class List2TrackForm(BaseForm):
child = twd.HidingTableLayout()
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome',
validator=twc.Validator(required=True),
)
feature_type = twf.SingleSelectField(
label='Feature type: ',
options=['genes', 'exons', 'transcripts'],
prompt_text=None,
help_text='Choose the kind of genomic features yo want to annotate',
validator=twc.Validator(required=True),
)
ids_list = twf.FileField(
label='IDs list: ',
help_text='Select the file with the list of IDs',
)
format = twf.SingleSelectField(
label='Output format: ',
options=["sql", "bed"],
prompt_text=None,
help_text='Format of the output file',
)
submit = twf.SubmitButton(id="submit", value="Submit")
class SmoothingForm(BaseForm):
track = twb.BsFileField(
label='Signal: ',
help_text='Select signal file (e.g. bedgraph)',
validator=twb.BsFileFieldValidator(required=True))
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
window_size = twf.TextField(
label='Window size: ',
validator=twc.IntValidator(required=True),
value=size_def,
help_text='Size of the sliding window')
window_step = twf.TextField(
label='Window step: ',
validator=twc.IntValidator(required=True),
value=step_def,
help_text='Size of steps between windows')
by_feature = twf.CheckBox(
label='Window size in features (not basepairs): ',
value=False,
help_text='Will count size and step parameters in number of features, not in basepairs')
format = twf.SingleSelectField(
label='Output format: ',
options=['sql','bedGraph','wig','bigWig','sga'],
prompt_text=None,
help_text='Format of the output file', )
submit = twf.SubmitButton(id="submit", value="Submit")
class GenomeGraphForm(BaseForm):
class SigMultiP(twb.BsMultiple):
label = 'Positive Signals: '
signals_plus = twb.BsFileField(
label=' ',
help_text='Signal files (e.g. bedgraph) to plot above the axis',
validator=twb.BsFileFieldValidator(required=False))
class SigMultiM(twb.BsMultiple):
label = 'Negative Signals: '
signals_minus = twb.BsFileField(
label=' ',
help_text='Signal files (e.g. bedgraph) to plot below the axis',
validator=twb.BsFileFieldValidator(required=False))
class FeatMulti(twb.BsMultiple):
label = 'Features: '
features = twb.BsFileField(
label=' ',
help_text=
'Features files (e.g. bed) to plot as segments on the axis',
validator=twb.BsFileFieldValidator(required=False))
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
submit = twf.SubmitButton(id="submit", value="Plot")
class DESeqForm(BaseForm):
child = twd.HidingTableLayout()
input_type = twd.HidingRadioButtonList(
label='Input type: ',
options=['Table', 'Signals'],
mapping={
'Table': ['table'],
'Signals': ['Group1', 'Group2', 'feature_type', 'assembly'],
},
value='Table',
help_text='Select input type (Formatted table, or signal tracks)')
table = twb.BsFileField(label='Table: ',
help_text='Select scores table',
validator=twb.BsFileFieldValidator(required=True))
class Group1(twb.BsMultiple):
label = 'Signals group 1: '
signals1 = twb.BsFileField(
label=' ',
help_text='Select signal files (position and score, e.g. bedgraph)',
validator=twb.BsFileFieldValidator(required=True))
class Group2(twb.BsMultiple):
label = 'Signals group 2: '
signals2 = twb.BsFileField(
label=' ',
help_text='Select signal files (position and score, e.g. bedgraph)',
validator=twb.BsFileFieldValidator(required=True))
feature_type = twd.HidingSingleSelectField(
label='Feature type: ',
options=ftypes,
prompt_text=None,
mapping={
ftypes[-1][0]: ['features'],
1: ['upstream', 'downstream']
},
help_text='Choose a feature set or upload your own',
validator=twc.Validator(required=True))
features = twb.BsFileField(
label='Custom feature set: ',
help_text='Select a feature file (e.g. bed)',
validator=twb.BsFileFieldValidator(required=True))
upstream = twf.TextField(label='Promoter upstream distance: ',
