From 6804ea67615b183abe80cdd03a0e359a8229d47e Mon Sep 17 00:00:00 2001
From: Dominik Burri <dominik.burri@unibas.ch>
Date: Fri, 26 Feb 2021 15:56:27 +0100
Subject: [PATCH] Remove unnecessary files in the results directory
---
Snakefile | 68 ++++++++++---------
tests/test_alfa/test.sh | 2 +
tests/test_create_dag_image/test.sh | 2 +
tests/test_create_rule_graph/test.sh | 2 +
.../expected_output.md5 | 18 -----
tests/test_integration_workflow/test.local.sh | 2 +
tests/test_integration_workflow/test.slurm.sh | 2 +
.../expected_output.md5 | 18 -----
.../test.local.sh | 2 +
.../test.slurm.sh | 2 +
workflow/rules/paired_end.snakefile.smk | 55 +++++++++++----
workflow/rules/single_end.snakefile.smk | 47 ++++++++++---
12 files changed, 127 insertions(+), 93 deletions(-)
diff --git a/Snakefile b/Snakefile
index 3ce2e93..46f802b 100644
--- a/Snakefile
+++ b/Snakefile
@@ -159,7 +159,7 @@ rule fastqc:
shell:
"(mkdir -p {output.outdir}; \
- fastqc --outdir {output.outdir} {input.reads}) \
+ fastqc --outdir {output.outdir} --threads {threads} {input.reads}) \
1> {log.stdout} 2> {log.stderr}"
@@ -169,16 +169,16 @@ rule create_index_star:
"""
input:
genome = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'genome',
search_id='organism',
- search_value=wildcards.organism),
+ search_value=wildcards.organism)),
gtf = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'gtf',
search_id='organism',
- search_value=wildcards.organism)
+ search_value=wildcards.organism))
output:
chromosome_info = os.path.join(
@@ -250,11 +250,11 @@ rule extract_transcriptome:
search_id='organism',
search_value=wildcards.organism)
output:
- transcriptome = os.path.join(
+ transcriptome = temp(os.path.join(
config['output_dir'],
"transcriptome",
"{organism}",
- "transcriptome.fa")
+ "transcriptome.fa"))
log:
stderr = os.path.join(
@@ -292,11 +292,11 @@ rule concatenate_transcriptome_and_genome:
search_value=wildcards.organism)
output:
- genome_transcriptome = os.path.join(
+ genome_transcriptome = temp(os.path.join(
config['output_dir'],
"transcriptome",
"{organism}",
- "genome_transcriptome.fa")
+ "genome_transcriptome.fa"))
singularity:
"docker://bash:5.0.16"
@@ -413,9 +413,9 @@ rule extract_transcripts_as_bed12:
get_sample('gtf')
output:
- bed12 = os.path.join(
+ bed12 = temp(os.path.join(
config['output_dir'],
- "full_transcripts_protein_coding.bed")
+ "full_transcripts_protein_coding.bed"))
singularity:
"docker://zavolab/zgtf:0.1"
@@ -515,12 +515,12 @@ rule calculate_TIN_scores:
"full_transcripts_protein_coding.bed")
output:
- TIN_score = os.path.join(
+ TIN_score = temp(os.path.join(
config['output_dir'],
"samples",
"{sample}",
"TIN",
- "TIN_score.tsv")
+ "TIN_score.tsv"))
params:
sample = "{sample}"
@@ -937,30 +937,32 @@ rule star_rpm:
search_value=wildcards.sample))
output:
- str1 = os.path.join(
+ str1 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"STAR_coverage",
- "{sample}_Signal.Unique.str1.out.bg"),
- str2 = os.path.join(
+ "{sample}_Signal.Unique.str1.out.bg")),
+ str2 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"STAR_coverage",
- "{sample}_Signal.UniqueMultiple.str1.out.bg"),
- str3 = os.path.join(
+ "{sample}_Signal.UniqueMultiple.str1.out.bg")),
+ str3 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"STAR_coverage",
- "{sample}_Signal.Unique.str2.out.bg"),
- str4 = os.path.join(
+ "{sample}_Signal.Unique.str2.out.bg")),
+ str4 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"STAR_coverage",
- "{sample}_Signal.UniqueMultiple.str2.out.bg")
+ "{sample}_Signal.UniqueMultiple.str2.out.bg"))
+
+ shadow: "full"
params:
out_dir = lambda wildcards, output:
@@ -1034,20 +1036,20 @@ rule rename_star_rpm_for_alfa:
search_value=wildcards.sample))
output:
- plus = os.path.join(
+ plus = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"ALFA",
"{unique}",
- "{sample}.{unique}.plus.bg"),
- minus = os.path.join(
+ "{sample}.{unique}.plus.bg")),
+ minus = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"ALFA",
"{unique}",
- "{sample}.{unique}.minus.bg")
+ "{sample}.{unique}.minus.bg"))
params:
orientation = lambda wildcards:
@@ -1081,10 +1083,10 @@ rule generate_alfa_index:
''' Generate ALFA index files from sorted GTF file '''
input:
gtf = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'gtf',
search_id='organism',
- search_value=wildcards.organism),
+ search_value=wildcards.organism)),
chr_len = os.path.join(
config["star_indexes"],
@@ -1164,20 +1166,20 @@ rule alfa_qc:
"sorted_genes.stranded.ALFA_index")
output:
- biotypes = os.path.join(
+ biotypes = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"ALFA",
"{unique}",
- "ALFA_plots.Biotypes.pdf"),
- categories = os.path.join(
+ "ALFA_plots.Biotypes.pdf")),
+ categories = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"ALFA",
"{unique}",
- "ALFA_plots.Categories.pdf"),
+ "ALFA_plots.Categories.pdf")),
table = os.path.join(
config["output_dir"],
"samples",
@@ -1382,13 +1384,13 @@ rule sort_bed_4_big:
"{sample}.{unique}.{strand}.bg")
output:
- sorted_bg = os.path.join(
+ sorted_bg = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
"bigWig",
"{unique}",
- "{sample}_{unique}_{strand}.sorted.bg")
+ "{sample}_{unique}_{strand}.sorted.bg"))
singularity:
"docker://cjh4zavolab/bedtools:2.27"
diff --git a/tests/test_alfa/test.sh b/tests/test_alfa/test.sh
index 1472685..5389734 100755
--- a/tests/test_alfa/test.sh
+++ b/tests/test_alfa/test.sh
@@ -33,6 +33,8 @@ snakemake \
--use-singularity \
--singularity-args="--bind ${PWD}/../input_files,${PWD}/../../images" \
--verbose \
+ --notemp \
+ --no-hooks \
results/ALFA/ALFA_plots_mqc.png
# Check md5 sum of some output files
diff --git a/tests/test_create_dag_image/test.sh b/tests/test_create_dag_image/test.sh
index afd8de4..1c954dd 100755
--- a/tests/test_create_dag_image/test.sh
+++ b/tests/test_create_dag_image/test.sh
@@ -26,5 +26,7 @@ snakemake \
--printshellcmds \
--dryrun \
--verbose \
+ --notemp \
+ --no-hooks \
| dot -Tsvg > "../../images/dag_test_workflow.svg"
diff --git a/tests/test_create_rule_graph/test.sh b/tests/test_create_rule_graph/test.sh
index 51e5383..287e08d 100755
--- a/tests/test_create_rule_graph/test.sh
+++ b/tests/test_create_rule_graph/test.sh
@@ -26,5 +26,7 @@ snakemake \
--printshellcmds \
--dryrun \
--verbose \
+ --notemp \
+ --no-hooks \
| dot -Tsvg > "../../images/rule_graph.svg"
diff --git a/tests/test_integration_workflow/expected_output.md5 b/tests/test_integration_workflow/expected_output.md5
index 9f1b02d..4093ded 100644
--- a/tests/test_integration_workflow/expected_output.md5
+++ b/tests/test_integration_workflow/expected_output.md5
@@ -20,7 +20,6 @@ ea36f062eedc7f54ceffea2b635a25a8 results/star_indexes/homo_sapiens/75/STAR_inde
500dd49da40b16799aba62aa5cf239ba results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.remove_polya_mate1.fastq
e90e31db1ce51d930645eb74ff70d21b results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.remove_adapters_mate2.fastq
1c0796d7e0bdab0e99780b2e11d80c19 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.remove_polya_mate2.fastq
-d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/map_genome/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.SJ.out.tab
9896744dd90ff3eef00c91fa1f721366 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq1/synthetic_10_reads_paired_synthetic_10_reads_paired.fq1_fastqc/fastqc_data.txt
