def cs_load_spreadsheets(workingdir, groupdict):
phrasebooks = biodata.phrasebooks(workingdir + '/misc/phrasebooks.csv')
ezbeta_phrasebook = phrasebooks['dan_ezbeta']
load_spreadsheets(groupdict, workingdir + \
'/ez beta data',
['(.*)_DeltaBurial.csv$'],phrasebook = ezbeta_phrasebook,
attribute_name = 'ez_data')
def cs_load_spreadsheets(workingdir, groupdict):
phrasebooks = biodata.phrasebooks(workingdir + "/misc/phrasebooks.csv")
ezbeta_phrasebook = phrasebooks["dan_ezbeta"]
load_spreadsheets(
groupdict,
workingdir + "/ez beta data",
["(.*)_DeltaBurial.csv$"],
phrasebook=ezbeta_phrasebook,
attribute_name="ez_data",
)
return structure_dir + '/aligned_{}.pdb'.format(pdbid)
# Daniel's aligned structures give "invalid/missing occupancy" and
# "invalid/missing B factor" warnings - thousands of them! Have to filter
# warnings or the structures won't get loaded
with warnings.catch_warnings():
warnings.simplefilter('ignore')
for group in groupdict.values():
group.structure = PDBParser().get_structure(group.name,
filename(group.name))
print('structures loaded after ' + str(time.time() - start))
afterstructures = time.time()
# Open the asymmetric ezbeta spreadsheets used for retrieving DSSP results
# and the residue numbers of the residues included in the dataset
phrasebooks = biodata.phrasebooks('weights phrasebook.csv')
weights_phrasebook = phrasebooks['weights']
for group in groupdict.values():
csv_name = group.name.upper() + '.csv'
if csv_name in os.listdir('non ppi residues'):
group.non_ppi_data=biodata.Spreadsheet('non ppi residues/'\
+ csv_name,
phrasebook = weights_phrasebook)
if csv_name in os.listdir('ppi residues'):
group.ppi_data = biodata.Spreadsheet('ppi residues/'\
+csv_name,
phrasebook = weights_phrasebook)
print('loading spreadsheets took ' + str(time.time() - afterstructures))
# Instead of select_by_predicate, selections will be created by