validator=twc.IntValidator(required=True),
value=prom_up_def,
help_text='Size of promoter upstream of TSS')
downstream = twf.TextField(label='Promoter downstream distance: ',
validator=twc.IntValidator(required=True),
value=prom_down_def,
help_text='Size of promoter downstream of TSS')
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
validator=twc.Validator(required=True),
help_text='Reference genome')
submit = twf.SubmitButton(id="submit", value="Submit")
class PairsPlotForm(BaseForm):
class SigMulti(twb.BsMultiple):
label = 'Signal: '
signals = twb.BsFileField(
label=' ',
help_text='Select signal file (e.g. bedgraph)',
validator=twb.BsFileFieldValidator(required=True))
child = twd.HidingTableLayout()
feature_type = twd.HidingSingleSelectField(
label='Feature type: ',
options=ftypes,
prompt_text=None,
mapping={
ftypes[-1][0]: ['features'],
1: ['upstream', 'downstream']
},
help_text='Choose a feature set or upload your own',
validator=twc.Validator(required=True))
features = twb.BsFileField(label='Custom feature set: ',
help_text='Select a feature file (e.g. bed)',
validator=twb.BsFileFieldValidator())
upstream = twf.TextField(label='Promoter upstream distance: ',
validator=twc.IntValidator(),
value=prom_up_def,
help_text='Size of promoter upstream of TSS')
downstream = twf.TextField(label='Promoter downstream distance: ',
validator=twc.IntValidator(),
value=prom_down_def,
help_text='Size of promoter downstream of TSS')
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
class HiMulti(twb.BsMultiple):
label = 'Features to highlight: '
highlights = twb.BsFileField(
label=' ',
help_text='Select a feature file (e.g. bed)',
validator=twb.BsFileFieldValidator())
mode = twd.HidingSingleSelectField(label='Plot type: ',
options=plot_types,
mapping={0: ['cormax']},
prompt_text=None)
cormax = twf.TextField(
label='Spatial range for correlation: ',
validator=twc.IntValidator(),
value=_cormax,
help_text='Maximum distance in bp to compute correlations')
submit = twf.SubmitButton(id="submit", value="Plot")
def __call__(self, **kw):
assembly = kw.get('assembly') or 'guess'
signals_plus = kw.get('SigMultiP', {}).get('signals_plus', [])
if not isinstance(signals_plus, list): signals_plus = [signals_plus]
signals_minus = kw.get('SigMultiM', {}).get('signals_minus', [])
if not isinstance(signals_minus, list): signals_minus = [signals_minus]
features = kw.get('FeatMulti', {}).get('features', [])
if not isinstance(features, list): features = [features]
sptracks = [
track(sig, chrmeta=assembly) for sig in signals_plus
if os.path.exists(sig)
]
smtracks = [
track(sig, chrmeta=assembly) for sig in signals_minus
if os.path.exists(sig)
]
ftracks = [
track(feat, chrmeta=assembly) for feat in features
if os.path.exists(feat)
]
snames = [t.name for t in sptracks + smtracks + ftracks]
if len(sptracks) > 0:
chrmeta = sptracks[0].chrmeta
elif len(smtracks) > 0:
chrmeta = smtracks[0].chrmeta
elif len(features) > 0:
chrmeta = ftracks[0].chrmeta
else:
raise ValueError("No data provided")
if assembly in [x[0] for x in genrep.GenRep().assemblies_available()]:
chrnames = genrep.Assembly(assembly).chrnames
else:
chrnames = [
x[1] for x in sorted([(v['length'], c)
for c, v in chrmeta.iteritems()],
reverse=True)
]
pdf = self.temporary_path(fname='genome_graph.pdf')
_fs = ['chr', 'start', 'end', 'score']
_ff = ['chr', 'start', 'end', 'name']
genomeGraph([(c, chrmeta[c]['length']) for c in chrnames],
[sig.read(fields=_fs) for sig in sptracks],
[sig.read(fields=_fs) for sig in smtracks],
[feat.read(fields=_ff) for feat in ftracks],
output=pdf,
new=True,
last=True,
legend=snames)
self.new_file(pdf, 'genome_graph')
return self.display_time()
def _get_chrmeta(self, chrmeta=None):
""":param chrmeta: (str or dict) assembly name, or dict of the type {chr: {'length': 1234}}."""
