DOCK GA Development Goals

From Rizzo_Lab
Revision as of 11:24, 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-
    1. adaptive mutation rate
    2. pick location of mutation based on something
    3. pick mutation type based on behavior of ensemble
    4. too large boost deletion
    5. too small more add
    6. change ...boost replace/sub
    7. mutation type selection based on probability vs ensemble
    8. complete x # y mutation so far so less prevalent etc
  7. 3 layer subs do no work so don't do them
  8. replace > 1 segment
  9. fitness-
    1. turn on and off niching adaptive/extinction
    2. reduce boost of fragments and all poor mols with niching
    3. pareto/mulitobjective ga
  10. selection-
    1. metropolis selection for tournament/roulette
    2. adaptive keep #p and #o
  11. extinction-
    1. automated vs on convergence
  12. stop-
    1. convergence
  13. which molecules are best-
    1. best first pruning - now uses descriptor score even if niching ned to delta to fitness/niching when used