From 3796e19bc39f59b7a88ff02d740bc55369bcc64e Mon Sep 17 00:00:00 2001
From: CJ Herrmann <christina.herrmann@unibas.ch>
Date: Tue, 13 Jul 2021 22:42:19 +0200
Subject: [PATCH] added cutadapt -m=1 to snakefiles to avoid empty reads,
updated doc
---
pipeline_documentation.md | 4 ++--
tests/input_files/rule_config.yaml | 12 ++++++++----
workflow/rules/paired_end.snakefile.smk | 2 ++
workflow/rules/single_end.snakefile.smk | 2 ++
4 files changed, 14 insertions(+), 6 deletions(-)
diff --git a/pipeline_documentation.md b/pipeline_documentation.md
index 5f96d48..e7a4be1 100644
--- a/pipeline_documentation.md
+++ b/pipeline_documentation.md
@@ -557,7 +557,7 @@ Remove adapter sequences from reads with
- Adapters to be removed; specify in sample table columns `fq1_3p`, `fq1_5p`,
`fq2_3p`, `fq2_5p`
- **rule_config.yaml:**
- - `-m 10`: Discard processed reads that are shorter than 10 (default 0, that might cause problems in downstream programs)
+ - `-m 10`: Discard processed reads that are shorter than 10 (default 0; Because empty reads will cause problems in downstream programs, -m=1 is hardcoded in the snakefile. That value will be overwritten by the value specified in `rule_config.yaml`)
- `-n 2`: search for all the given adapter sequences repeatedly, either until
no adapter match was found or until 2 rounds have been performed. (default 1)
@@ -579,7 +579,7 @@ Remove poly(A) tails from reads with
- **samples.tsv**
- Poly(A) stretches to be removed; specify in sample table columns `fq1_polya` and `fq2_polya`
- **rule_config.yaml**
- - `-m 10`: Discard processed reads that are shorter than 10 (default 0, that might cause problems in downstream programs)
+ - `-m 10`: Discard processed reads that are shorter than 10 (default 0; Because empty reads will cause problems in downstream programs, -m=1 is hardcoded in the snakefile. That value will be overwritten by the value specified in `rule_config.yaml`)
- `-O 1`: minimal overlap of 1 (default: 3)
- **Output**
- Reads file (`.fastq.gz`); used in
diff --git a/tests/input_files/rule_config.yaml b/tests/input_files/rule_config.yaml
index 2cdec07..c7f1242 100644
--- a/tests/input_files/rule_config.yaml
+++ b/tests/input_files/rule_config.yaml
@@ -96,23 +96,27 @@ prepare_bigWig:
remove_adapters_cutadapt:
# search for all the given adapter sequences repeatedly, either until no adapter match was found or until n rounds have been performed. (default 1, ZARP recommends 2)
-n: '2'
- # Discard processed reads that are shorter than 10 (default 0, ZARP strongly recommends m > 0, because empty reads might cause problems in downstream programs)
+ # Discard processed reads that are shorter than m (default 0, ZARP strongly recommends m > 0, because empty reads will cause problems in downstream programs;
+ # Hardcoded to -m=1 in both snakefiles; that value will be overwritten by the -m value specified here!)
-m: '10'
pe_remove_adapters_cutadapt:
# search for all the given adapter sequences repeatedly, either until no adapter match was found or until n rounds have been performed. (default 1, ZARP recommends 2)
-n: '2'
- # Discard processed reads that are shorter than 10 (default 0, ZARP strongly recommends m > 0, because empty reads might cause problems in downstream programs)
+ # Discard processed reads that are shorter than m (default 0, ZARP strongly recommends m > 0, because empty reads will cause problems in downstream programs;
+ # Hardcoded to -m=1 in both snakefiles; that value will be overwritten by the -m value specified here!)
-m: '10'
remove_polya_cutadapt:
- # Discard processed reads that are shorter than 10 (default 0, ZARP strongly recommends m > 0, because empty reads might cause problems in downstream programs)
+ # Discard processed reads that are shorter than m (default 0, ZARP strongly recommends m > 0, because empty reads will cause problems in downstream programs;
+ # Hardcoded to -m=1 in both snakefiles; that value will be overwritten by the -m value specified here!)
-m: '10'
# Minimal overlap of adapter and read (default 3, ZARP recommends 1 in order to remove all 3' As)
-O: '1'
pe_remove_polya_cutadapt:
- # Discard processed reads that are shorter than 10 (default 0, ZARP strongly recommends m > 0, because empty reads might cause problems in downstream programs)
+ # Discard processed reads that are shorter than m (default 0, ZARP strongly recommends m > 0, because empty reads will cause problems in downstream programs;
+ # Hardcoded to -m=1 in both snakefiles; that value will be overwritten by the -m value specified here!)
-m: '10'
# Minimal overlap of adapter and read (default 3, ZARP recommends 1 in order to remove all 3' As)
-O: '1'
diff --git a/workflow/rules/paired_end.snakefile.smk b/workflow/rules/paired_end.snakefile.smk
index 37c5546..76a88f1 100644
--- a/workflow/rules/paired_end.snakefile.smk
+++ b/workflow/rules/paired_end.snakefile.smk
@@ -79,6 +79,7 @@ rule pe_remove_adapters_cutadapt:
-g {params.adapter_5_mate1} \
-A {params.adapter_3_mate2} \
-G {params.adapter_5_mate2} \
+ -m 1 \
{params.additional_params} \
-o {output.reads1} \
-p {output.reads2} \
@@ -177,6 +178,7 @@ rule pe_remove_polya_cutadapt:
-g {params.polya_5_mate1} \
-A {params.polya_3_mate2} \
-G {params.polya_5_mate2} \
+ -m 1 \
{params.additional_params} \
-o {output.reads1} \
-p {output.reads2} \
diff --git a/workflow/rules/single_end.snakefile.smk b/workflow/rules/single_end.snakefile.smk
index e270aba..cd7bb1d 100644
--- a/workflow/rules/single_end.snakefile.smk
+++ b/workflow/rules/single_end.snakefile.smk
@@ -66,6 +66,7 @@ rule remove_adapters_cutadapt:
-j {threads} \
-a {params.adapters_3} \
-g {params.adapters_5} \
+ -m 1 \
{params.additional_params} \
-o {output.reads} \
{input.reads}) \
@@ -140,6 +141,7 @@ rule remove_polya_cutadapt:
-j {threads} \
-a {params.polya_3} \
-g {params.polya_5} \
+ -m 1 \
{params.additional_params} \
-o {output.reads} \
{input.reads};) \
--
GitLab