US 12,248,885 B2
System and method for feedback-driven automated drug discovery
Povilas Norvaisas, Manacor (ES); Roy Tal, Dallas, TX (US); Zygimantas Jocys, Hove (GB); Charles Dazler Knuff, Dallas, TX (US); Alvaro Prat, Barcelona (ES); Gintautas Kamuntavicius, Vilniaus rajonas (LT); Hisham Abdel Aty, Clitheroe (GB); Orestis Bastas, Vyronas (GR); and Nikola Nonkovic, Belgrade (RS)
Assigned to RO5 INC., Dallas, TX (US)
Filed by Ro5 Inc., Dallas, TX (US)
Filed on Jun. 21, 2022, as Appl. No. 17/845,813.
Application 17/845,813 is a continuation in part of application No. 17/540,142, filed on Dec. 1, 2021, granted, now 11,354,582, issued on Jun. 7, 2022.
Application 17/845,813 is a continuation in part of application No. 17/398,190, filed on Aug. 10, 2021, granted, now 11,367,006, issued on Jun. 21, 2022.
Application 17/540,142 is a continuation in part of application No. 17/202,722, filed on Mar. 16, 2021, granted, now 11,256,994, issued on Feb. 22, 2022.
Application 17/398,190 is a continuation in part of application No. 17/202,722, filed on Mar. 16, 2021, granted, now 11,256,994, issued on Feb. 22, 2022.
Application 17/202,722 is a continuation in part of application No. 17/174,677, filed on Feb. 12, 2021, granted, now 11,615,324.
Application 17/174,677 is a continuation of application No. 17/171,494, filed on Feb. 9, 2021, granted, now 11,176,462, issued on Nov. 16, 2021.
Application 17/171,494 is a continuation of application No. 17/166,435, filed on Feb. 3, 2021, granted, now 11,080,607.
Claims priority of provisional application 63/287,915, filed on Dec. 9, 2021.
Claims priority of provisional application 63/126,388, filed on Dec. 16, 2020.
Claims priority of provisional application 63/126,372, filed on Dec. 16, 2020.
Claims priority of provisional application 63/126,349, filed on Dec. 16, 2020.
Prior Publication US 2022/0351053 A1, Nov. 3, 2022
Int. Cl. G16B 50/10 (2019.01); G06F 16/951 (2019.01); G06F 18/22 (2023.01); G06N 3/08 (2023.01); G06N 5/022 (2023.01); G16B 15/00 (2019.01); G16B 40/00 (2019.01); G16B 45/00 (2019.01)
CPC G06N 5/022 (2013.01) [G06F 16/951 (2019.01); G06F 18/22 (2023.01); G06N 3/08 (2013.01); G16B 15/00 (2019.02); G16B 40/00 (2019.02); G16B 45/00 (2019.02); G16B 50/10 (2019.02)] 12 Claims
OG exemplary drawing
 
1. A system for feedback-driven automated drug discovery, comprising:
an iterative physical testing system comprising:
automated biochemical assay equipment configured to:
receive an amount of a drug candidate molecule and an assay procedure from the laboratory equipment controller, the assay procedure comprising a first parameter;
automatically perform an assay of the drug candidate molecule according to the assay procedure to produce an assay result, the assay result comprising an indication as to whether the first parameter has been met by the drug candidate molecule; and
where the assay result indicates that the first parameter has been met, send the assay result for that assay to the laboratory API that will send it to the to a bioactivity module along with chemical notation for the drug candidate molecule; and
a chemical synthesizer configured to:
receive synthesis instructions from the laboratory equipment controller;
synthesize a new drug candidate molecule from a supply of chemicals using chemical notation of precursors and synthesis steps provided by a retrosynthesis system; and
provide an amount of the new drug candidate molecule to the automated biochemical assay equipment as defined by the laboratory workflow control module;
a computing device comprising a memory, a processor, and a non-volatile data storage device;
a laboratory equipment orchestration software operating on the computing device, the laboratory equipment orchestration software comprising:
a laboratory API module that communicates with the artificial intelligence assistance system, receives instructions from it, sends back the data and provides information about the available chemical libraries, chemical synthesis capabilities and resources;
a laboratory workflow control module that receives instructions from the artificial intelligence assistance system through a laboratory API and defines experimental workflows that the roboticized laboratory will follow, the experimental workflows comprising:
receipt of a set of possible drug candidates from a bioactivity module;
performance of primary assays on the set of possible drug candidates;
sending of primary assay results to an artificial intelligence system for analysis;
receipt a new drug candidate from a de novo ligand discovery module;
performance of a secondary assay on the new drug candidate; and
outputting a result of the secondary assay;
a laboratory equipment utilization planning module that receives instructions from the laboratory workflow control module and plans laboratory module use and resource allocation; and
a laboratory equipment controller that receives the instructions from the laboratory equipment utilization planning module and sends the instructions to the appropriate laboratory equipment modules: the biochemical assay and automated chemical synthesis modules;
an artificial intelligence assistance system operating on the computing device, the artificial intelligence assistance system comprising:
a chemical database stored in the non-volatile data storage device, the chemical database comprising known interactions of ligands with protein binding sites and rules for retrosynthesis of molecules;
a bioactivity module operating on the computing device which causes the computing device to:
receive the assay procedures;
generate a set of possible drug candidates based on the assay procedures; and
send chemical notation for the set of possible drug candidates to the automated biochemical assay equipment for performance of primary assays; a de novo ligand discovery module operating on the computing device which causes the computing device to:
receive the primary assay result, the drug candidate molecule, and the binding site from the chemical database;
perform one or more interpolations or perturbations of the drug candidate molecule to generate a new drug candidate molecule predicted to meet or exceed the first parameter, the prediction being based on the known interactions of ligands with protein binding sites from the chemical database; and
send chemical notation for the new drug candidate molecule to a retrosynthesis system for retrosynthesis; and
a retrosynthesis system operating on the computing device which causes the computing device to:
receive the chemical notation for the new drug candidate molecule;
perform retrosynthesis of the new drug candidate molecule using the rules for retrosynthesis of molecules of the chemical database; and
send to the chemical synthesizer chemical notation for precursors and synthesis steps for synthesizing the new drug candidate molecule.