def process_output_fpocket_filter(search_list, tmp_folder, input_pockets_zip,
output_filter_pockets_zip, remove_tmp,
out_log):
""" Creates the output_filter_pockets_zip """
# decompress the input_pockets_zip file to tmp_folder
cluster_list = fu.unzip_list(zip_file=input_pockets_zip,
dest_dir=tmp_folder,
out_log=out_log)
# list all files of tmp_folder
pockets_list = [str(i) for i in Path(tmp_folder).iterdir()]
# select search_list items from pockets_list
sel_pockets_list = [
p for p in pockets_list for s in search_list if s + '_' in p
]
fu.log('Creating %s output file' % output_filter_pockets_zip, out_log)
# compress output to output_filter_pockets_zip
fu.zip_list(zip_file=output_filter_pockets_zip,
file_list=sel_pockets_list,
out_log=out_log)
if remove_tmp:
# remove temporary folder
fu.rm(tmp_folder)
fu.log('Removed temporary folder: %s' % tmp_folder, out_log)
def launch(self) -> int:
"""Execute the :class:`PdbClusterZip <api.pdb_cluster_zip.PdbClusterZip>` api.pdb_cluster_zip.PdbClusterZip object."""
# check input/output paths and parameters
self.check_data_params(self.out_log, self.err_log)
# Setup Biobb
if self.check_restart(): return 0
self.stage_files()
check_mandatory_property(self.pdb_code, 'pdb_code', self.out_log, self.__class__.__name__)
self.pdb_code = self.pdb_code.strip().lower()
file_list = []
#Downloading PDB_files
pdb_code_list = get_cluster_pdb_codes(pdb_code=self.pdb_code, cluster=self.cluster, out_log=self.out_log, global_log=self.global_log)
unique_dir = fu.create_unique_dir()
for pdb_code in pdb_code_list:
pdb_file = os.path.join(unique_dir, pdb_code+".pdb")
pdb_string = download_pdb(pdb_code=pdb_code, api_id=self.api_id, out_log=self.out_log, global_log=self.global_log)
write_pdb(pdb_string, pdb_file, self.filter, self.out_log, self.global_log)
file_list.append(os.path.abspath(pdb_file))
#Zipping files
fu.log("Zipping the pdb files to: %s" % self.output_pdb_zip_path)
fu.zip_list(self.output_pdb_zip_path, file_list, out_log=self.out_log)
if self.remove_tmp:
# remove temporary folder
fu.rm(unique_dir)
fu.log('Removed temporary folder: %s' % unique_dir, self.out_log)
return 0
def process_output_trjconv_str_ens(tmp_folder, remove_tmp, output_file,
glob_pattern, out_log):
""" Compresses, moves and removes temporal files generated by the wrapper """
# list all files in temporary folder
tmp_fl = list(Path(tmp_folder).glob(glob_pattern))
files_list = []
for file_name in tmp_fl:
files_list.append(file_name)
# adding files from temporary folder to zip
fu.zip_list(output_file, files_list, out_log)
if remove_tmp:
# remove temporary folder
fu.rm(tmp_folder)
fu.log('Removed temporary folder: %s' % tmp_folder, out_log)
def main(config, system=None):
start_time = time.time()
conf = settings.ConfReader(config, system)
global_log, _ = fu.get_logs(path=conf.get_working_dir_path(),
light_format=True)
global_prop = conf.get_prop_dic()
global_paths = conf.get_paths_dic()
dhdl_paths_listA = []
dhdl_paths_listB = []
for ensemble, mutation in conf.properties['mutations'].items():
ensemble_prop = conf.get_prop_dic(prefix=ensemble)
ensemble_paths = conf.get_paths_dic(prefix=ensemble)
# step0_image
global_log.info(
ensemble +
" Step 0: gmx image: Imaging trajectories to remove PBC issues")
