def process_overhangs(repo, project, overhangs_file, instanceid, authorid,
date):
with open(overhangs_file) as file:
inputlines = file.readlines()
validate_input_file(inputlines[0], overhangs_file)
if len(inputlines) <= 1:
return
collections = {}
collections['authorid'] = authorid
collections['datecreated'] = date
collections['description'] = 'Overhangs described in ' + instanceid
collections['name'] = 'overhang-' + instanceid
collectionid = uuid.uuid4()
collections['idcollection'] = collectionid
repo['collections'].append(collections)
repository.add_object_to_collection(repo, collectionid,
project['idcollection'], 'COLLECTION',
authorid, date)
for line in inputlines:
if ',' not in line:
continue
tokens = line.split(',')
featurename = 'overhang-' + tokens[0]
featuresequence = tokens[1].lower()
featureid = repository.create_feature(repo, featurename,
featuresequence, 'overhang',
date)
repository.add_object_to_collection(repo, collectionid, featureid,
'FEATURE', authorid, date)
def persist_part_feature(repo, vectorname, part, familyname, authorid, date):
nsa, fiveprimeoverhang, threeprimeoverhang = get_nucseq_annotations(
repo, vectorname)
partseq = part['nucseq']['sequence'].strip().lower()
start = len(fiveprimeoverhang['feature']['nucseq']['sequence'].strip())
end = len(partseq) - len(
threeprimeoverhang['feature']['nucseq']['sequence'].strip())
partfeatureseq = partseq[start:end]
partfeature = repository.create_feature(repo, 'Feature-' + part['name'],
partfeatureseq, familyname, date)
repository.add_feature_to_nucseq(
repo, 'Feature-' + part['name'], part['nucseq'], partfeature,
len(fiveprimeoverhang['feature']['nucseq']['sequence']), authorid,
date)
def process_vectors(repo, project, vectorsfiles, directories, instanceid,
authorid, date):
for vectorsfile in vectorsfiles:
with open(vectorsfile) as file:
lines = file.readlines()
validate_input_file(lines[0], vectorsfile)
if len(lines) <= 1:
continue
vectors = {}
vectors['authorid'] = authorid
vectors['datecreated'] = date
vectors['description'] = 'Vectors described in ' + instanceid
collectionid = uuid.uuid4()
vectors['idcollection'] = collectionid
repo['collections'].append(vectors)
repository.add_object_to_collection(repo, project['idcollection'],
vectors['idcollection'],
'COLLECTION', authorid, date)
lineno = 0
for line in lines[1:]:
tokens = line.split(',')
tokens = [t.strip() for t in tokens if len(t.strip()) > 0]
if len(tokens) < 5:
raise ValueError(
'The Values.csv file does not have the required number of tokens on line '
+ lineno)
vectorfilename = tokens[0]
vectorname = 'Vector-' + tokens[1]
resistancename = 'Resistance-' + tokens[2]
fiveprimeoverhangname = 'Overhang-' + tokens[3]
threeprimeoverhangname = 'Overhang-' + tokens[4]
if len(tokens) > 5:
description = tokens[5]
else:
description = 'From ' + vectorfilename + ': ' + \
fiveprimeoverhangname + ', ' + \
threeprimeoverhangname + ', ' + resistancename
directories = [d for d in directories if os.path.isdir(d)]
for directory in directories:
files = os.listdir(directory)
if vectorfilename in files:
vectorsequence = read_genbank_file(directory + '/' +
vectorfilename)
break
vector = {}
vector['authorid'] = authorid
vector['datecreated'] = date
vector['description'] = description
vector['name'] = vectorname
vectorid = uuid.uuid4()
vector['idvector'] = vectorid
nucseq = {}
nucseq['datecreated'] = date
nucseq['idnucseq'] = vectorid
nucseq['sequence'] = vectorsequence
vector['nucseq'] = nucseq
vector['iscircular'] = True
repo['nucseq'].append(nucseq)
repo['vectors'].append(vector)
ft2 = {}
foundfeature1 = False
foundfeature2 = False
overhangfeatures = repository.get_features_by_family_name(
repo, 'overhang')
for feature in overhangfeatures:
if not foundfeature1 and feature['name'].upper(
) == fiveprimeoverhangname.upper():
position = repository.get_overhang_position_in_vector(
vectorsequence, feature['nucseq']['sequence'])
repository.add_feature_to_nucseq(repo, vectorname, nucseq,
feature, position,
authorid, date)
foundfeature1 = True
if not foundfeature2 and feature['name'].upper(
) == threeprimeoverhangname.upper():
position = repository.get_overhang_position_in_vector(
vectorsequence, feature['nucseq']['sequence'])
repository.add_feature_to_nucseq(repo, vectorname, nucseq,
feature, position,
authorid, date)
ft2 = feature
foundfeature2 = True
if not foundfeature1 or not foundfeature2:
raise ValueError(
'The overhangs caused by vector ' + vectorname +
' were not defined in the overhangs manifest.')
foundfeature = False
for feature in repository.get_features_by_family_name(
repo, 'resistance'):
if feature['name'].upper() == resistancename.upper():
position = nucseq['sequence'].find(
feature['nucseq']['sequence'])
repository.add_feature_to_nucseq(repo, vectorname, nucseq,
feature, position,
authorid, date)
foundfeature = True
if not foundfeature:
overhangpos = repository.get_overhang_position_in_vector(
vectorsequence, ft2['nucseq']['sequence'])
if overhangpos < 0:
raise ValueError('The overhang ' + ft2['name'] +
' could not be found in the vector ' +
vectorname)
startpos = overhangpos + len(ft2['nucseq']['sequence']) + 1
resistancesequence = nucseq['sequence'][
startpos:len(nucseq['sequence'])]
f = repository.create_feature(repo, resistancename,
resistancesequence, 'resistance',
date)
position = nucseq['sequence'].find(f['nucseq']['sequence'])
repository.add_feature_to_nucseq(repo, vectorname, nucseq, f,
position, authorid, date)
repository.add_object_to_collection(repo, collectionid,
f['idfeature'], 'FEATURE',
authorid, date)
repository.add_object_to_collection(repo, collectionid, vectorid,
'VECTOR', authorid, date)
lineno += 1