if isinstance(chrmeta, dict):
return chrmeta
if isinstance(chrmeta, basestring) and not (str(chrmeta) == "guess"):
self.assembly = chrmeta
if self.assembly is None:
return {}
from bbcflib import genrep
if genrep.GenRep().assemblies_available(self.assembly):
self.assembly = genrep.Assembly(self.assembly)
return self.assembly.chrmeta
else:
self.assembly = None
return {}
class RatiosForm(BaseForm):
numerator = twb.BsFileField(
label='Numerator: ',
help_text='Select the track with the numerators',
validator=twb.BsFileFieldValidator(required=True))
denominator = twb.BsFileField(
label='Denominator: ',
help_text='Select the track with the denominators',
validator=twb.BsFileFieldValidator(required=True))
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
format = twf.SingleSelectField(
label='Output format ',
prompt_text=None,
options=["bedGraph", "sql", "wig", "bigWig", "sga"],
validator=twc.Validator(required=True),
help_text='Format of the output file')
window_size = twf.TextField(
label='Window size: ',
validator=twc.IntValidator(),
value=size_def,
help_text='Size of the sliding window in bp (default: 1)')
pseudo = twf.TextField(
label='Pseudo-count: ',
validator=twb.FloatValidator(min=0, max=1000),
value=pseudo_def,
help_text='Value to be added to both signals (default: 0.5)')
threshold = twf.TextField(
label='Threshold: ',
validator=twb.FloatValidator(min=0, max=1000),
value=threshold_def,
help_text=
'This sets ratio=1 at each genomic position satisfying numerator value < threshold (default: 0)'
)
log = twf.CheckBox(label='Log ratios: ',
value=False,
help_text='Computes the log2 of the ratios')
distribution = twf.CheckBox(
label='Plot distribution: ',
value=False,
help_text=
'Creates a graphical representation of the distributions of the ratios based on a sample of genomic regions'
)
submit = twf.SubmitButton(id="submit", value="Submit")
class OverlapForm(BaseForm):
child = twd.HidingTableLayout()
features = twb.BsFileField(
label='Features file: ',
help_text='Upload your own file',
validator=twb.BsFileFieldValidator(required=True))
filter = twb.BsFileField(label='Filter file: ',
help_text='Upload your own file',
validator=twb.BsFileFieldValidator(required=True))
format = twf.SingleSelectField(
label='Output format: ',
options=["txt", "bed", "sql", "bedGraph", "bigWig"],
validator=twc.Validator(required=True),
help_text='Format of the output file')
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
submit = twf.SubmitButton(id="submit", value="Submit")
class CombineForm(BaseForm):
child = twd.HidingTableLayout()
class TrackMulti(twb.BsMultiple):
label = 'Tracks: '
tracks = twb.BsFileField(
label=' ',
help_text='Select files to combine',
validator=twb.BsFileFieldValidator(required=True))
format = twf.SingleSelectField(label='Output format: ',
options=["sql", "bed", "sga"],
prompt_text=None,
validator=twc.Validator(required=True),
help_text='Format of the output file')
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
submit = twf.SubmitButton(id="submit", value="Quantify")
class Table2TracksForm(BaseForm):
table = twb.BsFileField(label='Table: ',
help_text='Select table',
validator=twb.BsFileFieldValidator(required=True))
id_columns = twf.TextField(
label='columns id: ',
validator=twc.Validator(required=True),
value='',
help_text=
'comma separated list of columns id for which signal tracks will be generated (e.g. 3,5)'
)
format = twf.SingleSelectField(
label='Output format: ',
options=["sql", "bedgraph", "bigwig", "wig"],
validator=twc.Validator(required=False),
help_text='Output file(s) format (default: bedGraph)')
assembly = twf.SingleSelectField(
label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
submit = twf.SubmitButton(id="submit", value="Submit")
class FileConvertForm(BaseForm):
hover_help = True
show_errors = True
infile = twb.BsFileField(label='File: ',
help_text='Select file.',
validator=twb.BsFileFieldValidator(required=True))
child = twd.HidingTableLayout()
to = twd.HidingSingleSelectField(label='Output format: ',
options=format_list,
prompt_text=None,
mapping={'sql': ['dtype', 'assembly'],
'bigwig': ['assembly']},
validator=twc.Validator(required=True),
help_text='Select the format of your result')
dtype = twf.SingleSelectField(label='Output datatype: ',
prompt_text=None,
options=['quantitative', 'qualitative'],
help_text='Choose sql data type attribute')
assembly = twf.SingleSelectField(label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