ensemble_paths['step0_image']['input_traj_path'] = conf.properties[
'input_trajs'][ensemble]['input_traj_path']
ensemble_paths['step0_image']['input_top_path'] = conf.properties[
'input_trajs'][ensemble]['input_tpr_path']
gmx_image_pc(**ensemble_paths["step0_image"],
properties=ensemble_prop["step0_image"])
# step1_trjconv
global_log.info(
ensemble +
" Step 1: gmx trjconv: Extract snapshots from equilibrium trajectories"
)
ensemble_paths['step1_trjconv_' +
ensemble]['input_top_path'] = conf.properties[
'input_trajs'][ensemble]['input_tpr_path']
gmx_trjconv_str_ens_pc(**ensemble_paths['step1_trjconv_' + ensemble],
properties=ensemble_prop['step1_trjconv_' +
ensemble])
for ensemble, mutation in conf.properties['mutations'].items():
ensemble_prop = conf.get_prop_dic(prefix=ensemble)
ensemble_paths = conf.get_paths_dic(prefix=ensemble)
compss_wait_on_file(ensemble_paths['step1_trjconv_' +
ensemble]["output_str_ens_path"])
with zipfile.ZipFile(
ensemble_paths['step1_trjconv_' +
ensemble]["output_str_ens_path"]) as zip_f:
unique_dir = os.path.abspath(
fu.create_unique_dir(
prefix=ensemble_prop['step1_trjconv_' +
ensemble]['working_dir_path'] + '/' +
ensemble + '/'))
zip_f.extractall(unique_dir)
state_pdb_list = [
os.path.join(unique_dir, name) for name in zip_f.namelist()
]
for pdb_path in state_pdb_list:
pdb_name = os.path.splitext(os.path.basename(pdb_path))[0]
prop = conf.get_prop_dic(prefix=os.path.join(ensemble, pdb_name))
paths = conf.get_paths_dic(prefix=os.path.join(ensemble, pdb_name))
# Fixing terminal residues
newpdb = pdb_path + ".term.gro"
#fix_gro("/gpfs/scratch/bsc19/bsc19611/RATG13-RBD/fixGro.sh", pdb_path, newpdb)
fix_term(pdb_path, newpdb)
# Fixing terminal residues
#newpdb2 = pdb_path + ".term.gro"
#cmd2 = "sed 's/600ASN /600NASN/g' " + pdb_path + "| sed 's/ 1SER / 1NSER /g' | sed 's/597ASP /597CASP/g' | sed 's/793PRO /793CPRO/g' > " + newpdb2
#subprocess.call(cmd2, shell=True)
paths['step1_pmx_mutate']['input_structure_path'] = newpdb
# step1_pmx_mutate
global_log.info(ensemble + " " + pdb_name +
" Step 1: pmx mutate: Generate Hybrid Structure")
prop['step1_pmx_mutate']['mutation_list'] = mutation
mutate_pc(**paths["step1_pmx_mutate"],
properties=prop["step1_pmx_mutate"])
# step1.1_check_dummies
global_log.info(ensemble + " " + pdb_name +
" Step 1.1 Check for dummy atoms")
extract_atoms_pc(**paths['step1.1_check_dummies'],
properties=prop['step1.1_check_dummies'])
#compss_wait_on_file(paths['step1.1_check_dummies']['output_structure_path'])
#try:
# dummy = bool(os.path.getsize(paths['step1.1_check_dummies']['output_structure_path']))
#except:
# global_log.info("Error ocurred while checking the file containing dummy atoms")
# global_log.info(sys.exc_info()[0])
# step1.2_remove_ligand
#global_log.info(ensemble + " " + pdb_name + " Step 1.2 Remove ligand")
#remove_ligand_pc(**paths['step1.2_remove_ligand'], properties=prop['step1.2_remove_ligand'])
# step2_gmx_pdb2gmx
global_log.info(ensemble + " " + pdb_name +
" Step 2: gmx pdb2gmx: Generate Topology")
pdb2gmx_pc(**paths["step2_gmx_pdb2gmx"],
properties=prop["step2_gmx_pdb2gmx"])
# step2.1_sort_gro
#global_log.info(ensemble + " " + pdb_name + " Step 2.1 Sort gro residues")
