diff --git a/Snakefile b/Snakefile
index eeb801f8d26cfdbe2ad2c6a9df16cfea8601d625..2f5842ad042cb5bd14cb17afb3d72795efff88fc 100644
--- a/Snakefile
+++ b/Snakefile
@@ -210,7 +210,13 @@ rule fastqc:
"{mate}"))
params:
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--outdir',))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--outdir',
+ )
+ )
threads: 2
@@ -282,7 +288,18 @@ rule create_index_star:
"{index_size}",
"STAR_index/STAR_"),
sjdbOverhang = "{index_size}",
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--runMode','--sjdbOverhang', '--genomeDir', '--genomeFastaFiles', '--outFileNamePrefix', '--sjdbGTFfile'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--runMode',
+ '--sjdbOverhang',
+ '--genomeDir',
+ '--genomeFastaFiles',
+ '--outFileNamePrefix',
+ '--sjdbGTFfile',
+ )
+ )
singularity:
"docker://zavolab/star:2.7.3a-slim"
@@ -336,7 +353,14 @@ rule extract_transcriptome:
"transcriptome.fa"))
params:
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('-w', '-g'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-w',
+ '-g',
+ )
+ )
log:
stderr = os.path.join(
@@ -426,7 +450,16 @@ rule create_index_salmon:
params:
kmerLen = "{kmer}",
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--transcripts','--decoys', '--index', '--kmerLen'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--transcripts',
+ '--decoys',
+ '--index',
+ '--kmerLen',
+ )
+ )
singularity:
"docker://zavolab/salmon:1.1.0-slim"
@@ -474,7 +507,13 @@ rule create_index_kallisto:
output_dir = os.path.join(
config['kallisto_indexes'],
"{organism}"),
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('-i',))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-i',
+ )
+ )
singularity:
"docker://zavolab/kallisto:0.46.1-slim"
@@ -512,7 +551,14 @@ rule extract_transcripts_as_bed12:
"full_transcripts_protein_coding.bed"))
params:
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--gtf', '--bed12'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--gtf',
+ '--bed12',
+ )
+ )
singularity:
"docker://zavolab/zgtf:0.1"
@@ -556,7 +602,11 @@ rule index_genomic_alignment_samtools:
"{sample}.{seqmode}.Aligned.sortedByCoord.out.bam.bai")
params:
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=())
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=()
+ )
singularity:
"docker://zavolab/samtools:1.10-slim"
@@ -628,7 +678,15 @@ rule calculate_TIN_scores:
params:
sample = "{sample}",
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('-i', '-r', '--names'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-i',
+ '-r',
+ '--names',
+ )
+ )
log:
stderr = os.path.join(
@@ -697,7 +755,18 @@ rule salmon_quantmerge_genes:
"{sample}",
sample=pd.unique(samples_table.index.values)),
salmon_merge_on = "{salmon_merge_on}",
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--quants', '--genes', '--transcripts', '--names', '--column', '--output'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--quants',
+ '--genes',
+ '--transcripts',
+ '--names',
+ '--column',
+ '--output',
+ )
+ )
log:
stderr = os.path.join(
@@ -765,12 +834,22 @@ rule salmon_quantmerge_transcripts:
search_id='index',
search_value=i)
for i in pd.unique(samples_table.index.values)]),
-
sample_name_list = expand(
"{sample}",
sample=pd.unique(samples_table.index.values)),
salmon_merge_on = "{salmon_merge_on}",
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--quants', '--genes', '--transcripts', '--names', '--column', '--output'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--quants',
+ '--genes',
+ '--transcripts',
+ '--names',
+ '--column',
+ '--output',
+ )
+ )
log:
stderr = os.path.join(
@@ -842,7 +921,17 @@ rule kallisto_merge_genes:
sample_name_list = ','.join(expand(
"{sample}",
sample=pd.unique(samples_table.index.values))),
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--input', '--names', '--txOut', '--anno', '--output'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--input',
+ '--names',
+ '--txOut',
+ '--anno',
+ '--output',
+ )
+ )
log:
stderr = os.path.join(
@@ -914,7 +1003,16 @@ rule kallisto_merge_transcripts:
sample_name_list = ','.join(expand(
"{sample}",
sample=pd.unique(samples_table.index.values))),
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--input', '--names', '--txOut', '--output'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--input',
+ '--names',
+ '--txOut',
+ '--output',
+ )
+ )
log:
stderr = os.path.join(
@@ -954,7 +1052,14 @@ rule pca_salmon:
"pca_salmon_{molecule}"))
params:
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--tpm', '--out'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--tpm',
