#                       mr_rosetta
#
# Run automr/autobuild/rosetta together 


# Type phenix.doc for help

usage: phenix.mr_rosetta mtzfile.mtz sequence.dat [pdbfile.pdb] [labin='FP=FP PHIB=PHIM FOM=FOMM'] 

Values of all params:
mr_rosetta {
  input_files {
    seq_file = "seq.dat"
    hhr_files = None
    alignment_files = None
    model_info_file = None
    data = "fobs.mtz"
    data_labels = None
    free_r_data = None
    free_r_labels = None
    labin = None
    search_models = "coords1.pdb"
    copies_in_search_models = None
    mr_rosetta_solutions = "averaged.pkl"
    ids_to_load = None
    map_coeffs = None
    labin_map_coeffs = None
    map = None
    refinement_params = None
    display_solutions = False
    fragment_files = None
    fragment_files_chain_list = None
    fragment_files_9_mer_by_chain = None
    fragment_files_3_mer_by_chain = None
    use_dummy_fragment_files = False
    sort_fragment_files = True
  }
  output_files {
    log = "mr_rosetta.log"
    params_out = "mr_rosetta_params.eff"
  }
  directories {
    temp_dir = ""
    workdir = ""
    output_dir = ""
    gui_output_dir = None
    top_output_dir = None
    rosetta_path = ""
    rosetta_binary_dir = "rosetta_source/bin"
    rosetta_binary_name = "mr_protocols.default"
    rosetta_script_dir = "rosetta_source/src/apps/public/electron_density"
    rosetta_database_dir = "rosetta_database"
  }
  read_hhpred {
    number_of_models = 1
    number_of_models_to_skip = 0
    copies_to_extract = None
    only_extract_proper_symmetry = False
  }
  place_model {
    run_place_model = True
    prerefine {
      run_prerefine = False
      number_of_prerefine_models = 1000
      number_of_models_in_ensemble = 1
    }
    model_already_placed = False
    model_already_aligned = False
    number_of_output_models = 5
    align_with_sculptor = True
    identity = None
    identity_for_scoring_only = 25
    use_all_plausible_sg = True
    overlap_allowed = 10
    selection_criteria_rot_value = 75
    fast_search_mode = True
    search_down_percent = 25
    mr_resolution = 3
    refine_after_mr = True
    denmod_after_refine = True
    ps_in_rebuild = False
    find_ncs_after_mr = True
    min_length_ncs = 10
    fixed_model = None
    fixed_model_identity = None
    sufficient_number_finished = None
    fixed_ensembles {
      fixed_ensembleID_list = None
      fixed_euler_list = 0 0 0
      fixed_frac_list = 0 0 0
      fixed_frac_list_is_fractional = True
    }
    copies_of_search_model_to_place = None
  }
  rescore_mr {
    run_rescore_mr = True
    nstruct = 5
    relax = False
    include_unrelaxed_in_scoring = False
    align = True
    edit_model = False
    stage_to_rescore = "mr_solution"
  }
  rosetta_rebuild {
    run_rosetta_rebuild = True
    stage_to_rebuild = "rescored_mr_solution"
    max_solutions_to_rebuild = 5
    min_solutions_to_rebuild = 1
    llg_percent_of_max_to_keep = 50
    rosetta_models = 100
    chunk_size = 1
    edit_model = True
    superpose_model = False
  }
  rosetta_rescore {
    run_rosetta_rescore = True
    percentage_to_rescore = 20
    min_solutions_to_rescore = 2
  }
  similarity {
    run_similarity = False
    required_cc = 0.2
    number_of_required_cc = 5
  }
