From 17bfe0b6c3ad4670b800557c56a782fc972517c2 Mon Sep 17 00:00:00 2001
From: Blaise Li <blaise.li__git@nsup.org>
Date: Tue, 12 Dec 2017 18:12:26 +0100
Subject: [PATCH] Folder rearrangement.
For RNA-seq and GRO-seq, log and data directories are now subdirectories
of output directories. local_annot_dir also moves as subdirectory of
GRO-seq output.
---
PRO-seq/PRO-seq.snakefile | 7 ++++---
RNA_Seq_Cecere/RNA-seq.snakefile | 4 ++--
2 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/PRO-seq/PRO-seq.snakefile b/PRO-seq/PRO-seq.snakefile
index 4ef50ee..de075fc 100644
--- a/PRO-seq/PRO-seq.snakefile
+++ b/PRO-seq/PRO-seq.snakefile
@@ -117,8 +117,6 @@ ANNOT_BIOTYPES = config["annot_biotypes"]
#METAGENE_BIOTYPES=["protein_coding", "DNA_transposons_rmsk", "RNA_transposons_rmsk"]
METAGENE_BIOTYPES=["protein_coding"]
ID_LISTS = ["lfc_statuses", "germline_specific", "histone", "spermatogenic_Ortiz_2014", "oogenic_Ortiz_2014"]
-log_dir = config["log_dir"]
-data_dir = config["data_dir"]
annot_dir = config["annot_dir"]
gene_lists_dir = "/pasteur/entites/Mhe/bli/Gene_lists"
avail_id_lists = set(glob(OPJ(gene_lists_dir, "*_ids.txt")))
@@ -126,11 +124,14 @@ chrom_sizes = get_chrom_sizes(config["genome_size"])
genomelen = sum(chrom_sizes.values())
genome_binned = "/pasteur/entites/Mhe/Genomes/C_elegans/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/genome_binned_10.bed"
#gene_lists_dir = config["gene_lists_dir"]
-local_annot_dir = config["local_annot_dir"]
+#local_annot_dir = config["local_annot_dir"]
aligner = config["aligner"]
index = config["index"]
convert_dir = config["convert_dir"]
output_dir = config["output_dir"]
+log_dir = OPJ(output_dir, "logs")
+data_dir = OPJ(output_dir, "data")
+local_annot_dir = OPJ(output_dir, "annotations")
# Used to skip some genotype x treatment x replicate number combinations
# when some of them were not sequenced
forbidden = {frozenset(wc_comb.items()) for wc_comb in config["missing"]}
diff --git a/RNA_Seq_Cecere/RNA-seq.snakefile b/RNA_Seq_Cecere/RNA-seq.snakefile
index 971b67b..d79a509 100644
--- a/RNA_Seq_Cecere/RNA-seq.snakefile
+++ b/RNA_Seq_Cecere/RNA-seq.snakefile
@@ -106,8 +106,6 @@ COND_COLUMNS = pd.DataFrame(CONDITIONS).assign(
BIOTYPES = config["biotypes"]
ID_LISTS = ["lfc_statuses", "germline_specific", "histone", "spermatogenic_Ortiz_2014", "oogenic_Ortiz_2014"]
-log_dir = config["log_dir"]
-data_dir = config["data_dir"]
annot_dir = config["annot_dir"]
gene_lists_dir = "/pasteur/entites/Mhe/bli/Gene_lists"
avail_id_lists = set(glob(OPJ(gene_lists_dir, "*_ids.txt")))
@@ -124,6 +122,8 @@ aligner = config["aligner"]
COUNTERS = ["feature_count"]
convert_dir = config["convert_dir"]
output_dir = config["output_dir"]
+log_dir = OPJ(output_dir, "logs")
+data_dir = OPJ(output_dir, "data")
SIZE_FACTORS = ["protein_coding", "miRNA", "median_ratio_to_pseudo_ref"]
assert set(SIZE_FACTORS).issubset(set(BIOTYPES) | {"median_ratio_to_pseudo_ref"})
--
GitLab