+ '--out',
+ )
+ )
log:
stderr = os.path.join(
@@ -993,7 +1098,14 @@ rule pca_kallisto:
"pca_kallisto_{molecule}"))
params:
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--tpm', '--out'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--tpm',
+ '--out',
+ )
+ )
log:
stderr = os.path.join(
@@ -1084,7 +1196,16 @@ rule star_rpm:
os.path.join(
os.path.dirname(output.str1),
str(wildcards.sample) + "_"),
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--runMode', '--inputBAMfile', '--outWigType', '--outFileNamePrefix'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--runMode',
+ '--inputBAMfile',
+ '--outWigType',
+ '--outFileNamePrefix',
+ )
+ )
singularity:
"docker://zavolab/star:2.7.3a-slim"
@@ -1194,7 +1315,6 @@ rule generate_alfa_index:
'gtf',
search_id='organism',
search_value=wildcards.organism)),
-
chr_len = os.path.join(
config["star_indexes"],
"{organism}",
@@ -1220,7 +1340,16 @@ rule generate_alfa_index:
genome_index = "sorted_genes",
out_dir = lambda wildcards, output:
os.path.dirname(output.index_stranded),
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('-a', '-g', '--chr_len', '-o'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-a',
+ '-g',
+ '--chr_len',
+ '-o',
+ )
+ )
threads: 4
@@ -1317,7 +1446,15 @@ rule alfa_qc:
'alfa_directionality',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('-g', '--bedgraph', '-s'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-g',
+ '--bedgraph',
+ '-s',
+ )
+ )
singularity:
"docker://zavolab/alfa:1.1.1-slim"
@@ -1360,7 +1497,16 @@ rule prepare_multiqc_config:
logo_path = config['report_logo'],
multiqc_intro_text = config['report_description'],
url = config['report_url'],
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--config', '--intro-text', '--custom-logo', '--url'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--config',
+ '--intro-text',
+ '--custom-logo',
+ '--url',
+ )
+ )
log:
stderr = os.path.join(
@@ -1466,7 +1612,14 @@ rule multiqc_report:
results_dir = os.path.join(
config["output_dir"]),
log_dir = config["log_dir"],
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('--outdir', '--config'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--outdir',
+ '--config',
+ )
+ )
log:
stderr = os.path.join(
@@ -1512,7 +1665,13 @@ rule sort_bed_4_big:
"{sample}_{unique}_{strand}.sorted.bg"))
params:
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=('-i', ))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-i',
+ )
+ )
singularity:
"docker://cjh4zavolab/bedtools:2.27"
@@ -1568,7 +1727,11 @@ rule prepare_bigWig:
"{sample}_{unique}_{strand}.bw")
params:
- additional_params = parse_rule_config(rule_config, current_rule=current_rule, immutable=())
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=()
+ )
singularity:
"docker://zavolab/bedgraphtobigwig:4-slim"
diff --git a/pipeline_documentation.md b/pipeline_documentation.md
index 65c22a2d54ecda99dd71aeb102a40bc4420fecc8..5f96d48eba52621b0962c5e8ce9c88392894086b 100644
--- a/pipeline_documentation.md
+++ b/pipeline_documentation.md
@@ -104,7 +104,7 @@ sample | Descriptive sample name | `str`
seqmode | Required for various steps of the workflow. One of `pe` (for paired-end libraries) or `se` (for single-end libraries). | `str`
fq1 | Path of library file in `.fastq.gz` format (or mate 1 read file for paired-end libraries) | `str`
index_size | Required for [STAR](#third-party-software-used). Ideally the maximum read length minus 1 (`max(ReadLength)-1`). Values lower than maximum read length may result in lower mapping accuracy, while higher values may result in longer processing times. | `int`
-kmer | Required for [Salmon](#third-party-software-used). Default value of 31 usually works fine for reads of 75 bp or longer. Consider using lower values of poor mapping is observed. | `int`
+kmer | Required for [Salmon](#third-party-software-used). Default value of 31 usually works fine for reads of 75 bp or longer. Consider using lower values if poor mapping is observed. | `int`
fq2 | Path of mate 2 read file in `.fastq.gz` format. Value ignored for for single-end libraries. | `str`
fq1_3p | Required for [Cutadapt](#third-party-software-used). 3' adapter of mate 1. Use value such as `XXXXXXXXXXXXXXX` if no adapter present or if no trimming is desired. | `str`
fq1_5p | Required for [Cutadapt](#third-party-software-used). 5' adapter of mate 1. Use value such as `XXXXXXXXXXXXXXX` if no adapter present or if no trimming is desired. | `str`
@@ -157,7 +157,7 @@ Create index for [**STAR**](#third-party-software-used) short read aligner.
