def new_selection(self, project_id, s, job_name, job_description, *args, **kw):
'''
Called by the browser. Transform a selection to a new track;
'''
user = handler.user.get_user_in_session(request)
sels = json.loads(s)
project = DBSession.query(Project).filter(Project.id == project_id).first()
if project is None :
return {'error' : "project id %s doesn't exist" % project_id}
path = track.common.temporary_path()
with track.new(path, 'sql') as t:
t.fields = simple_fields
for chromosome in sels:
t.write(chromosome, ((marquee['start'], marquee['end'], 0, '', 0 , '') for marquee in sels[chromosome]))
t.datatype = constants.FEATURES
t.assembly = project.sequence.name
task_id, track_id = handler.track.create_track(user.id, project.sequence, f=path, trackname='%s %s'
% (job_name, job_description), project=project)
if task_id == constants.NOT_SUPPORTED_DATATYPE :
return {'error' : "not supported datatype" % project_id}
job_id = handler.job.new_sel(user.id, project.id, job_description, job_name, task_id=task_id)
return {'job_id' : job_id,
'job_name' : job_name,
'job_description' : job_description,
'status' : 'RUNNING'}
def export(self, path, format=None):
with track.new(path, format) as t:
for chrom in self:
t.write(chrom, self.read(chrom))
t.chrmeta = self.chrmeta
t.info = self.info
self.close()
def runTest(self):
out_path = temporary_path('.sql')
with track.new(out_path) as t:
for chrom in range(5): t.write(str(chrom), [(0,10,'A',0.0,-1)])
cur = t.cursor()
cur.execute("CREATE table tmp (koopa text,troopa text)")
cur.execute("INSERT into tmp values (?,?)", (1,2))
def create_repeat_annotation(sequence, fname):
if checkfile(fname):
return
annotation = (x.isupper() for x in sequence)
intervals = simulator.sequence_to_intervals(simulator.get_sequence(annotation, sequence), "repeat")
with track.new(fname, "bed") as t:
t.fields = ["start", "end", "name"]
t.write("chr1", intervals)
def runTest(self):
out_path = temporary_path('.sql')
with track.new(out_path) as t:
for chrom in range(5):
t.write(str(chrom), [(0, 10, 'A', 0.0, -1)])
cur = t.cursor()
cur.execute("CREATE table tmp (koopa text,troopa text)")
cur.execute("INSERT into tmp values (?,?)", (1, 2))
def runTest(self):
in_path = samples['small_signals'][7]['sql']
out_path = temporary_path('.sql')
with track.load(in_path) as i:
with track.new(out_path) as o:
for chrom in i: o.write(chrom, i.read(chrom))
self.assertEqual(list(o.read('chrI')), list(i.read('chrI')))
os.remove(out_path)
def runTest(self):
in_path = samples['small_signals'][7]['sql']
out_path = temporary_path('.sql')
with track.load(in_path) as i:
with track.new(out_path) as o:
for chrom in i:
o.write(chrom, i.read(chrom))
self.assertEqual(list(o.read('chrI')), list(i.read('chrI')))
os.remove(out_path)
def create_repeat_annotation(sequence, fname):
if checkfile(fname):
return
annotation = (x.isupper() for x in sequence)
intervals = simulator.sequence_to_intervals(
simulator.get_sequence(annotation, sequence), 'repeat')
with track.new(fname, 'bed') as t:
t.fields = ['start', 'end', 'name']
t.write("chr1", intervals)
def ucsc_geneid_fix(in_gtf, out_gtf, remote=None, local=None):
"""Updates 'gene_id' entries in GTF files downloaded from UCSC
Table Browser to contain gene IDs instead of transcript IDs.
If the output GTF file name already exists, it will be overwritten.
:param in_gtf: path to input GTF file
:type in_gtf: str
:param out_gtf: path to output GTF file
:type out_gtf: str
:param remote: UCSC database and annotation source to use
:type remote: dict('db': str, 'annot_src': str)
:param local: two-column file name containing transcript-gene mapping,
only when `db` and `annot_src` are None
:type local: str
:returns: None
"""
# remote not defined
if remote is None:
# then local must be defined
if local is None:
raise ValueError("Missing `remote` or `local` arguments")
mapping = get_local_transcript_gene_mapping(local)
# remote defined
else:
# then local can not be defined
if local is not None:
raise ValueError("Only supply `remote` or `local` argument, " "not both.")
