def test_read_sdf(self):
compounds = compound_parsing.read_sdf('test_compounds.sdf',
inchi_path='../data/Inchikey_IDs.json',
mol2_file_dir=os.path.join(self.scratch, 'mol2_files'),
callback_url=os.environ['SDK_CALLBACK_URL'])
self.assertEqual(len(compounds), 10)
self.assertCountEqual(compounds[0].keys(), comp_keys - {'deltagerr', 'deltag'})
assert len(compounds[0]['fingerprints']) == 2
assert 'mol' in compounds[0]
def compound_set_from_file(self, ctx, params):
"""
CompoundSetFromFile
string staging_file_path
:param params: instance of type "compoundset_upload_params" ->
structure: parameter "workspace_name" of String, parameter
"staging_file_path" of String, parameter "compound_set_name" of
String
:returns: instance of type "compoundset_upload_results" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "compoundset_ref" of type "obj_ref"
"""
# ctx is the context object
# return variables are: output
#BEGIN compound_set_from_file
self._check_required_param(params, ['workspace_name',
'staging_file_path',
'compound_set_name'])
scratch_file_path = self.dfu.download_staging_file(
{'staging_file_subdir_path': params['staging_file_path']}
).get('copy_file_path')
# I probably should be uploading the raw files to shock
ext = os.path.splitext(scratch_file_path)[1]
file_name = os.path.basename(scratch_file_path)
if ext == '.sdf':
compounds = parse.read_sdf(scratch_file_path)
elif ext == '.tsv':
compounds = parse.read_tsv(scratch_file_path)
else:
raise ValueError('Invalid input file type. Expects .tsv or .sdf')
compoundset = {
'id': params['compound_set_name'],
'name': params['compound_set_name'],
'description': 'Compound Set produced from %s' % file_name,
'compounds': compounds,
}
output = self._save_to_ws_and_report(ctx, 'compound_set_from_file',
params['workspace_name'],
params['staging_file_path'],
compoundset)
#END compound_set_from_file
# At some point might do deeper type checking...
if not isinstance(output, dict):
raise ValueError('Method compound_set_from_file return value ' +
'output is not type dict as required.')
# return the results
return [output]
def compound_set_from_file(self, ctx, params):
"""
CompoundSetFromFile
string staging_file_path
:param params: instance of type "compoundset_upload_params" ->
structure: parameter "workspace_id" of String, parameter
"staging_file_path" of String, parameter "compound_set_name" of
String, parameter "mol2_staging_file_path" of String
:returns: instance of type "compoundset_upload_results" -> structure:
parameter "report_name" of String, parameter "report_ref" of
String, parameter "compoundset_ref" of type "obj_ref"
"""
# ctx is the context object
# return variables are: output
#BEGIN compound_set_from_file
self._check_param(
params, ['workspace_id', 'staging_file_path', 'compound_set_name'],
opt_param=['mol2_staging_file_path'])
scratch_file_path = self.dfu.download_staging_file({
'staging_file_subdir_path':
params['staging_file_path']
}).get('copy_file_path')
# I probably should be uploading the raw files to shock
mol2_staging_file_path = params.get('mol2_staging_file_path')
mol2_file_dir = None
if mol2_staging_file_path:
mol2_scratch_file_path = self.dfu.download_staging_file({
'staging_file_subdir_path':
mol2_staging_file_path
}).get('copy_file_path')
try:
logging.info("start unpacking mol2 file")
mol2_file_path_out = self.dfu.unpack_file(
{'file_path': mol2_scratch_file_path})['file_path']
mol2_file_dir = os.path.dirname(mol2_file_path_out)
except Exception:
raise ValueError('Cannot unpack mol2 file: {}'.format(
os.path.basename(mol2_file_path_out)))
ext = os.path.splitext(scratch_file_path)[1]
file_name = os.path.basename(scratch_file_path)
if ext == '.sdf':
compounds = parse.read_sdf(scratch_file_path,
mol2_file_dir=mol2_file_dir,
callback_url=self.callback_url)
elif ext == '.tsv':
compounds = parse.read_tsv(scratch_file_path,
mol2_file_dir=mol2_file_dir,
callback_url=self.callback_url)
else:
raise ValueError('Invalid input file type. Expects .tsv or .sdf')
compoundset = {
'id': params['compound_set_name'],
'name': params['compound_set_name'],
'description': 'Compound Set produced from %s' % file_name,
'compounds': compounds,
}
output = self._save_to_ws_and_report(params['workspace_id'],
params['staging_file_path'],
compoundset)
#END compound_set_from_file
# At some point might do deeper type checking...
if not isinstance(output, dict):
raise ValueError('Method compound_set_from_file return value ' +
'output is not type dict as required.')
# return the results
return [output]
def test_read_sdf():
compounds = compound_parsing.read_sdf('test_compounds.sdf')
assert len(compounds) == 10
assert not set(compounds[0].keys()) ^ (comp_keys - {'deltagerr', 'deltag'})
assert len(compounds[0]['fingerprints']) == 2