  refine_top_models {
    run_refine_top_models = True
    stage_to_refine = None
    sort_score_type = None
    percent_to_refine = 20
    denmod_after_refine = True
    remove_clashing_residues = None
    clash_cutoff = 1.5
  }
  average_density_top_models {
    run_average_density_top_models = True
    percent_to_average = 100
  }
  relax_top_models {
    run_relax_top_models = True
    stage_to_relax = None
    number_to_relax = 2
    nstruct = 5
  }
  autobuild_top_models {
    run_autobuild_top_models = True
    number_to_autobuild = 2
    quick = False
    phase_and_build = False
    macro_cycles = None
    remove_residues_on_special_positions = True
    morph = False
    edit_model = True
    use_map_coeffs = True
  }
  setup_repeat_mr_rosetta {
    run_setup_repeat_mr_rosetta = True
    repeats = 1
    template_repeats = 0
    morph_repeats = 0
    number_to_repeat = 1
    acceptable_r = 0.25
    minimum_delta_r = None
  }
  repeat_mr_rosetta {
    run_repeat_mr_rosetta = True
    copies_in_new_search_group = 1
    update_map_coeffs_with_autobuild = True
  }
  rosetta_modeling {
    map_resolution = 3
    map_grid_spacing = 1.5
    map_weight = 1
    map_window = 5
    include_solvation_energy = True
    weights_file = None
  }
  crystal_info {
    resolution = 0
    space_group = None
    chain_type = *PROTEIN DNA RNA
    ncs_copies = Auto
  }
  control {
    verbose = False
    debug = True
    raise_sorry = False
    dry_run = False
    nproc = 1
    group_run_command = "sh "
    queue_commands = None
    condor_universe = "vanilla"
    add_double_quotes_in_condor = True
    condor = None
    one_subprocess_level = None
    single_run_command = "sh "
    last_process_is_local = True
    background = None
    ignore_errors_in_subprocess = True
    check_run_command = False
    max_wait_time = 1
    check_wait_time = 10
    wait_between_submit_time = 1
    wizard_directory_number = None
    n_dir_max = 100000
    number_to_print = 5
    write_run_directory_to_file = None
    rosetta_command = None
    rosetta_3_6_or_later = None
    fast = None
    generate_fragment_files = None
    resolve_command_list = None
    start_point = place_model rescore_mr rosetta_rebuild rosetta_rescore \
                  similarity refine_top_models average_density_top_models \
                  *relax_top_models autobuild_top_models \
                  setup_repeat_mr_rosetta repeat_mr_rosetta
    stop_point = place_model rescore_mr rosetta_rebuild rosetta_rescore \
                 similarity refine_top_models average_density_top_models \
                 *relax_top_models autobuild_top_models \
                 setup_repeat_mr_rosetta repeat_mr_rosetta
    clean_up = None
    add_id = True
    test_flag_value = None
  }
  non_user_params {
    file_base = None
    print_citations = True
    highest_id = 0
    is_sub_process = True
    dummy_autobuild = False
    dummy_refinement = False
    dummy_rosetta = False
    prerefine_only = False
    skip_clash_guard = True
    correct_special_position_tolerance = None
    ncs_in_refinement = *torsion cartesian None
    comparison_mtz = None
    labin_comparison_mtz = None
    write_local_files = False
    rosetta_fixed_seed = 1209
  }
}

