def test_construct_references(self):
# import argparse
from ample.util import config_util, argparse_util
options = config_util.AMPLEConfigOptions()
argso = argparse_util.process_command_line(args=['-mtz', 'foo', '-fasta', 'bar'])
options.populate(argso)
refMgr = reference_manager.ReferenceManager(options.d)
ref_references = '* Bibby et al. (2012). AMPLE: A cluster-and-truncate approach to solve the crystal structures of small proteins using rapidly computed ab initio models. Acta Crystallogr. Sect. D Biol. Crystallogr. 68(12), 1622-1631. [doi:10.1107/S0907444912039194]\n\n* Winn et al. (2011). Overview of the CCP4 suite and current developments. Acta Crystallographica Section D 67(4), 235-242. [doi:10.1107/S0907444910045749]\n\n* Thomas et al. (2015). Routine phasing of coiled-coil protein crystal structures with AMPLE. IUCrJ 2(2), 198-206. [doi:10.1107/S2052252515002080]\n\n* Simkovic et al. (2016). Residue contacts predicted by evolutionary covariance extend the application of ab initio molecular replacement to larger and more challenging protein folds. IUCrJ 3(4), 259-270. [doi:10.1107/S2052252516008113]\n\n* Bradley et al. (2005). Toward High-Resolution de Novo Structure Prediction for Small Proteins. Science 309(5742), 1868-1871. [doi:10.1126/science.1113801]\n\n* Grosse-Kunstleve et al. (2002). The Computational Crystallography Toolbox: crystallographic algorithms in a reusable software framework. Journal of Applied Crystallography 35(1), 126-136. [doi:10.1107/S0021889801017824]\n\n* Theobald et al. (2006). THESEUS: maximum likelihood superpositioning and analysis of macromolecular structures. Bioinformatics 22(17), 2171-2172. [doi:10.1093/bioinformatics/btl332]\n\n* Krissinel et al. (2012). Enhanced fold recognition using efficient short fragment clustering. Journal of molecular biochemistry 1(2), 76-85. [doi:]\n\n* Zhang et al. (2004). SPICKER: A clustering approach to identify near-native protein folds. Journal of Computational Chemistry 25(6), 865-871. [doi:10.1002/jcc.20011]\n\n* Keegan et al. (2018). Recent developments in MrBUMP: better search-model preparation, graphical interaction with search models, and solution improvement and assessment. Acta Crystallographica Section D 74(3), 167-182. [doi:10.1107/S2059798318003455]\n\n* Murshudov et al. (1997). Refinement of macromolecular structures by the maximum-likelihood method. Acta Crystallogr. Sect. D Biol. Crystallogr. 53(3), 240-255. [doi:10.1107/S0907444996012255]\n\n* Thorn et al. (2013). Extending molecular-replacement solutions with SHELXE. Acta Crystallogr. Sect. D Biol. Crystallogr. 69(11), 2251-2256. [doi:10.1107/S0907444913027534]\n\n* Cohen et al. (2008). ARP/wARP and molecular replacement: the next generation. Acta Crystallogr. Sect. D Biol. Crystallogr. 64(1), 49-60. [doi:10.1107/S0907444907047580]\n\n'
ref_references_windows = '* Bibby et al. (2012). AMPLE: A cluster-and-truncate approach to solve the crystal structures of small proteins using rapidly computed ab initio models. Acta Crystallogr. Sect. D Biol. Crystallogr. 68(12), 1622-1631. [doi:10.1107/S0907444912039194]\r\n\r\n* Winn et al. (2011). Overview of the CCP4 suite and current developments. Acta Crystallographica Section D 67(4), 235-242. [doi:10.1107/S0907444910045749]\r\n\r\n* Thomas et al. (2015). Routine phasing of coiled-coil protein crystal structures with AMPLE. IUCrJ 2(2), 198-206. [doi:10.1107/S2052252515002080]\r\n\r\n* Simkovic et al. (2016). Residue contacts predicted by evolutionary covariance extend the application of ab initio molecular replacement to larger and more challenging protein folds. IUCrJ 3(4), 259-270. [doi:10.1107/S2052252516008113]\r\n\r\n* Bradley et al. (2005). Toward High-Resolution de Novo Structure Prediction for Small Proteins. Science 309(5742), 1868-1871. [doi:10.1126/science.1113801]\r\n\r\n* Grosse-Kunstleve et al. (2002). The Computational Crystallography Toolbox: crystallographic algorithms in a reusable software framework. Journal of Applied Crystallography 35(1), 