Techniques for data-enabled drug discovery

One or more non-transitory computer readable media including instructions that, when executed by one or more processors, cause the one or more processors to determine one or more potential drug candidates during a drug discovery process by performing the steps of:

• generating a plurality of likelihoods by determining, for each edit heuristic included in a plurality of edit heuristics, a likelihood that a target bioactivity associated with a query molecule specification is preserved when the edit heuristic is applied to the query molecule specification, wherein each edit heuristic included in the plurality of edit heuristics specifies a different type of modification to a structure of an existing molecule;
• generating a subset of the plurality of edit heuristics based on the plurality of likelihoods;
• applying the subset of the plurality of edit heuristics to the query molecule specification to generate a plurality of derived molecule specifications;
• performing one or more mapping operations on the plurality of derived molecule specifications to generate a plurality of mapped molecule specifications that are compressed digital representations of the plurality of derived molecule specifications;
• performing one or more hash-based search operations on a mapped catalog of available molecules that can be acquired based on the plurality of mapped molecule specifications to determine the one or more potential drug candidates;
• and
• causing one or more search results that include the one or more potential drug candidates to be outputted.

A system comprising:

• one or more memories storing instructions;
• and
• one or more processors coupled to the one or more memories that, when executing the instructions, perform the steps of:
• generating a plurality of likelihoods by determining, for each edit heuristic included in a plurality of edit heuristics, a likelihood that a target bioactivity associated with a query molecule specification is preserved when the edit heuristic is applied to the query molecule specification, wherein each edit heuristic included in the plurality of edit heuristics specifies a different type of modification to a structure of an existing molecule;
• generating a subset of the plurality of edit heuristics based on the plurality of likelihoods;
• applying the subset of the plurality of edit heuristics to the query molecule specification to generate a plurality of derived molecule specifications;
• performing one or more mapping operations on the plurality of derived molecule specifications to generate a plurality of mapped molecule specifications that are compressed digital representations of the plurality of derived molecule specifications;
• performing one or more hash-based search operations on a mapped catalog of available molecules that can be acquired based on the plurality of mapped molecule specifications to determine one or more potential drug candidates;
• and
• causing one or more search results that include the one or more potential drug candidates to be outputted.