What are the optimal numbers of mutations and crossovers etc.?

Computer-Aided Drug Design at the Durrant Lab Forums AutoGrow4 What are the optimal numbers of mutations and crossovers etc.?

Viewing 1 reply thread
  • Author
    Posts
    • #37271
      Christian
      Guest

      Hello,
      I’m just dealing with the adjustment of AutoGrow’s parameters regarding the genetic algorithm. According to the defaults, these look like
      "number_of_mutants_first_generation": 10,
      "number_of_crossovers_first_generation": 10,
      "number_of_mutants": 3,
      "number_of_crossovers": 3,
      "number_elitism_advance_from_previous_gen": 3,
      "top_mols_to_seed_next_generation": 5,
      "diversity_mols_to_seed_first_generation": 3,
      "diversity_seed_depreciation_per_gen": 0,
      Are these the optimal values? Do they depend from the size of the starting set? I am just working with 32 compounds.
      Thank you very much for any suggestions!
      With best regards
      Christian

    • #37850
      Jacob Durrant
      Keymaster

      Hi Christian. Thanks for all your interest in AutoGrow. Unfortunately, the ideal settings will depend very much on the initial population of ligands, both in terms of numbers and available chemical moieties where optimizing fragments can be added. I’d recommend trying a few different settings to see which one gives the best results. Take care.

Viewing 1 reply thread
  • The topic ‘What are the optimal numbers of mutations and crossovers etc.?’ is closed to new replies.