#sort_gro_residues_pc(**paths['step2.1_sort_gro'], properties=prop['step2.1_sort_gro'])
# step2.2_lig_gmx_appendLigand
#global_log.info(ensemble + " " + pdb_name +" Step 2.2_lig: gmx appendLigand: Append a ligand to a GROMACS topology")
#append_ligand_pc(**paths["step2.2_lig_gmx_appendLigand"], properties=prop["step2.2_lig_gmx_appendLigand"])
# step3_pmx_gentop
global_log.info(ensemble + " " + pdb_name +
" Step 3: pmx gentop: Generate Hybrid Topology")
gentop_pc(**paths["step3_pmx_gentop"],
properties=prop["step3_pmx_gentop"])
# step4_gmx_makendx, step5_gmx_grompp, step6_gmx_mdrun
#global_log.info(ensemble + " " + pdb_name +" Check structure and Step 4-6 (Dummies): gmx make_ndx: Generate Gromacs Index file to select atoms to freeze, gmx grompp: Creating portable binary run file for energy minimization, gmx mdrun: Running energy minimization")
#check_structure_and_run_ndx_pc(ensemble, **paths["step4_gmx_makendx"], properties_makendx=prop["step4_gmx_makendx"], **paths["step5_gmx_grompp"], properties_grompp=prop["step5_gmx_grompp"], **paths["step6_gmx_mdrun"], properties_mdrun=prop["step6_gmx_mdrun"])
# step4_gmx_makendx, step5_gmx_grompp, step6_gmx_mdrun
global_log.info(
ensemble + " " + pdb_name +
" Step 4-6 (Check structure and ndx): gmx make_ndx: Generate Gromacs Index file to select atoms to freeze, gmx grompp: Creating portable binary run file for energy minimization, gmx mdrun: Running energy minimization"
)
fu.create_dir(prop["step4_gmx_makendx"]['working_dir_path'] + "/" +
ensemble + "/" + pdb_name + "/step4_gmx_makendx")
fu.create_dir(prop["step5_gmx_grompp"]['working_dir_path'] + "/" +
ensemble + "/" + pdb_name + "/step5_gmx_grompp")
fu.create_dir(prop["step6_gmx_mdrun"]['working_dir_path'] + "/" +
ensemble + "/" + pdb_name + "/step6_gmx_mdrun")
check_structure_and_run_ndx_pc(
ensemble,
output_structure_path=paths['step1.1_check_dummies']
['output_structure_path'],
**paths["step4_gmx_makendx"],
properties_makendx=prop["step4_gmx_makendx"],
**paths["step5_gmx_grompp"],
properties_grompp=prop["step5_gmx_grompp"],
**paths["step6_gmx_mdrun"],
properties_mdrun=prop["step6_gmx_mdrun"])
# step7_gmx_grompp
global_log.info(
ensemble + " " + pdb_name +
" Step 7: gmx grompp: Creating portable binary run file for system equilibration"
)
grompp_pc(**paths["step7_gmx_grompp"],
properties=prop["step7_gmx_grompp"])
# step8_gmx_mdrun
global_log.info(ensemble + " " + pdb_name +
" Step 8: gmx mdrun: Running system equilibration")
mdrun_pc(**paths["step8_gmx_mdrun"],
properties=prop["step8_gmx_mdrun"])
# step9_gmx_grompp
global_log.info(
ensemble + " " + pdb_name +
" Step 9: Creating portable binary run file for thermodynamic integration (ti)"
)
grompp_pc(**paths["step9_gmx_grompp"],
properties=prop["step9_gmx_grompp"])
# step10_gmx_mdrun
global_log.info(
ensemble + " " + pdb_name +
" Step 10: gmx mdrun: Running thermodynamic integration")
mdrun_dhdl_pc(**paths["step10_gmx_mdrun"],
properties=prop["step10_gmx_mdrun"])
if ensemble == "stateA":
dhdl_paths_listA.append(
paths["step10_gmx_mdrun"]["output_dhdl_path"])
elif ensemble == "stateB":
dhdl_paths_listB.append(
paths["step10_gmx_mdrun"]["output_dhdl_path"])
# Creating zip file containing all the dhdl files
dhdlA_path = os.path.join(