submit = twf.SubmitButton(id="submit", value="Convert")
class MergeTracksForm(BaseForm):
forward = twb.BsFileField(label='Forward: ',
help_text='Select forward density file',
validator=twb.BsFileFieldValidator(required=True))
reverse = twb.BsFileField(label='Reverse: ',
help_text='Select reverse density file',
validator=twb.BsFileFieldValidator(required=True))
assembly = twf.SingleSelectField(label='Assembly: ',
options=genrep.GenRep().assemblies_available(),
help_text='Reference genome')
shift = twf.TextField(label='Shift: ',
validator=twc.IntValidator(required=True),
value=0,
help_text='Enter positive downstream shift ([fragment_size-read_length]/2), \
or a negative value to estimate shift by cross-correlation')
format = twf.SingleSelectField(label='Output format: ',
options=['sql','bed','bedGraph','wig','bigWig','sga'],
prompt_text=None,
help_text='Format of the output file', )
method = twf.RadioButtonList(label='Method: ',
options=['mean','min','max','geometric','median','sum'],
value='mean',
help_text='Select the score combination method')
submit = twf.SubmitButton(id="submit", value='Merge tracks')
def __call__(self,opts):
self.opts = opts
if os.path.exists(self.opts.wdir):
os.chdir(self.opts.wdir)
else:
raise Usage("Working directory '%s' does not exist." %self.opts.wdir)
##### Connect to Minilims, recover global variables, fetch job info
self.minilims = os.path.join(self.opts.basepath,self.name+"_minilims")
M = MiniLIMS(self.minilims)
if not((self.opts.key != None or (self.opts.config and os.path.exists(self.opts.config)))):
raise Usage("Need a job key or a configuration file")
if self.opts.key:
self.globals = use_pickle(M, "global variables")
htss = frontend.Frontend( url=self.globals['hts_mapseq']['url'] )
self.job = htss.job( self.opts.key )
[M.delete_execution(x) for x in \
M.search_executions(with_description=self.opts.key,fails=True)]
if self.job.options.get("config_file"):
if os.path.exists(self.job.options["config_file"]):
self.opts.config = os.path.abspath(self.job.options["config_file"])
elif os.path.exists("config.txt"):
self.opts.config = os.path.abspath("config.txt")
if self.opts.config and os.path.exists(self.opts.config):
(self.job,self.globals) = frontend.parseConfig( self.opts.config, self.job, self.globals )
elif os.path.exists(self.opts.config):
(self.job,self.globals) = frontend.parseConfig( self.opts.config )
self.opts.key = self.job.description
else:
raise Usage("Need either a job key (-k) or a configuration file (-c).")
##### Genrep instance
if 'fasta_file' in self.job.options:
if os.path.exists(self.job.options['fasta_file']):
self.job.options['fasta_file'] = os.path.abspath(self.job.options['fasta_path'])
else:
for ext in (".fa",".fa.gz",".tar.gz"):
if os.path.exists("ref_sequence"+ext):
self.job.options['fasta_file'] = os.path.abspath("ref_sequence"+ext)
if not os.path.exists(self.job.options['fasta_file']):
raise Usage("Don't know where to find fasta file %s." %self.job.options["fasta_file"])
g_rep = genrep.GenRep( url=self.globals.get("genrep_url"),
root=self.globals.get("bwt_root") )
##### Configure facility LIMS
if 'lims' in self.globals:
from bbcflib import daflims
self.job.dafl = dict((loc,daflims.DAFLIMS( username=self.globals['lims']['user'],
password=pwd ))
for loc,pwd in self.globals['lims']['passwd'].iteritems())
########################################################################
########################## EXECUTION #################################
########################################################################
##### Logging
logfile_name = os.path.abspath(self.opts.key+".log")
debugfile_name = os.path.abspath(self.opts.key+".debug")
self.logfile = open(logfile_name,'w')
self.debugfile = open(debugfile_name,'w')
self.debug_write(json.dumps(self.globals)+"\n")
with execution( M, description=self.opts.key,
remote_working_directory=self.opts.wdir ) as ex:
self.log_write("Enter execution. Current working directory: %s" %ex.working_directory)
self.job.assembly = genrep.Assembly( assembly=self.job.assembly_id,
genrep=g_rep,
fasta=self.job.options.get('fasta_file'),
annot=self.job.options.get('annot_file'),
intype=self.job.options.get('input_type_id',0),
ex=ex, via=self.opts.via,
bowtie2=self.job.options.get("bowtie2",True) )
##### Check all the options
if not self.check_options():
raise Usage("Problem with options %s" %self.opts)
self.debug_write(json.dumps(self.job.options))
self.init_files( ex )
##### Run workflow
self.log_write("Starting workflow.")
