def get_data_plots(args, baseoutdir, methods, study, dsets):
metafos = heads.read_metadata(study)
assert len(set([metafos[ds]['locus'] for ds in dsets
])) # make sure everybody has the same locus
mfo = metafos[dsets[0]]
data_outdirs = [
heads.get_datadir(
study, 'processed', extra_str='gls-gen-paper-' + args.label) +
'/' + ds for ds in dsets
]
outdir = get_outdir(
args,
baseoutdir,
varname='data',
varval=study + '/' + '-vs-'.join(dsets)
) # for data, only the plots go here, since datascripts puts its output somewhere else
if len(dsets) > 1 and len(methods) == 1: # sample vs sample
glslabels = dsets
title = get_dset_title([metafos[ds] for ds in dsets])
if study != 'kate-qrs':
title += ' %s' % methstr(methods[0])
title_color = methods[0]
legends = get_dset_legends([metafos[ds] for ds in dsets])
legend_title = methstr(
methods[0]
) if study == 'kate-qrs' else None # for kate-qrs we need to put the subject _and_ the isotype in the title, so there's no room for the method
pie_chart_faces = False
print '%s:' % utils.color('green', methods[0]),
elif len(methods) > 1 and len(dsets) == 1: # method vs method
glslabels = methods
title = get_dset_title([mfo])
title_color = None
legends = [methstr(m) + ' only' for m in methods]
legend_title = None
pie_chart_faces = True
print '%s:' % utils.color('green', dsets[0]),
else:
raise Exception('one of \'em has to be length 1: %d %d' %
(len(methods), len(dsets)))
print '%s' % (' %s ' % utils.color('light_blue', 'vs')).join(glslabels)
make_gls_tree_plot(args,
outdir + '/' + '-vs-'.join(methods) + '/gls-gen-plots',
study + '-' + '-vs-'.join(dsets),
glsfnames=[
get_gls_fname(ddir,
meth,
locus=mfo['locus'],
data=True) for ddir in data_outdirs
for meth in methods
],
glslabels=glslabels,
locus=mfo['locus'],
title=title,
title_color=title_color,
legends=legends,
legend_title=legend_title,
pie_chart_faces=pie_chart_faces)
def write_single_zenodo_subdir(zenodo_dir, args, study, dset, method, mfo):
method_outdir = heads.get_datadir(study, 'processed', extra_str=args.label) + '/' + dset
gls_dir = get_gls_dir(method_outdir, method, data=True)
print ' %s --> %s' % (gls_dir, zenodo_dir)
glfo = glutils.read_glfo(gls_dir, mfo['locus'], remove_orfs='partis' in method)
glutils.write_glfo(zenodo_dir, glfo)
if method == 'partis':
# allele finding plots
plotdir = gls_dir.replace('hmm/germline-sets', 'plots/sw/allele-finding')
if not os.path.exists(zenodo_dir + '/fits'):
os.makedirs(zenodo_dir + '/fits')
for genedir in glob.glob(plotdir + '/try-0/*'): # would be nice to copy html, but links will be wrong
subprocess.check_call(['cp', '-r', genedir, zenodo_dir + '/fits/'])
# csv prevalence files
for tmpreg in utils.regions:
with open(gls_dir.replace('/germline-sets', '/%s_gene-probs.csv' % tmpreg)) as infile:
reader = csv.DictReader(infile)
countfo = {line['%s_gene' % tmpreg] : int(line['count']) for line in reader}
old_total = sum(countfo.values())
orf_genes = [g for g in countfo if g not in glfo['seqs'][tmpreg]] # this is kind of dangerous... but the genes are read from the same parameter dir that we're reading this prevalence file, so the only way it's gonna be missing is if we just removed it with the read_glfo() line above
for ogene in orf_genes:
