Difference between revisions of "DOCK GA Development Goals"
From Rizzo_Lab
(→To Do List) |
(→To Do List) |
||
| Line 29: | Line 29: | ||
#bring in new parents based on convergence | #bring in new parents based on convergence | ||
#Mutations- | #Mutations- | ||
| − | #adaptive mutation rate | + | ##adaptive mutation rate |
| − | #pick location of mutation based on something | + | ##pick location of mutation based on something |
| − | #pick mutation type based on behavior of | + | ##pick mutation type based on behavior of ensemble |
##too large boost deletion | ##too large boost deletion | ||
| − | #too small more add | + | ##too small more add |
| − | #change ...boost replace/sub | + | ##change ...boost replace/sub |
| − | #mutation type selection based on probability vs ensemble | + | ##mutation type selection based on probability vs ensemble |
| − | #complete x # y mutation so far so less prevalent etc | + | ##complete x # y mutation so far so less prevalent etc |
#3 layer subs do no work so don't do them | #3 layer subs do no work so don't do them | ||
#replace > 1 segment | #replace > 1 segment | ||
#fitness- | #fitness- | ||
| − | #turn on and off niching adaptive/extinction | + | ##turn on and off niching adaptive/extinction |
| − | #reduce boost of fragments and all poor mols with niching | + | ##reduce boost of fragments and all poor mols with niching |
| − | #pareto/mulitobjective ga | + | ##pareto/mulitobjective ga |
#selection- | #selection- | ||
| − | #metropolis selection for tournament/roulette | + | ##metropolis selection for tournament/roulette |
| − | #adaptive keep #p and #o | + | ##adaptive keep #p and #o |
#extinction- | #extinction- | ||
| − | #automated vs on convergence | + | ##automated vs on convergence |
#stop- | #stop- | ||
| − | #convergence | + | ##convergence |
#which molecules are best- | #which molecules are best- | ||
| − | #best first pruning - now uses descriptor score even if niching ned to delta to fitness/niching when used | + | ##best first pruning - now uses descriptor score even if niching ned to delta to fitness/niching when used |
Revision as of 10:24, 13 May 2019
| 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
- -xover (guided based on score) - Good v Good ; Bad v Good ; Bad v Bad
- nonexhaustive xover (pick subset of xover based on probability)
- 2-3 point xover at once
- adaptive maintenance ensemble based on ensemble convergence
- bring in new parents based on convergence
- Mutations-
- adaptive mutation rate
- pick location of mutation based on something
- pick mutation type based on behavior of ensemble
- too large boost deletion
- too small more add
- change ...boost replace/sub
- mutation type selection based on probability vs ensemble
- complete x # y mutation so far so less prevalent etc
- 3 layer subs do no work so don't do them
- replace > 1 segment
- fitness-
- turn on and off niching adaptive/extinction
- reduce boost of fragments and all poor mols with niching
- pareto/mulitobjective ga
- selection-
- metropolis selection for tournament/roulette
- adaptive keep #p and #o
- extinction-
- automated vs on convergence
- stop-
- convergence
- which molecules are best-
- best first pruning - now uses descriptor score even if niching ned to delta to fitness/niching when used