global_prop["step11_pmx_analyse"]['working_dir_path'], 'dhdlA.zip')
dhdlB_path = os.path.join(
global_prop["step11_pmx_analyse"]['working_dir_path'], 'dhdlB.zip')
for dhdl_file in dhdl_paths_listA:
compss_wait_on_file(dhdl_file)
for dhdl_file in dhdl_paths_listB:
compss_wait_on_file(dhdl_file)
fu.zip_list(dhdlA_path, dhdl_paths_listA)
fu.zip_list(dhdlB_path, dhdl_paths_listB)
# step11_pmx_analyse
global_log.info(
ensemble +
" Step 11: pmx analyse: Calculate free energies from fast growth thermodynamic integration simulations"
)
global_paths["step11_pmx_analyse"]["input_a_xvg_zip_path"] = dhdlA_path
global_paths["step11_pmx_analyse"]["input_b_xvg_zip_path"] = dhdlB_path
analyse_pc(**global_paths["step11_pmx_analyse"],
properties=global_prop["step11_pmx_analyse"])
elapsed_time = time.time() - start_time
global_log.info('')
global_log.info('')
global_log.info('Execution successful: ')
global_log.info(' Workflow_path: %s' % conf.get_working_dir_path())
global_log.info(' Config File: %s' % config)
if system:
global_log.info(' System: %s' % system)
global_log.info('')
global_log.info('Elapsed time: %.1f minutes' % (elapsed_time / 60))
global_log.info('')
def process_output_fpocket(tmp_folder, output_pockets_zip, output_summary,
sort_by, remove_tmp, out_log, classname):
""" Creates the output_pockets_zip and generates the output_summary """
path = str(PurePath(tmp_folder).joinpath('input_out'))
if not Path(path).is_dir():
if remove_tmp:
# remove temporary folder
fu.rm(tmp_folder)
fu.log('Removing temporary folder: %s' % tmp_folder, out_log)
fu.log(
classname +
': Error executing fpocket, please check your properties', out_log)
raise SystemExit(
classname +
': Error executing fpocket, please check your properties')
# summary
# read input_info.txt file
info = PurePath(path).joinpath('input_info.txt')
with open(info, 'r') as info_text:
lines = info_text.readlines()
lines = [x for x in lines if x != '\n']
data = {}
# parse input_info.txt file to python object
pocket = ''
for line in lines:
if not line.startswith('\t'):
# first level: pocket
num = re.findall('\d+', line)[0]
pocket = 'pocket' + num
data[pocket] = {}
else:
# second level: pocket properties
groups = re.findall('(.*)(?:\ *\:\ *)(.*)', line)[0]
key = groups[0].lower().strip()
key = re.sub(r'\-|\.', '', key)
key = re.sub(r'\s+', '_', key)
value = float(groups[1]) if '.' in groups[1] else int(groups[1])
data[pocket][key] = value
# get number of pockets
fu.log('%d pockets found' % (len(data)), out_log)
# sort data by sort_by property
fu.log('Sorting output data by %s' % (sort_by), out_log)
data = dict(
sorted(data.items(),
key=lambda item: float(item[1][sort_by]),
reverse=True))
# compress pockets
pockets = PurePath(path).joinpath('pockets')
files_list = [str(i) for i in Path(pockets).iterdir()]
fu.zip_list(zip_file=output_pockets_zip,
file_list=files_list,
out_log=out_log)
# save summary
fu.log('Saving summary to %s file' % (output_summary), out_log)
with open(output_summary, 'w') as outfile:
json.dump(data, outfile, indent=4)
if remove_tmp:
# remove temporary folder
fu.rm(tmp_folder)
fu.log('Removed temporary folder: %s' % tmp_folder, out_log)
def main(config, system=None):