6946ba80af318b9c1052b264dc674a51 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq1/synthetic_10_reads_paired_synthetic_10_reads_paired.fq1_fastqc/fastqc.fo
2603f3031242e97411a71571f6ad9e53 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq1/synthetic_10_reads_paired_synthetic_10_reads_paired.fq1_fastqc/summary.txt
@@ -45,18 +44,9 @@ b28aac49f537b8cba364b6422458ad28 results/samples/synthetic_10_reads_paired_synt
69b70e3f561b749bf10b186dd2480a8a results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq2/synthetic_10_reads_paired_synthetic_10_reads_paired.fq2_fastqc/Images/per_sequence_quality.png
b28aac49f537b8cba364b6422458ad28 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq2/synthetic_10_reads_paired_synthetic_10_reads_paired.fq2_fastqc/Images/per_tile_quality.png
5b950b5dfe3c7407e9aac153db330a38 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq2/synthetic_10_reads_paired_synthetic_10_reads_paired.fq2_fastqc/Images/sequence_length_distribution.png
-2e77276535976efccb244627231624bf results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/quant_kallisto/abundance.tsv
-d013650f813b815a790c9e6a51c7559b results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/quant_kallisto/pseudoalignments.bam
d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/quant_kallisto/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.kallisto.pseudo.sam
-981b59830d74d300bb5dd3e602e0d86f results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/lib_format_counts.json
-989d6ee63b728fced9ec0249735ab83d results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/ambig_info.tsv
-3407f87245d0003e0ffbfdf6d8c04f20 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/expected_bias
-92bcd0592d22a6a58d0360fc76103e56 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/observed_bias
-92bcd0592d22a6a58d0360fc76103e56 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/observed_bias_3p
-d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/unmapped_names.txt
500dd49da40b16799aba62aa5cf239ba results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.se.remove_adapters_mate1.fastq
500dd49da40b16799aba62aa5cf239ba results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.se.remove_polya_mate1.fastq
-d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/map_genome/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.se.SJ.out.tab
fdb8c6ddd39b606414b2785d6ec2da8a results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/fastqc_data.txt
3cb70940acdcca512207bd8613085538 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/fastqc.fo
fc276a1711cc35f7a9d5328bdbbab810 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/summary.txt
@@ -69,15 +59,7 @@ e4c1a39967ec9547a2e4c71c97982ee0 results/samples/synthetic_10_reads_mate_1_synt
69b70e3f561b749bf10b186dd2480a8a results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/Images/per_sequence_quality.png
b28aac49f537b8cba364b6422458ad28 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/Images/per_tile_quality.png
5b950b5dfe3c7407e9aac153db330a38 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/Images/sequence_length_distribution.png
-50a9b89a9f1da2c438cb0041b64faa0e results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/quant_kallisto/abundance.tsv
-fd8242418230a4edb33350be2e4f1d78 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/quant_kallisto/pseudoalignments.bam
d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/quant_kallisto/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.se.kallisto.pseudo.sam
