def save_differential_expression_csv(clustering_key, de, matrix, base_dir,
cluster_names = None,
file_name = 'differential_expression'):
out_dir = base_dir
if clustering_key is not None:
out_dir = os.path.join(base_dir, clustering_key)
cr_io.makedirs(out_dir, allow_existing=True)
diff_expression_fn = os.path.join(out_dir, file_name + '.csv')
diff_expression_header = ['Feature ID', 'Feature Name']
n_clusters = de.data.shape[1] / 3
for i in xrange(n_clusters):
if cluster_names is None:
diff_expression_header += ['Cluster %d Mean Counts' % (i + 1),
'Cluster %d Log2 fold change' % (i + 1),
'Cluster %d Adjusted p value' % (i + 1), ]
else:
diff_expression_header += ['Perturbation %s, Mean Counts' % cluster_names[i],
'Perturbation %s, Log2 fold change' % cluster_names[i],
'Perturbation %s, Adjusted p value' % cluster_names[i], ]
diff_expression_prefixes = [(f.id, f.name) for f in matrix.feature_ref.feature_defs]
analysis_io.save_matrix_csv(diff_expression_fn,
de.data,
diff_expression_header,
diff_expression_prefixes)
def save_lsa_csv(lsa_map, matrix, base_dir):
for n_components, lsa in lsa_map.iteritems():
n_components_dir = os.path.join(base_dir, '%d_components' % n_components)
cr_io.makedirs(n_components_dir, allow_existing=True)
matrix_fn = os.path.join(n_components_dir, 'projection.csv')
n_columns = lsa.transformed_lsa_matrix.shape[1]
assert n_columns <= n_components
matrix_header = ['Barcode'] + ['PC-%d' % (i + 1) for i in xrange(n_columns)]
analysis_io.save_matrix_csv(matrix_fn, lsa.transformed_lsa_matrix, matrix_header,
matrix.bcs)
components_fn = os.path.join(n_components_dir, 'components.csv')
components_header = ['PC'] + [f.id for f in matrix.feature_ref.feature_defs]
analysis_io.save_matrix_csv(components_fn, lsa.components, components_header,
range(1, n_components + 1))
variance_fn = os.path.join(n_components_dir, 'variance.csv')
variance_header = ['PC', 'Proportion.Variance.Explained']
analysis_io.save_matrix_csv(variance_fn, lsa.variance_explained, variance_header,
range(1, n_components + 1))
dispersion_fn = os.path.join(n_components_dir, 'dispersion.csv')
dispersion_header = ['Feature', 'Normalized.Dispersion']
analysis_io.save_matrix_csv(dispersion_fn, lsa.dispersion, dispersion_header,
[f.id for f in matrix.feature_ref.feature_defs])
features_fn = os.path.join(n_components_dir, 'features_selected.csv')
# TODO: there are two columns here, but only 1 entry in the header...BAD
features_header = ['Feature']
analysis_io.save_matrix_csv(features_fn, lsa.features_selected, features_header, range(1, len(lsa.features_selected) + 1))
def save_pca_csv(pca_map, matrix, base_dir):
for n_components, pca in pca_map.iteritems():
n_components_dir = os.path.join(base_dir,
'%d_components' % n_components)
cr_utils.makedirs(n_components_dir, allow_existing=True)
matrix_fn = os.path.join(n_components_dir, 'projection.csv')
matrix_header = ['Barcode'
] + ['PC-%d' % (i + 1) for i in xrange(n_components)]
cr_io.save_matrix_csv(matrix_fn, pca.transformed_pca_matrix,
matrix_header, matrix.bcs)
components_fn = os.path.join(n_components_dir, 'components.csv')
components_header = ['PC'] + [gene.id for gene in matrix.genes]
cr_io.save_matrix_csv(components_fn, pca.components, components_header,
range(1, n_components + 1))
variance_fn = os.path.join(n_components_dir, 'variance.csv')
variance_header = ['PC', 'Proportion.Variance.Explained']
cr_io.save_matrix_csv(variance_fn, pca.variance_explained,
variance_header, range(1, n_components + 1))
dispersion_fn = os.path.join(n_components_dir, 'dispersion.csv')
dispersion_header = ['Gene', 'Normalized.Dispersion']
cr_io.save_matrix_csv(dispersion_fn, pca.dispersion, dispersion_header,
[gene.id for gene in matrix.genes])
genes_fn = os.path.join(n_components_dir, 'genes_selected.csv')
genes_header = ['Gene']
cr_io.save_matrix_csv(genes_fn, pca.genes_selected, genes_header,
range(1,
len(pca.genes_selected) + 1))
def save_clustering_csv(base_dir, clustering_key, labels, barcodes):
out_dir = os.path.join(base_dir, clustering_key)
cr_io.makedirs(out_dir, allow_existing=True)
clusters_fn = os.path.join(out_dir, 'clusters.csv')
header = ['Barcode', 'Cluster']
analysis_io.save_matrix_csv(clusters_fn, labels, header, barcodes)
def save_tsne_csv(tsne_map, matrix, base_dir):