start_time = time.time()
conf = settings.ConfReader(config, system)
global_log, _ = fu.get_logs(path=conf.get_working_dir_path(),
light_format=True)
global_prop = conf.get_prop_dic(global_log=global_log)
global_paths = conf.get_paths_dic()
dhdl_paths_listA = []
dhdl_paths_listB = []
for ensemble, mutation in conf.properties['mutations'].items():
ensemble_prop = conf.get_prop_dic(prefix=ensemble,
global_log=global_log)
ensemble_paths = conf.get_paths_dic(prefix=ensemble)
#Create and launch bb
global_log.info(
ensemble +
" Step 0: gmx trjconv: Extract snapshots from equilibrium trajectories"
)
ensemble_paths['step0_trjconv']['input_traj_path'] = conf.properties[
'input_trajs'][ensemble]['input_traj_path']
ensemble_paths['step0_trjconv']['input_top_path'] = conf.properties[
'input_trajs'][ensemble]['input_tpr_path']
GMXTrjConvStrEns(**ensemble_paths["step0_trjconv"],
properties=ensemble_prop["step0_trjconv"]).launch()
with zipfile.ZipFile(
ensemble_paths["step0_trjconv"]["output_str_ens_path"],
'r') as zip_f:
zip_f.extractall()
state_pdb_list = zip_f.namelist()
for pdb_path in state_pdb_list:
pdb_name = os.path.splitext(pdb_path)[0]
prop = conf.get_prop_dic(prefix=os.path.join(ensemble, pdb_name),
global_log=global_log)
paths = conf.get_paths_dic(prefix=os.path.join(ensemble, pdb_name))
#Create and launch bb
global_log.info("Step 1: pmx mutate: Generate Hybrid Structure")
paths['step1_pmx_mutate']['input_structure_path'] = pdb_path
prop['step1_pmx_mutate']['mutation_list'] = mutation
Mutate(**paths["step1_pmx_mutate"],
properties=prop["step1_pmx_mutate"]).launch()
# Step 2: gmx pdb2gmx: Generate Topology
# From pmx tutorial:
# gmx pdb2gmx -f mut.pdb -ff amber99sb-star-ildn-mut -water tip3p -o pdb2gmx.pdb
global_log.info("Step 2: gmx pdb2gmx: Generate Topology")
Pdb2gmx(**paths["step2_gmx_pdb2gmx"],
properties=prop["step2_gmx_pdb2gmx"]).launch()
# Step 3: pmx gentop: Generate Hybrid Topology
# From pmx tutorial:
# python generate_hybrid_topology.py -itp topol_Protein.itp -o topol_Protein.itp -ff amber99sb-star-ildn-mut
global_log.info("Step 3: pmx gentop: Generate Hybrid Topology")
Gentop(**paths["step3_pmx_gentop"],
properties=prop["step3_pmx_gentop"]).launch()
# Step 4: gmx make_ndx: Generate Gromacs Index File to select atoms to freeze
# From pmx tutorial:
# echo -e "a D*\n0 & ! 19\nname 20 FREEZE\nq\n" | gmx make_ndx -f frame0/pdb2gmx.pdb -o index.ndx
global_log.info(
"Step 4: gmx make_ndx: Generate Gromacs Index file to select atoms to freeze"
)
MakeNdx(**paths["step4_gmx_makendx"],
properties=prop["step4_gmx_makendx"]).launch()
if ensemble == 'stateA':
# In stateA, with lamdda=0, we don't need the energy minimization step, so simply get the output
# from the step2 (pdb2gmx) as output from the step6 (energy minimization)
# From pmx tutorial:
# There are no dummies in this state at lambda=0, therefore simply convert mut.pdb to emout.gro
paths['step7_gmx_grompp']['input_gro_path'] = paths[
'step2_gmx_pdb2gmx']['output_gro_path']
elif ensemble == 'stateB':
# Step 5: gmx grompp: Creating portable binary run file for energy minimization
# From pmx tutorial:
# gmx grompp -c pdb2gmx.pdb -p topol.top -f ../../mdp/em_FREEZE.mdp -o em.tpr -n ../index.ndx
global_log.info(
