From cb228b23853775360556aa9a5d9400b8e450bbc4 Mon Sep 17 00:00:00 2001
From: Fontrodona Nicolas <nicolas.fontrodona@ens-lyon.fr>
Date: Fri, 6 Nov 2020 16:08:57 +0100
Subject: [PATCH] modification of get_community_file function to be able to
chose the subfolder in which we want to create file
---
src/find_interaction_cluster/config.py | 10 +++++-----
src/find_interaction_cluster/nt_and_community.py | 14 ++++++--------
src/find_interaction_cluster/sf_and_communities.py | 11 +++++++----
3 files changed, 18 insertions(+), 17 deletions(-)
diff --git a/src/find_interaction_cluster/config.py b/src/find_interaction_cluster/config.py
index 4c6cbcfb..3c3d262c 100644
--- a/src/find_interaction_cluster/config.py
+++ b/src/find_interaction_cluster/config.py
@@ -37,7 +37,7 @@ def get_weight_folder(weight: int, global_weight: int):
def get_community_file(project: str, weight: int, global_weight: int,
same_gene: bool, feature: str = 'exon',
- ext: str = ".txt", stat: bool = False):
+ ext: str = ".txt", sub_fold: str = ''):
"""
Get the output file of interest.
@@ -51,13 +51,12 @@ def get_community_file(project: str, weight: int, global_weight: int,
same gene
:param the kind of feature analyzed
:param ext: The file extension
- :param stat: True to place the result in 'sf_community_enrichment' \
- subfolder
+ :param subfolder: if filled, then the data are recovered from a subfolder
:return: The filename of interest
"""
folder = get_weight_folder(weight, global_weight)
- if stat:
- folder = folder / 'sf_community_enrichment'
+ if sub_fold != '':
+ folder = folder / sub_fold
folder.mkdir(exist_ok=True, parents=True)
if global_weight != 0:
project = f"global-weight-{global_weight}"
@@ -116,4 +115,5 @@ class ConfigGraph:
get_hip_folder = get_hipmcl_folder
get_hipmcl_prog = get_hipmcl_prog
good_projects = get_good_project()
+ ppi_threshold = 700
diff --git a/src/find_interaction_cluster/nt_and_community.py b/src/find_interaction_cluster/nt_and_community.py
index 3f769be1..0b7a0140 100644
--- a/src/find_interaction_cluster/nt_and_community.py
+++ b/src/find_interaction_cluster/nt_and_community.py
@@ -253,7 +253,7 @@ def get_stat_nt_communities(df: pd.DataFrame, project: str, weight: int,
global_weight,
same_gene, feature,
f"{nt}_stat.txt",
- True)
+ "sf_community_enrichment")
nfolder = outfile.parent / "nt_analysis"
nfolder.mkdir(exist_ok=True, parents=True)
noutfile = nfolder / outfile.name
@@ -269,7 +269,7 @@ def get_stat_nt_communities(df: pd.DataFrame, project: str, weight: int,
global_weight,
same_gene, feature,
f"{nt}_VS_CTRL_stat.txt",
- True)
+ "sf_community_enrichment")
noutfile_ctrl = nfolder / outfile_ctrl.name
sum_df.to_csv(noutfile_ctrl, sep="\t", index=False)
return pd.Series(res)
@@ -345,11 +345,9 @@ def multiple_nt_lmm_launcher(ps: int, weights: List[int],
else:
df = create_dataframe(project, weight, global_weight, same_gene,
feature)
- nfile_table = ConfigGraph.get_community_file(project, weight,
- global_weight,
- same_gene, feature,
- f"_nt_table.txt",
- True)
+ nfile_table = ConfigGraph.get_community_file(
+ project, weight, global_weight, same_gene, feature,
+ f"_nt_table.txt", "sf_community_enrichment")
df.to_csv(nfile_table, sep="\t", index=False)
dic_df[ckey] = df
args = [df, project, weight, global_weight, same_gene, nt, feature,
@@ -370,7 +368,7 @@ def multiple_nt_lmm_launcher(ps: int, weights: List[int],
dic_project[project],
same_gene, feature,
f"lmm-nt_stat.txt",
- True)
+ "sf_community_enrichment")
nfolder = outfile.parent / "nt_analysis"
noutfile = nfolder / outfile.name
fdf.to_csv(noutfile, sep="\t", index=False)
diff --git a/src/find_interaction_cluster/sf_and_communities.py b/src/find_interaction_cluster/sf_and_communities.py
index b950c8b2..ac965851 100644
--- a/src/find_interaction_cluster/sf_and_communities.py
+++ b/src/find_interaction_cluster/sf_and_communities.py
@@ -182,7 +182,7 @@ def glmm_maker(expanded_df: pd.DataFrame, outfile: Path) -> float:
... "%reg in community": [40, 42.85], 'pval': [1, 0.5], 'padj': [1, 1]})
>>> e_df = expand_dataframe(d)
>>> outfile = ConfigGraph.get_community_file("Test", 1, 1, True,
- ... "_stat.txt", True)
+ ... "_stat.txt", "sf_community_enrichment")
>>> glmm_maker(e_df, outfile)
1.0
"""
@@ -235,7 +235,8 @@ def glmm_statistics(df: pd.DataFrame, sf_name: str, reg: str,
expanded_df = expand_dataframe(ndf)
outfile = ConfigGraph.get_community_file(project, weight, global_weight,
same_gene, feature,
- f"{sf_name}_{reg}_stat.txt", True)
+ f"{sf_name}_{reg}_stat.txt",
+ "sf_community_enrichment")
noutfold = outfile.parent / "expanded_df"
noutfold.mkdir(exist_ok=True, parents=True)
noutfile = noutfold / outfile.name
@@ -411,7 +412,8 @@ def multiple_stat_launcher(ps: int, weights: List[int],
outfile = ConfigGraph.get_community_file(project, weight,
dic_project[project],
same_gene, feature,
- "_stat.txt", True)
+ "_stat.txt",
+ "sf_community_enrichment")
df.to_csv(outfile, sep="\t", index=False)
glm_df = pd.DataFrame(list_series)
glm_df["padj"] = multipletests(glm_df['pval'].values,
@@ -419,7 +421,8 @@ def multiple_stat_launcher(ps: int, weights: List[int],
outfile = ConfigGraph.get_community_file(project, weight,
dic_project[project],
same_gene, feature,
- "_glmm_stat.txt", True)
+ "_glmm_stat.txt",
+ "sf_community_enrichment")
glm_df.to_csv(outfile, sep="\t", index=False)
--
GitLab