-d6ae863b39ca6ec5d0f63c03036f9dda results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/lib_format_counts.json
-989d6ee63b728fced9ec0249735ab83d results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/ambig_info.tsv
-3407f87245d0003e0ffbfdf6d8c04f20 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/expected_bias
-92bcd0592d22a6a58d0360fc76103e56 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/observed_bias
-92bcd0592d22a6a58d0360fc76103e56 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/observed_bias_3p
-d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/unmapped_names.txt
3ce47cb1d62482c5d62337751d7e8552 results/transcriptome/homo_sapiens/transcriptome.fa
6b44c507f0a1c9f7369db0bb1deef0fd results/alfa_indexes/homo_sapiens/75/ALFA/sorted_genes.stranded.ALFA_index
2caebc23faf78fdbbbdbb118d28bd6b5 results/alfa_indexes/homo_sapiens/75/ALFA/sorted_genes.unstranded.ALFA_index
diff --git a/tests/test_integration_workflow/test.local.sh b/tests/test_integration_workflow/test.local.sh
index 883424d..69b179d 100755
--- a/tests/test_integration_workflow/test.local.sh
+++ b/tests/test_integration_workflow/test.local.sh
@@ -33,6 +33,8 @@ snakemake \
--rerun-incomplete \
--use-singularity \
--singularity-args="--bind ${PWD}/../input_files,${PWD}/../../images" \
+ --notemp \
+ --no-hooks \
--verbose
# Create a Snakemake report after the workflow execution
diff --git a/tests/test_integration_workflow/test.slurm.sh b/tests/test_integration_workflow/test.slurm.sh
index 0145ae7..c6c8410 100755
--- a/tests/test_integration_workflow/test.slurm.sh
+++ b/tests/test_integration_workflow/test.slurm.sh
@@ -35,6 +35,8 @@ snakemake \
--rerun-incomplete \
--use-singularity \
--singularity-args="--bind ${PWD}/../input_files,${PWD}/../../images" \
+ --notemp \
+ --no-hooks \
--verbose
# Create a Snakemake report after the workflow execution
diff --git a/tests/test_integration_workflow_multiple_lanes/expected_output.md5 b/tests/test_integration_workflow_multiple_lanes/expected_output.md5
index 0f264a7..1f2ce96 100644
--- a/tests/test_integration_workflow_multiple_lanes/expected_output.md5
+++ b/tests/test_integration_workflow_multiple_lanes/expected_output.md5
@@ -20,7 +20,6 @@ ea36f062eedc7f54ceffea2b635a25a8 results/star_indexes/homo_sapiens/75/STAR_inde
500dd49da40b16799aba62aa5cf239ba results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.remove_polya_mate1.fastq
e90e31db1ce51d930645eb74ff70d21b results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.remove_adapters_mate2.fastq
1c0796d7e0bdab0e99780b2e11d80c19 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.remove_polya_mate2.fastq
-d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/map_genome/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.SJ.out.tab
9896744dd90ff3eef00c91fa1f721366 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq1/synthetic_10_reads_paired_synthetic_10_reads_paired.fq1_fastqc/fastqc_data.txt
6946ba80af318b9c1052b264dc674a51 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq1/synthetic_10_reads_paired_synthetic_10_reads_paired.fq1_fastqc/fastqc.fo
2603f3031242e97411a71571f6ad9e53 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq1/synthetic_10_reads_paired_synthetic_10_reads_paired.fq1_fastqc/summary.txt
@@ -45,18 +44,9 @@ b28aac49f537b8cba364b6422458ad28 results/samples/synthetic_10_reads_paired_synt
69b70e3f561b749bf10b186dd2480a8a results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq2/synthetic_10_reads_paired_synthetic_10_reads_paired.fq2_fastqc/Images/per_sequence_quality.png
