RESUMO
G protein-coupled receptors (GPCRs) play an essential role in critical human activities, and they are considered targets for a wide range of drugs. Accordingly, based on these crucial roles, GPCRs are mainly considered and focused on pharmaceutical research. Hence, there are a lot of investigations on GPCRs. Experimental laboratory research is very costly in terms of time and expenses, and accordingly, there is a marked tendency to use computational methods as an alternative method. In this study, a prediction model based on machine learning (ML) approaches was developed to predict GPCRs and ligand interactions. Decision tree (DT), random forest (RF), multilayer perceptron (MLP), support vector machine (SVM), and Naive Bayes (NB) were the algorithms that were investigated in this study. After several optimization steps, receiver operating characteristic (ROC) for DT, RF, MLP, SVM, and NB algorithm were 95.2, 98.1, 96.3, 95.5, and 97.3, respectively. Accordingly final model was made base on the RF algorithm. The current computational study compared with others focused on specific and important types of proteins (GPCR) interaction and employed/examined different types of sequence-based features to obtain more accurate results. Drug science researchers could widely use the developed prediction model in this study. The developed predictor was applied over 16,132 GPCR-ligand pairs and about 6778 potential interactions predicted.
Assuntos
Algoritmos , Máquina de Vetores de Suporte , Teorema de Bayes , Humanos , Ligantes , Aprendizado de MáquinaRESUMO
BACKGROUND: Urticarial vasculitis (UV) is a clinicopathologic entity in which skin lesions resemble urticaria clinically but last more than 24 hours and resolve with residual purpura. In this study, we evaluated distinguishing histological features of UV from common urticaria to differentiate between these two entities. METHODS: During 1 year, 55 urticaria and 245 UV samples were assessed. The selection criteria for UV included: (1) samples that the histological diagnosis was confirmed by two independent dermatopathologists, (2) the histological diagnosis of UV was inconsistent with the first clinical impression and lesion characteristics. RESULTS: Of our 245 UV patients, 96% had endothelial swelling, 18% had red blood cell (RBC) extravasation, neutrophilic infiltration was seen in 46.7%, and perivascular, interstitial, and perineural eosinophilic infiltration in 198 (81.8%), 181 (74.2%), and 118 (48.1%), respectively. Among different histological findings, endothelial cell swelling as well as neutrophil around vessels and eosinophilic infiltrations were statistically different between two groups (P-value Ë 0.001). Both urticaria and UV samples showed a predominantly lymphocytic infiltration more than 10 cells per high power field (HPF) (98.2% of urticaria, 98.8% of UV), and only two patients (0.8%) with UV had predominant neutrophilic infiltration (more than 10 cells/HPF). CONCLUSION: We have found that both urticaria and UV showed a predominantly lymphocytic infiltration along with RBC extravasation, endothelial cell swelling, and fibrin deposition in UV. Moreover, significant perineural, perivascular, and interstitial infiltration of eosinophil in UV lesions compared to urticaria was another point that indicates special contribution of these cells in UV pathogenesis.