DOCK GA Development Goals

From Rizzo_Lab
Revision as of 11:23, 13 May 2019 by Jbickel (talk | contribs) (To Do List)
Jump to: navigation, search
Tasks src Owner Complete?
Fix bug that collapsed atom coordinates everywhere? nowhere? everyone No
Added Delimeter header conf_gen_ga LEP Yes
Fix xover only feature conf_gen_ga LEP Yes
Put in error messages for mut_rate > 1 conf_gen_ga LEP Yes
Manual user-defined mutation type conf_gen_ga LEP Yes
Remove check only option conf_gen_ga LEP Yes

To Do List

  1. -xover (guided based on score) - Good v Good ; Bad v Good ; Bad v Bad
  2. nonexhaustive xover (pick subset of xover based on probability)
  3. 2-3 point xover at once
  4. adaptive maintenance ensemble based on ensemble convergence
  5. bring in new parents based on convergence
  6. Mutations-
  7. adaptive mutation rate
  8. pick location of mutation based on something
  9. pick mutation type based on behavior of esemble
    1. too large boost deletion
  10. too small more add
  11. change ...boost replace/sub
  12. mutation type selection based on probability vs ensemble
  13. complete x # y mutation so far so less prevalent etc
  14. 3 layer subs do no work so don't do them
  15. replace > 1 segment
  16. fitness-
  17. turn on and off niching adaptive/extinction
  18. reduce boost of fragments and all poor mols with niching
  19. pareto/mulitobjective ga
  20. selection-
  21. metropolis selection for tournament/roulette
  22. adaptive keep #p and #o
  23. extinction-
  24. automated vs on convergence
  25. stop-
  26. convergence
  27. which molecules are best-
  28. best first pruning - now uses descriptor score even if niching ned to delta to fitness/niching when used