"Step 5: gmx grompp: Creating portable binary run file for energy minimization"
)
Grompp(**paths["step5_gmx_grompp"],
properties=prop["step5_gmx_grompp"]).launch()
# Step 6: gmx mdrun: Running energy minimization
# From pmx tutorial:
# gmx mdrun -s em.tpr -c emout.gro -v
global_log.info(
ensemble +
" Step 6: gmx mdrun: Running energy minimization")
Mdrun(**paths["step6_gmx_mdrun"],
properties=prop["step6_gmx_mdrun"]).launch()
# Step 7: gmx grompp: Creating portable binary run file for system equilibration
# From pmx tutorial:
# gmx grompp -c emout.gro -p topol.top -f ../../mdp/eq_20ps.mdp -o eq_20ps.tpr -maxwarn 1
global_log.info(
ensemble +
" Step 7: gmx grompp: Creating portable binary run file for system equilibration"
)
Grompp(**paths["step7_gmx_grompp"],
properties=prop["step7_gmx_grompp"]).launch()
# Step 8: gmx mdrun: Running system equilibration
# From pmx tutorial:
# gmx mdrun -s eq_20ps.tpr -c eqout.gro -v
global_log.info(ensemble +
" Step 8: gmx mdrun: Running system equilibration")
Mdrun(**paths["step8_gmx_mdrun"],
properties=prop["step8_gmx_mdrun"]).launch()
# Step 9: gmx grompp: Creating portable binary run file for thermodynamic integration (ti)
# From pmx tutorial:
# gmx grompp -c eqout.gro -p topol.top -f ../../mdp/ti.mdp -o ti.tpr -maxwarn 1
global_log.info(
ensemble +
" Step 9: Creating portable binary run file for thermodynamic integration (ti)"
)
Grompp(**paths["step9_gmx_grompp"],
properties=prop["step9_gmx_grompp"]).launch()
# Step 10: gmx mdrun: Running thermodynamic integration
# From pmx tutorial:
# gmx mdrun -s ti.tpr -c eqout.gro -v
global_log.info(
ensemble +
" Step 10: gmx mdrun: Running thermodynamic integration")
Mdrun(**paths["step10_gmx_mdrun"],
properties=prop["step10_gmx_mdrun"]).launch()
if ensemble == "stateA":
dhdl_paths_listA.append(
paths["step10_gmx_mdrun"]["output_dhdl_path"])
elif ensemble == "stateB":
dhdl_paths_listB.append(
paths["step10_gmx_mdrun"]["output_dhdl_path"])
#Creating zip file containing all the dhdl files
dhdlA_path = 'dhdlA.zip'
dhdlB_path = 'dhdlB.zip'
fu.zip_list(dhdlA_path, dhdl_paths_listA)
fu.zip_list(dhdlB_path, dhdl_paths_listB)
# Step 11: pmx analyse: Calculate free energies from fast growth thermodynamic integration simulations
# From pmx tutorial:
# python analyze_dhdl.py -fA ../stateA/frame*/dhdl*.xvg -fB ../stateB/frame*/dhdl*.xvg --nbins 25 -t 293 --reverseB
global_log.info(
ensemble +
" Step 11: pmx analyse: Calculate free energies from fast growth thermodynamic integration simulations"
)
global_paths["step11_pmx_analyse"]["input_A_xvg_zip_path"] = dhdlA_path
global_paths["step11_pmx_analyse"]["input_B_xvg_zip_path"] = dhdlB_path
Analyse(**global_paths["step11_pmx_analyse"],
properties=global_prop["step11_pmx_analyse"]).launch()
elapsed_time = time.time() - start_time
global_log.info('')
global_log.info('')
global_log.info('Execution successful: ')
global_log.info(' Workflow_path: %s' % conf.get_working_dir_path())
global_log.info(' Config File: %s' % config)
if system:
global_log.info(' System: %s' % system)
global_log.info('')
global_log.info('Elapsed time: %.1f minutes' % (elapsed_time / 60))
global_log.info('')
def main(config, imaged_traj_available):
start_time = time.time()