- Gene annotation file (`.gtf`)
- **Parameters**
- **samples.tsv**
- - `--sjdbOverhang`: maximum read length - 1; lower values may reduce accuracy,higher values may increase STAR runtime; specify in sample table column `index_size`
+ - `--sjdbOverhang`: maximum read length - 1; lower values may reduce accuracy, higher values may increase STAR runtime; specify in sample table column `index_size`
- **Output**
- STAR index; used in [**map_genome_star**](#map_genome_star)
- Index includes files:
diff --git a/workflow/rules/paired_end.snakefile.smk b/workflow/rules/paired_end.snakefile.smk
index 153ce3ab923ec41537823abc5196c4d1aa81cb5e..3f7834cb49f85437ad83fade6cf66b91e2b682ec 100644
--- a/workflow/rules/paired_end.snakefile.smk
+++ b/workflow/rules/paired_end.snakefile.smk
@@ -39,7 +39,18 @@ rule pe_remove_adapters_cutadapt:
get_sample('fq2_3p', search_id='index', search_value=wildcards.sample),
adapter_5_mate2 = lambda wildcards:
get_sample('fq2_5p', search_id='index', search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('-a', '-A', '-g', '-G', '-o', '-p'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-a',
+ '-A',
+ '-g',
+ '-G',
+ '-o',
+ '-p',
+ )
+ )
singularity:
"docker://zavolab/cutadapt:1.16-slim"
@@ -123,7 +134,18 @@ rule pe_remove_polya_cutadapt:
'fq2_polya_5p',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('-a', '-A', '-g', '-G', '-o', '-p'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-a',
+ '-A',
+ '-g',
+ '-G',
+ '-o',
+ '-p',
+ )
+ )
singularity:
"docker://zavolab/cutadapt:1.16-slim"
@@ -174,8 +196,8 @@ rule pe_map_genome_star:
'index_size',
search_id='index',
search_value=wildcards.sample),
- "STAR_index",
- "chrNameLength.txt"),
+ "STAR_index",
+ "chrNameLength.txt"),
reads1 = os.path.join(
config["output_dir"],
"samples",
@@ -216,7 +238,7 @@ 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",
@@ -238,7 +260,23 @@ rule pe_map_genome_star:
'pass_mode',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('--twopassMode', '--genomeDir', '--readFilesIn', '--readFilesCommand', '--outFilterMultimapNmax', '--outFileNamePrefix', '--outSAMattributes', '--outStd', '--outSAMtype', '--outSAMattrRGline', '--alignEndsType'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--twopassMode',
+ '--genomeDir',
+ '--readFilesIn',
+ '--readFilesCommand',
+ '--outFilterMultimapNmax',
+ '--outFileNamePrefix',
+ '--outSAMattributes',
+ '--outStd',
+ '--outSAMtype',
+ '--outSAMattrRGline',
+ '--alignEndsType',
+ )
+ )
singularity:
"docker://zavolab/star:2.7.3a-slim"
@@ -303,7 +341,7 @@ rule pe_quantification_salmon:
'kmer',
search_id='index',
search_value=wildcards.sample),
- "salmon.idx")
+ "salmon.idx")
output:
gn_estimates = os.path.join(
@@ -346,7 +384,20 @@ rule pe_quantification_salmon:
'libtype',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('--libType', '--fldMean', '--fldSD', '--index', '--geneMap', '-1', '-2', '-o'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--libType',
+ '--fldMean',
+ '--fldSD',
+ '--index',
+ '--geneMap',
+ '-1',
+ '-2',
+ '-o',
+ )
+ )
log:
stderr = os.path.join(
