def name_filter(sum_dict, align_dict, name_list):
"""Accepts a list of names. Returns a new Summary block and Alignment block which
contain the info only for those names passed."""
new_sum_dict = FSSP.FSSPSumDict()
new_align_dict = copy.deepcopy(align_dict)
for cur_pdb_name in name_list:
for prot_num in sum_dict:
if sum_dict[prot_num].pdb2 + sum_dict[prot_num].chain2 == cur_pdb_name:
new_sum_dict[prot_num] = sum_dict[prot_num]
prot_numbers = sorted(new_sum_dict)
for pos_num in new_align_dict.abs_res_dict:
new_align_dict.abs(pos_num).pos_align_dict = {}
for prot_num in prot_numbers:
new_align_dict.abs(pos_num).pos_align_dict[prot_num] = \
align_dict.abs(pos_num).pos_align_dict[prot_num]
return new_sum_dict, new_align_dict
def filter(sum_dict, align_dict, filter_attribute, low_bound, high_bound):
"""Filter a passed summary section and alignment section.
Filter according to a numeric attribute in the summary section.
Return new summary and alignment sections.
"""
new_sum_dict = FSSP.FSSPSumDict()
new_align_dict = copy.deepcopy(align_dict)
for prot_num in sum_dict:
attr_value = getattr(sum_dict[prot_num], filter_attribute)
if attr_value >= low_bound and attr_value <= high_bound:
new_sum_dict[prot_num] = sum_dict[prot_num]
prot_numbers = sorted(new_sum_dict)
for pos_num in new_align_dict.abs_res_dict:
new_align_dict.abs(pos_num).pos_align_dict = {}
for prot_num in prot_numbers:
new_align_dict.abs(pos_num).pos_align_dict[
prot_num] = align_dict.abs(pos_num).pos_align_dict[prot_num]
return new_sum_dict, new_align_dict
def filter(sum_dict, align_dict, filter_attribute, low_bound, high_bound):
"""filters a passed summary section and alignment section according to a numeric
attribute in the summary section. Returns new summary and alignment sections"""
new_sum_dict = FSSP.FSSPSumDict()
new_align_dict = copy.deepcopy(align_dict)
# for i in align_dict:
# new_align_dict[i] = copy.copy(align_dict[i])
# new_align_dict = copy.copy(align_dict)
for prot_num in sum_dict:
attr_value = getattr(sum_dict[prot_num], filter_attribute)
if attr_value >= low_bound and attr_value <= high_bound:
new_sum_dict[prot_num] = sum_dict[prot_num]
prot_numbers = new_sum_dict.keys()
prot_numbers.sort()
for pos_num in new_align_dict.abs_res_dict:
new_align_dict.abs(pos_num).pos_align_dict = {}
for prot_num in prot_numbers:
new_align_dict.abs(pos_num).pos_align_dict[prot_num] = \
align_dict.abs(pos_num).pos_align_dict[prot_num]
return new_sum_dict, new_align_dict
# Copyright 2001 by Iddo Friedberg. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
from Bio import FSSP
from Bio.FSSP import FSSPTools
import sys
import os
# import pickle
test_file = os.path.join('FSSP', '1cnv.fssp')
f = sys.stdout
f.write("\nRead in %s\n" % os.path.basename(test_file))
handle = open(test_file)
head_rec, sum_rec, align_rec = FSSP.read_fssp(handle)
handle.close()
f.write("...1cnv.fssp read\n")
for i in [
"author", "compnd", "database", "header", "nalign", "pdbid",
"seqlength", "source"
]:
f.write('head_rec.%s %s\n' % (i, str(getattr(head_rec, i))))
f.write("\nlen(sum_rec) = %d; head_rec.nalign = %d\n" %
(len(sum_rec), head_rec.nalign))
f.write("The above two numbers should be the same\n")
f.write("\nCreate a multiple alignment instance using Bio.Align\n")
alignment = FSSPTools.mult_align(sum_rec, align_rec)
f.write("...Done\n")
# Percent ID filtering takes too long.. remove from test.
def setUpClass(cls):
path = os.path.join("FSSP", "1cnv.fssp")
handle = open(path)
cls.head_rec, cls.sum_rec, cls.align_rec = FSSP.read_fssp(handle)
handle.close()
from Bio import FSSP, Align
from Bio.FSSP import FSSPTools
import sys
import os
import cPickle
import time
test_file = os.path.join('FSSP', '1cnv.fssp')
f = sys.stdout
f.write("\nRead in %s\n" % os.path.basename(test_file))
handle = open(test_file)
head_rec, sum_rec, align_rec = FSSP.read_fssp(handle)
handle.close()
f.write("...1cnv.fssp read\n")
for i in ["author", "compnd", "database", "header", "nalign",
"pdbid", "seqlength", "source"]:
f.write('head_rec.%s %s\n' % (i, str(getattr(head_rec,i))))
f.write("\nlen(sum_rec) = %d; head_rec.nalign = %d\n" %
(len(sum_rec), head_rec.nalign))
f.write("The above two numbers should be the same\n")
f.write("\nCreate a multiple alignment instance using Bio.Align\n")
alignment = FSSPTools.mult_align(sum_rec, align_rec)
f.write("...Done\n")
# Percent ID filtering takes too long.. remove from test.
# f.write("\nFilter in percent ID's >= 15%\n")
# sum_ge_15, align_ge_15 = FSSPTools.filter(sum_rec, align_rec, 'pID', 15,100)
# f.write("\nnumber of records filtered in: %d\n" % len(sum_ge_15))
# k = sum_ge_15.keys()
# k.sort()
def setUpClass(cls):
path = os.path.join("FSSP", "1cnv.fssp")
with open(path) as handle:
cls.head_rec, cls.sum_rec, cls.align_rec = FSSP.read_fssp(handle)
from Bio import FSSP, Align
from Bio.FSSP import FSSPTools
import sys
import os
import cPickle
import time
test_file = os.path.join('FSSP', '1cnv.fssp')
f = sys.stdout
f.write("\nRead in %s\n" % os.path.basename(test_file))
head_rec, sum_rec, align_rec = FSSP.read_fssp(open(test_file))
f.write("...1cnv.fssp read\n")
for i in ["author", "compnd", "database", "header", "nalign",
"pdbid", "seqlength", "source"]:
f.write('head_rec.%s %s\n' % (i, str(getattr(head_rec,i))))
f.write("\nlen(sum_rec) = %d; head_rec.nalign = %d\n" %
(len(sum_rec), head_rec.nalign))
f.write("The above two numbers should be the same\n")
f.write("\nCreate a multiple alignment instance using Bio.Align\n")
alignment = FSSPTools.mult_align(sum_rec, align_rec)
f.write("...Done\n")
# Percent ID filtering takes too long.. remove from test.
# f.write("\nFilter in percent ID's >= 15%\n")
# sum_ge_15, align_ge_15 = FSSPTools.filter(sum_rec, align_rec, 'pID', 15,100)
# f.write("\nnumber of records filtered in: %d\n" % len(sum_ge_15))
# k = sum_ge_15.keys()
# k.sort()
# f.write("\nRecords filtered in %s\n" % k)
# Pickling takes too long.. remove from test.
