IFOWONCO uses advanced computational modelling techniques coupled with state of the art machine learning to rapidly identify and optimize drug candidates.
In-silico drug prediction and identification has historically been challenging. The significant false positive rates have typically meant that many candidates need to be evaluated in a laboratory, adding to the cost of such approaches and the time taken. Molecular dynamic simulations can be incorporated into the approach which improve significantly the success rate. However, these are extremely compute intensive approaches which has historically limited their potential.
IFOWONCO has developed a molecular modelling technique that incorporates machine learning which significantly increases the rate at which compounds can be characterized using molecular dynamics. Our artificial intelligence approach can quickly identify promising compounds whilst determining compounds unlikely to usefully bind to a target, accurately estimating both the pose and the binding affinity of these compounds.
The platform can be also used to identify drug candidates for re-purposing and to accurately predict the binding affinity of modified compounds before actual synthesis.