|
|
| (3 intermediate revisions by one other user not shown) |
| Line 1: |
Line 1: |
| − | For this experiment required files will include
| + | *[[2024 DOCK GA tutorial 1 with 1NDV]] |
| − | 2NNQ.lig.mol2
| + | *[[2019 DOCK GA tutorial 1 with 2NNQ]] |
| − | =='''I. Fragment Library Generation for 2NNQ'''==
| |
| − | | |
| − | ===Fragment Libraries===
| |
| − | For this experiment a general fragment library to account for all the possible ligands the GA can produce. A focused Fragment library will not be enough to account for all the possibilities since it is too small of a set of data.
| |
| − | | |
| − | The first step for this experiment is to generate a directory to perform the work in
| |
| − | mkdir 2NNQ_GA
| |
| − | Go into this new directory and then create another directory that will store all the fragment molecules
| |
| − | mkdir fraglib
| |
| − | Enter the file directory fraglib
| |
| − | cd fraglib
| |
| − | Create a new file called 2NNQ.fraglib
| |
| − | touch 2NNQ.fraglib
| |
| − | dock6 -i 2NNQ.fraglib
| |
| − | Answer the following prompts using these responses
| |
| − | conformer_search_type flex
| |
| − | write_fragment_libraries yes
| |
| − | fragment_library_prefix 2NNQ.fraglib
| |
| − | fragment_library_freq_cutoff 1
| |
| − | fragment_library_sort_method freq
| |
| − | fragment_library_trans_origin no
| |
| − | use_internal_energy no
| |
| − | ligand_atom_file ../../2NNQ_Tutorial/1.dockprep/2nnq_lig_withH.mol2
| |
| − | limit_max_ligands no
| |
| − | skip_molecule no
| |
| − | read_mol_solvation no
| |
| − | calculate_rmsd no
| |
| − | use_database_filter no
| |
| − | orient_ligand no
| |
| − | bump_filter no
| |
| − | score_molecules no
| |
| − | atom_model all
| |
| − | vdw_defn_file /gpfs/projects/AMS536/zzz.programs/dock6/parameters/vdw_AMBER_parm99.defn
| |
| − | flex_defn_file /gpfs/projects/AMS536/zzz.programs/dock6/parameters/flex.defn
| |
| − | flex_drive_file /gpfs/projects/AMS536/zzz.programs/dock6/parameters/flex_drive.tbl
| |
| − | ligand_outfile_prefix 2NNQ_frag_output
| |
| − | write_orientations no
| |
| − | num_scored_conformers 1
| |
| − | rank_ligands no
| |
| − | | |
| − | The only aspect that is relevant of this fragment library generated is the torsion environment that should be titled 2NNQ.fraglib_torenv.dat
| |
| − | Following this step the torsion environments of this molecule will be combined with the file titled full_sorted_fraglib.dat using the python software combine_torenv.py
| |
| − | py /gpfs/projects/rizzo/zzz.programs/torsion_env_combination/combine_torenv.py 2NNQ.fraglib_torenv.dat /gpfs/projects/rizzo/zzz.programs/dock6.10_2019.06.18/parameters/fraglib_torenv.dat
| |
| − | | |
| − | This should generate a new list of torsion environments titled unique_full_sorted_fraglib.dat
| |
| − | =='''II. Performing a GA using 2NNQ'''==
| |
| − | | |
| − | For this part a new directory will be created in the 2NNQ_GA. This will just be 2NNQ_GA_results. cd into that directory and create a new file titled 2NNQ_GA.in.
| |
| − | mkdir 2NNQ_GA_results
| |
| − | cd 2NNQ_GA_results
| |
| − | touch 2NNQ_GA.in
| |
| − | Following this dock6 will be performed on the molecule
| |
| − | dock6 -i 2NNQ_GA.in -o 2NNQ_GA.out
| |
| − | Input the following in order to get the GA working properly. The file will ask for ga_mutations. This will prompt you with addition, deletion, substitution, and replacement mutations and respond yes to all them unless there is a specific purpose to your code to not include these mutation types.