126-136. [doi:10.1107/S0021889801017824]\r\n\r\n* Theobald et al. (2006). THESEUS: maximum likelihood superpositioning and analysis of macromolecular structures. Bioinformatics 22(17), 2171-2172. [doi:10.1093/bioinformatics/btl332]\r\n\r\n* Krissinel et al. (2012). Enhanced fold recognition using efficient short fragment clustering. Journal of molecular biochemistry 1(2), 76-85. [doi:]\r\n\r\n* Zhang et al. (2004). SPICKER: A clustering approach to identify near-native protein folds. Journal of Computational Chemistry 25(6), 865-871. [doi:10.1002/jcc.20011]\r\n\r\n* Keegan et al. (2018). Recent developments in MrBUMP: better search-model preparation, graphical interaction with search models, and solution improvement and assessment. Acta Crystallographica Section D 74(3), 167-182. [doi:10.1107/S2059798318003455]\r\n\r\n* Murshudov et al. (1997). Refinement of macromolecular structures by the maximum-likelihood method. Acta Crystallogr. Sect. D Biol. Crystallogr. 53(3), 240-255. [doi:10.1107/S0907444996012255]\r\n\r\n* Thorn et al. (2013). Extending molecular-replacement solutions with SHELXE. Acta Crystallogr. Sect. D Biol. Crystallogr. 69(11), 2251-2256. [doi:10.1107/S0907444913027534]\r\n\r\n* Cohen et al. (2008). ARP/wARP and molecular replacement: the next generation. Acta Crystallogr. Sect. D Biol. Crystallogr. 64(1), 49-60. [doi:10.1107/S0907444907047580]\r\n\r\n'
# We may not run (e.g.) arpwarp, so need to be tolerant of missing citations.
if sys.platform.startswith("win"):
self.assertGreaterEqual(ref_references_windows.index(refMgr.citation_list_as_text), 0)
else:
self.assertGreaterEqual(ref_references.index(refMgr.citation_list_as_text), 0)
options.d['nmr_model_in'] = 'foo'
options.d['transmembrane'] = True
options.d['use_scwrl'] = True
options.d['do_mr'] = False
refMgr = reference_manager.ReferenceManager(options.d)
ref_references = '<h3>References</h3><ol><li> Bibby et al. (2012). AMPLE: A cluster-and-truncate approach to solve the crystal structures of small proteins using rapidly computed ab initio models. Acta Crystallogr. Sect. D Biol. Crystallogr. 68(12), 1622-1631. [doi:10.1107/S0907444912039194]</li><li> Winn et al. (2011). Overview of the CCP4 suite and current developments. Acta Crystallographica Section D 67(4), 235-242. [doi:10.1107/S0907444910045749]</li><li> Thomas et al. (2015). Routine phasing of coiled-coil protein crystal structures with AMPLE. IUCrJ 2(2), 198-206. [doi:10.1107/S2052252515002080]</li><li> Simkovic et al. (2016). Residue contacts predicted by evolutionary covariance extend the application of ab initio molecular replacement to larger and more challenging protein folds. IUCrJ 3(4), 259-270. [doi:10.1107/S2052252516008113]</li><li> Bradley et al. (2005). Toward High-Resolution de Novo Structure Prediction for Small Proteins. Science 309(5742), 1868-1871. [doi:10.1126/science.1113801]</li><li> Bibby et al. (2013). Application of the AMPLE cluster-and-truncate approach to NMR structures for molecular replacement. Acta Crystallogr. Sect. D Biol. Crystallogr. 69(11), 2194-2201. [doi:10.1107/S0907444913018453]</li><li> Thomas et al. (2017). Approaches to ab initio molecular replacement of alpha-helical transmembrane proteins. Acta Crystallographica Section D 73(12), 985-996. [doi:10.1107/S2059798317016436]</li><li> Grosse-Kunstleve et al. (2002). The Computational Crystallography Toolbox: crystallographic algorithms in a reusable software framework. Journal of Applied Crystallography 35(1), 126-136. [doi:10.1107/S0021889801017824]</li><li> Theobald et al. (2006). THESEUS: maximum likelihood superpositioning and analysis of macromolecular structures. Bioinformatics 22(17), 2171-2172. [doi:10.1093/bioinformatics/btl332]</li><li> Krissinel et al. (2012). Enhanced fold recognition using efficient short fragment clustering. Journal of molecular biochemistry 1(2), 76-85. [doi:]</li><li> Krivov et al. (2009). Improved prediction of protein side-chain conformations with SCWRL4. Proteins: Struct., Funct., Bioinf. 77(4), 778-795. [doi:10.1002/prot.22488]</li></ol>'
