Drugs that are discovered and developed typically fail in the clinic due to efficacy and/or safety, both of which are often the result of inadequate pre-clinical target validation.
Modern Drug Discovery and Development pipeline is extremely supported by the computational and Machine learning methods (C-ML) for increasing their success rates. We call it knowledge-based innovation which is revolutionizing the R&D.
C-ML implemented right from target identification – target validation – Hit identification- lead discovery – lead optimization – pre-clinical to clinical trials.
Biological target upon binding with a drug molecule modulates its activity and alleviates the disease condition. The binding pocket of the target where it binds to a drug called as a druggable pocket. Thus the druggable pocket of the target is the pocket where it binds to the drug with high affinity and modulates the function of the target with a therapeutic benefit.
Immunocure uses bioinformatics, molecular dynamic simulations, chemoinformatic tools to identify the druggable pockets based on the size, shape, electronic features, and the solvent-exposed regions for the given 3D structure. Further using bio/chemo-informatic tools we will identify the commonality in the binding pockets for the polypharmacology.
Target validation process
To validate a given target, Immunocure uses CADD expertise and in-house cutting-edge AI tools in the following steps.
- Druggability prediction
- Off-target prediction