def join(args, outs, chunk_defs, chunk_outs):
if args.filtered_matrix is None:
outs.tsne = None
outs.tsne_summary = {}
return
if not os.path.exists(outs.tsne):
os.mkdir(outs.tsne)
outs.tsne_summary = {'h5': {}, 'csv': {}}
for method in args.factorization:
# get all tsnes for a given method
chunk_h5s = [os.path.join(chunk_out.tsne, method + '_tsne.h5')
for chunk_def, chunk_out in zip(chunk_defs, chunk_outs) if chunk_def.method == method]
chunk_csv_dirs = [os.path.join(chunk_out.tsne, method + '_tsne_csv')
for chunk_def, chunk_out in zip(chunk_defs, chunk_outs) if chunk_def.method == method]
analysis_io.combine_h5_files(chunk_h5s,
os.path.join(outs.tsne, method + "_tsne.h5"),
[analysis_constants.ANALYSIS_H5_TSNE_GROUP])
for csv_dir in chunk_csv_dirs:
cr_io.copytree(csv_dir,
os.path.join(outs.tsne, method + "_tsne_csv"),
allow_existing=True)
outs.tsne_summary['h5'][method] = os.path.join(outs.tsne, method + "_tsne.h5")
outs.tsne_summary['csv'][method] = os.path.join(outs.tsne, method + "_tsne_csv")
def main(args, outs):
list_of_files = [
args.protospacer_calls_summary, args.protospacer_calls_per_cell,
args.cells_per_protospacer, args.protospacer_umi_thresholds_csv,
args.protospacer_umi_thresholds_json,
args.perturbation_efficiencies_by_feature,
args.perturbations_efficiencies_by_target
]
cr_io.makedirs(outs.crispr_analysis, allow_existing=True)
for (file_path, file_name) in itertools.izip(
list_of_files, protospacer_calling.CRISPR_ANALYSIS_FILE_NAMES):
if file_path is None:
continue
cr_io.copy(file_path, os.path.join(outs.crispr_analysis, file_name))
if os.path.isdir(args.perturbation_effects_by_feature):
perturbation_effects_by_feature_dir = os.path.join(
outs.crispr_analysis, 'perturbation_effects_by_feature')
cr_io.makedirs(perturbation_effects_by_feature_dir,
allow_existing=True)
cr_io.copytree(args.perturbation_effects_by_feature,
perturbation_effects_by_feature_dir,
allow_existing=True)
if os.path.isdir(args.perturbation_effects_by_target):
perturbation_effects_by_target_dir = os.path.join(
outs.crispr_analysis, 'perturbation_effects_by_target')
cr_io.makedirs(perturbation_effects_by_target_dir, allow_existing=True)
cr_io.copytree(args.perturbation_effects_by_target,
perturbation_effects_by_target_dir,
allow_existing=True)
def join(args, outs, chunk_defs, chunk_outs):
if args.skip:
return
chunk_out = chunk_outs[0]
cr_io.copy(chunk_out.pca_h5, outs.pca_h5)
cr_io.copytree(chunk_out.pca_csv, outs.pca_csv)
def join(args, outs, chunk_defs, chunk_outs):
if args.skip:
outs.analysis = None
outs.analysis_csv = None
outs.summary = None
return
chunk_out = chunk_outs[0]
cr_io.copytree(chunk_out.analysis, outs.analysis)
cr_io.copytree(chunk_out.analysis_csv, outs.analysis_csv)
summary = {}
# batch correction summary
if args.chemistry_batch_correction is True:
summary[
'batch_effect_score_before_correction'] = args.batch_score_before_correction
summary[
'batch_effect_score_after_correction'] = args.batch_score_after_correction
if args.is_multi_genome:
with open(args.multi_genome_summary) as reader:
multi_genome_summary = json.load(reader)
summary.update(multi_genome_summary)
else:
summary = summary
with open(outs.summary, 'w') as f:
json.dump(summary, f, indent=4, sort_keys=True)
def join(args, outs, chunk_defs, chunk_outs):
if args.skip or not args.is_multi_genome:
return
chunk_out = chunk_outs[0]
cr_io.copy(chunk_out.multi_genome_summary, outs.multi_genome_summary)
cr_io.copytree(chunk_out.multi_genome_csv, outs.multi_genome_csv)
cr_io.copytree(chunk_out.multi_genome_json, outs.multi_genome_json)
def main(args, outs):
if args.skip:
return
for h5, csv in zip(args.pca_h5_list, args.pca_csv_list):
if h5 is not None and csv is not None:
cr_io.copy(h5, outs.pca_h5)
cr_io.copytree(csv, outs.pca_csv)
def join(args, outs, chunk_defs, chunk_outs):
if args.skip:
return
chunk_h5s = [chunk_out.tsne_h5 for chunk_out in chunk_outs]
chunk_csv_dirs = [chunk_out.tsne_csv for chunk_out in chunk_outs]
analysis_io.combine_h5_files(chunk_h5s, outs.tsne_h5,
[analysis_constants.ANALYSIS_H5_TSNE_GROUP])
for csv_dir in chunk_csv_dirs:
cr_io.copytree(csv_dir, outs.tsne_csv, allow_existing=True)
