def plot_results(res, path):
"""Some results plots"""
if res is None or len(res) == 0:
return
counts = base.pivot_count_data(res, idxcols=['name','ref'])
x = base.get_fractions_mapped(res)
print (x)
import seaborn as sns
sns.set_style('white')
sns.set_context("paper",font_scale=1.2)
fig = plotting.plot_fractions(x)
fig.savefig(os.path.join(path,'libraries_mapped.png'))
fig = plotting.plot_sample_counts(counts)
fig.savefig(os.path.join(path,'total_per_sample.png'))
fig = plotting.plot_read_count_dists(counts)
fig.savefig(os.path.join(path,'top_mapped.png'))
scols,ncols = base.get_column_names(counts)
for l,df in counts.groupby('ref'):
if 'mirbase' in l:
fig = plotting.plot_read_count_dists(df)
fig.savefig(os.path.join(path,'top_%s.png' %l))
#if len(scols)>1:
# fig = plotting.expression_clustermap(counts)
# fig.savefig(os.path.join(path,'expr_map.png'))
return
def map_genomic_features(self):
"""Map to a single set of features with a reference genome, requires we
use ensembl gtf with biotype for best results"""
out = self.output
temp = self.temp_path
ref_name = self.ref_name
features = self.features
if ref_name in self.aligner_params:
params = self.aligner_params[ref_name]
else:
params = ''
if ref_name == '':
print ('you need to provide a reference genome')
return
print ()
print ('found features files %s' %features)
print ('mapping to reference genome')
res = base.map_genome_features(self.files, ref_name, features,
outpath=temp, aligner=self.aligner,
aligner_params=params)
counts = base.pivot_count_data(res, idxcols=['name','gene_name','gene_biotype'])
res.to_csv( os.path.join(out, 'features_found.csv'), index=False )
counts.to_csv( os.path.join(out, 'feature_counts.csv'), index=False)
print ('results saved to feature_counts.csv')
plot_feature_results(res, out)
return
def map_genomic_features(self):
"""Map to a single set of features with a reference genome, requires we
use ensembl gtf with biotype for best results"""
out = self.output
temp = self.temp_path
ref_name = self.ref_name
features = self.features
if ref_name in self.aligner_params:
params = self.aligner_params[ref_name]
else:
params = ''
if ref_name == '':
print ('you need to provide a reference genome')
return
print ()
print ('found features files %s' %features)
print ('mapping to reference genome')
res = base.map_genome_features(self.files, ref_name, features,
outpath=temp, aligner=self.aligner,
aligner_params=params)
counts = base.pivot_count_data(res, idxcols=['name','gene_name','gene_biotype'])
res.to_csv( os.path.join(out, 'features_found.csv'), index=False )
counts.to_csv( os.path.join(out, 'feature_counts.csv'), index=False)
print ('results saved to feature_counts.csv')
plot_feature_results(res, out)
return
def plot_results(res, path):
"""Some results plots"""
if res is None or len(res) == 0:
return
counts = base.pivot_count_data(res, idxcols=['name', 'ref'])
x = base.get_fractions_mapped(res)
print(x)
import seaborn as sns
sns.set_style('white')
sns.set_context("paper", font_scale=1.2)
fig = plotting.plot_fractions(x)
fig.savefig(os.path.join(path, 'libraries_mapped.png'))
fig = plotting.plot_sample_counts(counts)
fig.savefig(os.path.join(path, 'total_per_sample.png'))
fig = plotting.plot_read_count_dists(counts)
fig.savefig(os.path.join(path, 'top_mapped.png'))
scols, ncols = base.get_column_names(counts)
for l, df in counts.groupby('ref'):
if 'mirbase' in l:
fig = plotting.plot_read_count_dists(df)
fig.savefig(os.path.join(path, 'top_%s.png' % l))
#if len(scols)>1:
# fig = plotting.expression_clustermap(counts)
# fig.savefig(os.path.join(path,'expr_map.png'))
return
def plot_feature_results(res, path):
"""plot results from feature counting"""
if res is None or len(res) == 0:
return
counts = base.pivot_count_data(res, idxcols=['name','gene_name','gene_biotype'])
x = base.get_fractions_mapped(res, by=['gene_biotype','label'])
print (x)
fig = plotting.plot_fractions(x)
fig.savefig(os.path.join(path,'features_mapped.png'))
fig = plotting.plot_sample_counts(counts)
fig.savefig(os.path.join(path,'total_features_per_sample.png'))
fig = plotting.plot_read_count_dists(counts)
fig.savefig(os.path.join(path,'top_feature_counts.png'))
return
def plot_feature_results(res, path):
"""plot results from feature counting"""
if res is None or len(res) == 0:
return
counts = base.pivot_count_data(res, idxcols=['name','gene_name','gene_biotype'])
x = base.get_fractions_mapped(res, by=['gene_biotype','label'])
print (x)
fig = plotting.plot_fractions(x)
fig.savefig(os.path.join(path,'features_mapped.png'))
fig = plotting.plot_sample_counts(counts)
fig.savefig(os.path.join(path,'total_features_per_sample.png'))
fig = plotting.plot_read_count_dists(counts)
fig.savefig(os.path.join(path,'top_feature_counts.png'))
return
def map_mirnas(self):
"""Map miRNAs using mirbase with isomir counts and do novel prediction
if a reference genome and index is provided"""
out = self.output
libraries = self.libraries
temp = self.temp_path
ref_name = self.ref_name
mat_name = 'mirbase-%s' %self.species
self.aligner_params[mat_name] = self.mirna_params
novel.VERBOSE = self.verbose
if self.check_index(ref_name) == False:
print ('no index for reference genome')
ref_name = ''
print ('mapping miRNAs..')
