From d18d5994709595b4396513a79dbebff1368c92cf Mon Sep 17 00:00:00 2001
From: BIOPZ-Gypas Foivos <foivos.gypas@unibas.ch>
Date: Wed, 28 Nov 2018 19:48:39 +0100
Subject: [PATCH] Creation of bed file for the CDS coordinates
---
snakemake/prepare_annotation/Snakefile | 22 ++++++++++++++++++++--
snakemake/process_data/Snakefile | 2 +-
2 files changed, 21 insertions(+), 3 deletions(-)
diff --git a/snakemake/prepare_annotation/Snakefile b/snakemake/prepare_annotation/Snakefile
index 7240fe2..5320edf 100644
--- a/snakemake/prepare_annotation/Snakefile
+++ b/snakemake/prepare_annotation/Snakefile
@@ -1,6 +1,6 @@
configfile: "config.yaml"
-localrules: create_output_and_log_directories, create_tab_delimited_CDS_file, finish
+localrules: create_output_and_log_directories, create_tab_delimited_CDS_file, create_bed_CDS_file, finish
#################################################################################
### Finish rule
@@ -10,7 +10,7 @@ rule finish:
input:
idx_other = os.path.join(config["output_dir"], "other_RNAs_sequence.idx"),
idx_transcripts = os.path.join(config["output_dir"], "longest_pc_transcript_per_gene.idx"),
- tsv = os.path.join(config["output_dir"], "transcript_id_gene_id_CDS.tsv")
+ bed = os.path.join(config["output_dir"], "transcript_id_gene_id_CDS.bed")
#################################################################################
### Create output and log directories
@@ -115,6 +115,24 @@ rule create_tab_delimited_CDS_file:
--fasta {input.transcripts} \
--out {output.tsv}) &> {log}"
+#################################################################################
+### BED CDS table
+#################################################################################
+
+rule create_bed_CDS_file:
+ input:
+ tsv = os.path.join(config["output_dir"], "transcript_id_gene_id_CDS.tsv")
+ output:
+ bed = os.path.join(config["output_dir"], "transcript_id_gene_id_CDS.bed")
+ params:
+ cluster_log = os.path.join(config["cluster_log"], "create_bed_CDS_file.log")
+ log:
+ os.path.join(config["local_log"], "create_bed_CDS_file.log")
+ # singularity:
+ # "docker://zavolab/python_htseq_biopython:3.6.5_0.10.0_1.71"
+ shell:
+ "(tail -n+2 {input.tsv} | awk \'{{print $1 \"\t\" $3-1 \"\t\" $4 \"\t\" $2 }}\' > {output.bed}) &> {log}"
+
#################################################################################
### Generate segemehl index for transcripts
#################################################################################
diff --git a/snakemake/process_data/Snakefile b/snakemake/process_data/Snakefile
index d74b958..a1db044 100644
--- a/snakemake/process_data/Snakefile
+++ b/snakemake/process_data/Snakefile
@@ -233,7 +233,7 @@ rule remove_multimappers:
rule sam2bam_sort_and_index:
input:
- sam = os.path.join(config["output_dir"], "{sample}/transcripts.mapped.sam")
+ sam = os.path.join(config["output_dir"], "{sample}/transcripts.mapped.unique.sam")
output:
bam = os.path.join(config["output_dir"], "{sample}/transcripts.mapped.unique.sorted.bam"),
bai = os.path.join(config["output_dir"], "{sample}/transcripts.mapped.unique.sorted.bam.bai")
--
GitLab