diff --git a/CLIP/iCLIP.snakefile b/CLIP/iCLIP.snakefile
index 621a47def797d0f5613cbf26cafacc245b2ece13..40257c080969a945e308bb2a9a72104ae1187ab8 100644
--- a/CLIP/iCLIP.snakefile
+++ b/CLIP/iCLIP.snakefile
@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Blaise Li
+# Copyright (C) 2020-2023 Blaise Li
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
@@ -76,8 +76,21 @@ genome_db = genome_dict["db"][aligner]
# bed file binning the genome in 10nt bins
genome_binned = genome_dict["binned"]
annot_dir = genome_dict["annot_dir"]
-# TODO: figure out the difference between OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]
+# What are the difference between
+# OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]?
+# /!\ gene_ids_data_dir contains more conversion dicts,
+# but is not influenced by genome preparation customization,
+# like splitting of miRNAs into 3p and 5p.
+# Currently not used
convert_dir = genome_dict.get("convert_dir", gene_ids_data_dir)
+# For wormid2name, load in priority the one
+# that might contain custom gene names, like for splitted miRNAs
+with open(
+ genome_dict.get(
+ "converter",
+ OPJ(convert_dir, "wormid2name.pickle")),
+ "rb") as dict_file:
+ wormid2name = load(dict_file)
gene_lists_dir = genome_dict["gene_lists_dir"]
avail_id_lists = set(glob(OPJ(gene_lists_dir, "*_ids.txt")))
diff --git a/Degradome-seq/Degradome-seq.snakefile b/Degradome-seq/Degradome-seq.snakefile
index 36a43167047acb8b9d4c52d09848aec39e7feffa..58889de398258b24ec158659abe226010595ed63 100644
--- a/Degradome-seq/Degradome-seq.snakefile
+++ b/Degradome-seq/Degradome-seq.snakefile
@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Blaise Li
+# Copyright (C) 2020-2023 Blaise Li
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
@@ -107,8 +107,20 @@ genome_db = genome_dict["db"][aligner]
# bed file binning the genome in 10nt bins
genome_binned = genome_dict["binned"]
annot_dir = genome_dict["annot_dir"]
-# TODO: figure out the difference between OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]
+# What are the difference between
+# OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]?
+# /!\ gene_ids_data_dir contains more conversion dicts,
+# but is not influenced by genome preparation customization,
+# like splitting of miRNAs into 3p and 5p.
convert_dir = genome_dict.get("convert_dir", gene_ids_data_dir)
+# For wormid2name, load in priority the one
+# that might contain custom gene names, like for splitted miRNAs
+with open(
+ genome_dict.get(
+ "converter",
+ OPJ(convert_dir, "wormid2name.pickle")),
+ "rb") as dict_file:
+ wormid2name = load(dict_file)
gene_lists_dir = genome_dict["gene_lists_dir"]
avail_id_lists = set(glob(OPJ(gene_lists_dir, "*_ids.txt")))
@@ -509,9 +521,11 @@ rule compute_efficiency:
with open(OPJ(convert_dir, "wormid2cosmid.pickle"), "rb") as dict_file:
tpm_and_eff = tpm_and_eff.assign(cosmid=tpm_and_eff.apply(
column_converter(load(dict_file)), axis=1))
- with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
- tpm_and_eff = tpm_and_eff.assign(name=tpm_and_eff.apply(
- column_converter(load(dict_file)), axis=1))
+ #with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
+ # tpm_and_eff = tpm_and_eff.assign(name=tpm_and_eff.apply(
+ # column_converter(load(dict_file)), axis=1))