# remote must have 'db'
if "db" not in remote:
raise ValueError("Missing remote database name")
# and 'annot_src'
if "annot" not in remote:
raise ValueError("Missing remote annotation source name")
db = remote["db"]
annot = remote["annot"]
if annot not in QUERIES.keys():
raise ValueError("Invalid annotation source " "name: {0}".format(annot))
mapping = get_ucsc_transcript_gene_mapping(annot, db, cred=CRED)
# remove output file if it exists
if os.path.exists(out_gtf):
os.remove(out_gtf)
with track.load(in_gtf, readonly=True) as in_track, track.new(out_gtf, format="gtf") as out_track:
# since GTF has custom fields, need to set the out_track to use
# in_track's fields
out_track.fields = in_track.fields
for chrom in in_track.chromosomes:
chrom_rec = in_track.read(chrom)
out_track.write(chrom, update_gene_id_attr(chrom_rec, mapping))
def newTrack(self, info=None, name=None):
# Close previous track #
if self.current_track: self.closeCurrentTrack()
# Get a file name #
path = self.file_paths.next()
# Add it to the result #
self.tracks.append(path)
# Create it #
self.current_track = track.new(path)
# Add the metadata #
if info: self.current_track.info.update(info)
def runTest(self):
in_path = samples['small_features'][1]['sql']
out_path = temporary_path('.sql')
chrom = 'chrI'
with track.load(in_path) as i:
with track.new(out_path) as o:
o.fields = track.default_fields
o.write(chrom, i.read(chrom, ('start', 'end')))
got = tuple(o.read(chrom).next())
expected = (0, 10, None, None, None)
self.assertEqual(got, expected)
os.remove(out_path)
def runTest(self):
in_path = samples['small_features'][1]['sql']
out_path = temporary_path('.sql')
chrom = 'chrI'
with track.load(in_path) as i:
with track.new(out_path) as o:
o.fields = track.default_fields
o.write(chrom, i.read(chrom, ('start','end')))
got = tuple(o.read(chrom).next())
expected = (0, 10, None, None, None)
self.assertEqual(got, expected)
os.remove(out_path)
def new_selection(self, project_id, s, job_name, job_description, *args,
**kw):
'''
Called by the browser. Transform a selection to a new track;
'''
user = handler.user.get_user_in_session(request)
sels = json.loads(s)
project = DBSession.query(Project).filter(
Project.id == project_id).first()
if project is None:
return {'error': "project id %s doesn't exist" % project_id}
path = track.common.temporary_path()
with track.new(path, 'sql') as t:
t.fields = simple_fields
for chromosome in sels:
t.write(chromosome,
((marquee['start'], marquee['end'], 0, '', 0, '')
for marquee in sels[chromosome]))
t.datatype = constants.FEATURES
t.assembly = project.sequence.name
task_id, track_id = handler.track.create_track(
user.id,
project.sequence,
f=path,
trackname='%s %s' % (job_name, job_description),
project=project)
if task_id == constants.NOT_SUPPORTED_DATATYPE:
return {'error': "not supported datatype" % project_id}
job_id = handler.job.new_sel(user.id,
project.id,
job_description,
job_name,
task_id=task_id)
return {
'job_id': job_id,
'job_name': job_name,
'job_description': job_description,
'status': 'RUNNING'
}
def runTest(self):
in_path = temporary_path('.sql')
out_path = temporary_path('.sql')
with track.new(in_path) as t:
t.fields = ('start','end','score')
t.assembly = 'sacCer2'
t.write('chrI',[(0,2,10),(2,4,20),(6,8,10)])
result = window_smoothing(t, 2)
result.export(out_path)
with track.load(out_path) as t:
data = t.read('chrI')
got = map(tuple, data)
expected = [(0, 1, 8.0),
(1, 3, 12.0),
(3, 5, 10.0),
(5, 6, 8.0),
(6, 9, 4.0),
(9, 10, 2.0)]