# if tmpreg == 'v':
# _, nearest_gene, _ = glutils.find_nearest_gene_with_same_cpos(glfo, glfo['seqs'][tmpreg][ogene]) # oops, that's dumb... of course it isn't there
# else:
nearest_gene = glutils.find_nearest_gene_using_names(glfo, ogene)
# print ' adding %d to %s from %s' % (countfo[ogene], utils.color_gene(nearest_gene), utils.color_gene(ogene))
countfo[nearest_gene] += countfo[ogene]
for ogene in orf_genes:
del countfo[ogene]
assert old_total == sum(countfo.values())
with open('%s/%s_gene-probs.csv' % (zenodo_dir, tmpreg), 'w') as outfile:
writer = csv.DictWriter(outfile, ('%s_gene' % tmpreg, 'count'))
writer.writeheader()
for gene in countfo:
writer.writerow({'%s_gene' % tmpreg : gene, 'count' : countfo[gene]})
elif method == 'tigger-default':
# doesn't seem to have written anything
pass
elif method == 'igdiscover':
# for fname in ['errorhistograms.pdf', 'V_usage.pdf', 'V_usage.tab']:
# subprocess.check_call(['cp', '%s/work/final/%s' % (gls_dir, fname), zenodo_dir + '/'])
subprocess.check_call(['cp', '-r', '%s/work/final' % gls_dir, zenodo_dir + '/']) # aw, screw it, just write everything. The simulation stuff is already huge, anyway
else:
assert False
def get_data_plots(args, region, baseoutdir, methods, study, dsets):
metafos = heads.read_metadata(study)
assert len(set([metafos[ds]['locus'] for ds in dsets])) # make sure everybody has the same locus
mfo = metafos[dsets[0]]
data_outdirs = [heads.get_datadir(study, 'processed', extra_str=args.label) + '/' + ds for ds in dsets]
outdir = get_outdir(args, baseoutdir, varname='data', varval=study + '/' + '-vs-'.join(dsets)) # for data, only the plots go here, since datascripts puts its output somewhere else
title, title_color, legends, legend_title = None, None, None, None
pie_chart_faces = False
if len(dsets) > 1 and len(methods) == 1: # sample vs sample
glslabels = dsets
title = get_dset_title([metafos[ds] for ds in dsets])
if study != 'kate-qrs':
title += ' %s' % methstr(methods[0])
title_color = methods[0]
legends = get_dset_legends([metafos[ds] for ds in dsets])
legend_title = methstr(methods[0]) if study == 'kate-qrs' else None # for kate-qrs we need to put the subject _and_ the isotype in the title, so there's no room for the method
print '%s:' % utils.color('green', methods[0]),
elif len(methods) > 1 and len(dsets) == 1: # method vs method
glslabels = methods
title = get_dset_title([mfo])
title_color = None
legends = [methstr(m) + ' only' for m in methods]
legend_title = None
pie_chart_faces = len(methods) > 2 # True
print '%s:' % utils.color('green', dsets[0]),
else: # single sample plot
glslabels = dsets
print '%s' % (' %s ' % utils.color('light_blue', 'vs')).join(glslabels)
plotdir = outdir + '/' + '-vs-'.join(methods) + '/gls-gen-plots'
if args.all_regions: # NOTE not actually checking this by running... but it's the same as the gls-gen one, so it should be ok
plotdir += '/' + region
param_dirs = None
if args.add_gene_counts_to_tree_plots: # this returns 'None' for non-partis methods, which is ok for now, but I think I do usually have the parameter dir somewhere if I've run the annotation performance stuff
param_dirs = [get_param_dir(ddir, meth) for ddir in data_outdirs for meth in methods]
make_gls_tree_plot(args, region, plotdir, study + '-' + '-vs-'.join(dsets),
glsfnames=[get_gls_fname(region, ddir, meth, locus=mfo['locus'], data=True) for ddir in data_outdirs for meth in methods],