conf = settings.ConfReader(config)
global_log, _ = fu.get_logs(path=conf.get_working_dir_path(),
light_format=True)
global_prop = conf.get_prop_dic()
global_paths = conf.get_paths_dic()
dhdl_paths_listA = []
dhdl_paths_listB = []
for ensemble, mutation in conf.properties['mutations'].items():
ensemble_prop = conf.get_prop_dic(prefix=ensemble)
ensemble_paths = conf.get_paths_dic(prefix=ensemble)
if not imaged_traj_available:
# step0_image There isn't an imaged trajectory
global_log.info(
ensemble +
" Step 0: gmx image: Imaging trajectories to remove PBC issues"
)
ensemble_paths['step0_image']['input_top_path'] = conf.properties[
'input_trajs'][ensemble]['input_tpr_path']
ensemble_paths['step0_image']['input_traj_path'] = conf.properties[
'input_trajs'][ensemble]['input_traj_path']
gmx_image_pc(**ensemble_paths["step0_image"],
properties=ensemble_prop["step0_image"])
else:
# An imaged trajectory is available
ensemble_paths['step1_trjconv_' +
ensemble]['input_traj_path'] = conf.properties[
'input_trajs'][ensemble]['input_traj_path']
# step1_trjconv
global_log.info(
ensemble +
" Step 1: gmx trjconv: Extract snapshots from equilibrium trajectories"
)
ensemble_paths['step1_trjconv_' +
ensemble]['input_top_path'] = conf.properties[
'input_trajs'][ensemble]['input_tpr_path']
gmx_trjconv_str_ens_pc(**ensemble_paths['step1_trjconv_' + ensemble],
properties=ensemble_prop['step1_trjconv_' +
ensemble])
for ensemble, mutation in conf.properties['mutations'].items():
ensemble_prop = conf.get_prop_dic(prefix=ensemble)
ensemble_paths = conf.get_paths_dic(prefix=ensemble)
compss_wait_on_file(ensemble_paths['step1_trjconv_' +
ensemble]["output_str_ens_path"])
with zipfile.ZipFile(
ensemble_paths['step1_trjconv_' +
ensemble]["output_str_ens_path"]) as zip_f:
unique_dir = os.path.abspath(
fu.create_unique_dir(
prefix=ensemble_prop['step1_trjconv_' +
ensemble]['working_dir_path'] + '/' +
ensemble + '/'))
zip_f.extractall(unique_dir)
state_pdb_list = [
os.path.join(unique_dir, name) for name in zip_f.namelist()
]
for pdb_path in state_pdb_list:
pdb_name = os.path.splitext(os.path.basename(pdb_path))[0]
prop = conf.get_prop_dic(prefix=os.path.join(ensemble, pdb_name))
paths = conf.get_paths_dic(prefix=os.path.join(ensemble, pdb_name))
# step2_pmx_mutate
global_log.info(ensemble + " " + pdb_name +
" Step 2: pmx mutate: Generate Hybrid Structure")
paths['step2_pmx_mutate']['input_structure_path'] = pdb_path
prop['step2_pmx_mutate']['mutation_list'] = mutation
mutate_pc(**paths["step2_pmx_mutate"],
properties=prop["step2_pmx_mutate"])
# step3_check_dummies
global_log.info(ensemble + " " + pdb_name +
" Step 3 Check for dummy atoms")
extract_atoms_pc(**paths['step3_check_dummies'],
properties=prop['step3_check_dummies'])
compss_wait_on_file(
paths['step3_check_dummies']['output_structure_path'])
try:
dummy = bool(
os.path.getsize(
paths['step3_check_dummies']['output_structure_path']))
except:
global_log.info(
"Error ocurred while checking the file containing dummy atoms"
)
global_log.info(sys.exc_info()[0])
# step4_gmx_pdb2gmx
global_log.info(ensemble + " " + pdb_name +
" Step 4: gmx pdb2gmx: Generate Topology")
pdb2gmx_pc(**paths["step4_gmx_pdb2gmx"],
properties=prop["step4_gmx_pdb2gmx"])
