摘要
Target identification is a critical step following the discovery of small molecules that elicit a biological phenotype. G-protein coupled recaptors (GPCRs) are among the most important drug targets for the pharmaceutical industry. The present work seeks to provide an in silico model of known GPCR protein fishing technologies in order to rapidly fish out potential drug targets on the basis of amino acid sequences and seven transmembrane regions (TMs) of GPCRs. Some scoring matrices were trained on 22 groups of GPCRs in the GPCRDB database. These models were employed to predict the GPCR proteins in two groups of test sets. On average, the mean correct rate of each TM of 38 GPCRs from two test sets (ST23 and ST24) was found 62% and 57.5%, respectively, using training set 18 (SLD18);the mean hit rate of each TM of 38 GPCRs from ST23 and ST24 was found 68.1% and 64.7%, respectively. Based on the scoring matrices of PreMod, the mean correct rate of each TM of GPCRs from ST23 and ST24 was found 62% and 62.04%, respectively;the mean hit rate of each TM of GPCRs from ST23 and ST24 was found 67.7% and 68.0%, respecttively. The means of GPCRs in ST23 based on SLD18 is close to those based on PreMod;whereas the means of GPCRs in ST24 based on?SLD18 is less than those based on PreMod. Moreover, the accuracy (“2”) and validity (“2 + 1”) rates of prediction all seven TMs of 38 GPCRs by the scoring matrices of PreMod are more than those by SLD18, SLA14 and SLA3;whereas the hit rates (94.74% and 97.37%) by PreMod are less than those of?SLA3 but bigger than those of?SLD18 and SLA14, respectively. This is the reason that we choose PreMod to predict some potential drug targets. 22 GPCR proteins in the sense chain of chromosome 19 constructing validation set were predicted and validated by PreMod whose hit rate is up to 90.91%. Further evaluation is under investigation.
Target identification is a critical step following the discovery of small molecules that elicit a biological phenotype. G-protein coupled recaptors (GPCRs) are among the most important drug targets for the pharmaceutical industry. The present work seeks to provide an in silico model of known GPCR protein fishing technologies in order to rapidly fish out potential drug targets on the basis of amino acid sequences and seven transmembrane regions (TMs) of GPCRs. Some scoring matrices were trained on 22 groups of GPCRs in the GPCRDB database. These models were employed to predict the GPCR proteins in two groups of test sets. On average, the mean correct rate of each TM of 38 GPCRs from two test sets (ST23 and ST24) was found 62% and 57.5%, respectively, using training set 18 (SLD18);the mean hit rate of each TM of 38 GPCRs from ST23 and ST24 was found 68.1% and 64.7%, respectively. Based on the scoring matrices of PreMod, the mean correct rate of each TM of GPCRs from ST23 and ST24 was found 62% and 62.04%, respectively;the mean hit rate of each TM of GPCRs from ST23 and ST24 was found 67.7% and 68.0%, respecttively. The means of GPCRs in ST23 based on SLD18 is close to those based on PreMod;whereas the means of GPCRs in ST24 based on?SLD18 is less than those based on PreMod. Moreover, the accuracy (“2”) and validity (“2 + 1”) rates of prediction all seven TMs of 38 GPCRs by the scoring matrices of PreMod are more than those by SLD18, SLA14 and SLA3;whereas the hit rates (94.74% and 97.37%) by PreMod are less than those of?SLA3 but bigger than those of?SLD18 and SLA14, respectively. This is the reason that we choose PreMod to predict some potential drug targets. 22 GPCR proteins in the sense chain of chromosome 19 constructing validation set were predicted and validated by PreMod whose hit rate is up to 90.91%. Further evaluation is under investigation.