b28aac49f537b8cba364b6422458ad28 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq2/synthetic_10_reads_paired_synthetic_10_reads_paired.fq2_fastqc/Images/per_tile_quality.png
5b950b5dfe3c7407e9aac153db330a38 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/fastqc/fq2/synthetic_10_reads_paired_synthetic_10_reads_paired.fq2_fastqc/Images/sequence_length_distribution.png
-2e77276535976efccb244627231624bf results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/quant_kallisto/abundance.tsv
-d013650f813b815a790c9e6a51c7559b results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/quant_kallisto/pseudoalignments.bam
d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/quant_kallisto/synthetic_10_reads_paired_synthetic_10_reads_paired.pe.kallisto.pseudo.sam
-981b59830d74d300bb5dd3e602e0d86f results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/lib_format_counts.json
-989d6ee63b728fced9ec0249735ab83d results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/ambig_info.tsv
-3407f87245d0003e0ffbfdf6d8c04f20 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/expected_bias
-92bcd0592d22a6a58d0360fc76103e56 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/observed_bias
-92bcd0592d22a6a58d0360fc76103e56 results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/observed_bias_3p
-d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_paired_synthetic_10_reads_paired/synthetic_10_reads_paired_synthetic_10_reads_paired.salmon.pe/aux_info/unmapped_names.txt
500dd49da40b16799aba62aa5cf239ba results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.se.remove_adapters_mate1.fastq
500dd49da40b16799aba62aa5cf239ba results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.se.remove_polya_mate1.fastq
-d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/map_genome/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.se.SJ.out.tab
fdb8c6ddd39b606414b2785d6ec2da8a results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/fastqc_data.txt
3cb70940acdcca512207bd8613085538 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/fastqc.fo
fc276a1711cc35f7a9d5328bdbbab810 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/summary.txt
@@ -69,15 +59,7 @@ e4c1a39967ec9547a2e4c71c97982ee0 results/samples/synthetic_10_reads_mate_1_synt
69b70e3f561b749bf10b186dd2480a8a results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/Images/per_sequence_quality.png
b28aac49f537b8cba364b6422458ad28 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/Images/per_tile_quality.png
5b950b5dfe3c7407e9aac153db330a38 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/fastqc/fq1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.fq1_fastqc/Images/sequence_length_distribution.png
-50a9b89a9f1da2c438cb0041b64faa0e results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/quant_kallisto/abundance.tsv
-fd8242418230a4edb33350be2e4f1d78 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/quant_kallisto/pseudoalignments.bam
d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/quant_kallisto/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.se.kallisto.pseudo.sam
-d6ae863b39ca6ec5d0f63c03036f9dda results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/lib_format_counts.json
-989d6ee63b728fced9ec0249735ab83d results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/ambig_info.tsv
-3407f87245d0003e0ffbfdf6d8c04f20 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/expected_bias
-92bcd0592d22a6a58d0360fc76103e56 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/observed_bias
-92bcd0592d22a6a58d0360fc76103e56 results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/observed_bias_3p
