def combine_phenotype_data_and_clustering(run_parameters):
"""This is to insert the sample clusters column into the phenotype dataframe.
Returns:
phenotype_df: phenotype dataframe with the first column as sample clusters.
"""
phenotype_df = kn.get_spreadsheet_df(
run_parameters['phenotype_name_full_path'])
phenotype_df.insert(0, 'Cluster_ID', np.nan) # pylint: disable=no-member
cluster_labels_df = pd.read_csv(
run_parameters['cluster_mapping_full_path'],
index_col=0,
header=None,
sep='\t')
cluster_labels_df.columns = ['Cluster_ID']
common_samples = kn.find_common_node_names(phenotype_df.index,
cluster_labels_df.index)
phenotype_df.loc[common_samples,
'Cluster_ID'] = cluster_labels_df.loc[common_samples,
'Cluster_ID'] # pylint: disable=no-member
return phenotype_df
def generate_similarity_mat(expression_df, signature_df,similarity_measure):
"""generate matrix which save the similarity value of input dataframes
Args:
expression_df: genes x samples dataframe.
signature_df: genes x samples dataframe.
Returns:
similarity_mat: matrix with similarity values
"""
genes_in_expression = expression_df.index
genes_in_signature = signature_df.index
common_genes = kn.find_common_node_names(genes_in_expression, genes_in_signature)
expression_mat = expression_df.loc[common_genes, :].values
signature_mat = signature_df.loc[common_genes, :].values
nx = expression_mat.shape[1]
if (similarity_measure == "cosine" ):
similarity_mat = cosine_similarity(expression_mat.T, signature_mat.T)
elif (similarity_measure == "spearman"):
similarity_mat = spearmanr(expression_mat, signature_mat)[0]
similarity_mat = similarity_mat[0:nx,nx:]
elif (similarity_measure == "pearson"):
similarity_mat = get_pearsonr(expression_mat, signature_mat)
return similarity_mat
def run_fisher(run_parameters):
''' wrapper: call sequence to perform fisher gene-set characterization
Args:
run_parameters: dictionary of run parameters
'''
# -----------------------------------
# - Data read and extraction Section -
# -----------------------------------
spreadsheet_df = kn.get_spreadsheet_df(
run_parameters['spreadsheet_name_full_path'])
prop_gene_network_df = kn.get_network_df(
run_parameters['pg_network_name_full_path'])
spreadsheet_gene_names = kn.extract_spreadsheet_gene_names(spreadsheet_df)
prop_gene_network_n1_names, \
prop_gene_network_n2_names = kn.extract_network_node_names(prop_gene_network_df)
# -----------------------------------------------------------------------
# - limit the gene set to the intersection of network and user gene set -
# -----------------------------------------------------------------------
common_gene_names = kn.find_common_node_names(prop_gene_network_n2_names,
spreadsheet_gene_names)
common_gene_names_dict = kn.create_node_names_dict(common_gene_names)
prop_gene_network_n1_names_dict = kn.create_node_names_dict(
prop_gene_network_n1_names)
reverse_prop_dict = kn.create_reverse_node_names_dict(
prop_gene_network_n1_names_dict)
# ----------------------------------------------------------------------------
# - restrict spreadsheet and network to common genes and drop everthing else -
# ----------------------------------------------------------------------------
new_spreadsheet_df = kn.update_spreadsheet_df(spreadsheet_df,
common_gene_names)
prop_gene_network_df = kn.update_network_df(prop_gene_network_df,
common_gene_names, "node_2")
prop_gene_network_df['wt'] = 1
# ----------------------------------------------------------------------------
# - map every gene name to an integer index in sequential order startng at 0 -
# ----------------------------------------------------------------------------
prop_gene_network_df = kn.map_node_names_to_index(
prop_gene_network_df, prop_gene_network_n1_names_dict, "node_1")
prop_gene_network_df = kn.map_node_names_to_index(prop_gene_network_df,
common_gene_names_dict,
"node_2")
# --------------------------------------------
# - store the network in a csr sparse format -
# --------------------------------------------
universe_count = len(common_gene_names)
prop_gene_network_sparse = kn.convert_network_df_to_sparse(
prop_gene_network_df, universe_count, len(prop_gene_network_n1_names))
fisher_contingency_pval = get_fisher_exact_test(prop_gene_network_sparse,
reverse_prop_dict,
new_spreadsheet_df)
fisher_final_result = save_fisher_test_result(
fisher_contingency_pval, run_parameters['results_directory'],
spreadsheet_df.columns.values, 2)
map_and_save_droplist(spreadsheet_df, common_gene_names, 'fisher_droplist',
run_parameters)
return fisher_final_result
def select_genes_df(spreadsheet_df, gene_select_list):
""" Subset genes based on given gene set. Output is a spreadsheet with fewer rows
Args:
spreadsheet_df: genes x samples data frame
gene_select_list: list of some gene names in the spreadsheet
Returns:
spreadsheet_intersected_df: data frame with only the genes in the intersection of input gene names.
"""
gene_names = kn.extract_spreadsheet_gene_names(spreadsheet_df)
intersection_names = kn.find_common_node_names(gene_names,
gene_select_list)
return spreadsheet_df.loc[intersection_names]
def common_samples_df(sxp_1_df, sxp_2_df):
""" Make two spreadsheets consistent by samples: two new spreadsheets created
with samples being the intersection of sample sets of given spreadsheets.
Args:
sxp_1_df: samples x phenotypes dataframe (sxp_1_df = kn.get_spreadsheet_df(sxp_filename_1))
sxp_2_df: samples x phenotypes dataframe
Returns:
sxp_1_trim_df: samples x phenotypes with only sample names in both input dataframes
sxp_2_trim_df: samples x phenotypes with only sample names in both input dataframes
"""
sxp_1_gene_names = kn.extract_spreadsheet_gene_names(sxp_1_df)
sxp_2_gene_names = kn.extract_spreadsheet_gene_names(sxp_2_df)
common_samples_list = kn.find_common_node_names(sxp_1_gene_names,
sxp_2_gene_names)
return sxp_1_df.loc[common_samples_list], sxp_2_df.loc[common_samples_list]
def test_find_common_node_names(self):
ret = kn.find_common_node_names(self.list_1, self.list_2)
self.assertEqual(True, set(ret) == set([1]), 'incorrect intersection')