self.assertEqual(got, expected)
os.remove(in_path)
os.remove(out_path)
def main(n, datadir='data/train_sequences/', fname='simulated_alignment'):
s1name = "sequence1"
s2name = "sequence2"
s3name = "sequence3"
annotation_name = 'gene'
alignment_extension = ".fa"
annotations_extension = ".bed"
config_extension = ".js"
if len(sys.argv) > 1:
n = int(sys.argv[1])
if len(sys.argv) > 2:
fname = sys.argv[2]
master_gene_sequence = MarkovChain(P_START_GENE, P_STOP_GENE)
human_delete_sequence = MarkovChain(P_START_DELETE, P_STOP_DELETE)
mouse_delete_sequence = MarkovChain(P_START_DELETE, P_STOP_DELETE)
horse_delete_sequence = MarkovChain(P_START_DELETE, P_STOP_DELETE)
mutator_coin = BiasedCoin(P_NOT_MUTATE_GENE)
master_gene = list()
human_gene = list()
mouse_gene = list()
horse_gene = list()
human_dna = list()
mouse_dna = list()
horse_dna = list()
for i in range(n):
# create master_gene item
g = g2 = g3 = g4 = master_gene_sequence.get_state()
# mutate master_gene item
if g:
g2 = mutator_coin.flip()
g3 = mutator_coin.flip()
g4 = mutator_coin.flip()
dna_mutation_coin = create_dna_mutation_coin(g2 + g3)
dna_mutation_coin2 = create_dna_mutation_coin(g2 + g4)
# create DNA item
c = c2 = c3 = random.randint(0, 3)
c2 = mutate(c2, g2 + g3)
c, c2, c3 = [DNA_CHARS[i] for i in (c, c2, c3)]
if not dna_mutation_coin.flip():
char_index = random.randint(0, 2)
if DNA_CHARS[char_index] == c2:
char_index = 3
c2 = DNA_CHARS[char_index]
if not dna_mutation_coin2.flip():
char_index = random.randint(0, 2)
if DNA_CHARS[char_index] == c3:
char_index = 3
c3 = DNA_CHARS[char_index]
# delete DNA item
if human_delete_sequence.get_state():
c = '-'
if mouse_delete_sequence.get_state():
c2 = '-'
if horse_delete_sequence.get_state():
c3 = '-'
# add items to sequence
master_gene.append(g)
human_gene.append(g2)
mouse_gene.append(g3)
horse_gene.append(g4)
human_dna.append(c)
mouse_dna.append(c2)
horse_dna.append(c3)
# output
s1fname = os.path.join(
datadir,
fname + '_' + s1name + '_' + annotation_name + annotations_extension)
if os.path.isfile(s1fname):
os.remove(s1fname)
s2fname = os.path.join(
datadir,
fname + '_' + s2name + '_' + annotation_name + annotations_extension)
if os.path.isfile(s2fname):
os.remove(s2fname)
s3fname = os.path.join(
datadir,
fname + '_' + s3name + '_' + annotation_name + annotations_extension)
if os.path.isfile(s3fname):
os.remove(s3fname)
intervals1 = sequence_to_intervals(get_sequence(human_gene, human_dna),
annotation_name)
intervals2 = sequence_to_intervals(get_sequence(mouse_gene, mouse_dna),
annotation_name)
intervals3 = sequence_to_intervals(get_sequence(horse_gene, horse_dna),
annotation_name)
annotations = Annotations()
annotations.setAnnotations([annotation_name])
annotations.addSequences([s1name, s2name, s3name])
annotations.addAnnotationFile(s1name, annotation_name, s1fname)
annotations.addAnnotationFile(s2name, annotation_name, s2fname)
# annotations.addAnnotationFile(s3name, annotation_name, s3fname)
Fasta.save(
[
(s1name, ''.join(human_dna)),
(s2name, ''.join(mouse_dna)),
# (s3name, ''.join(horse_dna))
],
os.path.join(datadir, fname + alignment_extension))
with track.new(s1fname, 'bed') as t:
t.fields = ['start', 'end', 'name']
t.write("chr1", intervals1)
with track.new(s2fname, 'bed') as t:
t.fields = ['start', 'end', 'name']
t.write("chr1", intervals2)
# with track.new(s3fname, 'bed') as t:
# t.fields = ['start', 'end', 'name']
# t.write("chr1", intervals3)
with Open(os.path.join(datadir, fname + config_extension), "w") as f:
json.dump(annotations.toJSON(), f)
