for org, settings in org_sets :
wb(org.ljust(8))
print ':', settings.get('description','No description')
#for k,v in settings.items() :
# print ' '*4+k+": "+str(v)
org = ''
all_settings = {}
all_settings.update(global_settings)
all_settings.update(local_settings)
while org not in valid_org_settings :
org = input('Choose organism configuration, one of ('+','.join(valid_org_settings)+')')
# check for the required settings
required_settings = ['description','genome_dir','refgene_anno_path','theme_hypotheses','theme_markov']
if not check_org_settings(org,required_settings) :
warn(textwrap.fill('Selected organism settings must have the following settings defined:\n\
%s\n\
Either select another organism or define these settings in your local\
configuration file.'%required_settings))
org = ''
print
json_dict['org'] = org
############################################################################
# UCSC
############################################################################
ucsc_text = """The pipeline can include a step to automatically make called
peak data available on the web for integration with UCSC genome browser."""
parser.add_option('--output',dest='output',default=None,help='file to output fasta records to [default: stdout]')
parser.add_option('--bed',dest='bed',action='store_true', help='also produce a BED formatted file representing sampled sequences')
parser.add_option('--bed-output',dest='bed_output',default='output.bed',help='with --bed, file to output BED records to [default: %default]')
parser.add_option('-v','--verbose',dest='verbose',action='store_true',help='print out debug information')
if __name__ == '__main__' :
opts, args = parser.parse_args(sys.argv[1:])
if len(args) < 2 :
parser.error('Must be 2 non-option arguments')
organism, fasta_fns = args[0], args[1:]
reqd_settings = ['genome_dir','refgene_anno_path']
if not check_org_settings(organism,reqd_settings) :
parser.error('The <organism> settings set must contain paths for %s'%reqd_settings)
# load up all the fasta records
fasta_recs = {}
for fasta_fn in fasta_fns :
fasta = fasta_to_dict(fasta_fn)
fasta_recs.update(fasta)
# parse --num-seqs argument
if opts.num_seqs.endswith('x') :
num_seq_factor = float(opts.num_seqs[:-1])
num_seqs = int(len(fasta_recs)*num_seq_factor)
else :
try :
num_seqs = int(opts.num_seqs)