self.main_func(ex,**self.main_args)
##### Add logs to the LIMS in admin mode
self.logfile.flush()
self.debugfile.flush()
log_desc = set_file_descr('logfile.txt', step='log', type='txt', view="admin")
debug_desc = set_file_descr('debug.txt', step='log', type='txt', view="admin")
ex.add(os.path.join(logfile_name), description=log_desc)
ex.add(os.path.join(debugfile_name), description=debug_desc)
##### Create GDV project
if self.job.options['create_gdv_project']: self.gdv_create(ex)
########################################################################
######################## POSTPROCESSING ##############################
########################################################################
allfiles = get_files( ex.id, M )
if self.job.options['create_gdv_project'] and \
self.job.options['gdv_project'].get('project',{}).get('id',0)>0:
allfiles['url'] = self.gdv_upload(allfiles.get('sql',{}))
self.logfile.close()
self.debugfile.close()
print json.dumps(allfiles)
with open(self.opts.key+".done",'w') as done: json.dump(allfiles,done)
self.send_email()
return 0
from bsPlugins import *
from bein import execution
from bbcflib import genrep
from bbcflib.common import fasta_composition
from bbcflib.motif import save_motif_profile
from bbcflib.track import track, FeatureStream
import os
g = genrep.GenRep()
available_motifs = g.motifs_available()
assembly_list = g.assemblies_available()
input_types = [(0, 'Fasta upload'), (1, 'Select regions from genome')]
input_map = {0: ['fastafile'], 1: ['regions']}
meta = {'version': "1.0.0",
'author': "BBCF",
'contact': "*****@*****.**"}
in_parameters = [{'id': 'input_type', 'type': 'radio'},
{'id': 'fastafile', 'type': 'userfile'},
{'id': 'background', 'type': 'txt'},
{'id': 'assembly', 'type': 'assembly'},
{'id': 'regions', 'type': 'track'},
{'id': 'motifs', 'type': 'list'},
{'id': 'customMotif', 'type': 'txt'},
{'id': 'threshold', 'type': 'float', 'required': True}]
out_parameters = [{'id': 'motif_track', 'type': 'track'}]
class MotifScanForm(BaseForm):
def main():
try:
# Parse args
parser = optparse.OptionParser(usage=usage, description=descr)
for opt in opts:
parser.add_option(opt[0],opt[1],help=opt[2],**opt[3])
# Get variables
(opt, args) = parser.parse_args()
if opt.assembly:
assembly_id = re.search('([._\-\w]+)', str(opt.assembly)).groups()[0]
genrep_root = os.path.abspath(opt.root)
genrep_url = normalize_url(opt.url)
if opt.output:
fout = open(re.search('([._\-\w]+)', str(opt.output)).groups()[0], 'w')
else:
fout = sys.stdout
regions = None
if opt.regions:
if os.path.exists(opt.regions):
regions = opt.regions
else:
regions = []
for x in str(opt.regions).split(","):
chrom,start,end = re.search('(\S+):(\d+)\-(\d+)',x).groups()[0:3]
regions.append([chrom,int(start),int(end)])
# Program body
g_rep = genrep.GenRep(url=genrep_url, root=genrep_root)
if opt.assembly:
assembly = genrep.Assembly(assembly=assembly_id,genrep=g_rep,intype=opt.intype)
if opt.list:
if opt.assembly:
table = ["\t".join((v['ac'],k,str(v['length'])))
for k,v in assembly.chrmeta.iteritems()]
fout.write("\n".join(table)+"\n")
else:
fout.write("\n".join(v[1] for v in g_rep.assemblies_available())+"\n")
return 0
if not(opt.assembly):
parser.print_help()
return 0
if regions:
seq = assembly.fasta_from_regions(regions=regions, out=fout)[0]