def join(args, outs, chunk_defs, chunk_outs):
if args.skip:
return
chunk_h5s = [chunk_out.diffexp_h5 for chunk_out in chunk_outs]
chunk_csv_dirs = [chunk_out.diffexp_csv for chunk_out in chunk_outs]
analysis_io.combine_h5_files(chunk_h5s, outs.diffexp_h5, [analysis_constants.ANALYSIS_H5_DIFFERENTIAL_EXPRESSION_GROUP,
analysis_constants.ANALYSIS_H5_KMEANS_DIFFERENTIAL_EXPRESSION_GROUP])
for csv_dir in chunk_csv_dirs:
cr_io.copytree(csv_dir, outs.diffexp_csv, allow_existing=True)
def join(args, outs, chunk_defs, chunk_outs):
if args.filtered_matrix is None:
outs.reduced_data = None
outs.reduction_summary = {}
return
if not os.path.exists(outs.reduced_data):
cr_io.mkdir(outs.reduced_data)
# copy chunk outs
for chunk_out in chunk_outs:
cr_io.copytree(chunk_out.reduced_data, outs.reduced_data, allow_existing=True)
# Use final destinations to update summary
outs.reduction_summary = {'h5': {}, 'csv': {}}
for method in args.factorization:
outs.reduction_summary['h5'][method] = os.path.join(outs.reduced_data, method, method + ".h5")
outs.reduction_summary['csv'][method] = os.path.join(outs.reduced_data, method, method + "_csv")
def main(args, outs):
outs.clustering_summary = {}
if args.filtered_matrix is None:
outs.clustering = None
return
if not os.path.exists(outs.clustering):
cr_io.mkdir(outs.clustering)
# NOTE: both graph clustering and normal clustering should have run for given method
assert args.clustering_summary['h5'].keys(
) == args.graph_clustering_summary['h5'].keys()
outs.clustering_summary = {'h5': {}, 'csv': {}}
for method in args.clustering_summary['h5'].keys():
if method not in ALLOWED_FACTORIZATIONS:
raise ValueError("invalid method")
merge_h5 = [
args.clustering_summary['h5'][method],
args.graph_clustering_summary['h5'][method]
]
groups = [
analysis_constants.ANALYSIS_H5_MAP_CLUSTERING[method],
analysis_constants.ANALYSIS_H5_CLUSTERING_GROUP
]
out_method_dir = os.path.join(outs.clustering, method)
cr_io.mkdir(out_method_dir, allow_existing=True)
out_clustering_h5 = os.path.join(out_method_dir,
"{}_clustering.h5".format(method))
outs.clustering_summary['h5'][method] = out_clustering_h5
analysis_io.combine_h5_files(merge_h5, out_clustering_h5, groups)
_csv1 = os.path.join(args.clustered_data, method,
CLUSTER_FILE_HEAD[method] + "_csv")
_csv2 = os.path.join(args.knn_clusters, method, "clusters_csv")
out_csv = os.path.join(out_method_dir, method + "_csv")
cr_io.copytree(_csv1, out_csv, allow_existing=True)
cr_io.copytree(_csv2, out_csv, allow_existing=True)
outs.clustering_summary['csv'][method] = out_csv
def join(args, outs, chunk_defs, chunk_outs):
if args.filtered_matrix is None:
outs.clustered_data = None
outs.clustering_summary = {}
return
if not os.path.exists(outs.clustered_data):
cr_io.mkdir(outs.clustered_data)
outs.clustering_summary = {'h5': {}, 'csv': {}}
for method in args.factorization:
chunk_h5s = [
os.path.join(chunk_out.clustered_data, method,
CLUSTER_FILE_HEAD[method] + ".h5")
for chunk_out in chunk_outs
]
chunk_csv_dirs = [
os.path.join(chunk_out.clustered_data, method,
CLUSTER_FILE_HEAD[method] + "_csv")
for chunk_out in chunk_outs
]
method_dir = os.path.join(outs.clustered_data, method)
cr_io.mkdir(method_dir, allow_existing=True)
analysis_io.combine_h5_files(
chunk_h5s,
os.path.join(method_dir, CLUSTER_FILE_HEAD[method] + ".h5"), [
analysis_constants.ANALYSIS_H5_CLUSTERING_GROUP,
analysis_constants.ANALYSIS_H5_MAP_CLUSTERING[method]
])
for csv_dir in chunk_csv_dirs:
cr_io.copytree(csv_dir,
os.path.join(method_dir,
CLUSTER_FILE_HEAD[method] + "_csv"),
allow_existing=True)
outs.clustering_summary['h5'][method] = os.path.join(
method_dir, CLUSTER_FILE_HEAD[method] + ".h5")
outs.clustering_summary['csv'][method] = os.path.join(
method_dir, CLUSTER_FILE_HEAD[method] + "_csv")
def join(args, outs, chunk_defs, chunk_outs):
if args.filtered_peak_bc_matrix is None or not args.reduction_summary[
'h5'].keys():
outs.analysis = None
outs.analysis_csv = None
outs.feature_bc_matrix = None
return
# Make the FBM
# build joint Peak + TF count matrix for single genomes
# combine peak annotations for single genome analysis
peak_annotation = None
if args.peak_annotation:
