diff --git a/config/references/design_files.hg19.yaml b/config/references/design_files.hg19.yaml index 14b1cc65..8ea0eff4 100644 --- a/config/references/design_files.hg19.yaml +++ b/config/references/design_files.hg19.yaml @@ -4,147 +4,173 @@ cnv_amp_genes: path: cnv/cnv_amp_genes.bed checksum: 7bae2d8c592e54207c4b8effaca2bf4f + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/cnv/cnv_amp_genes.bed cnv_loh_genes: path: cnv/cnv_loh_genes.bed checksum: 38d3acbe99bb9626ccc0ab1815b6e35b + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/cnv/cnv_loh_genes.bed bcftools_filter_include_region: exon: path: design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.MUC6_31_rm.exon_only.reannotated.230222.bed checksum: c85f3369444cd6f27a397eef0a24fff9 + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.MUC6_31_rm.exon_only.reannotated.230222.bed bcftools_filter_exclude_region: blacklist: checksum: 2eaeb99aa53fc2b7b173c328b6bd1672 path: cnv/cnvkit_germline_blacklist_20221221.bed + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/cnv/cnvkit_germline_blacklist_20221221.bed bcftools_id_snps: snps_bed: checksum: ab9b7084d599606bb52142d26158f5e1 path: design/ID_SNPs.bed + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/ID_SNPs.bed call_small_cnv_amplifications: regions_file: checksum: 24447a09e6691ca7382f4400b06943cf path: cnv/cnv_amplification_genes.tsv + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/cnv/cnv_amplification_genes.tsv call_small_cnv_deletions: regions_file: checksum: e044cf88e5e50e68a3a797be5720e6c0 path: cnv/cnv_deletion_genes.tsv + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/cnv/cnv_deletion_genes.tsv exon_skipping: design_bed: checksum: 7fe64299477aa4b6a5f5783cce9fa30f path: design/Twist_RNA_Design5.annotated.bed + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/Twist_RNA_Design5.annotated.bed filter_fuseq_wes: gene_white_list: checksum: d762e65cc9d9d01d022db7de7c31cc68 path: fuseq_wes/fuseq_wes_gene_white_list.txt + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/fuseq_wes/fuseq_wes_gene_white_list.txt transcript_black_list: checksum: 586ad13ce609fdf5390d299cbbaae183 path: fuseq_wes/fuseq_wes_transcript_black_list.txt + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/fuseq_wes/fuseq_wes_transcript_black_list.txt fuseq_wes: params: checksum: d2e6d449027c49e24f026261082fa5bb path: fuseq_wes/fuseq_params.txt + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/fuseq_wes/fuseq_params.txt gatk_collect_allelic_counts: SNP_interval: checksum: 47cee8e04769d13e1c282fedf7333eac path: cnv/gnomad_SNP_0.001_target.annotated.interval_list + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/cnv/gnomad_SNP_0.001_target.annotated.interval_list gene_fuse: genes: checksum: c35fc6fbf81ce2e1cc55b536742ccf02 path: gene_fuse/GMS560_fusion_w_pool2.hg19.221117.csv + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/gene_fuse/GMS560_fusion_w_pool2.hg19.221117.csv hotspot_annotation: hotspots: checksum: 59fe5daf8039746c6690fce5e55d5115 path: design/Hotspots_combined_regions_nodups.csv + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/Hotspots_combined_regions_nodups.csv hotspot_info: hotspot_mutations: checksum: 59fe5daf8039746c6690fce5e55d5115 path: design/Hotspots_combined_regions_nodups.csv + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/Hotspots_combined_regions_nodups.csv hotspot_report: hotspot_mutations: checksum: 59fe5daf8039746c6690fce5e55d5115 path: design/Hotspots_combined_regions_nodups.csv + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/Hotspots_combined_regions_nodups.csv manta_config_t: extra: checksum: b8f464f2af0d71c4e91fcdbd90378b6d path: design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.210608.bed.gz + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.210608.bed.gz extra_tbi: checksum: 9c57e51d22b33d8683698d9c8d0c4b7a path: design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.210608.bed.gz.tbi + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.210608.bed.gz.tbi purecn: intervals: checksum: 0857e05962696cd3c2e5a4ea94d0fb2c path: purecn/targets_twist-gms-st_hg19_25000_intervals.txt + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/cnv/targets_twist-gms-st_hg19_25000_intervals.txt purecn_coverage: intervals: checksum: 