@@ -401,7 +452,7 @@ rule pe_genome_quantification_kallisto:
'organism',
search_id='index',
search_value=wildcards.sample),
- "kallisto.idx")
+ "kallisto.idx")
output:
pseudoalignment = os.path.join(
@@ -430,7 +481,20 @@ rule pe_genome_quantification_kallisto:
'kallisto_directionality',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('--single', '-i', '-o', '-l', '-s', '--pseudobam', '--fr-stranded', '--rf-stranded'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--single',
+ '-i',
+ '-o',
+ '-l',
+ '-s',
+ '--pseudobam',
+ '--fr-stranded',
+ '--rf-stranded',
+ )
+ )
singularity:
diff --git a/workflow/rules/single_end.snakefile.smk b/workflow/rules/single_end.snakefile.smk
index 37cc4192ae31a3757161163c2fd86556c30106fd..337ae752b58ddaccdfcd351b63e6cc18b2982934 100644
--- a/workflow/rules/single_end.snakefile.smk
+++ b/workflow/rules/single_end.snakefile.smk
@@ -29,7 +29,18 @@ rule remove_adapters_cutadapt:
'fq1_5p',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('-a', '-A', '-g', '-G', '-o', '-p'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-a',
+ '-A',
+ '-g',
+ '-G',
+ '-o',
+ '-p',
+ )
+ )
singularity:
"docker://zavolab/cutadapt:1.16-slim"
@@ -88,7 +99,18 @@ rule remove_polya_cutadapt:
'fq1_polya_5p',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('-a', '-A', '-g', '-G', '-o', '-p'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '-a',
+ '-A',
+ '-g',
+ '-G',
+ '-o',
+ '-p',
+ )
+ )
singularity:
"docker://zavolab/cutadapt:1.16-slim"
@@ -182,7 +204,23 @@ rule map_genome_star:
'pass_mode',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('--twopassMode', '--genomeDir', '--readFilesIn', '--readFilesCommand', '--outFilterMultimapNmax', '--outFileNamePrefix', '--outSAMattributes', '--outStd', '--outSAMtype', '--outSAMattrRGline', '--alignEndsType'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--twopassMode',
+ '--genomeDir',
+ '--readFilesIn',
+ '--readFilesCommand',
+ '--outFilterMultimapNmax',
+ '--outFileNamePrefix',
+ '--outSAMattributes',
+ '--outStd',
+ '--outSAMtype',
+ '--outSAMattrRGline',
+ '--alignEndsType',
+ )
+ )
singularity:
"docker://zavolab/star:2.7.3a-slim"
@@ -295,7 +333,19 @@ rule quantification_salmon:
'sd',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('--libType', '--fldMean', '--fldSD', '--index', '--geneMap', '--unmatedReads', '-o'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--libType',
+ '--fldMean',
+ '--fldSD',
+ '--index',
+ '--geneMap',
+ '--unmatedReads',
+ '-o',
+ )
+ )
log:
stderr = os.path.join(
config["log_dir"],
@@ -384,7 +434,20 @@ rule genome_quantification_kallisto:
'kallisto_directionality',
search_id='index',
search_value=wildcards.sample),
- additional_params = parse_rule_config(rule_config,current_rule=current_rule, immutable=('--single', '-i', '-o', '-l', '-s', '--pseudobam', '--fr-stranded', '--rf-stranded'))
+ additional_params = parse_rule_config(
+ rule_config,
+ current_rule=current_rule,
+ immutable=(
+ '--single',
+ '-i',
+ '-o',
+ '-l',
+ '-s',
+ '--pseudobam',
+ '--fr-stranded',
+ '--rf-stranded',
+ )
+ )
threads: 8