+ tpm_and_eff = tpm_and_eff.assign(name=tpm_and_eff.apply(
+ column_converter(wormid2name), axis=1))
tpm_and_eff = add_tags_column(tpm_and_eff, input.tags_table, "biotype")
tpm_and_eff.to_csv(output.eff_file, sep="\t", na_rep="NA")
@@ -538,9 +552,11 @@ rule gather_efficiency:
with open(OPJ(convert_dir, "wormid2cosmid.pickle"), "rb") as dict_file:
eff_data = eff_data.assign(cosmid=eff_data.apply(
column_converter(load(dict_file)), axis=1))
- with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
- eff_data = eff_data.assign(name=eff_data.apply(
- column_converter(load(dict_file)), axis=1))
+ #with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
+ # eff_data = eff_data.assign(name=eff_data.apply(
+ # column_converter(load(dict_file)), axis=1))
+ eff_data = eff_data.assign(name=eff_data.apply(
+ column_converter(wormid2name), axis=1))
#eff_data = add_tags_column(eff_data, input.tags_table, "biotype")
eff_data.to_csv(output.eff_file, sep="\t", na_rep="NA")
diff --git a/PRO-seq/PRO-seq.snakefile b/PRO-seq/PRO-seq.snakefile
index 0afa4e96fc2f51824deaedba196ba007970fe634..92bcc696ccbf507a941e7a04fe85bc13437e21f3 100644
--- a/PRO-seq/PRO-seq.snakefile
+++ b/PRO-seq/PRO-seq.snakefile
@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Blaise Li
+# Copyright (C) 2020-2023 Blaise Li
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
@@ -205,29 +205,29 @@ if isinstance(config["genome_dict"], (str, bytes)):
genome_dict = yload(fh)
else:
genome_dict = config["genome_dict"]
-# genome_dict = config.get("genome_dict", None)
-# if genome_dict is not None:
-if True:
- genome = genome_dict["name"]
- chrom_sizes = get_chrom_sizes(genome_dict["size"])
- chrom_sizes.update(valmap(int, genome_dict.get("extra_chromosomes", {})))
- genomelen = sum(chrom_sizes.values())
- genome_db = genome_dict["db"][aligner]
- # bed file binning the genome in 10nt bins
- genome_binned = genome_dict["binned"]
- annot_dir = genome_dict["annot_dir"]
- # TODO: figure out the difference between OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]
- convert_dir = genome_dict.get("convert_dir", gene_ids_data_dir)
- gene_lists_dir = genome_dict["gene_lists_dir"]
-else:
- genome = "C_elegans"
- chrom_sizes = get_chrom_sizes(config["genome_size"])
- genomelen = sum(chrom_sizes.values())
- genome_db = config["index"]
- genome_binned = f"/pasteur/entites/Mhe/Genomes/{genome}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/genome_binned_10.bed"
- annot_dir = config["annot_dir"]
- convert_dir = genome_dict.get("convert_dir", gene_ids_data_dir)
- gene_lists_dir = "/pasteur/entites/Mhe/bli/Gene_lists"
+genome = genome_dict["name"]
+chrom_sizes = get_chrom_sizes(genome_dict["size"])
+chrom_sizes.update(valmap(int, genome_dict.get("extra_chromosomes", {})))
+genomelen = sum(chrom_sizes.values())
+genome_db = genome_dict["db"][aligner]
+# bed file binning the genome in 10nt bins
+genome_binned = genome_dict["binned"]
+annot_dir = genome_dict["annot_dir"]
+convert_dir = genome_dict.get("convert_dir", gene_ids_data_dir)
+# What are the difference between
+# OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]?
+# /!\ gene_ids_data_dir contains more conversion dicts,
+# but is not influenced by genome preparation customization,
+# like splitting of miRNAs into 3p and 5p.