annotations = pd.read_csv(args.peak_annotation,
sep='\t')[['gene', 'peak_type']]
annotations = annotations.replace(np.nan, '', regex=True)
annotations = annotations.values.astype(str).tolist()
peak_annotation = []
for row in annotations:
genes = row[0].split(";")
annotation = row[1].split(";")
promoter = []
nearby_gene = []
assert len(annotation) == len(genes)
for en, kind in enumerate(annotation):
if kind == 'promoter':
promoter += [genes[en]]
nearby_gene += [genes[en]]
peak_annotation += [[';'.join(promoter), ';'.join(nearby_gene)]]
fbm = cr_matrix.CountMatrix.load_h5_file(args.filtered_peak_bc_matrix)
mapping = None
if args.filtered_tf_bc_matrix:
# combine matrices, ensure the barcodes are same and ordered the same way
tf_matrix = cr_matrix.CountMatrix.load_h5_file(
args.filtered_tf_bc_matrix)
assert (fbm.bcs == tf_matrix.bcs).all()
if peak_annotation is not None:
fbm.feature_ref = FeatureReference.addtags(
fbm.feature_ref, ['promoter', 'nearby_gene'], peak_annotation)
tf_matrix.feature_ref = FeatureReference.addtags(
tf_matrix.feature_ref, ['promoter', 'nearby_gene'])
combined_feature_defs = FeatureReference.join(fbm.feature_ref,
tf_matrix.feature_ref)
combined_matrix = vstack([fbm.m, tf_matrix.m])
# explicit map linking rows in diffexp to combined matrix
mapping = np.zeros((tf_matrix.features_dim, 2))
for x in range(tf_matrix.features_dim):
mapping[x, 0] = x
mapping[x, 1] = x + fbm.features_dim
fbm = cr_matrix.CountMatrix(combined_feature_defs, fbm.bcs,
combined_matrix)
fbm.save_h5_file(outs.feature_bc_matrix,
sw_version=martian.get_pipelines_version())
# Pytables doesn't support variable len strings, so use h5py first
with h5.File(outs.feature_bc_matrix, 'r') as matrix, \
h5.File(outs.analysis, 'w') as out:
# TODO: copy the first group; fixme when we have a key
name = matrix.keys()[0]
matrix.copy(matrix[name], out, name='matrix')
factorizations = args.reduction_summary['h5'].keys()
USE_FACTORIZATION = DEFAULT_FACTORIZATION if DEFAULT_FACTORIZATION in factorizations else factorizations[
0]
with tables.open_file(outs.analysis, 'a') as out:
for summary, key in zip([
args.reduction_summary, args.clustering_summary,
args.tsne_summary, args.enrichment_analysis_summary
], [USE_FACTORIZATION, 'clustering', 'tsne', 'enrichment']):
if summary is None or not summary:
continue
print(key, summary)
data_h5 = summary['h5'][USE_FACTORIZATION]
with tables.open_file(data_h5, 'r') as indata:
indata.copy_children(indata.root, out.root, recursive=True)
dirname = os.path.join(outs.analysis_csv, key)
cr_io.copytree(summary['csv'][USE_FACTORIZATION], dirname)
# if mapping is present (single genome case), so is the coloring matrix
if mapping is not None:
with h5.File(outs.analysis, 'a') as out:
out.create_dataset('feature_DE_map', data=mapping)
args.coerce_strings()
tf_propZ_matrix = np.loadtxt(args.tf_propZ_matrix)
with h5.File(outs.analysis, 'a') as out:
out.create_dataset('diffexp_coloring_matrix', data=tf_propZ_matrix)
def copy_subdirs(src_dir, dest_dir):
for subdir in os.listdir(src_dir):
cr_io.copytree(os.path.join(src_dir, subdir), os.path.join(dest_dir, subdir))
def main(args, outs):
if args.skip:
return
if args.is_multi_genome:
cr_io.copytree(args.multi_genome_json, outs.analysis)
cr_io.copytree(args.multi_genome_csv, outs.analysis_csv)
analysis_h5 = analysis_io.h5_path(outs.analysis)
cr_io.makedirs(os.path.dirname(analysis_h5), allow_existing=True)
# Pytables doesn't support variable len strings, so use h5py first
with h5.File(args.matrix_h5, 'r') as matrix,\
h5.File(analysis_h5, 'w') as out:
# TODO: copy the first group; fixme when we have a key
name = matrix.keys()[0]
matrix.copy(matrix[name], out, name='matrix')
with 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, 'a') as out:
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_io.copytree(args.pca_csv, pca_dir)
clustering_dir = os.path.join(outs.analysis_csv, 'clustering')
cr_io.copytree(args.clustering_csv, clustering_dir)
diffexp_dir = os.path.join(outs.analysis_csv, 'diffexp')
cr_io.copytree(args.diffexp_csv, diffexp_dir)
tsne_dir = os.path.join(outs.analysis_csv, 'tsne')
cr_io.copytree(args.tsne_csv, tsne_dir)
