def save_gem_class_json(self, base_dir):
json_file_path = MultiGenomeAnalysis.json_path(base_dir)
cr_utils.makedirs(os.path.dirname(json_file_path), allow_existing=True)
with open(json_file_path, 'w') as f:
json.dump(tk_safe_json.json_sanitize(self.result),
f,
indent=4,
sort_keys=True)
def main(args, outs):
if args.skip or args.is_multi_genome:
return
cr_io.combine_h5_files([args.kmeans_h5, args.graphclust_h5], outs.clustering_h5,
[cr_constants.ANALYSIS_H5_KMEANS_GROUP,
cr_constants.ANALYSIS_H5_CLUSTERING_GROUP])
csv_path = os.path.join(outs.clustering_csv)
cr_utils.makedirs(csv_path, allow_existing=True)
copy_subdirs(args.kmeans_csv, csv_path)
copy_subdirs(args.graphclust_csv, csv_path)
def save_gem_class_csv(self, base_dir):
csv_file_path = os.path.join(base_dir, 'gem_classification.csv')
cr_utils.makedirs(os.path.dirname(csv_file_path), allow_existing=True)
with open(csv_file_path, 'wb') as f:
writer = csv.writer(f)
writer.writerow([
'barcode', self.result['genome0'], self.result['genome1'],
'call'
])
for i in xrange(len(self.result['barcode'])):
call = self.result['call'][i]
call = call.replace(cr_constants.GEM_CLASS_GENOME0,
self.result['genome0'])
call = call.replace(cr_constants.GEM_CLASS_GENOME1,
self.result['genome1'])
writer.writerow([
self.result['barcode'][i],
self.result['count0'][i],
self.result['count1'][i],
call,
])
def main(args, outs):
if args.skip:
return
if args.is_multi_genome:
cr_utils.copytree(args.multi_genome_json, outs.analysis)
cr_utils.copytree(args.multi_genome_csv, outs.analysis_csv)
return
analysis_h5 = cr_io.h5_path(outs.analysis)
cr_utils.makedirs(os.path.dirname(analysis_h5), allow_existing=True)
with tables.open_file(args.matrix_h5, 'r') as matrix,\
tables.open_file(args.pca_h5, 'r') as pca,\
tables.open_file(args.clustering_h5, 'r') as clustering,\
tables.open_file(args.diffexp_h5, 'r') as diffexp,\
tables.open_file(args.tsne_h5, 'r') as tsne,\
tables.open_file(analysis_h5, 'w') as out:
# NOTE - genome name is replaced with 'matrix'
mat_groups = [m for m in matrix.root]
matrix.copy_node(mat_groups[0], out.root, recursive=True, newname='matrix')
pca.copy_children(pca.root, out.root, recursive=True)
clustering.copy_children(clustering.root, out.root, recursive=True)
diffexp.copy_children(diffexp.root, out.root, recursive=True)
tsne.copy_children(tsne.root, out.root, recursive=True)
pca_dir = os.path.join(outs.analysis_csv, 'pca')
cr_utils.copytree(args.pca_csv, pca_dir)
clustering_dir = os.path.join(outs.analysis_csv, 'clustering')
cr_utils.copytree(args.clustering_csv, clustering_dir)
diffexp_dir = os.path.join(outs.analysis_csv, 'diffexp')
cr_utils.copytree(args.diffexp_csv, diffexp_dir)
tsne_dir = os.path.join(outs.analysis_csv, 'tsne')
cr_utils.copytree(args.tsne_csv, tsne_dir)
