Denovo generation of molecules using manifold traversal

A method comprising:

• receiving, by a device comprising a memory storing instructions for use in identifying at least one candidate molecule and a processor in communication with the memory, drug data;
• converting, by the device, the drug data into at least one point in a latent space using a grammar variational auto-encoder (VAE) model;
• receiving, by the device, a query for the at least one candidate molecule;
• selecting, by the device, one or more points in the latent space based on the query for the at least one candidate molecule;
• creating, by the device, a k-dimensional tree graph based on the query for the at least one candidate molecule and based on the selected one or more points;
• determining, by the device, a plurality of paths in the latent space according to an interpolation technique;
• receiving, by the device, preference data;
• determining, by the device, an optimum path from the plurality of paths based on the preference data;
• determining, by the device, at least one candidate point on the optimum path;
• and
• determining, by the device, a drug molecular structure for each of the at least one candidate point using an inverse of the grammar VAE model.

A product comprising:

• machine-readable media other than a transitory signal;
• instructions stored on the machine-readable media for identify at least one candidate molecule;
• and
• wherein when a processor executes the instructions, the product is configured to cause the processor to:
• receive drug data;
• convert the drug data into at least one point in a latent space using a grammar variational auto-encoder (VAE) model;
• receive a query for the at least one candidate molecule;
• select one or more points in the latent space based on the query for the at least one candidate molecule;
• create a k-dimensional tree graph based on the query for the at least one candidate molecule and based on the selected one or more points;
• determine a plurality of paths in the latent space according to an interpolation technique;
• receive preference data;
• determine an optimum path from the plurality of paths based on the preference data;
• determine at least one candidate point on the optimum path;
• and
• determine a drug molecular structure for each of the at least one candidate point using an inverse of the grammar VAE model.