Starting mr_rosetta
Date: Thu Sep 11 16:07:22 2014 
Directory: /home/smas036/phenix_test_mpi/test_relax

HOSTNAME: build-wm-p
Log file will be mr_rosetta.log 
Splitting output to  mr_rosetta.log
Checking rosetta paths:
  rosetta binary: /share/apps/Rosetta/3.5/rosetta-mpi-gcc-4.4.6/rosetta-3.5/rosetta_source/bin/mr_protocols.default.linuxgccrelease 
  database_dir: /share/apps/Rosetta/3.5/rosetta-mpi-gcc-4.4.6/rosetta-3.5/rosetta_database 
  script_dir: /share/apps/Rosetta/3.5/rosetta-mpi-gcc-4.4.6/rosetta-3.5/rosetta_source/src/apps/public/electron_density


================================================================================
Setting up reflection file and labels
================================================================================
LABIN LINE TO BE USED: FP=FP SIGFP=SIGFP FreeR_flag=FreeR_flag 

Identifying plausible values of ncs_copies

Number of residues in unique chains in seq file: 8
Cell volume:  15387.62
Equivalent positions:2

Maximum number of NCS copies based on cell contents:  5
Best guess of number of NCS copies: 4
Estimate of solvent fraction: 0.44
Choosing value of ncs copies leading to solvent content closest to 50%
Possible NCS copies to test: [4]

================================================================================
 LOADING EXISTING SOLUTIONS
================================================================================
Loading solutions from /home/smas036/phenix_test_mpi/test_relax/averaged.pkl 
RESULTS:  [
ID: 8  Model: S_COORD_0001_ed.pdb Single chain: S_COORD_0001_ed.pdb 
Stage: refined_rescored_rosetta_solution  MR_LLG:     6.90  
Group: None
CRYST1   25.000   25.000   25.000  90.00 100.00  90.00 P 1 21 1
map_coeffs: averaged_map_coeffs.mtz labin:FP=FAVG PHIB=PHIFAVG 
map: averaged_map_coeffs_nf.map
Placed model: coords1.pdb 
component_solutions: None]
S_COORD_0001_ed.pdb (model) set to /home/smas036/phenix_test_mpi/test_relax/S_COORD_0001_ed.pdb
coords1.pdb (search_model) set to /home/smas036/phenix_test_mpi/test_relax/coords1.pdb
coords1.pdb (placed_model) set to /home/smas036/phenix_test_mpi/test_relax/coords1.pdb
averaged_map_coeffs_nf.map (map) set to /home/smas036/phenix_test_mpi/test_relax/averaged_map_coeffs_nf.map
edited_align.ali (alignment_file) set to /home/smas036/phenix_test_mpi/test_relax/edited_align.ali
seq.dat (seq_file) set to /home/smas036/phenix_test_mpi/test_relax/seq.dat
S_COORD_0001_ed.pdb (model_one_copy) set to /home/smas036/phenix_test_mpi/test_relax/S_COORD_0001_ed.pdb
S_COORD_0001_ed.pdb (parent_model) set to /home/smas036/phenix_test_mpi/test_relax/S_COORD_0001_ed.pdb

Loaded 1 previous solutions: 
(list is in /home/smas036/phenix_test_mpi/test_relax/WORK_1/solutions_loaded.log) 
SET CRYSTAL SYMMETRY FROM INPUT SOLUTION:  CRYST1   25.000   25.000   25.000  90.00 100.00  90.00 P 1 21 1

Methods to be run:

place_model : False
rescore_mr : False
rosetta_rebuild : False
rosetta_rescore : False
similarity : False
refine_top_models : False
average_density_top_models : False
relax_top_models : True
autobuild_top_models : False
setup_repeat_mr_rosetta : False
repeat_mr_rosetta : False


Note: dummy fragments files will be used:  ['/share/apps/phenix/binary/phenix-1.9-1692/phenix/phenix/rosetta/dummy_fragments_file_3.gz', '/share/apps/phenix/binary/phenix-1.9-1692/phenix/phenix/rosetta/dummy_fragments_file_9.gz']
(This is ok if your template has no gaps)

Stage to relax: refined_rescored_rosetta_solution 

================================================================================
   RELAXING ROSETTA SOLUTIONS FOLLOWED BY LLG RECALCULATION

================================================================================
Taking top 2 solutions to relax
Candidate: ID: 8  SCORE :   6.90 STAGE: refined_rescored_rosetta_solution
General result for relaxing: 
ID: 8  Model: /home/smas036/phenix_test_mpi/test_relax/S_COORD_0001_ed.pdb Single chain: /home/smas036/phenix_test_mpi/test_relax/S_COORD_0001_ed.pdb 
Stage: refined_rescored_rosetta_solution  MR_LLG:     6.90  
Group: None
CRYST1   25.000   25.000   25.000  90.00 100.00  90.00 P 1 21 1
map_coeffs: averaged_map_coeffs.mtz labin:FP=FAVG PHIB=PHIFAVG 
map: /home/smas036/phenix_test_mpi/test_relax/averaged_map_coeffs_nf.map
Placed model: /home/smas036/phenix_test_mpi/test_relax/coords1.pdb 
component_solutions: None

