This application is aimed to aid the search for novel antiviral agents among the drug-like compounds.
We extracted bioactivity records and chemical structures of compounds tested for the inhibitory activity towards viral proteins from ChEMBL v29 [1] and processed them as it was described earlier [2].
We created the training set containing structures of 14 855 chemical compounds. All molecules having Activity, Ki, IC50, EC50 or Kd lesser than or equal to 10 000 nM were considered as “actives”. Using this set, we trained PASS [3, 4] to classify drug-like molecules as “actives” and “inactives” against 66 proteins of 56 viral strains. The average accuracy of prediction assessed as IAP (corresponds numerically to the ROC AUC) in Leave-One-Out Cross-Validation equals 0.98.
Using our application, one could select the most promising chemical compounds for synthesis and determine the priorities for testing their antiviral activity.
The prediction may be performed for the molecules that correspond to the applicability domain limited by the structures of the training set:
References:
1. Gaulton, A., et al. (2016), The ChEMBL database in 2017. Nucleic acids research, 45(D1), D945-D954. 2. Pogodin, P. V., et al. (2015), PASS Targets: Ligand-based multi-target computational system based on a public data and naïve Bayes approach. SAR and QSAR in Environmental Research, 26(10), 783-793. 3. Filimonov, D. A., et al. (2014). Prediction of the biological activity spectra of organic compounds using the PASS online web resource. Chemistry of Heterocyclic Compounds, 50(3), 444-457. 4. Poroikov, V.V., et al. (2019) Computer-aided prediction of biological activity spectra for organic compounds: the possibilities and limitations. Russ. Chem. Bull., 68 (12), 2143-2154.
AntiVir-Pred allows the user to predict whether a chemical compound can inhibit the activity 66 proteins of 56 viruses in concentration below the or equal to 10 000 nM. Each activity's score is expressed as a value of confidence, which represents the difference between probabilities to inhibit and not to inhibit the particular protein. The higher confidence means the higher chance of the prediction to be true.
Only activities with Pa > Pi (confidence > 0) are considered as possible for particular compound.
It is necessary to remember that probability Pa reflects the similarity of the molecule under prediction with the structures of molecules, which are the most typical in a sub-set of "actives" in the training set. Therefore, usually, there is no direct correlation between the Pa values and quantitative characteristics of activities.
One may choose which activities have to be tested for the studied compounds based on a compromise between the desire to discover novel biological action and the risk to obtain a negative result in experimental testing.
Detailed explanation of how to interpet the results of PASS is given in the publcation Poroikov, V.V., et al. (2019) Computer-aided prediction of biological activity spectra for organic compounds: the possibilities and limitations. Russ. Chem. Bull., 68 (12), 2143-2154.
Laboratory for Structure-Function Based Drug Design, Department for Bioinformatics, Institute of Biomedical Chemistry (IBMC) Pogodinskaya Str. 10, Moscow, Russia, 119121.
------------------------------
• Prof. Dr. Vladimir Poroikov, Tel: +7 499 246-09-20, Fax: +7 499 245-08-57, E-mail: vladimir.poroikov@ibmc.msk.ru
• PhD. MD. Dmitry Druzhilovsky, Tel: +7 499 255-30-29, Fax: +7 499 245-08-57, E-mail: dmitry.druzhilovsky@ibmc.msk.ru
Input chemical structure first, please