Prediction
Pharmacophores
Confident predictions that are fully explainable.
Predict potential binding using Machine Learning (ML) models that are fully explainable.
A module within the MCPairs platform.
How Pharmacophores Works
Prediction in four steps
Input Compound
Submit a compound for prediction.
Choose Models
Select/deselect models you wish to screen against.
View Results
View your results in Quick or Detailed view.
Export Results
Export results and continue your workflow in MCPairs.
Explore Pharmacophores
Prediction at your fingertips
Binding Heatmap
Screen your compounds through our Pharmacophore models to receive structural highlights for features that may help binding.
Explainable AI
Understand the parts of the module that lead to the prediction.
Nearest Neighbours
Show the compounds in the model dataset closest to your input and their measured data.
Why use Pharmacophores?
Key Benefits
Fully Explainable
Uses Machine Learning (ML) models that are fully explainable.
Nearest Neighbours
Output from two models provides higher confidence. View the original data.
Complements RuleDesign®
Complements RuleDesign® by predicting potency of suggested molecules.
Web-based access
Access through MCPairs Online —no software installation required.
