What is GRCPnet?

Involved in many diseases such as cancer, diabetes, neurodegenerative, inflammatory and respiratory disorders, G-protein coupled receptors (GPCRs) are among the most frequent targets of therapeutic drugs. Over half of all prescription drugs currently on the market are actually acting by targeting GPCRs directly or indirectly. A lot of efforts have been invested for studying GPCRs in both academic institutions and pharmaceutical industries. However, it is time-consuming and expensive to determine whether a chemical and a GPCR are to interact with each other in a cellular network purely by means of experimental techniques. Although some computational methods were developed in this regard based on the knowledge of the 3D (dimensional) structure of protein, unfortunately their usage is quite limited because the 3D structures for most GPCRs are still unknown. To overcome the situation, a multi-target QSAR classifier, called GPCRnet, was developed to predict the interactions between GPCRs and chemicals in cellular networking. GPCRnet is an open 2web server that could be used for netting or predicting the binding of multiple GPCR targets for any given molecule.

  How does GPCRnet work?

GPCRnet simultaneously constructs a large number of QSAR modelsQSAR models based on current chemogenomics data to make future predictions. We used GPCR SARfari database as our training datasets. Following a series of data pre-processing steps, 101,114 compounds associated with 237 GPCR proteins remained with 222,020 activity end-points, which were used for model building. A compound was considered active when the mean activity value was below 10 uM. All compounds higher than 10 uM are considered inactive. A series of high confidence QSAR models were built using these positive and negative sets. Naïve Bayes models were built with different fingerprint representations for 237 human proteins. For each model, the model performance is strictly evaluated using five-fold cross validation and the external validation set. To obtain the more reliable prediction, we also ensembleensemble the Naive Bayes models from different molecular fingerprints to yield the final output. Detailed information could be found in the Documentation section. When the user submits a molecule, the server will predict the activity of the user’s molecule across 237 GPCR proteinsGPCR proteins by establishing the high quality QSAR model for each GPCR protein.

  What is the GPCRnet’s application?

Drug-target interactions (DTIs) are central to current drug discovery processes and public health fields. In drug discovery process, one of the challenges is to identify the potential targets for drug-like compounds. Once the target is successfully identified, several receptor-based drug design methods could be easily used to optimize the structure of compounds, aims at improving the biological activity of these compounds. However, this is usually a very difficult task for most of medicinal chemists. Furthermore, analyzing the DTI profiling of the drugs helps to infer drug indications, adverse drug reactions, drug-drug interactions, and drug mode of actions. Involved in many diseases such as cancer, diabetes, neurodegenerative, inflammatory and respiratory disorders, GPCRs are among the most frequent targets of therapeutic drugs. GPCR-associated proteins may play at least the following four distinct roles in receptor signaling:

  • 1 (1) directly mediate receptor signaling, as in the case of G proteins;
  • 2 (2) regulate receptor signaling through controlling receptor localization and/or trafficking;
  • 3 (3) act as a scaffold, physically linking the receptor to various effectors;
  • 4 (4) act as an allosteric modulator of receptor conformation, altering receptor pharmacology and/or other aspects of receptor function.
Therefore, it is of high importance to reliably and fast predict DTI profiling of the chemicals on a genome-scale level. GPCRnet was developed in order to attempt address the difficulties. When the user submits a molecule, the server will predict the activity of the user’s molecule across 237 GPCR proteins by establishing the high quality QSAR model for each GPCR protein, thus generating a DTI profiling that can used as a feature vector for wide applications, such as predicting potential GPCR targets, toxicity classification, drug-drug interactions, and drug mode of action.


Copyright @ 2012-2015 Computational Biology & Drug Design Group,
School of Pharmaceutical Sciences, Central South University. All rights reserved.

The recommended browsers: Safari, Firefox, Chrome, IE(Ver.>8).
 E-mail: biomed@csu.edu.cn