Running separate job to score each result

Returning one set of results for each model to rescore

============================================================================== 
Starting sub-processes Group of rescore MR rosetta:Rescoring set of rosetta models... 
==============================================================================

Splitting work into 1 jobs and running with 1 processors using sh 
background=None in /home/smas036/phenix_test_mpi/test_relax/GROUP_OF_RESCORE_MR_ROSETTA_1
Final job will be run with sh  with background=True
Starting job 1...Log will be: /home/smas036/phenix_test_mpi/test_relax/GROUP_OF_RESCORE_MR_ROSETTA_1/RUN_FILE_1.log
Collecting all runs now

Collecting run_file: /home/smas036/phenix_test_mpi/test_relax/GROUP_OF_RESCORE_MR_ROSETTA_1/RUN_FILE_1  
info_file: /home/smas036/phenix_test_mpi/test_relax/GROUP_OF_RESCORE_MR_ROSETTA_1/INFO_FILE_1 
method: mr_rosetta 
logfile: /home/smas036/phenix_test_mpi/test_relax/GROUP_OF_RESCORE_MR_ROSETTA_1/RUN_FILE_1.log
Reading pickle file from /home/smas036/phenix_test_mpi/test_relax/GROUP_OF_RESCORE_MR_ROSETTA_1/RUN_1/results.pkl
============================================================================== 
DONE with running subprocesses Group of rescore MR rosetta:Rescoring set of rosetta models
==============================================================================

Solution with relaxed versions: 
ID: 8  Model: /home/smas036/phenix_test_mpi/test_relax/S_COORD_0001_ed.pdb Single chain: /home/smas036/phenix_test_mpi/test_relax/S_COORD_0001_ed.pdb 
Stage: refined_rescored_rosetta_solution  MR_LLG:     6.90  
Group: None
CRYST1   25.000   25.000   25.000  90.00 100.00  90.00 P 1 21 1
map_coeffs: averaged_map_coeffs.mtz labin:FP=FAVG PHIB=PHIFAVG 
map: /home/smas036/phenix_test_mpi/test_relax/averaged_map_coeffs_nf.map
Placed model: /home/smas036/phenix_test_mpi/test_relax/coords1.pdb 
component_solutions: None 
Relaxed solutions (1)

Best relaxed rosetta solutions:


Writing solutions as csv to results.csv 

Saved overall mr_rosetta results in results.pkl

To see details of these results type
    phenix.mr_rosetta mr_rosetta_solutions=results.pkl  display_solutions=True


Finishing up mr_rosetta...


Citations for mr_rosetta:

Adams PD, Afonine PV, Bunkoczi G, Chen VB, Davis IW, Echols N, Headd JJ, Hung
LW, Kapral GJ, Grosse-Kunstleve RW, McCoy AJ, Moriarty NW, Oeffner R, Read RJ,
Richardson DC, Richardson JS, Terwilliger TC, Zwart PH. (2010) PHENIX: a
comprehensive Python-based system for macromolecular structure solution. Acta
Cryst. D66:213-221.

DiMaio F, Terwilliger TC, Read RJ, Wlodawer A, Oberdorfer G, Wagner U, Valkov
E, Alon A, Fass D, Axelrod HL, Das D, Vorobiev SM, Iwaï H, Pokkuluri PR, Baker
D. (2011) Improved molecular replacement by density- and energy-guided protein
structure optimization. Nature 473:540-3.

Söding J. (2005) Protein homology detection by HMM-HMM comparison.
Bioinformatics 21:951-60.

All done