def load_centers(iterable):
dict_ = CIDict()
for row in iterable:
if row[0] != '':
dict_.update({row[0]:row[1]})
for key, value in dict_.items():
# Turns '(1,2,3)' etc, that is, textual representations of vectors,
# into Vector objects. Will cut off the last digit of the third
# componant, but I don't care because the third componant will
# always be 0.0
dict_[key] = np.array([float(y[:-1]) for y in value[1:].split()])
return dict_
def __init__(self, iterable, normalize = False):
self.normalize = normalize
self.ref = CIDict()
colmap = CIDict()
for column, letter in enumerate(iterable.next()):
if letter != '':
self.ref.update({letter: dict()})
colmap.update({letter: column})
curvetypes = iterable.next()
for letter, column in colmap.items():
self.ref[letter].update({'curve': curvetypes[column]})
for parameter in [{'sigmoidal': 'e0', 'gaussian': 'emin'},
{'sigmoidal': 'zmid', 'gaussian': 'zmin'},
{'sigmoidal': 'n', 'gaussian': 'sigma'}]:
paramrow = iterable.next()
for letter in self.ref.keys():
curvetype = self.ref[letter]['curve']
self.ref[letter].update({parameter[curvetype]: \
float(paramrow[colmap[letter]])})
from sundries import CIDict
from sundries import one_letter
from Bio.PDB import PDBParser
import warnings
import csv
# Retrieve the sequences from the BBTMOUT alignment, including -'s for gaps
bbtm_align= list(AlignIO.read('Swiss-PDB structural alignment.aln',
'clustal'))
# Assuming the first is 1A0S, the second is 1AF6:
sequences = CIDict((('1A0S',str(bbtm_align[0].seq)),
('1AF6',str(bbtm_align[1].seq))))
# Check that I'm right about the first being 1AF6, the second being 1A0S
firstfive_of = CIDict()
for pdbid, sequence in sequences.items():
firstfive_of.update({pdbid: ''})
for letter in sequence:
if letter != '-':
firstfive_of[pdbid] += letter
if len(firstfive_of[pdbid]) == 5:
break
assertion_error_message = 'wrong aligned sequences in sequences dictionary'
assertion_error_message += ": 1a0s's first five are {},"\
.format(firstfive_of['1a0s'])\
+" and 1af6's first five are {}"\
.format(firstfive_of['1af6'])
assert firstfive_of['1a0s'] == 'SGFEF' \
and firstfive_of['1af6'] == 'VDFHG',\
for filename in weight_file_paths]
# weights maps pdbids to spreadsheets
weights = CIDict()
for spreadsheet in spreadsheets:
pdbid_list = spreadsheet.get_column('pdbid')
pdbid_filtered = filter(lambda x: x != '', pdbid_list)
pdbid_set = set(pdbid_filtered)
# I expect there to only be one pdbid
assert len(pdbid_set) == 1, 'more than 1 pdbid in one spreadsheet'
pdbid = list(pdbid_set)[0]
weights.update({pdbid: spreadsheet})
# selections maps pdbids to sets of resis
selections = CIDict()
for pdbid, spreadsheet in weights.items():
def not_blank(string):
return string != ''
resis = filter(not_blank, spreadsheet.get_column('resi'))
selections.update({pdbid: set(resis)})
# A new global variable for looping over these proteins
asymmetric_dataset = CIDict([(pdbid, groupdict[pdbid]) \
for pdbid in weights.keys()])
# Make the spreadsheets available through groupdict
for pdbid, group in asymmetric_dataset.items():
group.non_ppi = weights[pdbid]
# Make selection