diff --git a/.gitignore b/.gitignore index 8c51880..4d326e9 100644 --- a/.gitignore +++ b/.gitignore @@ -13,4 +13,4 @@ test.csv test2.csv .nf-test .nf-test.log -nf-test-report.tap +nf-test-report* diff --git a/bin/help/pta.nf b/bin/help/pta.nf index abb28ae..44a8276 100644 --- a/bin/help/pta.nf +++ b/bin/help/pta.nf @@ -15,7 +15,7 @@ The following are human specific parameters. To see help for mouse, add `--gen_o --pdx | false | Options: false, true. If specified, 'Xengsort' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. --xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false. --xengsort_idx_path | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa. ---xengsort_idx_name | 'hg38_GRCm38-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index +--xengsort_idx_name | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index --deduplicate_reads | false | Options: false, true. If specified, run bbmap clumpify on input reads. Clumpify will deduplicate reads prior to trimming. This can help with mapping and downstream steps when analyzing high coverage WGS data. diff --git a/bin/help/rna_fusion.nf b/bin/help/rna_fusion.nf index 239f13b..00bbb40 100644 --- a/bin/help/rna_fusion.nf +++ b/bin/help/rna_fusion.nf @@ -50,7 +50,7 @@ Parameter | Default | Description --ref_fa | '/projects/compsci/omics_share/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta'| Xengsort graft fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false. --xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false. --xengsort_idx_path | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa. ---xengsort_idx_name | 'hg38_GRCm38-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index +--xengsort_idx_name | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index ''' } diff --git a/bin/help/rnaseq.nf b/bin/help/rnaseq.nf index 8366612..5229183 100644 --- a/bin/help/rnaseq.nf +++ b/bin/help/rnaseq.nf @@ -52,7 +52,7 @@ Parameter | Default | Description --ref_fa | '/projects/compsci/omics_share/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta'| Xengsort graft fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false. --xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false. --xengsort_idx_path | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa. ---xengsort_idx_name | 'hg38_GRCm38-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index +--xengsort_idx_name | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index There are two additional parameters that are human specific. They are: diff --git a/bin/help/somatic_wes.nf b/bin/help/somatic_wes.nf index e699974..916b6c8 100644 --- a/bin/help/somatic_wes.nf +++ b/bin/help/somatic_wes.nf @@ -24,7 +24,7 @@ Parameter | Default | Description --pdx | false | Options: false, true. If specified, 'Xengsort' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. --xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false. --xengsort_idx_path = | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa. ---xengsort_idx_name = | 'hg38_GRCm38-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index +--xengsort_idx_name = | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index --genotype_targets | '/projects/compsci/omics_share/human/GRCh38/supporting_files/ancestry_panel/snp_panel_v2_targets_annotations.snpwt.bed.gz' | Target SNP bed file for the ancestry panel. Can contain annotation information. --snpID_list | '/projects/compsci/omics_share/human/GRCh38/supporting_files/ancestry_panel/snp_panel_v2.list' | Target SNPs in list used in BCFtools filtering step diff --git a/bin/help/somatic_wes_pta.nf b/bin/help/somatic_wes_pta.nf index 758b955..f272e15 100644 --- a/bin/help/somatic_wes_pta.nf +++ b/bin/help/somatic_wes_pta.nf @@ -24,7 +24,7 @@ Parameter | Default | Description --pdx | false | Options: false, true. If specified, 'Xengsort' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. --xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false. --xengsort_idx_path = | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa. ---xengsort_idx_name = | 'hg38_GRCm38-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index +--xengsort_idx_name = | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index --genotype_targets | '/projects/compsci/omics_share/human/GRCh38/supporting_files/ancestry_panel/snp_panel_v2_targets_annotations.snpwt.bed.gz' | Target SNP bed file for the ancestry panel. Can contain annotation information. --snpID_list | '/projects/compsci/omics_share/human/GRCh38/supporting_files/ancestry_panel/snp_panel_v2.list' | Target SNPs in list used in BCFtools filtering step diff --git a/config/pta.config b/config/pta.config index 8e84b0f..f72fa3d 100644 --- a/config/pta.config +++ b/config/pta.config @@ -32,7 +32,7 @@ params { // xengsort index xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort' - xengsort_idx_name = 'hg38_GRCm38-NOD_ShiLtJ' + xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ' // Reference fasta ref_fa = params.reference_cache+'/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta' diff --git a/config/rna_fusion.config b/config/rna_fusion.config index 69438d2..b4a6069 100644 --- a/config/rna_fusion.config +++ b/config/rna_fusion.config @@ -25,7 +25,7 @@ params { ref_fa = params.reference_cache+'/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta' xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort' - xengsort_idx_name = 'hg38_GRCm38-NOD_ShiLtJ' + xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ' // READ LENGTH ADJUSTMENTS: read_length = 150 // change relative to sample being processed. 75, 100, 125, and 150 are supported. diff --git a/config/rnaseq.config b/config/rnaseq.config index 864876b..468014d 100644 --- a/config/rnaseq.config +++ b/config/rnaseq.config @@ -109,7 +109,7 @@ if (params.gen_org=='human' && params.pdx){ params.ref_fa = params.reference_cache+'/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta' params.xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' params.xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort' - params.xengsort_idx_name = 'hg38_GRCm38-NOD_ShiLtJ' + params.xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ' // General RSEM params.seed_length = '25' diff --git a/config/somatic_wes.config b/config/somatic_wes.config index bb9f498..fa401ae 100644 --- a/config/somatic_wes.config +++ b/config/somatic_wes.config @@ -43,7 +43,7 @@ params { // Xengsort index xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort' - xengsort_idx_name = 'hg38_GRCm38-NOD_ShiLtJ' + xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ' // WES capture array BED and GATK intervals lists target_gatk = params.reference_cache+'/human/GRCh38/supporting_files/capture_kit_files/agilent/v7/S31285117_MergedProbes_no_gene_names.bed' diff --git a/config/somatic_wes_pta.config b/config/somatic_wes_pta.config index de648d1..ebf354b 100644 --- a/config/somatic_wes_pta.config +++ b/config/somatic_wes_pta.config @@ -40,7 +40,7 @@ params { // include for Xengsort index xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort' - xengsort_idx_name = 'hg38_GRCm38-NOD_ShiLtJ' + xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ' // WES capture array BED and GATK intervals lists target_gatk = params.reference_cache+'/human/GRCh38/supporting_files/capture_kit_files/agilent/v7/S31285117_MergedProbes_no_gene_names.bed' diff --git a/tests/workflows/rnaseq.nf.test b/tests/workflows/rnaseq.nf.test index af0f2a3..2f49a48 100644 --- a/tests/workflows/rnaseq.nf.test +++ b/tests/workflows/rnaseq.nf.test @@ -69,7 +69,7 @@ nextflow_workflow { params { outdir = "tests/results" gen_org = "human" - sample_folder = "${baseDir}/test/rna/human" + sample_folder = "${baseDir}/test/rna/human/pdx" pubdir = "tests/results" pdx = true pipeline = 'rnaseq'