self.assertEqual(refMgr.citations_as_html, ref_references)
def create_citation_tab(self, ample_dict):
if self.citation_tab_id:
return
self.citation_tab_id = "citation_tab"
pyrvapi.rvapi_insert_tab(self.citation_tab_id, "Citation",
self.log_tab_id, False)
refMgr = reference_manager.ReferenceManager(ample_dict)
bibtex_file = refMgr.save_citations_to_file(ample_dict)
if self.ccp4i2:
# The horror of ccp4i2 means that this all gets dumped into xml so we can't use any markup tags
tdata = refMgr.citations_as_text
else:
tdata = refMgr.methods_as_html
tdata += refMgr.citations_as_html
tdata += '<hr><p>A bibtex file with the relevant citations has been saved to: {}</p>'.format(
bibtex_file)
pyrvapi.rvapi_add_text(tdata, self.citation_tab_id, 0, 0, 1, 1)
if not self.ccp4i2:
pyrvapi.rvapi_add_data(
"bibtex_file",
"Citations as BIBTEX",
self.fix_path(bibtex_file),
"text",
self.citation_tab_id,
2,
0,
1,
1,
True,
)
return self.citation_tab_id
def main(self, args=None):
"""Main AMPLE routine.
We require this as the multiprocessing module (only on **!!*%$$!! Windoze)
requires that the main module can be imported. We there need ample to be
a python script that can be imported, hence the main routine with its
calling protected by the if __name__=="__main__":...
args is an option argument that can contain the command-line arguments
for the program - required for testing.
"""
argso = argparse_util.process_command_line(args=args)
self.amopt = amopt = config_util.AMPLEConfigOptions()
amopt.populate(argso)
# Setup things like logging, file structure, etc...
amopt.d = self.setup(amopt.d)
rosetta_modeller = options_processor.process_rosetta_options(amopt.d)
# Display the parameters used
logger.debug(amopt.prettify_parameters())
amopt.write_config_file()
#######################################################
# SCRIPT PROPER STARTS HERE
time_start = time.time()
# Create function for monitoring jobs - static function decorator?
if self.ample_output:
def monitor():
return self.ample_output.display_results(amopt.d)
else:
monitor = None
if amopt.d['benchmark_mode'] and amopt.d['native_pdb']:
# Process the native before we do anything else
benchmark_util.analysePdb(amopt.d)
# Create constituent models from an NMR ensemble
if amopt.d['nmr_model_in']:
nmr_mdir = os.path.join(amopt.d['work_dir'], 'nmr_models')
amopt.d['modelling_workdir'] = nmr_mdir
logger.info(
'Splitting NMR ensemble into constituent models in directory: {0}'
.format(nmr_mdir))
amopt.d['models'] = pdb_edit.split_pdb(amopt.d['nmr_model_in'],
directory=nmr_mdir,
strip_hetatm=True,
same_size=True)
logger.info('NMR ensemble contained {0} models'.format(
len(amopt.d['models'])))
# Modelling business happens here
self.modelling(amopt.d, rosetta_modeller)
amopt.write_config_file()
# Ensembling business next
if amopt.d['make_ensembles']:
self.ensembling(amopt.d)
amopt.write_config_file()
# Some MR here
if amopt.d['do_mr']:
self.molecular_replacement(amopt.d)
amopt.write_config_file()
# Timing data
time_stop = time.time()
elapsed_time = time_stop - time_start
run_in_min = elapsed_time / 60
run_in_hours = run_in_min / 60
msg = os.linesep + \
'All processing completed (in {0:6.2F} hours)'.format(
run_in_hours) + os.linesep
msg += '----------------------------------------' + os.linesep
logging.info(msg)
# Benchmark mode
if amopt.d['benchmark_mode']:
self.benchmarking(amopt.d)
amopt.write_config_file()
amopt.write_config_file()
# Flag to show that we reached the end without error - useful for integration testing
amopt.d['AMPLE_finished'] = True
ample_util.save_amoptd(amopt.d)
logger.info("AMPLE finished at: %s",
time.strftime("%a, %d %b %Y %H:%M:%S", time.gmtime()))
ref_mgr = reference_manager.ReferenceManager(amopt.d)
ref_mgr.save_citations_to_file(amopt.d)
logger.info(ref_mgr.citations_as_text)
logger.info(reference_manager.footer)
# Finally update pyrvapi results
if self.ample_output:
self.ample_output.display_results(amopt.d)
self.ample_output.rvapi_shutdown(amopt.d)
self.cleanup(amopt.d)
return
def main(self, args=None):
"""Main AMPLE routine.