+# For wormid2name, load in priority the one
+# that might contain custom gene names, like for splitted miRNAs
+with open(
+ genome_dict.get(
+ "converter",
+ OPJ(convert_dir, "wormid2name.pickle")),
+ "rb") as dict_file:
+ wormid2name = load(dict_file)
+gene_lists_dir = genome_dict["gene_lists_dir"]
avail_id_lists = set(glob(OPJ(gene_lists_dir, "*_ids.txt")))
#gene_lists_dir = config["gene_lists_dir"]
#local_annot_dir = config["local_annot_dir"]
@@ -1260,8 +1260,9 @@ rule differential_expression:
######################
with open(OPJ(convert_dir, "wormid2cosmid.pickle"), "rb") as dict_file:
res = res.assign(cosmid=res.apply(column_converter(load(dict_file)), axis=1))
- with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
- res = res.assign(name=res.apply(column_converter(load(dict_file)), axis=1))
+ #with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
+ # res = res.assign(name=res.apply(column_converter(load(dict_file)), axis=1))
+ res = res.assign(name=res.apply(column_converter(wormid2name), axis=1))
# Just to see if column_converter works also with named column, and not just index:
# with open(OPJ(convert_dir, "cosmid2name.pickle"), "rb") as dict_file:
# res = res.assign(name=res.apply(column_converter(load(dict_file), "cosmid"), axis=1))
diff --git a/RNA_Seq_Cecere/RNA-seq.snakefile b/RNA_Seq_Cecere/RNA-seq.snakefile
index 0ee820e0265319ce50b2971ead25243e39b7149b..9723776207cebe1ee2c5aedec68f03f7386362b2 100644
--- a/RNA_Seq_Cecere/RNA-seq.snakefile
+++ b/RNA_Seq_Cecere/RNA-seq.snakefile
@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Blaise Li
+# Copyright (C) 2020-2023 Blaise Li
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
@@ -286,8 +286,20 @@ genome_db = genome_dict["db"][aligner]
# bed file binning the genome in 10nt bins
genome_binned = genome_dict["binned"]
annot_dir = genome_dict["annot_dir"]
-# TODO: figure out the difference between OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]
+# What are the difference between
+# OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]?
+# /!\ gene_ids_data_dir contains more conversion dicts,
+# but is not influenced by genome preparation customization,
+# like splitting of miRNAs into 3p and 5p.
convert_dir = genome_dict.get("convert_dir", gene_ids_data_dir)
+# For wormid2name, load in priority the one
+# that might contain custom gene names, like for splitted miRNAs
+with open(
+ genome_dict.get(
+ "converter",
+ OPJ(convert_dir, "wormid2name.pickle")),
+ "rb") as dict_file:
+ wormid2name = load(dict_file)
gene_lists_dir = genome_dict["gene_lists_dir"]
avail_id_lists = set(glob(OPJ(gene_lists_dir, "*_ids.txt")))
#COUNTERS = config["counters"]
@@ -1809,8 +1821,9 @@ rule compute_RPM_folds:
######################
with open(OPJ(convert_dir, "wormid2cosmid.pickle"), "rb") as dict_file:
lfc = lfc.assign(cosmid=lfc.apply(column_converter(load(dict_file)), axis=1))
- with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
- lfc = lfc.assign(name=lfc.apply(column_converter(load(dict_file)), axis=1))
+ #with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
+ #lfc = lfc.assign(name=lfc.apply(column_converter(load(dict_file)), axis=1))
+ lfc = lfc.assign(name=lfc.apply(column_converter(wormid2name), axis=1))
pd.concat((RPM, lfc), axis=1).to_csv(output.fold_results, sep="\t")
@@ -1871,8 +1884,9 @@ rule differential_expression:
######################
with open(OPJ(convert_dir, "wormid2cosmid.pickle"), "rb") as dict_file:
res = res.assign(cosmid=res.apply(column_converter(load(dict_file)), axis=1))
- with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
- res = res.assign(name=res.apply(column_converter(load(dict_file)), axis=1))
+ #with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
+ #res = res.assign(name=res.apply(column_converter(load(dict_file)), axis=1))
+ res = res.assign(name=res.apply(column_converter(wormid2name), axis=1))
# Just to see if column_converter works also with named column, and not just index:
# with open(OPJ(convert_dir, "cosmid2name.pickle"), "rb") as dict_file:
# res = res.assign(name=res.apply(column_converter(load(dict_file), "cosmid"), axis=1))
diff --git a/Ribo-seq/Ribo-seq.snakefile b/Ribo-seq/Ribo-seq.snakefile
index 0a26b8e3e02d319bb271940cc238420ec0fb2d42..b1c0b2d11d6a9286da97c9f29a5051f042d18a4b 100644
--- a/Ribo-seq/Ribo-seq.snakefile
+++ b/Ribo-seq/Ribo-seq.snakefile
@@ -1,4 +1,4 @@
-# Copyright (C) 2020 Blaise Li
+# Copyright (C) 2020-2023 Blaise Li
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
@@ -345,8 +345,20 @@ genome_db = genome_dict["db"][aligner]
genome_binned = genome_dict["binned"]
annot_dir = genome_dict["annot_dir"]
exon_lengths_file = OPJ(annot_dir, "union_exon_lengths.txt"),
-# TODO: figure out the difference between OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]
+# What are the difference between
+# OPJ(convert_dir, "wormid2name.pickle") and genome_dict["converter"]?