# step5_pmx_gentop
global_log.info(ensemble + " " + pdb_name +
" Step 5: pmx gentop: Generate Hybrid Topology")
gentop_pc(**paths["step5_pmx_gentop"],
properties=prop["step5_pmx_gentop"])
if not dummy:
paths['step9_gmx_grompp']['input_gro_path'] = paths[
'step4_gmx_pdb2gmx']['output_gro_path']
else:
# step6_gmx_makendx
global_log.info(
ensemble + " " + pdb_name +
" Step 6: (Dummies): gmx make_ndx: Generate Gromacs Index file to select atoms to freeze"
)
make_ndx_pc(**paths["step6_gmx_makendx"],
properties=prop["step6_gmx_makendx"])
# step7_gmx_grompp
global_log.info(
ensemble + " " + pdb_name +
" Step 7: (Dummies): gmx grompp: Creating portable binary run file for energy minimization"
)
grompp_ndx_pc(**paths["step7_gmx_grompp"],
properties=prop["step7_gmx_grompp"])
# step8_gmx_mdrun
global_log.info(
ensemble + " " + pdb_name +
" Step 8: (Dummies): gmx mdrun: Running energy minimization"
)
mdrun_pc(**paths["step8_gmx_mdrun"],
properties=prop["step8_gmx_mdrun"])
# step9_gmx_grompp
global_log.info(
ensemble + " " + pdb_name +
" Step 9: gmx grompp: Creating portable binary run file for system equilibration"
)
grompp_pc(**paths["step9_gmx_grompp"],
properties=prop["step9_gmx_grompp"])
# step10_gmx_mdrun
global_log.info(
ensemble + " " + pdb_name +
" Step 10: gmx mdrun: Running system equilibration")
mdrun_pc(**paths["step10_gmx_mdrun"],
properties=prop["step10_gmx_mdrun"])
# step11_gmx_grompp
global_log.info(
ensemble + " " + pdb_name +
" Step 11: Creating portable binary run file for thermodynamic integration (ti)"
)
grompp_pc(**paths["step11_gmx_grompp"],
properties=prop["step11_gmx_grompp"])
# step12_gmx_mdrun
global_log.info(
ensemble + " " + pdb_name +
" Step 12: gmx mdrun: Running thermodynamic integration")
mdrun_dhdl_pc(**paths["step12_gmx_mdrun"],
properties=prop["step12_gmx_mdrun"])
if ensemble == "stateA":
dhdl_paths_listA.append(
paths["step12_gmx_mdrun"]["output_dhdl_path"])
elif ensemble == "stateB":
dhdl_paths_listB.append(
paths["step12_gmx_mdrun"]["output_dhdl_path"])
# Creating zip file containing all the dhdl files
dhdlA_path = os.path.join(
global_prop["step13_pmx_analyse"]['working_dir_path'], 'dhdlA.zip')
dhdlB_path = os.path.join(
global_prop["step13_pmx_analyse"]['working_dir_path'], 'dhdlB.zip')
for dhdl_file in dhdl_paths_listA:
compss_wait_on_file(dhdl_file)
for dhdl_file in dhdl_paths_listB:
compss_wait_on_file(dhdl_file)
fu.zip_list(dhdlA_path, dhdl_paths_listA)
fu.zip_list(dhdlB_path, dhdl_paths_listB)
# step13_pmx_analyse
global_log.info(
ensemble +
" Step 13: pmx analyse: Calculate free energies from fast growth thermodynamic integration simulations"
)
global_paths["step13_pmx_analyse"]["input_a_xvg_zip_path"] = dhdlA_path
global_paths["step13_pmx_analyse"]["input_b_xvg_zip_path"] = dhdlB_path
analyse_pc(**global_paths["step13_pmx_analyse"],
properties=global_prop["step13_pmx_analyse"])
elapsed_time = time.time() - start_time
global_log.info('')
global_log.info('')
global_log.info('Execution successful: ')
global_log.info(' Workflow_path: %s' % conf.get_working_dir_path())
global_log.info(' Config File: %s' % config)
global_log.info('')
global_log.info('Elapsed time: %.1f minutes' % (elapsed_time / 60))
global_log.info('')