles. In retrospective virtual screening, 50-90% of the known active compounds were listed within the first 0.1% of the ranked database. To check the validity of the constructed classifiers, we developed a method for feature extraction and visualization using SVM. As a result, potential pharmacophore points were weighted according to their importance for COX-2 and thrombin inhibition. Known thrombin and COX-2 pharmacophore points were correctly recognized by the machine learning system. In a prospective virtual screening study, several potential COX-2 inhibitors were predicted and tested in a cellular activity assay. A benzimidazole derivative exhibited significant inhibitory activity with an IC50 of 0.2 mu M, which is better than Celecoxib in our assay. It was demonstrated that the SVM machine-learning method can be used in virtual screening and be analyzed in a human-interpretable way that results in a set of rules for designing novel molecules.
@article{Franke:2005aa,
Abstract = {Support vector machines (SVM) were trained to predict cyclooxygenase 2 (COX-2) and thrombin inhibitors. The classifiers were obtained using sets of known COX-2 and thrombin inhibitors as "positive examples" and a large collection of screening compounds as "negative examples". Molecules were encoded by topological pharmacophore-point triangles. In retrospective virtual screening, 50-90\% of the known active compounds were listed within the first 0.1\% of the ranked database. To check the validity of the constructed classifiers, we developed a method for feature extraction and visualization using SVM. As a result, potential pharmacophore points were weighted according to their importance for COX-2 and thrombin inhibition. Known thrombin and COX-2 pharmacophore points were correctly recognized by the machine learning system. In a prospective virtual screening study, several potential COX-2 inhibitors were predicted and tested in a cellular activity assay. A benzimidazole derivative exhibited significant inhibitory activity with an IC50 of 0.2 mu M, which is better than Celecoxib in our assay. It was demonstrated that the SVM machine-learning method can be used in virtual screening and be analyzed in a human-interpretable way that results in a set of rules for designing novel molecules.},
Author = {Franke, L. and Byvatov, E. and Werz, O. and Steinhilber, D. and Schneider, P. and Schneider, G.},
Date-Added = {2007-12-11 17:01:03 -0500},
Date-Modified = {2009-03-06 16:35:15 -0500},
Doi = {10.1021/jm050619h},
Journal = {J.~Med.~Chem.},
Keywords = {phamacophore; thrombin; inhibitor},
Local-Url = {file://localhost/Users/rguha/Documents/articles/jm050619h.pdf},
Number = {22},
Pages = {6997--7004},
Title = {Extraction and Visualization of Potential Pharmacophore Points Using Support Vector Machines: {A}pplication to Ligand-Based Virtual Screening for {COX-2} Inhibitors},
Volume = {48},
Year = {2005},
Bdsk-File-1 = {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},
Bdsk-Url-1 = {http://dx.doi.org/10.1021/jm050619h}}
Downloads: 0
{"_id":"Ft3GrcNamCQJFpPd4","bibbaseid":"franke-byvatov-werz-steinhilber-schneider-schneider-extractionandvisualizationofpotentialpharmacophorepointsusingsupportvectormachinesapplicationtoligandbasedvirtualscreeningforcox2inhibitors-2005","downloads":0,"creationDate":"2016-02-18T13:03:35.195Z","title":"Extraction and Visualization of Potential Pharmacophore Points Using Support Vector Machines: Application to Ligand-Based Virtual Screening for COX-2 Inhibitors","author_short":["Franke, L.","Byvatov, E.","Werz, O.","Steinhilber, D.","Schneider, P.","Schneider, G."],"year":2005,"bibtype":"article","biburl":"https://dl.dropboxusercontent.com/u/26998770/main.bib","bibdata":{"bibtype":"article","type":"article","abstract":"Support vector machines (SVM) were trained to predict cyclooxygenase 2 (COX-2) and thrombin inhibitors. The classifiers were obtained using sets of known COX-2 and thrombin inhibitors as \"positive examples\" and a large collection of screening compounds as \"negative examples\". Molecules were encoded by topological pharmacophore-point triangles. In retrospective virtual screening, 50-90% of the known active compounds were listed within the first 0.1% of the ranked database. To check the validity of the constructed classifiers, we developed a method for feature extraction and visualization using SVM. As a result, potential pharmacophore points were weighted according to their importance for COX-2 and thrombin inhibition. Known thrombin and COX-2 pharmacophore points were