We require this as the multiprocessing module (only on **!!*%$$!! Windoze)
requires that the main module can be imported. We there need ample to be
a python script that can be imported, hence the main routine with its
calling protected by the if __name__=="__main__":...
args is an option argument that can contain the command-line arguments
for the program - required for testing.
"""
argso = argparse_util.process_command_line(args=args)
# Work directory and loggers need to be setup before we do anything else
self.setup_workdir(argso)
global logger
logger = logging_util.setup_logging(argso)
# Logging and work directories in place so can start work
self.amopt = amopt = config_util.AMPLEConfigOptions()
amopt.populate(argso)
amopt.d = self.setup(amopt.d)
rosetta_modeller = options_processor.process_rosetta_options(amopt.d)
logger.debug(
amopt.prettify_parameters()) # Display the parameters used
amopt.write_config_file()
time_start = time.time()
if self.ample_output:
def monitor():
return self.ample_output.display_results(amopt.d)
else:
monitor = None
# Highlight deprecated command line arguments
if amopt.d['submit_cluster']:
message = "-%s has been deprecated and will be removed in version %s!" % (
'submit_cluster', 1.6)
warnings.warn(message, DeprecationWarning)
if amopt.d["submit_pe_lsf"]:
message = "-%s has been deprecated and will be removed in version %s! Use -submit_pe instead" % (
'submit_pe_lsf', 1.6)
warnings.warn(message, DeprecationWarning)
if amopt.d["submit_pe_sge"]:
message = "-%s has been deprecated and will be removed in version %s! Use -submit_pe instead" % (
'submit_pe_sge', 1.6)
warnings.warn(message, DeprecationWarning)
# Process any files we may have been given
model_results = process_models.extract_and_validate_models(amopt.d)
if model_results:
process_models.handle_model_import(amopt.d, model_results)
if amopt.d['benchmark_mode'] and amopt.d['native_pdb']:
# Process the native before we do anything else
benchmark_util.analysePdb(amopt.d)
# Create constituent models from an NMR ensemble
if amopt.d['nmr_model_in']:
nmr_mdir = os.path.join(amopt.d['work_dir'], 'nmr_models')
amopt.d['modelling_workdir'] = nmr_mdir
logger.info(
'Splitting NMR ensemble into constituent models in directory: {0}'
.format(nmr_mdir))
amopt.d['processed_models'] = pdb_edit.split_pdb(
amopt.d['nmr_model_in'],
directory=nmr_mdir,
strip_hetatm=True,
same_size=True)
logger.info('NMR ensemble contained {0} models'.format(
len(amopt.d['processed_models'])))
# Modelling business happens here
if self.modelling_required(amopt.d):
self.modelling(amopt.d, rosetta_modeller)
ample_util.save_amoptd(amopt.d)
amopt.write_config_file()
# Ensembling business next
if amopt.d['make_ensembles']:
self.ensembling(amopt.d)
amopt.write_config_file()
# Some MR here
if amopt.d['do_mr']:
self.molecular_replacement(amopt.d)
amopt.write_config_file()
# Timing data
time_stop = time.time()
elapsed_time = time_stop - time_start
run_in_min = elapsed_time / 60
run_in_hours = run_in_min / 60
msg = os.linesep + 'All processing completed (in {0:6.2F} hours)'.format(
run_in_hours) + os.linesep
msg += '----------------------------------------' + os.linesep
logging.info(msg)
# Benchmark mode
if amopt.d['benchmark_mode']:
self.benchmarking(amopt.d)
amopt.write_config_file()
amopt.write_config_file()
# Flag to show that we reached the end without error - useful for integration testing
amopt.d['AMPLE_finished'] = True
ample_util.save_amoptd(amopt.d)
logger.info("AMPLE finished at: %s",
time.strftime("%a, %d %b %Y %H:%M:%S", time.gmtime()))
ref_mgr = reference_manager.ReferenceManager(amopt.d)
ref_mgr.save_citations_to_file(amopt.d)
logger.info(ref_mgr.citations_as_text)
logger.info(reference_manager.footer)
# Finally update pyrvapi results
if self.ample_output:
self.ample_output.display_results(amopt.d)
self.ample_output.rvapi_shutdown(amopt.d)
self.cleanup(amopt.d)
return