for n_tsne_components, tsne in tsne_map.iteritems():
n_tsne_components_dir = os.path.join(
base_dir, '%d_components' % n_tsne_components)
cr_utils.makedirs(n_tsne_components_dir, allow_existing=True)
matrix_fn = os.path.join(n_tsne_components_dir, 'projection.csv')
matrix_header = ['Barcode'] + [
'TSNE-%d' % (i + 1) for i in xrange(n_tsne_components)
]
cr_io.save_matrix_csv(matrix_fn, tsne.transformed_tsne_matrix,
matrix_header, matrix.bcs)
def save_tsne_csv(tsne, matrix, base_dir):
"""Save a TSNE object to CSV"""
# Preserve backward compatibility with pre-3.0 CSV files
# where the CSV directory was named "2_components" and the HDF5 dataset was named "_2"
key = tsne.key + '_components'
tsne_dir = os.path.join(base_dir, key)
cr_io.makedirs(tsne_dir, allow_existing=True)
matrix_fn = os.path.join(tsne_dir, 'projection.csv')
n_tsne_components = tsne.transformed_tsne_matrix.shape[1]
matrix_header = ['Barcode'] + [
'TSNE-%d' % (i + 1) for i in xrange(n_tsne_components)
]
analysis_io.save_matrix_csv(matrix_fn, tsne.transformed_tsne_matrix,
matrix_header, matrix.bcs)
def save_differential_expression_csv_from_features(clustering_key, de, diff_expression_prefixes, base_dir):
out_dir = os.path.join(base_dir, clustering_key)
cr_io.makedirs(out_dir, allow_existing=True)
diff_expression_fn = os.path.join(out_dir, 'differential_expression.csv')
diff_expression_header = ['Feature ID', 'Feature Name']
n_clusters = de.data.shape[1] / 3
for i in xrange(n_clusters):
diff_expression_header += ['Cluster %d Mean Counts' % (i + 1),
'Cluster %d Log2 fold change' % (i + 1),
'Cluster %d Adjusted p value' % (i + 1), ]
analysis_io.save_matrix_csv(diff_expression_fn,
de.data,
diff_expression_header,
diff_expression_prefixes)
def save_pca_csv_with_bc_feature(pca_map, barcodes, features, base_dir):
for n_components, pca in pca_map.iteritems():
n_components_dir = os.path.join(base_dir,
'%d_components' % n_components)
cr_io.makedirs(n_components_dir, allow_existing=True)
matrix_fn = os.path.join(n_components_dir, 'projection.csv')
n_columns = pca.transformed_pca_matrix.shape[1]
assert n_columns <= n_components
matrix_header = ['Barcode'
] + ['PC-%d' % (i + 1) for i in xrange(n_columns)]
analysis_io.save_matrix_csv(matrix_fn, pca.transformed_pca_matrix,
matrix_header, barcodes)
# FBPCA presently provides 0-sized entries for the following PCA() member variables.
# This allows us to distinguish FBPCA from IRLBA, and also avoids weird empty files.
if pca.components.size > 0:
components_fn = os.path.join(n_components_dir, 'components.csv')
components_header = ['PC'] + [f.id for f in features]
analysis_io.save_matrix_csv(components_fn, pca.components,
components_header,
range(1, n_components + 1))
if pca.variance_explained.size > 0:
variance_fn = os.path.join(n_components_dir, 'variance.csv')
variance_header = ['PC', 'Proportion.Variance.Explained']
analysis_io.save_matrix_csv(variance_fn, pca.variance_explained,
variance_header,
range(1, n_components + 1))
if pca.dispersion.size > 0:
dispersion_fn = os.path.join(n_components_dir, 'dispersion.csv')
dispersion_header = ['Feature', 'Normalized.Dispersion']
analysis_io.save_matrix_csv(dispersion_fn, pca.dispersion,
dispersion_header,
[f.id for f in features])
if pca.features_selected.size > 0:
features_fn = os.path.join(n_components_dir,
'features_selected.csv')
# TODO: there are two columns here, but only 1 entry in the header...BAD
features_header = ['Feature']
analysis_io.save_matrix_csv(
features_fn, pca.features_selected, features_header,
range(1,
len(pca.features_selected) + 1))
def save_differential_expression_csv(clustering_key, de, matrix, base_dir):
out_dir = os.path.join(base_dir, clustering_key)
cr_utils.makedirs(out_dir, allow_existing=True)
diff_expression_fn = os.path.join(out_dir, 'differential_expression.csv')
diff_expression_header = ['Gene ID', 'Gene Name']
n_clusters = de.data.shape[1] / 3
for i in xrange(n_clusters):
diff_expression_header += [
'Cluster %d Mean UMI Counts' % (i + 1),
'Cluster %d Log2 fold change' % (i + 1),
'Cluster %d Adjusted p value' % (i + 1),
]
diff_expression_prefixes = [(gene.id, gene.name) for gene in matrix.genes]
cr_io.save_matrix_csv(diff_expression_fn, de.data, diff_expression_header,
diff_expression_prefixes)
