Improving chemical similarity ensemble approach in target prediction

Abstract

BackgroundIn silico target prediction of compounds plays an important role in drug discovery. The chemical similarity ensemble approach (SEA) is a promising method, which has been successfully applied in many drug-related studies. There are various models available analogous to SEA, because this approach is based on different types of molecular fingerprints. To investigate the influence of training data selection and the complementarity of different models, several SEA models were constructed and tested.ResultsWhen we used a test set of 37,138 positive and 42,928 negative ligand-target interactions, among the five tested molecular fingerprint methods, at significance level 0.05, Topological-based model yielded the best precision rate (83.7 %) and (0.784) while Atom pair-based model yielded the best (0.694). By employing an election system to combine the five models, a flexible prediction scheme was achieved with precision range from 71 to 90.6 %, range from 0.663 to 0.684 and range from 0.696 to 0.817.ConclusionsThe overall effectiveness of all of the five models could be ranked in decreasing order as follows: Atom pair Topological > Morgan > MACCS > Pharmacophore. Combining multiple SEA models, which takes advantages of different models, could be used to improve the success rates of the models. Another possibility of improving the model could be using target-specific classes or more active compounds.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-016-0130-x) contains supplementary material, which is available to authorized users.

Cannabinoid Type 1 Receptor (CB1) Ligands with Therapeutic Potential for Withdrawal Syndrome in Chemical Dependents of Cannabis sativa

“…from Stemphylium majusculum . In 1979, Achenbach and Kohl attributed antimicrobial activities against fungi ( Mucor hiemalis ), yeast ( Schizosaccharomyces pombe ) and Gram‐positive bacteria ( Bacillus subtilis and Staphylococcus aureus ) to this compound. From the discovery of the anticancer compound paclitaxel in Pestalotiopsis microspora , a fungal endophyte that asymptomatically parasitizes the Himalayan yew Taxus wallichiana , the importance of these fungi was highlighted, calling attention to the metabolites produced by these organisms .…”

Elucidating Direct Kinase Targets of Compound Danshen Dropping Pills Employing Archived Data and Prediction Models

“…Avoiding missing some important potential kinase targets, Multi-voting SEA algorithm [24] was utilized to predict potential direct targets of important components.…”

Structural designing of suppressors for autisms spectrum diseases using molecular dynamics sketch

“…In Cheminformatics one of the important step in drug discovery is target prediction. : Zhonghua Wang [9] proposed that Silico target prediction of compounds plays insignificant role in drug discovery. After target Identification, validation phase starts by determining whether the modulation of the target will produce a desired clinical result.…”

“…[3] There are very few drugs which have efficient but have very less accuracy. But the accuracy of such drugs can be improved using the [4] Cheminformatics technology and thereby increasing the efficiency of the drug.…”