def prepare_dataset(sdffile, dest=None, rename=True, conformations=False, overwrite=False):
""" This method bootstraps the analysis of Ames data.
- Rename the compounds
- Merge train/test
- Generate 3D conformations
- Save "master" and "saliviewer" tables
- Redirects stdout/stderr to a "prepare.log" file
"""
root, name = op.split(sdffile)
name = op.splitext(name)[0]
if not dest: dest = root
dest_sdf = op.join(dest, name + '-prepared.sdf')
master_table = op.join(dest, name + '-prepared-master.csv')
sali_table = op.join(dest, name + '-prepared-saliviewer.csv')
if op.exists(dest_sdf) and not overwrite:
print '%s is already there and not overwriting requested' % dest_sdf
else:
print 'Reading %s' % sdffile
mols = list(pybel.readfile('sdf', sdffile))
print '\tCreating dataset root: %s' % dest
if not op.exists(dest):
os.makedirs(dest)
if rename:
print '\tRenaming the compounds to keep track of the provenance'
rename_mols_by_index(mols, name + '-')
if conformations:
print '\tGenerating conformations'
for mol in mols:
if not any(name in mol.title for name in ('train-3988', 'train-4205', 'dsstox-4205', 'dsstox-4206')):
try:
print 'Conformation for %s' % mol.title
mol.make3D()
except Exception:
print 'Error computing a 3D conformation for %s' % mol.title
print '\tSaving compounds'
save_mols(mols, dest_sdf)
print '\tCreating \"master\" table: %s' % master_table
create_master_table(dest_sdf, master_table, fields=['Activity'])
print '\tCreating \"saliviewer\" table: %s' % sali_table
create_saliviewer_input(master_table, sali_table)
return dest_sdf, master_table
mols_dsstox = list(pybel.readfile('sdf', dsstox_original))
print 'Num molecules ames=%d, bursi=%d, dsstox=%d' % (len(mols_ames), len(mols_bursi), len(mols_dsstox))
#The activity is always stored in the same field
for mol in mols_bursi:
activity = '1' if mol.data['Ames test categorisation'] == 'mutagen' else '0'
mol.data['Activity'] = activity
mol.data['CAS_NO'] = mol.title
for mol in mols_dsstox:
mol.data['Activity'] = mol.data['Tox']
mol.data['CAS_NO'] = mol.data['CAS']
print '\tRenaming the compounds to keep track of the provenance'
rename_mols_by_index(mols_ames, 'ames-')
rename_mols_by_index(mols_bursi, 'bursi-')
rename_mols_by_index(mols_dsstox, 'dsstox-')
print '\tComputing and analyzing the union of the datasets'
cas_dupes = duplicates_by_field(mols_ames + mols_bursi + mols_dsstox)
#inchi_dupes = duplicates_by_format(mols_ames + mols_bursi + mols_dsstox,)
can_dupes = duplicates_by_format(mols_ames + mols_bursi + mols_dsstox, 'can')
#Quick and dirty retrieval of compounds for unit-tests
#Canonical smiles that are different due to
# - missing hydrogens (report)
# - bad perception of stereochemistry
# - charges
# - ...
can_dupes2 = {}