-d41d8cd98f00b204e9800998ecf8427e results/samples/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1/synthetic_10_reads_mate_1_synthetic_10_reads_mate_1.salmon.se/aux_info/unmapped_names.txt
3ce47cb1d62482c5d62337751d7e8552 results/transcriptome/homo_sapiens/transcriptome.fa
6b44c507f0a1c9f7369db0bb1deef0fd results/alfa_indexes/homo_sapiens/75/ALFA/sorted_genes.stranded.ALFA_index
2caebc23faf78fdbbbdbb118d28bd6b5 results/alfa_indexes/homo_sapiens/75/ALFA/sorted_genes.unstranded.ALFA_index
diff --git a/tests/test_integration_workflow_multiple_lanes/test.local.sh b/tests/test_integration_workflow_multiple_lanes/test.local.sh
index 018b47d..fd45fa4 100755
--- a/tests/test_integration_workflow_multiple_lanes/test.local.sh
+++ b/tests/test_integration_workflow_multiple_lanes/test.local.sh
@@ -33,6 +33,8 @@ snakemake \
--rerun-incomplete \
--use-singularity \
--singularity-args="--bind ${PWD}/../input_files,${PWD}/../../images" \
+ --notemp \
+ --no-hooks \
--verbose
# Create a Snakemake report after the workflow execution
diff --git a/tests/test_integration_workflow_multiple_lanes/test.slurm.sh b/tests/test_integration_workflow_multiple_lanes/test.slurm.sh
index f2dd459..74ba028 100755
--- a/tests/test_integration_workflow_multiple_lanes/test.slurm.sh
+++ b/tests/test_integration_workflow_multiple_lanes/test.slurm.sh
@@ -35,6 +35,8 @@ snakemake \
--rerun-incomplete \
--use-singularity \
--singularity-args="--bind ${PWD}/../input_files,${PWD}/../../images" \
+ --notemp \
+ --no-hooks \
--verbose
# Create a Snakemake report after the workflow execution
diff --git a/workflow/rules/paired_end.snakefile.smk b/workflow/rules/paired_end.snakefile.smk
index 25046d0..1777e2c 100644
--- a/workflow/rules/paired_end.snakefile.smk
+++ b/workflow/rules/paired_end.snakefile.smk
@@ -18,16 +18,16 @@ rule pe_remove_adapters_cutadapt:
"{sample}.fq2.fastq.gz"),
output:
- reads1 = os.path.join(
+ reads1 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.pe.remove_adapters_mate1.fastq.gz"),
- reads2 = os.path.join(
+ "{sample}.pe.remove_adapters_mate1.fastq.gz")),
+ reads2 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.pe.remove_adapters_mate2.fastq.gz")
+ "{sample}.pe.remove_adapters_mate2.fastq.gz"))
params:
adapter_3_mate1 = lambda wildcards:
@@ -91,16 +91,16 @@ rule pe_remove_polya_cutadapt:
"{sample}.pe.remove_adapters_mate2.fastq.gz")
output:
- reads1 = os.path.join(
+ reads1 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.pe.remove_polya_mate1.fastq.gz"),
- reads2 = os.path.join(
+ "{sample}.pe.remove_polya_mate1.fastq.gz")),
+ reads2 = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.pe.remove_polya_mate2.fastq.gz")
+ "{sample}.pe.remove_polya_mate2.fastq.gz"))
params:
polya_3_mate1 = lambda wildcards:
@@ -203,10 +203,12 @@ rule pe_map_genome_star:
"map_genome",
"{sample}.pe.Log.final.out")
+ shadow: "minimal"
+
params:
sample_id = "{sample}",
index = lambda wildcards:
- os.path.join(
+ os.path.abspath(os.path.join(
config["star_indexes"],
get_sample(
'organism',
@@ -216,7 +218,7 @@ rule pe_map_genome_star:
'index_size',
search_id='index',
search_value=wildcards.sample),
- "STAR_index"),
+ "STAR_index")),
outFileNamePrefix = os.path.join(
config["output_dir"],
"samples",
@@ -292,10 +294,10 @@ rule pe_quantification_salmon:
"{sample}",
"{sample}.pe.remove_polya_mate2.fastq.gz"),
gtf = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'gtf',
search_id='index',
- search_value=wildcards.sample),
+ search_value=wildcards.sample)),
index = lambda wildcards:
os.path.join(
config["salmon_indexes"],
@@ -321,7 +323,23 @@ rule pe_quantification_salmon:
"samples",
"{sample}",
"{sample}.salmon.pe",
