Basic Examples
Load the data:
The data consists of a set of Vina scores for the molecules from the SWEETLEAD dataset. The lower the score, the better the molecule is able to dock with either the isolated S-protein or the protein-receptor interface. To view the data in connection to the underlying molecules,
Begin by loading the SWEETLEAD dataset as an EntityStore:
Now add the Vina docking scores as properties for each entity:
Verify that the docking scores have been added as EntityProperty objects:
Now find the three entities with the lowest (best) Vina score for the isolated S-protein:
Create labeled structure diagrams from these molecules:
Find the compound with the best docking score for the protein-receptor interface:
Retrieve all properties from this Entity:
Search PubChem for similar molecules, using a Tanimoto similarity score of 99% or greater as a threshold:
Visualize the entity along with the similar compounds:
Analysis
Create a PredictorFunction to predict the Vina score based on topological descriptors. First get a list of entities with scores for docking to the isolated S-protein:
Using a list of properties that return numeric values for features, prepare a set of labeled data to work with:
Split the labeled data into training and test sets:
Create the predictor function:
Visualize the results using PredictorMeasurements: