def build_results(
interactions: pd.DataFrame, mean_analysis: pd.DataFrame,
percent_analysis: pd.DataFrame, clusters_means: dict,
result_precision: int) -> (pd.DataFrame, pd.DataFrame, pd.DataFrame):
core_logger.info('Building Simple results')
interacting_pair = cpdb_statistical_analysis_helper.interacting_pair_build(
interactions)
interactions_data_result = pd.DataFrame(interactions[[
'id_cp_interaction', 'name_1', 'name_2', 'ensembl_1', 'ensembl_2',
'source'
]].copy())
interactions_data_result = pd.concat(
[interacting_pair, interactions_data_result], axis=1, sort=False)
interactions_data_result['secreted'] = (interactions['secretion_1']
| interactions['secretion_2'])
interactions_data_result['is_integrin'] = (
interactions['integrin_interaction_1']
| interactions['integrin_interaction_2'])
interactions_data_result.rename(columns={
'name_1': 'partner_a',
'name_2': 'partner_b',
'ensembl_1': 'ensembl_a',
'ensembl_2': 'ensembl_b'
},
inplace=True)
interactions_data_result['partner_a'] = interactions_data_result[
'partner_a'].apply(lambda name: 'simple:{}'.format(name))
interactions_data_result['partner_b'] = interactions_data_result[
'partner_b'].apply(lambda name: 'simple:{}'.format(name))
significant_mean_rank, significant_means = cpdb_analysis_helper.build_significant_means(
mean_analysis, percent_analysis)
significant_means = significant_means.round(result_precision)
mean_analysis = mean_analysis.round(result_precision)
for key, cluster_means in clusters_means.items():
clusters_means[key] = cluster_means.round(result_precision)
# Document 2
means_result = pd.concat([interactions_data_result, mean_analysis],
axis=1,
join='inner',
sort=False)
# Document 3
significant_means_result = pd.concat(
[interactions_data_result, significant_mean_rank, significant_means],
axis=1,
join='inner',
sort=False)
# Document 5
deconvoluted_result = deconvoluted_result_build(clusters_means,
interactions)
return means_result, significant_means_result, deconvoluted_result
def build_results(interactions: pd.DataFrame,
mean_analysis: pd.DataFrame,
percent_analysis: pd.DataFrame,
clusters_means: dict,
result_precision: int,
counts_data: str) -> (pd.DataFrame, pd.DataFrame, pd.DataFrame):
core_logger.info('Building Simple results')
interacting_pair = cpdb_statistical_analysis_helper.interacting_pair_build(interactions)
gene_columns = ['{}_{}'.format(counts_data, suffix) for suffix in ('1', '2')]
gene_renames = {column: 'gene_{}'.format(suffix) for column, suffix in zip(gene_columns, ['a', 'b'])}
interactions_data_result = pd.DataFrame(
interactions[
['id_cp_interaction', 'name_1', 'name_2', 'receptor_1', 'receptor_2', *gene_columns,
'annotation_strategy']].copy())
interactions_data_result = pd.concat([interacting_pair, interactions_data_result], axis=1, sort=False)
interactions_data_result['secreted'] = (interactions['secreted_1'] | interactions['secreted_2'])
interactions_data_result['is_integrin'] = (
interactions['integrin_1'] | interactions['integrin_2'])
interactions_data_result['receptor'] = (
interactions['receptor_1'] | interactions['receptor_2'])
interactions_data_result.rename(
columns={'name_1': 'partner_a', 'name_2': 'partner_b', 'receptor_1': 'receptor_a', 'receptor_2': 'receptor_b',
**gene_renames},
inplace=True)
interactions_data_result['partner_a'] = interactions_data_result['partner_a'].apply(
lambda name: 'simple:{}'.format(name))
interactions_data_result['partner_b'] = interactions_data_result['partner_b'].apply(
lambda name: 'simple:{}'.format(name))
# Dedupe rows and filter only desired columns
interactions_data_result.drop_duplicates(inplace=True)
means_columns = ['id_cp_interaction', 'interacting_pair', 'partner_a', 'partner_b', 'gene_a', 'gene_b', 'secreted',
'receptor_a', 'receptor_b', 'annotation_strategy', 'is_integrin']
interactions_data_result = interactions_data_result[means_columns]
significant_mean_rank, significant_means = cpdb_analysis_helper.build_significant_means(mean_analysis,
percent_analysis)
significant_means = significant_means.round(result_precision)
mean_analysis = mean_analysis.round(result_precision)
for key, cluster_means in clusters_means.items():
clusters_means[key] = cluster_means.round(result_precision)
# Document 2
means_result = pd.concat([interactions_data_result, mean_analysis], axis=1, join='inner', sort=False)
# Document 3
significant_means_result = pd.concat([interactions_data_result, significant_mean_rank, significant_means], axis=1,
join='inner', sort=False)
# Document 5
deconvoluted_result = deconvoluted_result_build(clusters_means, interactions, counts_data)
return means_result, significant_means_result, deconvoluted_result
def build_results(
interactions: pd.DataFrame, mean_analysis: pd.DataFrame,
percent_analysis: pd.DataFrame, clusters_means: dict,
complex_compositions: pd.DataFrame, counts: pd.DataFrame,
genes: pd.DataFrame, result_precision: int,
counts_data: str) -> (pd.DataFrame, pd.DataFrame, pd.DataFrame):
"""
Sets the results data structure from method generated data. Results documents are defined by specs.
"""
core_logger.info('Building Complex results')
interacting_pair = cpdb_statistical_analysis_helper.interacting_pair_build(
interactions)
interactions = interactions.copy()
def simple_complex_indicator(interaction: pd.Series, suffix: str) -> str:
"""
Add simple/complex prefixes to interaction components
"""
if interaction['is_complex{}'.format(suffix)]:
return 'complex:{}'.format(interaction['name{}'.format(suffix)])
return 'simple:{}'.format(interaction['name{}'.format(suffix)])
interactions['partner_a'] = interactions.apply(
lambda interaction: simple_complex_indicator(interaction, '_1'),
axis=1)
interactions['partner_b'] = interactions.apply(
lambda interaction: simple_complex_indicator(interaction, '_2'),
axis=1)
significant_mean_rank, significant_means = cpdb_analysis_helper.build_significant_means(
mean_analysis, percent_analysis)
significant_means = significant_means.round(result_precision)
gene_columns = [
'{}_{}'.format(counts_data, suffix) for suffix in ('1', '2')
]
gene_renames = {
column: 'gene_{}'.format(suffix)
for column, suffix in zip(gene_columns, ['a', 'b'])
}
# Remove useless columns
interactions_data_result = pd.DataFrame(interactions[[
'id_cp_interaction', 'partner_a', 'partner_b', 'receptor_1',
'receptor_2', *gene_columns, 'annotation_strategy'
]].copy())
interactions_data_result = pd.concat(
[interacting_pair, interactions_data_result], axis=1, sort=False)
interactions_data_result['secreted'] = (interactions['secreted_1']
| interactions['secreted_2'])
interactions_data_result['is_integrin'] = (interactions['integrin_1']
| interactions['integrin_2'])
interactions_data_result.rename(columns={
**gene_renames, 'receptor_1': 'receptor_a',
'receptor_2': 'receptor_b'
},
inplace=True)
# Dedupe rows and filter only desired columns
interactions_data_result.drop_duplicates(inplace=True)
means_columns = [
'id_cp_interaction', 'interacting_pair', 'partner_a', 'partner_b',
'gene_a', 'gene_b', 'secreted', 'receptor_a', 'receptor_b',
'annotation_strategy', 'is_integrin'
]
interactions_data_result = interactions_data_result[means_columns]
mean_analysis = mean_analysis.round(result_precision)
# Round result decimals
for key, cluster_means in clusters_means.items():
clusters_means[key] = cluster_means.round(result_precision)
# Document 2
means_result = pd.concat([interactions_data_result, mean_analysis],
axis=1,
join='inner',
sort=False)
# Document 3
significant_means_result = pd.concat(
[interactions_data_result, significant_mean_rank, significant_means],
axis=1,
join='inner',
sort=False)
# Document 5
deconvoluted_result = deconvoluted_complex_result_build(
clusters_means, interactions, complex_compositions, counts, genes,
counts_data)
return means_result, significant_means_result, deconvoluted_result