+# /!\ gene_ids_data_dir contains more conversion dicts,
+# but is not influenced by genome preparation customization,
+# like splitting of miRNAs into 3p and 5p.
convert_dir = genome_dict.get("convert_dir", gene_ids_data_dir)
+# For wormid2name, load in priority the one
+# that might contain custom gene names, like for splitted miRNAs
+with open(
+ genome_dict.get(
+ "converter",
+ OPJ(convert_dir, "wormid2name.pickle")),
+ "rb") as dict_file:
+ wormid2name = load(dict_file)
gene_lists_dir = genome_dict["gene_lists_dir"]
avail_id_lists = set(glob(OPJ(gene_lists_dir, "*_ids.txt")))
index = genome_db
@@ -1305,8 +1317,9 @@ rule differential_expression:
######################
with open(OPJ(convert_dir, "wormid2cosmid.pickle"), "rb") as dict_file:
res = res.assign(cosmid=res.apply(column_converter(load(dict_file)), axis=1))
- with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
- res = res.assign(name=res.apply(column_converter(load(dict_file)), axis=1))
+ #with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
+ # res = res.assign(name=res.apply(column_converter(load(dict_file)), axis=1))
+ res = res.assign(name=res.apply(column_converter(wormid2name), axis=1))
# Just to see if column_converter works also with named column, and not just index:
# with open(OPJ(convert_dir, "cosmid2name.pickle"), "rb") as dict_file:
# res = res.assign(name=res.apply(column_converter(load(dict_file), "cosmid"), axis=1))
@@ -1536,9 +1549,11 @@ rule compute_efficiency:
with open(OPJ(convert_dir, "wormid2cosmid.pickle"), "rb") as dict_file:
tpm_and_eff = tpm_and_eff.assign(cosmid=tpm_and_eff.apply(
column_converter(load(dict_file)), axis=1))
- with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
- tpm_and_eff = tpm_and_eff.assign(name=tpm_and_eff.apply(
- column_converter(load(dict_file)), axis=1))
+ #with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
+ # tpm_and_eff = tpm_and_eff.assign(name=tpm_and_eff.apply(
+ # column_converter(load(dict_file)), axis=1))
+ tpm_and_eff = tpm_and_eff.assign(name=tpm_and_eff.apply(
+ column_converter(wormid2name), axis=1))
tpm_and_eff = add_tags_column(tpm_and_eff, input.tags_table, "biotype")
tpm_and_eff.to_csv(output.eff_file, sep="\t", na_rep="NA")
@@ -1565,9 +1580,11 @@ rule gather_efficiency:
with open(OPJ(convert_dir, "wormid2cosmid.pickle"), "rb") as dict_file:
eff_data = eff_data.assign(cosmid=eff_data.apply(
column_converter(load(dict_file)), axis=1))
- with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
- eff_data = eff_data.assign(name=eff_data.apply(
- column_converter(load(dict_file)), axis=1))
+ #with open(OPJ(convert_dir, "wormid2name.pickle"), "rb") as dict_file:
+ # eff_data = eff_data.assign(name=eff_data.apply(
+ # column_converter(load(dict_file)), axis=1))
+ eff_data = eff_data.assign(name=eff_data.apply(
+ column_converter(wormid2name), axis=1))
#eff_data = add_tags_column(eff_data, input.tags_table, "biotype")
eff_data.to_csv(output.eff_file, sep="\t", na_rep="NA")
diff --git a/small_RNA-seq/small_RNA-seq.snakefile b/small_RNA-seq/small_RNA-seq.snakefile
index 237118666af56162b1126a4a10781c6711f7d351..8d65830c1b571c87ef0f09e881d2d2f095a2a2f3 100644
--- a/small_RNA-seq/small_RNA-seq.snakefile
+++ b/small_RNA-seq/small_RNA-seq.snakefile
@@ -1,4 +1,4 @@
-# Copyright (C) 2020-2022 Blaise Li
+# Copyright (C) 2020-2023 Blaise Li
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by