| |
| − | conformer_search_type genetic
| |
| − | ga_molecule_file /Path/2nnq_lig_withH.mol2
| |
| − | ga_fraglib_scaffold_file /gpfs/projects/rizzo/zzz.programs/dock6.10_2019.06.14/parameters /fraglib_ga_scaffold.mol2
| |
| − | ga_fraglib_linker_file /gpfs/projects/rizzo/zzz.programs/dock6.10_2019.06.14/parameters /fraglib_linker.mol2
| |
| − | ga_fraglib_sidechain_file /gpfs/projects/rizzo/zzz.programs/dock6.10_2019.06.14/parameters/fraglib_sidechain.mol2
| |
| − | ga_torenv_table ../fraglib/unique_full_sorted_fraglib.dat
| |
| − | ga_max_generations 500
| |
| − | ga_xover_sampling_method_rand yes
| |
| − | ga_xover_max 150
| |
| − | ga_bond_tolerance 0.5
| |
| − | ga_angle_cutoff 0.14
| |
| − | ga_check_overlap no
| |
| − | ga_mutations yes
| |
| − | ga_mutate_addition yes
| |
| − | ga_mutate_deletion yes
| |
| − | ga_mutate_substitution yes
| |
| − | ga_mutate_replacement yes
| |
| − | ga_mutate_parents yes
| |
| − | ga_pmut_rate 0.3
| |
| − | ga_omut_rate 0.7
| |
| − | ga_max_mut_cycles 5
| |
| − | ga_mut_sampling_method rand
| |
| − | ga_num_random_picks 10
| |
| − | ga_max_root_size 5
| |
| − | ga_energy_cutoff 100
| |
| − | ga_heur_unmatched_num 2
| |
| − | ga_heur_matched_rmsd 2
| |
| − | ga_constraint_mol_wt 550
| |
| − | ga_constraint_rot_bon 10
| |
| − | ga_constraint_H_accept 10
| |
| − | ga_constraint_H_don 5
| |
| − | ga_constraint_formal_charge 4
| |
| − | ga_ensemble_size 200
| |
| − | ga_selection_method elitism
| |
| − | ga_elitism_combined no
| |
| − | ga_elitism_option max
| |
| − | ga_niching no
| |
| − | ga_selection_extinction no
| |
| − | ga_max_num_gen_with_no_crossover 1000
| |
| − | ga_output_prefix 2NNQ_GA_output
| |
| − | use_internal_energy yes
| |
| − | internal_energy_rep_exp 12
| |
| − | internal_energy_cutoff 100
| |
| − | use_database_filter no
| |
| − | orient_ligand no
| |
| − | bump_filter no
| |
| − | score_molecules yes
| |
| − | contact_score_primary no
| |
| − | grid_score_primary no
| |
| − | gist_score_primary no
| |
| − | multigrid_score_primary no
| |
| − | dock3.5_score_primary no
| |
| − | continuous_score_primary no
| |
| − | footprint_similarity_score_primary no
| |
| − | pharmacophore_score_primary no
| |
| − | hbond_score_primary no
| |
| − | descriptor_score_primary yes
| |
| − | descriptor_use_grid_score no
| |
| − | descriptor_use_multigrid_score no
| |
| − | descriptor_use_continuous_score no
| |
| − | descriptor_use_footprint_similarity no
| |
| − | descriptor_use_pharmacophore_score no
| |
| − | descriptor_use_tanimoto no
| |
| − | descriptor_use_hungarian no
| |
| − | descriptor_use_volume_overlap no
| |
| − | descriptor_use_gist no
| |
| − | minimize_ligand yes
| |
| − | minimize_anchor yes
| |
| − | minimize_flexible_growth yes
| |
| − | use_advanced_simplex_parameters no
| |
| − | simplex_max_cycles 1
| |
| − | simplex_score_converge 0.1
| |
| − | simplex_cycle_converge 1
| |
| − | simplex_trans_step 1
| |
| − | simplex_rot_step 0.1
| |
| − | simplex_tors_step 10
| |
| − | simplex_anchor_max_iterations 500
| |
| − | simplex_grow_max_iterations 500
| |
| − | simplex_grow_tors_premin_iterations 00
| |
| − | simplex_random_seed 0
| |
| − | simplex_restraint_min yes
| |
| − | simplex_coefficient_restraint 10
| |
| − | atom_model all
| |
| − | vdw_defn_file /gpfs/projects/AMS536/zzz.programs/dock6/parameters /vdw_AMBER_parm99.defn
| |
| − | flex_defn_file /gpfs/projects/AMS536/zzz.programs/dock6/parameters/flex.defn
| |
| − | flex_drive_file /gpfs/projects/AMS536/zzz.programs/dock6/parameters/flex_drive.tbl
| |
| − | | |
| − | For the last step send this to the slurm servers generate the results. This test will occur for 500 generations and is too computationally intensive for the head node.
| |
| − | | |
| − | First create a new file to send to the slurm system
| |
| − | vim 2NNQ_GA.sh
| |
| − | Following this input the following into the 2NNQ_GA.sh script
| |
| − | #!/bin/bash
| |
| − | #SBATCH --time=48:00:00
| |
| − | #SBATCH --nodes=1
| |
| − | #SBATCH --ntasks=40
| |
| − | #SBATCH --job-name=2NNQ_GA_input
| |
| − | #SBATCH --output=2NNQ_GA_output
| |
| − | #SBATCH -p long-40core
| |
| − | | |
| − | cd $SLURM_SUBMIT_DIR
| |
| − | dock6 -i 2NNQ_GA.in -o 2NNQ_GA.out
| |
| − | Following this you will send the script
| |
| − | qsub 2NNQ_GA.sh
| |
| − | | |
| − | To check on its status use the following
| |
| − | qstat -u username
| |
