def add_mapping_to_db():
f = FileHandler('../../data/mapping.txt')
for r in f:
tokens = r.split('\t')
rsname, gn, mn, version = tokens[0:4]
mapped_count, unique_count, pos_unique_count, neg_unique_count, s_name = tokens[4:9]
params = tokens[9:]
rs = Raw_sample.objects.get(name=rsname)
genome = Genome.objects.get(assembly_name=gn)
method = Method.objects.get(method_name=mn, method_version=version)
sid = transaction.savepoint()
try:
'''
param_set = Parameter_set(method_obj = method)
param_set.save()
for p in params:
t = p.split(':')
if len(t) == 1:
t.append('')
param = Parameter(param_set = param_set, param_name = t[0], param_value = t[1])
param.save()
'''
param_set = add_params_to_db(params, method)
mapping = Mapping(method_obj=method, genome_obj=genome, params=param_set, sample_obj=rs)
mapping.save()
sample = Sample(name = s_name, mapped_tags = mapped_count, unique_tags = unique_count, positive_unique_count = pos_unique_count, negative_unique_count = neg_unique_count, mapping_obj = mapping)
sample.save()
transaction.savepoint_commit(sid)
except IntegrityError:
print 'error'
transaction.savepoint_rollback(sid)
f.close()
def add_peakcalling_to_db():
f = FileHandler("../../data/peakcalling.txt")
for r in f:
tokens = r.split('\t')
s_name, method_name, method_version = tokens[0:3]
peak_file = tokens[3]
params = tokens[4:]
print "a"
sample = Sample.objects.get(name=s_name)
method = Method.objects.get(method_name = method_name, method_version = method_version)
print 'b'
'''
run = models.ForeignKey(Call_peak)
chrom = models.CharField(max_length=40)
start = models.PositiveIntegerField(null=False) #0-based
end = models.PositiveIntegerField(null=False) #1-based
size = models.PositiveIntegerField(null=False)
strand = models.CharField(max_length=1, choices=(('+', 'Positive'), ('-', 'Negative'), ('.', 'Unspecified')))
tag_count = models.FloatField(null=False)
summit_pos_pileup = models.PositiveSmallIntegerField(null=False) #Origin summit location by peak calling method
summit_val_pileup = models.FloatField(null=False)
summit_pos_5 = models.PositiveSmallIntegerField()
summit_val_5 = models.FloatField()
p_value = models.FloatField()
q_value = models.FloatField()
fold = models.FloatField()
'''
sid = transaction.savepoint()
try:
param_set = add_params_to_db(params, method)
callpeak = Call_peak(sample_obj = sample, method_obj = method, params = param_set)
callpeak.save()
sid = transaction.savepoint()
ph = FileHandler(peak_file)
for p in ph:
ptokens = p.split('\t')
chrom, start, end, length, strand, abs_summit, pileup, pileup_5, p_val, fold, q_val, _, tc, rpkm = ptokens
start = int(start)
abs_summit = int(abs_summit)
tc = float(tc)
#print p
newp = Peak(run=callpeak, chrom=chrom, start=start-1, end=end,
size=length, strand=strand, tag_count=tc, summit_pos_pileup=abs_summit-1-start,
summit_val_pileup = pileup, summit_pos_5 = abs_summit-1-start, summit_val_5=pileup_5,
p_value = p_val, q_value = q_val, fold = fold)
newp.save()
transaction.savepoint_commit(sid)
ph.close()
except IntegrityError, msg:
print msg
transaction.savepoint_rollback(sid)
def add_method_to_db():
f = FileHandler("../../data/methods.txt")
sid = transaction.savepoint()
for r in f:
tokens = r.split('\t')
m = Method(method_name=tokens[0],
method_type=tokens[1],
method_version=tokens[2])
sid = transaction.savepoint()
try:
m.save()
transaction.savepoint_commit(sid)
except DatabaseError:
transaction.savepoint_rollback(sid)
f.close()
def add_genome_to_db():
f = FileHandler("../../data/genomes.txt")
#sid = transaction.savepoint()
for r in f:
tokens = r.split('\t')
g = Genome(assembly_name = tokens[0],
alternative_assembly_name = tokens[1],
species = tokens[2],
size = tokens[3])
sid = transaction.savepoint() #create save points before transaction for rollback if error occurs.
try:
g.save()
transaction.savepoint_commit(sid)
except IntegrityError:
print "error"
transaction.savepoint_rollback(sid)
f.close()
def add_chromosomes_to_db():
genomes = Genome.objects.all()
if len(genomes) <= 0:
print "No genomes. Abort."
else:
for g in genomes:
f = FileHandler('../../data/%s.chrom.sizes'%g.assembly_name)
#sid = transaction.savepoint()
for r in f:
cname, csize = r.split()
chrom = Chromosome(name=cname, length=csize, genome_obj=g)
sid = transaction.savepoint()
try:
chrom.save()
transaction.savepoint_commit(sid)
except IntegrityError:
transaction.savepoint_rollback(sid)
print 'error'
f.close()
'''
dw = DownloadFromWeb("ftp.fu-berlin.de","pub/misc/movies/database" )
download = False
option = 0
try:
option = int(input("Do you want to download the new version of the databases if available? (1=yes, 0= no)"))
if option != 0 and option != 1:
raise ValueError()
except ValueError:
print("Option not found, assuming default value: no")
if option == 1:
download = True
result = dw.fetch("actresses.list.gz", download)
print(result)
result = dw.fetch("actors.list.gz", download)
print(result)
print("All fetched")
print("Loading actors")
actorHandler = FileHandler()
actorHandler.open("actors.list.gz")
actorHandler.loadData()
print("Actors loaded, closing files")
actorHandler.close()
print("Loading actresses")
actressHandler = FileHandler()
actressHandler.open("actresses.list.gz")
actressHandler.loadData()
print("Actresses loaded, closing files")
actressHandler.close()