res, counts = base.map_mirbase(self.files, outpath=temp, indexes=libraries,
species=self.species, ref_genome=ref_name,
pad5=self.pad5, pad3=self.pad3, aligner=self.aligner,
samplelabels=self.labels,
params=self.aligner_params,
verbose=self.verbose)
self.results = res
#seperate out mature counts and save
matcounts = counts[counts.ref==mat_name]
res.to_csv( os.path.join(out, 'results.csv'),index=False )
res = res[res.ref!=ref_name]
matcounts.to_csv( os.path.join(out, 'mirbase_mature_counts.csv'), index=False,
float_format='%.1f' )
counts.to_csv( os.path.join(out, 'all_counts.csv'), index=False, float_format='%.1f')
#get fractions per sample and plot results
c = base.pivot_count_data(res, idxcols=['name','ref'])
self.samples = s = base.get_fractions_mapped(res)
print (s)
plot_results(s, c, out)
#isomir counting
print ()
print ('counting isomirs..')
iso, isocounts = base.map_isomirs(self.files, temp, self.species,
samplelabels=self.labels)
if isocounts is not None:
isocounts.to_csv( os.path.join(out, 'isomir_counts.csv'),
index=False, float_format='%.1f')
else:
print ('no isomirs could be counted')
#novel prediction
#train classifier first if not present
novel.create_classifier()
if self.ref_fasta == '' or not os.path.exists(self.ref_fasta):
print ('no reference genome file, skipping novel mirna step')
elif ref_name == None or ref_name == '':
print ('no index for ref genome, required for novel mirna step')
elif check_viennarna() == False:
print ('Vienna RNA package not installed')
print ('see https://www.tbi.univie.ac.at/RNA/')
else:
print ()
print ('predicting novel mirnas..')
start = time.time()
#change map_rnas so it can use remaining files from previous run....?
allreads = utils.combine_aligned_reads(temp, idx=ref_name)
new,cl = novel.find_mirnas(allreads, self.ref_fasta, species=self.species,
score_cutoff=float(self.score_cutoff),
read_cutoff=int(self.read_cutoff),
cpus=self.cpus)
if new is None or len(new) == 0:
print ('Could not find any novel mirnas.')
print ('There may not be sufficient aligned reads or the score cutoff is too high.\n')
return
if self.strict == True:
new = new[new.mature_check=='ok']
print ('filtered %s' %len(new))
new.to_csv(os.path.join(out,'novel_mirna.csv'), index=False)
#pad mature novel and write to fasta for counting
novpad = base.get_mature_padded(new, idkey='mature_id', seqkey='mature')
novpad = novpad.drop_duplicates('name')
utils.dataframe_to_fasta(novpad,os.path.join(out,'novel.fa'),
seqkey='sequence', idkey='name')
novel.create_report(new, cl, self.species, outfile=os.path.join(out, 'novel.html'))
#now count novel mirnas for all samples
build_indexes(os.path.join(out,'novel.fa'), self.index_path)
r,nc = base.map_rnas(self.files, ['novel'], self.temp_path,
aligner=self.aligner,
samplelabels=self.labels)
nc.to_csv( os.path.join(out, 'novel_mirna_counts.csv'), index=False )
end = round(time.time()-start,1)
print ('took %s seconds' %str(end))
return