correctly recognized by the machine learning system. In a prospective virtual screening study, several potential COX-2 inhibitors were predicted and tested in a cellular activity assay. A benzimidazole derivative exhibited significant inhibitory activity with an IC50 of 0.2 mu M, which is better than Celecoxib in our assay. It was demonstrated that the SVM machine-learning method can be used in virtual screening and be analyzed in a human-interpretable way that results in a set of rules for designing novel molecules.","author":[{"propositions":[],"lastnames":["Franke"],"firstnames":["L."],"suffixes":[]},{"propositions":[],"lastnames":["Byvatov"],"firstnames":["E."],"suffixes":[]},{"propositions":[],"lastnames":["Werz"],"firstnames":["O."],"suffixes":[]},{"propositions":[],"lastnames":["Steinhilber"],"firstnames":["D."],"suffixes":[]},{"propositions":[],"lastnames":["Schneider"],"firstnames":["P."],"suffixes":[]},{"propositions":[],"lastnames":["Schneider"],"firstnames":["G."],"suffixes":[]}],"date-added":"2007-12-11 17:01:03 -0500","date-modified":"2009-03-06 16:35:15 -0500","doi":"10.1021/jm050619h","journal":"J.~Med.~Chem.","keywords":"phamacophore; thrombin; inhibitor","local-url":"file://localhost/Users/rguha/Documents/articles/jm050619h.pdf","number":"22","pages":"6997--7004","title":"Extraction and Visualization of Potential Pharmacophore Points Using Support Vector Machines: Application to Ligand-Based Virtual Screening for COX-2 Inhibitors","volume":"48","year":"2005","bdsk-file-1":"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","bdsk-url-1":"http://dx.doi.org/10.1021/jm050619h","bibtex":"@article{Franke:2005aa,\n\tAbstract = {Support vector machines (SVM) were trained to predict cyclooxygenase 2 (COX-2) and thrombin inhibitors. The classifiers were obtained using sets of known COX-2 and thrombin inhibitors as \"positive examples\" and a large collection of screening compounds as \"negative examples\". Molecules were encoded by topological pharmacophore-point triangles. In retrospective virtual screening, 50-90\\% of the known active compounds were listed within the first 0.1\\% of the ranked database. To check the validity of the constructed classifiers, we developed a method for feature extraction and visualization using SVM. As a result, potential pharmacophore points were weighted according to their importance for COX-2 and thrombin inhibition. Known thrombin and COX-2 pharmacophore points were correctly recognized by the machine learning system. In a prospective virtual screening study, several potential COX-2 inhibitors were predicted and tested in a cellular activity assay. A benzimidazole derivative exhibited significant inhibitory activity with an IC50 of 0.2 mu M, which is better than Celecoxib in our assay. It was demonstrated that the SVM machine-learning method can be used in virtual screening and be analyzed in a human-interpretable way that results in a set of rules for designing novel molecules.},\n\tAuthor = {Franke, L. and Byvatov, E. and Werz, O. and Steinhilber, D. and Schneider, P. and Schneider, G.},\n\tDate-Added = {2007-12-11 17:01:03 -0500},\n\tDate-Modified = {2009-03-06 16:35:15 -0500},\n\tDoi = {10.1021/jm050619h},\n\tJournal = {J.~Med.~Chem.},\n\tKeywords = {phamacophore; thrombin; inhibitor},\n\tLocal-Url = {file://localhost/Users/rguha/Documents/articles/jm050619h.pdf},\n\tNumber = {22},\n\tPages = {6997--7004},\n\tTitle = {Extraction and Visualization of Potential Pharmacophore Points Using Support Vector Machines: {A}pplication to Ligand-Based Virtual Screening for {COX-2} Inhibitors},\n\tVolume = {48},\n\tYear = {2005},\n\tBdsk-File-1 = {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},\n\tBdsk-Url-1 = {http://dx.doi.org/10.1021/jm050619h}}\n\n","author_short":["Franke, L.","Byvatov, E.","Werz, O.","Steinhilber, D.","Schneider, P.","Schneider, G."],"key":"Franke:2005aa","id":"Franke:2005aa","bibbaseid":"franke-byvatov-werz-steinhilber-schneider-schneider-extractionandvisualizationofpotentialpharmacophorepointsusingsupportvectormachinesapplicationtoligandbasedvirtualscreeningforcox2inhibitors-2005","role":"author","urls":{},"keyword":["phamacophore; thrombin; inhibitor"],"downloads":0},"search_terms":["extraction","visualization","potential","pharmacophore","points","using","support","vector","machines","application","ligand","based","virtual","screening","cox","inhibitors","franke","byvatov","werz","steinhilber","schneider","schneider"],"keywords":["phamacophore; thrombin; inhibitor"],"authorIDs":[],"dataSources":["c5japf9eAQRaeMS4h"]}