def test_annotateDownloadedfile():
structure_name = '2lbk'
file_format = 'pdb'
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
models = inputParser.annotate_basepairs(file)
assert len(models) == 8
def test_pdbListDownloadWithFormat():
structure_name = '2LBK'
file_format = 'pdb'
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
assert structure_name.lower() in file
assert file_format in file
with open(file) as f:
assert structure_name in f.readline()
def test_properStrandRead():
structure_name = '1ehz'
file_format = 'pdb'
desired_output = list(
'gCGGAUUUAgCUCAGuuGGGAGAGCgCCAGAcUgAAgAucUGGAGgUCcUGUGuuCGaUCCACAGAAUUCGCACCA'
.upper())
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
strand = inputParser.read_models_from_pdb_file(file)[0]
assert desired_output == strand['A']
def test_strandLensToughModel():
structure_name = '1ehz'
file_format = 'pdb'
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
models = inputParser.read_models_from_pdb_file(file)
assert 1 == len(models[0].keys())
assert 'G' == models[0]['A'][0]
assert 'G' == models[0]['A'][9]
for model in models:
assert len(model['A']) == 76
def test_strandTwoChains():
structure_name = '2z74'
file_format = 'pdb'
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
models = inputParser.read_models_from_pdb_file(file)
assert len(models[0].keys()) == 2
assert models[0]['A'][0] == 'A'
assert models[0]['A'][-1] == 'U'
assert models[0]['B'][0] == 'G'
assert models[0]['B'][-1] == 'A'
def test_strandLensMultipleModels():
structure_name = '2lbk'
file_format = 'pdb'
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
models = inputParser.read_models_from_pdb_file(file)
assert len(models) == 8
assert models[0]['A'][0] == 'G'
assert models[0]['A'][-1] == 'C'
for model in models:
assert len(model['A']) == 17
def test_build_dot_notation_canonical_only_one_layer():
structure_name = '2lbk'
file_format = 'pdb'
desired_output = ".(((((.....)))))."
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
models = inputParser.read_models_from_pdb_file(file)
text_strand = inputParser.build_txt_strand_from_chains(models[0])
base_pairs = inputParser.annotate_basepairs(file)
dot_notation = inputParser.make_dot_notation(text_strand, base_pairs[0])
assert desired_output == dot_notation
def test_fix_base_pairs_two_strand_model():
structure_name = '3g78'
file_format = 'pdb'
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
models = inputParser.read_complete_models(file)
base_pairs = inputParser.annotate_basepairs(file)[0]
fixed_base_pairs = inputParser.fix_base_pairs(models[0], base_pairs)
pair_with_z_strand = [
pair for pair in fixed_base_pairs if pair[1].strand == 'Z'
]
assert pair_with_z_strand[0][1].position == 418
def test_get_missing_residues_from_strandA_3G78():
structure_name = '3g78'
file_format = 'pdb'
desired_count = '-.{[.(.(((<..(((((((((((...(((.......)))..(((((...{{{.{{{...\
)))))..(((...(((..((((.((((((....))))))))))...]>..)))...))).\
..(((((((((((.(.....)...((((.......(......(...((((((..((((..\
[[[[[.))))...)))).}}}.}}}...))...)......)....)))))))))...)))\
)))...)))))))))))...}))).)(...((((....))))...).......(((.(..\
..((..........))...))))....(.(((..(((......)))...))).).(((.(\
((((((((....)))..)))))).)))...----------------------'.count('-')
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
missing_residues = inputParser.get_missing_residues_from_pdb(file)
assert desired_count == len(missing_residues)
def test_properLongStrandRead():
structure_name = '3g78'
file_format = 'pdb'
desired_output = list(
"uGUGCCCGGCAUGGGUGCAGUCUAUAGGGUGAGAGUCCCGAACUGUGAAGGCAGAAGUA\
ACAGUUAGCCUAACGCAAGGGUGUCCGUGGCGACAUGGAAUCUGAAGGAAGCGGACGGCA\
AACCUUCGGUCUGAGGAACACGAACUUCAUAUGAGGCUAGGUAUCAAUGGAUGAGUUUGC\
AUAACAAAACAAAGUCCUUUCUGCCAAAGUUGGUACAGAGUAAAUGAAGCAGAUUGAUGA\
AGGGAAAGACUGCAUUCUUACCCGGGGAGGUCUGGAAACAGAAGUCAGCAGAAGUCAUAG\
UACCCUGUUCGCAGGGGAAGGACGGAACAAGUAUGGCGUUCGCGCCUAAGCUUGAACCGC\
CGUAUACCGAACGGUACGUACGGUGGUGUG".upper())
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
models = inputParser.read_models_from_pdb_file(file)
assert desired_output == models[0]['A']
def test_build_dot_notation_canonical_huge_structure():
structure_name = '3g78'
file_format = 'pdb'
desired_count = '-.{[.(.(((<..(((((((((((...(((.......)))..(((((...{{{.{{{...\
)))))..(((...(((..((((.((((((....))))))))))...]>..)))...))).\
..(((((((((((.(.....)...((((.......(......(...((((((..((((..\
[[[[[.))))...)))).}}}.}}}...))...)......)....)))))))))...)))\
)))...)))))))))))...}))).)(...((((....))))...).......(((.(..\
..((..........))...))))....(.(((..(((......)))...))).).(((.(\
((((((((....)))..)))))).)))...----------------------.]]]]]...'.count('.')
file = inputParser.online_input(structure_name=structure_name,
file_format=file_format)
models = inputParser.read_complete_models(file)
text_strand = inputParser.build_txt_strand_from_chains(models[0])
base_pairs = inputParser.annotate_basepairs(file)
fixed_base_pairs = inputParser.fix_base_pairs(models[0], base_pairs[0])
dot_notation = inputParser.make_dot_notation(text_strand, fixed_base_pairs)
assert desired_count < dot_notation.count('.')
def test_pdbListDownload():
structure_name = '1FAT'
file = inputParser.online_input(structure_name)
assert structure_name.lower() in file
with open(file) as f:
assert structure_name in f.readline()
pretty_print_model(i, joined_chain_model, dot_notation)
def mcannotate_part(file_path):
"""
:rtype: void
:param file_path: path to pdb file
"""
base_pairs = inputParser.annotate_basepairs(file_path)
models = inputParser.read_complete_models(file_path)
for i, (model, base_pair) in enumerate(zip(models, base_pairs)):
fixed_base_pairs = inputParser.fix_base_pairs(model, base_pair)
joined_chain_model = inputParser.build_txt_strand_from_chains(model)
dot_notation = inputParser.make_dot_notation(joined_chain_model,
fixed_base_pairs)
pretty_print_model(i, joined_chain_model, dot_notation)
if __name__ == '__main__':
args = parser.parse_args()
prediction_mode = args.prediction_mode
filepath = inputParser.online_input(args.structure_name, 'pdb')
if prediction_mode == 'nuss':
nussinov_part(filepath)
elif prediction_mode == 'mcan':
mcannotate_part(filepath)
else:
print("Unrecognized prediction mode!")