- "quant.sf")
+ "quant.sf"),
+ meta_info = os.path.join(
+ config["output_dir"],
+ "samples",
+ "{sample}",
+ "{sample}.salmon.pe",
+ "aux_info",
+ "meta_info.json"),
+ flenDist = os.path.join(
+ config["output_dir"],
+ "samples",
+ "{sample}",
+ "{sample}.salmon.pe",
+ "libParams",
+ "flenDist.txt")
+
+ shadow: "minimal"
params:
output_dir = os.path.join(
@@ -397,7 +415,15 @@ rule pe_genome_quantification_kallisto:
"samples",
"{sample}",
"quant_kallisto",
- "{sample}.pe.kallisto.pseudo.sam")
+ "{sample}.pe.kallisto.pseudo.sam"),
+ abundances = os.path.join(
+ config["output_dir"],
+ "samples",
+ "{sample}",
+ "quant_kallisto",
+ "abundance.h5")
+
+ shadow: "minimal"
params:
output_dir = os.path.join(
@@ -428,6 +454,7 @@ rule pe_genome_quantification_kallisto:
-i {input.index} \
-o {params.output_dir} \
--pseudobam \
+ -t {threads} \
{params.directionality}-stranded \
{input.reads1} {input.reads2} > {output.pseudoalignment}) \
2> {log.stderr}"
diff --git a/workflow/rules/single_end.snakefile.smk b/workflow/rules/single_end.snakefile.smk
index 071b9e5..af71c97 100644
--- a/workflow/rules/single_end.snakefile.smk
+++ b/workflow/rules/single_end.snakefile.smk
@@ -11,11 +11,11 @@ rule remove_adapters_cutadapt:
"{sample}.fq1.fastq.gz")
output:
- reads = os.path.join(
+ reads = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.se.remove_adapters_mate1.fastq.gz")
+ "{sample}.se.remove_adapters_mate1.fastq.gz"))
params:
adapters_3 = lambda wildcards:
@@ -70,11 +70,11 @@ rule remove_polya_cutadapt:
"{sample}.se.remove_adapters_mate1.fastq.gz")
output:
- reads = os.path.join(
+ reads = temp(os.path.join(
config["output_dir"],
"samples",
"{sample}",
- "{sample}.se.remove_polya_mate1.fastq.gz")
+ "{sample}.se.remove_polya_mate1.fastq.gz"))
params:
polya_3 = lambda wildcards:
@@ -151,14 +151,16 @@ rule map_genome_star:
"map_genome",
"{sample}.se.Log.final.out")
+ shadow: "minimal"
+
params:
sample_id = "{sample}",
index = lambda wildcards:
- os.path.join(
+ os.path.abspath(os.path.join(
config["star_indexes"],
get_sample('organism', search_id='index', search_value=wildcards.sample),
get_sample('index_size', search_id='index', search_value=wildcards.sample),
- "STAR_index"),
+ "STAR_index")),
outFileNamePrefix = os.path.join(
config["output_dir"],
"samples",
@@ -241,10 +243,10 @@ rule quantification_salmon:
search_value=wildcards.sample),
"salmon.idx"),
gtf = lambda wildcards:
- get_sample(
+ os.path.abspath(get_sample(
'gtf',
search_id='index',
- search_value=wildcards.sample)
+ search_value=wildcards.sample))
output:
gn_estimates = os.path.join(
@@ -258,7 +260,23 @@ rule quantification_salmon:
"samples",
"{sample}",
"{sample}.salmon.se",
- "quant.sf")
+ "quant.sf"),
+ meta_info = os.path.join(
+ config["output_dir"],
+ "samples",
+ "{sample}",
+ "{sample}.salmon.se",
+ "aux_info",
+ "meta_info.json"),
+ flenDist = os.path.join(
+ config["output_dir"],
+ "samples",
+ "{sample}",
+ "{sample}.salmon.se",
+ "libParams",
+ "flenDist.txt")
+
+ shadow: "minimal"
params:
output_dir = os.path.join(
@@ -339,7 +357,15 @@ rule genome_quantification_kallisto:
"samples",
"{sample}",
"quant_kallisto",
- "{sample}.se.kallisto.pseudo.sam")
+ "{sample}.se.kallisto.pseudo.sam"),
+ abundances = os.path.join(
+ config["output_dir"],
+ "samples",
+ "{sample}",
+ "quant_kallisto",
+ "abundance.h5")
+
+ shadow: "minimal"
params:
output_dir = os.path.join(
@@ -383,6 +409,7 @@ rule genome_quantification_kallisto:
-l {params.fraglen} \
-s {params.fragsd} \
--pseudobam \
+ -t {threads} \
{params.directionality}-stranded \
{input.reads} > {output.pseudoalignment};) \
2> {log.stderr}"
--
GitLab