def data_from_sdf(sdf_file_path):
mol_dict = {}
row_id_list = []
row_id_dict = {}
col_id_list = []
col_id_dict = {}
# first pass, load the identifiers, MOL files, and tag names
col = 0
sdf = SDF(sdf_file_path)
while 1:
rec = sdf.read()
if not rec:
break
mol = rec.get('MOL')
# get the unique identifier
mol_id = mol[0].strip()
# store the MOL record
mol_dict[mol_id] = ''.join(mol)
# add row (assuming mol_id is unique)
row_id_list.append(mol_id)
row_id_dict[mol_id] = None
# add column (if new)
for key in rec.kees:
if key != 'MOL':
if key not in col_id_dict:
col_id_list.append(key)
col_id_dict[key] = None
# second pass, read the actual data into the table structure
content = {}
sdf = SDF(sdf_file_path)
while 1:
rec = sdf.read()
if not rec:
break
mol_id = rec.get('MOL')[0].strip()
for key in rec.kees:
if key != 'MOL':
content[ (mol_id,key) ] = rec.get(key)[0].strip()
return {
'content' : content,
'row_id_list' : row_id_list,
'col_id_list' : col_id_list,
'mol_dict' : mol_dict
}
def data_from_sdf(sdf_file_path):
mol_dict = {}
row_id_list = []
row_id_dict = {}
col_id_list = []
col_id_dict = {}
# first pass, load the identifiers, MOL files, and tag names
col = 0
sdf = SDF(sdf_file_path)
while 1:
rec = sdf.read()
if not rec:
break
mol = rec.get('MOL')
# get the unique identifier
mol_id = mol[0].strip()
# store the MOL record
mol_dict[mol_id] = ''.join(mol)
# add row (assuming mol_id is unique)
row_id_list.append(mol_id)
row_id_dict[mol_id] = None
# add column (if new)
for key in rec.kees:
if key != 'MOL':
if key not in col_id_dict:
col_id_list.append(key)
col_id_dict[key] = None
# second pass, read the actual data into the table structure
content = {}
sdf = SDF(sdf_file_path)
while 1:
rec = sdf.read()
if not rec:
break
mol_id = rec.get('MOL')[0].strip()
for key in rec.kees:
if key != 'MOL':
content[(mol_id, key)] = rec.get(key)[0].strip()
return {
'content': content,
'row_id_list': row_id_list,
'col_id_list': col_id_list,
'mol_dict': mol_dict
}
def load_annotated_sdf(filename, object=None, state=1, discrete=1, _self=cmd):
pymol = _self._pymol
cmd = _self
# get object name from file prefix
if object == None:
object = re.sub(r"\.[sS][dD][fF]$", "", filename)
# open the SD file
inp_sdf = SDF(filename)
# create a persistent place to store the annotations
if not hasattr(pymol.session, 'annotation'):
pymol.session.annotation = {}
# create a state-indexed dictionary for this object
state_dict = {}
pymol.session.annotation[object] = state_dict
while 1:
# get next record
sdf_rec = inp_sdf.read()
# if at end of list, break out of loop
if not sdf_rec: break
# get the MOL portion of the record
mol_list = sdf_rec.get('MOL')
# load it into PyMOL
cmd.read_molstr(string.join(mol_list, ''),
object,
state,
finish=0,
discrete=discrete)
# populate with tuple containing ordered list of keys
# and associated data dictionary
anno_list = ["\\955" + object]
for key in sdf_rec.kees:
if (key != 'MOL'):
data = sdf_rec.data[key]
print key, data
anno_list.append(
" \\595%s: \\559%s" %
(key, string.join(map(string.strip, sdf_rec.data[key]))))
state_dict[state] = anno_list
# increment the state index
state = state + 1
if state > 1:
cmd.zoom(object)
cmd.finish_object(object)
def load_annotated_sdf(filename, object=None, state=1, discrete=1, _self=cmd):
pymol=_self._pymol
cmd=_self
# get object name from file prefix
if object==None:
object = re.sub(r"\.[sS][dD][fF]$","",filename)
# open the SD file
inp_sdf = SDF(filename)
# create a persistent place to store the annotations
if not hasattr(pymol.session,'annotation'):
pymol.session.annotation = {}
# create a state-indexed dictionary for this object
state_dict = {}
pymol.session.annotation[object] = state_dict
while 1:
# get next record
sdf_rec = inp_sdf.read()
# if at end of list, break out of loop
if not sdf_rec: break
# get the MOL portion of the record
mol_list = sdf_rec.get('MOL')
# load it into PyMOL
cmd.read_molstr(''.join(mol_list),object,
state,finish=0,discrete=discrete)
# populate with tuple containing ordered list of keys
# and associated data dictionary
anno_list = [ "\\955"+object ]
for key in sdf_rec.kees:
if (key!='MOL'):
data = sdf_rec.data[key]
print(key,data)
anno_list.append(" \\595%s: \\559%s"%(
key,
' '.join(map(str.strip, sdf_rec.data[key]))))
state_dict[state] = anno_list
# increment the state index
state = state + 1
if state > 1:
cmd.zoom(object)
cmd.finish_object(object)