if opt.bowtie:
fout.write(">"+str(assembly.id)+":"+assembly.name+" bowtie index prefix\n")
fout.write(assembly.index_path+"\n")
if opt.bowtie2:
fout.write(">"+str(assembly.id)+":"+assembly.name+" bowtie2 index prefix\n")
fout.write(re.sub(r'bowtie/','bowtie2/',assembly.index_path)+"\n")
if opt.fasta:
fout.write(">"+str(assembly.id)+":"+assembly.name+" fasta file\n")
fout.write(assembly.fasta_path()+"\n")
if opt.db:
fout.write(">"+str(assembly.id)+":"+assembly.name+" sqlite file\n")
fout.write(assembly.sqlite_path+"\n")
if opt.genes:
if os.path.exists(opt.genes):
glist = _parse_list(opt.genes)
else:
glist = opt.genes.split(",")
for gcoord in assembly.gene_coordinates(glist):
fout.write("\t".join([str(x) for x in gcoord])+"\n")
if opt.all:
from bbcflib.track import track
if opt.intype == 1:
feats = assembly.exon_track()
elif opt.intype == 2:
feats = assembly.transcript_track()
else:
feats = assembly.gene_track()
with track(fout,format='bed',fields=['strand']) as _tfeat:
_tfeat.write(feats)
if opt.stats:
stats = assembly.statistics(frequency=True)
bases = ["A","C","G","T"]
fout.write("#Assembly: %s\n" % assembly.name)
[fout.write("%s\t%s\n" % (x,stats[x])) for x in bases]
fout.write("#N\t%s\n" % stats["N"] )
[[fout.write("%s\t%s\n" % (x+y,stats[x+y])) for y in bases]
for x in bases]
fout.close()
if opt.convert:
if not(os.path.exists(opt.convert)):
raise Usage("No such file: %s."%opt.convert)
if not(opt.output):
raise Usage("Need an output file name.")
import pysam
infile = pysam.Samfile( opt.convert )
header = infile.header
chromosomes = dict((v['ac'],k) for k,v in assembly.chrmeta.iteritems())
for h in header["SQ"]:
if h["SN"] in chromosomes:
h["SN"] = chromosomes[h["SN"]]
outfile = pysam.Samfile(re.search('([._\-\w]+)', str(opt.output)).groups()[0], 'wb', header=header )
for read in infile:
outfile.write(read)
outfile.close()
infile.close()
return 0
except Usage, err:
print >>sys.stderr, err.msg
print >>sys.stderr, usage
return 2
from bsPlugins import *
from bein import execution
from bbcflib.common import fasta_length
from bbcflib.motif import meme
from bbcflib import genrep
from bbcflib.track import track, FeatureStream
import os, tarfile
input_types = [(0, 'Fasta upload'), (1, 'Select regions from genome')]
input_map = {0: ['fastafile'], 1: ['assembly', 'regions']}
_nm = 4
assembly_list = genrep.GenRep().assemblies_available()
meta = {
'version': "1.0.0",
'author': "BBCF",
'contact': "*****@*****.**"
}
in_parameters = [{
'id': 'input_type',
'type': 'radio'
}, {
'id': 'fastafile',
'type': 'userfile'
}, {
'id': 'assembly',
'type': 'assembly'
}, {
'id': 'regions',
#!/usr/bin/env python
from bbcflib import genrep
import os, getopt, sys
opts = dict(getopt.getopt(sys.argv[1:], "d:", [])[0])
basepath = opts.get('-d') or "/data/epfl/bbcf/genrep/nr_assemblies"
basepath += "/%s"
for _a, info in genrep.GenRep().assemblies_available():
for n in range(100):
assembly = genrep.Assembly(_a)
gtf_path = os.path.join(basepath % "gtf",
"%s_%i.gtf.gz" % (assembly.md5, n))
if not (assembly.bbcf_valid and os.path.exists(gtf_path)): break
sql_path = os.path.join(basepath % "annot_tracks",
"%s_%i.sql" % (assembly.md5, n))
if os.path.exists(sql_path): continue
print info, gtf_path, sql_path
assembly.gtf_to_sql(gtf_path=gtf_path, sql_path=sql_path)