METHODS AND SYSTEMS FOR INTERACTIVE EVOLUTIONARY COMPUTING (IEC)

• US 20100199186A1
• Filed: 10/13/2009
• Published: 08/05/2010
• Est. Priority Date: 04/04/2003
• Status: Active Grant

• Current Assignee: Telepathy Labs, Inc.
• Original Assignee: Belinda Ome, Carl Anderson, Eric Bonabeau, Joseph A. Rothermich, Mark Sullivan, Oliver Bandte, Pablo Funes, Sergey Malinchik
• Inventors: Sullivan, Mark, Ome, Belinda, Rothermich, Joseph A., Bandte, Oliver, Anderson, Carl, Funes, Pablo, Malinchik, Sergey, Bonabeau, Eric
• Granted Patent: US 8,117,139 B2
• Time in Patent Office: Days
• US Class Current: 715/733
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G16C 20/50 Molecular design, e.g. of drugs
• CPC Class Codes: G16C 20/70 Machine learning, data mining or chemometrics

Abstract

Methods and systems for interactive evolutionary computing may include generating a set of candidate molecules based on an evolutionary scheme in which an objective function is a priori mathematically unexpressed, presenting data based on the set of candidate molecules to one or more users, receiving at least one input from the user(s), the input(s) based on the user(s)'"'"'s evaluation of the presented set of candidate molecules, and, based on the input(s), using at least the evolutionary scheme and the input(s) to generate an updated set of candidate molecules, and repeating the presenting and receiving.

Claims

1. In a computer system having a user interface including a display and an input device, a method, comprising:

generating a set of candidate molecules based on an evolutionary scheme in which an objective function to determine a fitness of a candidate molecule is a priori mathematically unexpressed,

presenting on the display data based on the set of candidate molecules to at least one user,

receiving through the input device at least one input from the at least one user, the at least one input based on the at least one user'"'"'s evaluation of the presented set of candidate molecules,

based on the at least one input, using at least the evolutionary scheme and the at least one input to generate an updated set of candidate molecules, and

repeating the presenting and receiving.

2. A method according to claim 1, where presenting data based on the set of candidate molecules includes selecting at least one candidate molecule from the set of candidate molecules to present.

3. A method according to claim 2, where selecting the at least one candidate molecule includes selecting based on at least one constraint.

4. A method according to claim 2, where selecting the at least one candidate molecule includes selecting based on at least one calculated property of the at least one candidate molecule.

5. A method according to claim 4, where selecting the at least one candidate molecule further includes selecting based on at least one calculated property of the at least one candidate molecule satisfying at least one condition.

6. A method according to claim 1, where presenting data based on the set of candidate molecules includes presenting a molecular structure of at least one candidate molecule of the set of candidate molecules.

7. A method according to claim 1, where presenting data based on the set of candidate molecules includes presenting at least one calculated property of at least one candidate molecule of the set of candidate molecules.

8. A method according to claim 7, where presenting data based on the set of candidate molecules further includes presenting at least one calculated value of at least one of an adsorption property, a distribution property, a metabolism property and an excretion property, of at least one candidate molecule of the set of candidate molecules.

9. A method according to claim 1, where the at least one user input includes at least one of:

a rank of a plurality of candidate molecules in the set of candidate molecules presented, a rating of a plurality of candidate molecules in the set of candidate molecules presented, a selection of at least one candidate molecule in the set of candidate molecules presented, a modification of a structure of at least one candidate molecule in the set of candidate molecules presented, a selection of at least one feature of at least one candidate molecule in the set of candidate molecules presented, an identification of at least one parent for a genetic algorithm, at least one constraint, a modification of at least one constraint, at least one condition, a modification of at least one genetic operator, and a specification of at least one genetic operator.

10. A method according to claim 1, further comprising modifying at least one candidate molecule of the set of candidate molecules presented based on at least one input from the at least one user.

11. A method according to claim 1, where using at least the evolutionary scheme and the at least one input to generate the updated set of candidate molecules includes:

generating a population based on the evolutionary scheme and the at least one user input.

12. A method according to claim 11, where using at least the evolutionary scheme and the at least one input to generate the updated set of candidate molecules further includes:

applying the population to at least one data set.

13. A method according to claim 11, where using at least the evolutionary scheme and the at least one input to generate the updated set of candidate molecules further includes:

generating the updated set of candidate molecules based upon at least one calculated property of at least one member of the population.

14. A method according to claim 1, where using at least the evolutionary scheme and the at least one input to generate the updated set of candidate molecules includes:

based on whether at least one condition is satisfied, iteratively using the evolutionary scheme and the at least one user input to generate the updated set of candidate molecules.

15. A method according to claim 14, where the at least one condition includes a specified number of generations of the evolutionary scheme having elapsed.

16. A method according to claim 1, where using at least the evolutionary scheme and the at least one input to generate the updated set of candidate molecules includes:

using a genetic operator to generate the updated set of candidate molecules.

17. A method according to claim 16, where the genetic operator includes at least one of:

crossover, and mutation.

18. A method according to claim 17, where the genetic operator is applied to modify a structure of at least one candidate molecule in the set of candidate molecules.

19. A method according to claim 1, where the method is terminated based on a user input.

20. A method according to claim 1, where the method is terminated based on at least one property of at least one candidate molecule in the set of candidate molecules satisfying at least one condition.

21. A method according to claim 1, where the instructions to the computer system to perform the method are communicated to a processor over a network.

22. A method according to claim 21, where the network is a local area network.

23. A method according to claim 1, where the at least one input from the at least one user is received over a network.

24. A method according to claim 23, where the network is a local area network.

25. A method according to claim 1, where the data presented on the display is transmitted over a network.

26. A method according to claim 25, where the network is a local area network.