glslabels=glslabels,
locus=mfo['locus'],
title=title,
title_color=title_color,
legends=legends,
legend_title=legend_title,
pie_chart_faces=pie_chart_faces,
param_dirs=param_dirs)
def get_data_plots(args, baseoutdir, method):
for var in args.varvals:
study, dset = var.split('/')
mfo = heads.read_metadata(study)[dset]
data_outdir = heads.get_datadir(
study, 'processed',
extra_str='gls-gen-paper-' + args.label) + '/' + dset
outdir = get_outdir(
args, baseoutdir, varname='data', varval=study + '/' + dset
) # for data, only the plots go here, since datascripts puts its output somewhere else
make_gls_tree_plot(args,
outdir + '/' + method + '/gls-gen-plots',
study + '-' + dset,
glsfnames=[
get_gls_fname(data_outdir,
method,
locus=mfo['locus'],
data=True)
],
glslabels=['data'])
def print_data_table(dsetfos, method, latex=False, emph_genes=['IGHV1-2*02+G35A', 'IGHD3-10*01', 'IGHJ4*02', 'IGKV3-15*01', 'IGKJ3*01']):
latex = True
def getvalstr(gene, val):
if gene is None or (utils.get_region(gene) == 'd' and not utils.has_d_gene(utils.get_locus(gene))):
return '%s %5.2s %s %-16s%s' % (cstr, ' - ', cstr, ' - ', 4 * ' ' if latex else '')
else:
if latex:
gstr = utils.shorten_gene_name(gene, use_one_based_indexing=True, n_max_mutstrs=5)
if emph_genes is not None and gene in emph_genes:
gstr = '\\color{red}{\\textbf{%s}}' % gstr
else:
gstr = utils.color_gene(gene, width=18)
return '%s %s%5.2f%s %s %-20s' % (cstr, estr, 100 * val, estr, cstr, gstr)
def print_line(rfos):
print ' %s%s' % (' '.join([getvalstr(g, v) for g, v in rfos]), lstr)
def ds_str(ds, region):
lstr = ds.split('-')[1]
return ('IG%s%s' % (('h' if lstr in ['g', 'm'] else lstr).upper(), region.upper())) if latex else ds
cstr = '&' if latex else ''
estr = '$' if latex else ''
lstr = '\\\\' if latex else ''
for region in utils.regions:
param_dirs = [get_param_dir(heads.get_datadir(study, 'processed', extra_str=args.label) + '/' + dset, method) for study, dset in dsetfos]
countfos = [utils.read_overall_gene_probs(pdir, normalize=True)[region] for pdir in param_dirs]
gene_val_str = (' %s ' % cstr).join([(' %s %s %-20s' % ('\\%' if latex else '', cstr, ds_str(ds, region))) for _, ds in dsetfos])
tmpline = ' %s %s %s' % (cstr, gene_val_str, lstr)
if latex:
hstr = '\\hline'
tmpline = ' %s\n%s\n %s' % (hstr, tmpline, hstr)
print tmpline
rowfos = [sorted(cfo.items(), key=operator.itemgetter(1), reverse=True) for cfo in countfos]
irow = 0
while True:
rfos = [rfo[irow] if irow < len(rfo) else (None, None) for rfo in rowfos]
if set(rfos) == set([(None, None)]):
break
print_line(rfos)
irow += 1
def get_data_pair_plots(args, baseoutdir, method, study, dsets):
mfo = heads.read_metadata(study)[dsets[0]]
assert heads.read_metadata(study)[dsets[1]]['locus'] == mfo['locus']
data_outdirs = [
heads.get_datadir(
study, 'processed', extra_str='gls-gen-paper-' + args.label) +
'/' + ds for ds in dsets
]
outdir = get_outdir(
args,
baseoutdir,
varname='data',
varval=study + '/' + '-vs-'.join(dsets)
) # for data, only the plots go here, since datascripts puts its output somewhere else
make_gls_tree_plot(args,
outdir + '/' + method + '/gls-gen-plots',
study + '-' + '-vs-'.join(dsets),
glsfnames=[
get_gls_fname(dout,
method,
locus=mfo['locus'],
data=True) for dout in data_outdirs
],
glslabels=dsets)