for region in [r for r in utils.regions if r in glfos[0]['seqs']]:
aset, bset = [set(g['seqs'][region]) for g in glfos]
tmpfo = glutils.get_empty_glfo(
args.locus) # make a new glfo that will only have non-shared genes
for glabel, gset, gfo in zip(
args.names, [aset - bset, bset - aset],
glfos): # <gset> is the genes that're only in <glabel>
for ogene in gset:
glutils.add_new_allele(tmpfo, {
'gene': '+'.join([ogene, glabel]),
'seq': gfo['seqs'][region][ogene],
'cpos': utils.cdn_pos(gfo, region, ogene)
},
use_template_for_codon_info=False)
# eh, maybe this doesn't really add anything?
# # add the nearest genes that they both have for comparison NOTE this gives one comparison gene for *each* gene, so usually you get a bunch of comparison/'both' genes in each block in the ascii output
# for bgene in aset & bset:
# _, nearest_gene, _ = glutils.find_nearest_gene_with_same_cpos(glfos[0], glfos[0]['seqs'][region][bgene], new_cpos=utils.cdn_pos(glfos[0], region, bgene)) # i think it doesn't matter which glfo we get it from, so arbitrarily choose the first one
# glutils.add_new_allele(tmpfo, {'gene' : '+'.join([nearest_gene, 'both']), 'seq' : glfos[0]['seqs'][region][nearest_gene], 'cpos' : utils.cdn_pos(glfos[0], region, bgene)}, use_template_for_codon_info=False)
print '%s: only in:\n %12s: %2d %s\n %12s: %2d %s' % (
utils.color('green', region), args.names[0], len(aset - bset),
utils.color_genes(sorted(aset - bset)), args.names[1],
len(bset - aset), utils.color_genes(sorted(bset - aset)))
if len(tmpfo['seqs'][region]) > 0:
print ' comparing to nearest genes that were in both (labeled \'both\'):'
glutils.print_glfo(tmpfo, only_region=region)
# ----------------------------------------------------------------------------------------
def get_genes(base, alleles=None):
if alleles is None: # take all of 'em
alleles = [
utils.allele(g) for g in glfo['seqs'][args.region]
if base == get_base(g)
]
return [
args.locus.upper() + args.region.upper() + base + '*' + al
for al in alleles
]
if args.bases == 'all':
glutils.print_glfo(glfo)
sys.exit(0)
args.bases = utils.get_arg_list(args.bases)
args.allele_numbers = utils.get_arg_list(args.allele_numbers)
genes = [
g for base in args.bases for g in get_genes(base, args.allele_numbers)
]
if len(genes) == 0:
raise Exception(
'couldn\'t find any genes for the specified --bases %s\n choices:\n %s'
% (' '.join(args.bases), ' '.join(
sorted(set([get_base(g) for g in glfo['seqs'][args.region]])))))
args.other_genes = utils.get_arg_list(args.other_genes)
if args.other_genes is not None:
genes += args.other_genes
if alleles is None: # take all of 'em
alleles = [
utils.allele(g) for g in glfo['seqs'][args.region]
if base == get_base(g)
]
return [
args.locus.upper() + args.region.upper() + base + '*' + al
for al in alleles
]
if args.bases == 'all':
input_groupfcn = None # lambda g: str(utils.primary_version(g) in ['4', '5']) # this example puts all the 4 and 5 primary versions in one group, and everybody else in another
glutils.print_glfo(
glfo,
only_region=(args.region if args.region != 'v' else None),
input_groupfcn=input_groupfcn
) # not much point in doing only v, since it's the one that takes most of the time
sys.exit(0)
args.bases = utils.get_arg_list(args.bases)
args.allele_numbers = utils.get_arg_list(args.allele_numbers)
genes = [
g for base in args.bases for g in get_genes(base, args.allele_numbers)
]
if len(genes) == 0:
raise Exception(
'couldn\'t find any genes for the specified --bases %s\n choices:\n %s'
% (' '.join(args.bases), ' '.join(
sorted(set([get_base(g) for g in glfo['seqs'][args.region]])))))
args.other_genes = utils.get_arg_list(args.other_genes)