0857e05962696cd3c2e5a4ea94d0fb2c path: purecn/targets_twist-gms-st_hg19_25000_intervals.txt + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/cnv/targets_twist-gms-st_hg19_25000_intervals.txt report_fusions: annotation_bed: checksum: af529c0ece5fe201de4d507000564ff7 path: rna_fusion/Twist_RNA_fusionpartners.bed + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/rna_fusion/Twist_RNA_fusionpartners.bed references: design_bed: checksum: 06751f8685f1d507f4c48774450c0275 path: design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.reannotated.230222.bed + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.reannotated.230222.bed design_intervals: checksum: babb76d1e2490619eef47cf5b41db9f7 path: design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.MUC6_31_rm.exon_only.reannotated.210608.interval_list + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/pool1_pool2.sort.merged.padded20.cnv200.hg19.split_fusion_genes.MUC6_31_rm.exon_only.reannotated.210608.interval_list design_intervals_gatk_cnv: checksum: 812f9f89faf750d1948f19166056f1d1 path: design/pool1_pool2_nochr_3c.sort.merged.padded20.cnv400.hg19.210311.met.annotated.bed.preprocessed.interval_list + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/pool1_pool2_nochr_3c.sort.merged.padded20.cnv400.hg19.210311.met.annotated.bed.preprocessed.interval_list design_intervals_rna: checksum: c9cda4a99bccb8d3ac2d11503d8b83e1 path: design/Twist_RNA_Design5.annotated.interval_list + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/design/Twist_RNA_Design5.annotated.interval_list report_gene_fuse: filter_fusions: checksum: b6bc58f14e2cee6e481f1cabf1fd2c0b path: gene_fuse/filter_fusions_20230214.csv + type: file url: https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files/raw/v0.1.0/gene_fuse/filter_fusions_20230214.csv \ No newline at end of file diff --git a/config/references/nextseq.hg19.pon.yaml b/config/references/nextseq.hg19.pon.yaml index e217cf41..449bfadf 100644 --- a/config/references/nextseq.hg19.pon.yaml +++ b/config/references/nextseq.hg19.pon.yaml @@ -4,17 +4,20 @@ db_string: checksum: 076f3a9bec5e9941eb4bbbf4594c0037 path: SVDB/all_TN_292_svdb_0.8_20220505.vcf + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882898 purecn: extra: checksum: eb311461a92b53a9494bba9625ecd4c3 path: purecn/mapping_bias_nextseq_27_hg19.rds + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882865 normaldb: checksum: d77528e5bfeec40791235e52dcbed7ef path: purecn/normalDB_nextseq_27_hg19.rds + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882874 @@ -22,33 +25,39 @@ normal_reference: checksum: eee609d42ca9ea071521664bdac6c4d6 path: PoN/gatk_cnv_nextseq_36.hdf5 + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882859 cnvkit_batch: normal_reference: checksum: 2c8f519a872d92ec1cb43bd29518a71b path: PoN/cnvkit_nextseq_36.cnn + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882850 cnvkit_batch_hrd: normal_reference_hrd: checksum: 89d2ca215b62651e5272a4bb70b7d217 path: PoN/cnvkit_nextseq_27_HRD.cnn + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882847 msisensor_pro: PoN: checksum: 23c9553c7043fff1a8428fcd3b231c60 path: PoN/Msisensor_pro_reference_nextseq_36.list_baseline + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882868 reference: background: checksum: 664471a52761adf69ed1f8310a60f445 path: Background/background_panel_nextseq_noUmea_27_dp500_af015.tsv + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882841 artifacts: checksum: 73531299238e0a0884405a892e6789ac path: Artifact/artifact_panel_nextseq_36.tsv + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882835 diff --git a/config/references/novaseq.hg19.pon.yaml b/config/references/novaseq.hg19.pon.yaml index 661c0fee..1f76e052 100644 --- a/config/references/novaseq.hg19.pon.yaml +++ b/config/references/novaseq.hg19.pon.yaml @@ -3,17 +3,20 @@ db_string: checksum: 076f3a9bec5e9941eb4bbbf4594c0037 path: SVDB/all_TN_292_svdb_0.8_20220505.vcf + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882898 purecn: extra: checksum: eb311461a92b53a9494bba9625ecd4c3 path: purecn/mapping_bias_nextseq_27_hg19.rds + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882865 normaldb: checksum: d77528e5bfeec40791235e52dcbed7ef path: purecn/normalDB_nextseq_27_hg19.rds + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882874 @@ -21,34 +24,40 @@ normal_reference: checksum: ab0a2f3276125c8695b72a2b2c5779ea path: PoN/gatk_cnv_novaseq_13.hdf5 + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882862 cnvkit_batch: normal_reference: checksum: e7853030e7a6b0ccbeffb7c008983a29 path: PoN/cnvkit_novaseq_13.cnn + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882853 cnvkit_batch_hrd: normal_reference_hrd: checksum: e7853030e7a6b0ccbeffb7c008983a29 path: PoN/cnvkit_novaseq_13_HRD.cnn + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882871 msisensor_pro: PoN: checksum: 40bda778c9208a366b39ec0e6cefde11 path: PoN/Msisensor_pro_reference_novaseq_13.list_baseline + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882871 reference: background: checksum: 563aa06990d90ed3ef33b4da1aac3c2e path: Background/background_panel_novaseq_13_dp500_af015.tsv + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882844 artifacts: checksum: 6d589735a4b922a6f7e852539f44a539 path: Artifact/artifact_panel_novaseq_13.tsv + type: file url: https://figshare.scilifelab.se/ndownloader/files/40882838 diff --git a/config/references/references.bianca.hg19.yaml b/config/references/references.bianca.hg19.yaml index c36c27fa..a139a3ab 100644 --- a/config/references/references.bianca.hg19.yaml +++ b/config/references/references.bianca.hg19.yaml @@ -2,11 +2,13 @@ fusioncatcher: genome_path: - path: /sw/bioinfo/FusionCatcher/1.33/bianca/fusioncatcher/data/human_v102/ + type: folder + path: /sw/bioinfo/FusionCatcher/1.33/bianca/fusioncatcher/data/human_v102/ reference: fasta_rna: path: /sw/data/CTAT_RESOURCE_LIB/2021-03/GRCh37_gencode_v19_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa + type: file # fai: # path: /sw/data/CTAT_RESOURCE_LIB/2021-03/GRCh37_gencode_v19_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ref_genome.fa.fai # dict: @@ -15,14 +17,18 @@ star: extra: path: /sw/data/reference/Homo_sapiens/GRCh37/program_files/lifescope/refGene/refGene.hg19.20101221.gtf + type: file genome_index: path: /sw/data/reference/Homo_sapiens/hg19/program_files/star/concat + type: file star-fusion: genome_path: path: /sw/data/CTAT_RESOURCE_LIB/2021-03/GRCh37_gencode_v19_CTAT_lib_Mar012021.plug-n-play/ctat_genome_lib_build_dir/ + type: folder vep: vep_cache: path: /sw/data/vep/107 + type: folder \ No newline at end of file diff --git a/config/references/references.hg19.yaml b/config/references/references.hg19.yaml index cf251cde..41ae5acf 100644 --- a/config/references/references.hg19.yaml +++ b/config/references/references.hg19.yaml @@ -4,66 +4,78 @@ blacklist: checksum: ca7b0b42ec2498814a5c408a5477e052 path: ref_data/arriba/blacklist_hg19_hs37d5_GRCh37_v2.3.0.tsv.gz + type: file url: https://figshare.scilifelab.se/ndownloader/files/40928345 extra1: checksum: b5bc63c70c9eb08c71528ee8b0186901 path: ref_data/arriba/protein_domains_hg19_hs37d5_GRCh37_v2.3.0.gff3 + type: file url: https://figshare.scilifelab.se/ndownloader/files/40928354 extra2: checksum: 2f063a0065c1c88d86c859b924d8d590 path: ref_data/arriba/known_fusions_hg19_hs37d5_GRCh37_v2.3.0.tsv.gz + type: file url: https://figshare.scilifelab.se/ndownloader/files/40928351 gtf: checksum: 57b812f0595dc8a446ca81fe568e142d path: ref_data/gtf/hg19.refGene.gtf + type: file url: https://figshare.scilifelab.se/ndownloader/files/42061200 data_folder: #checksum: path: ariba_v2.3.0.tar.gz + type: file url: https://figshare.scilifelab.se/ndownloader/files/42116952 arriba_draw_fusion: cytobands: checksum: 9333eaa96c56fa22624ab432b8391b2b path: ref_data/arriba/cytobands_hg19_hs37d5_GRCh37_v2.3.0.tsv + type: file url: https://figshare.scilifelab.se/ndownloader/files/40928348 protein_domains: checksum: b5bc63c70c9eb08c71528ee8b0186901 path: ref_data/arriba/protein_domains_hg19_hs37d5_GRCh37_v2.3.0.gff3 + type: file url: https://figshare.scilifelab.se/ndownloader/files/40928354 bwa: amb: checksum: b1998db7fbda653133fa278cd9b1e61b path: ref_data/hg19/hg19.with.mt.fasta.amb + type: file url: https://figshare.scilifelab.se/ndownloader/files/42061203 ann: checksum: 745e9a6afe1951cc54e8cc1b6c1429ff path: ref_data/hg19/hg19.with.mt.fasta.ann + type: file url: https://figshare.scilifelab.se/ndownloader/files/42061206 bwt: checksum: da1a091388a038c22e1d5c555db00a8b path: ref_data/hg19/hg19.with.mt.fasta.bwt + type: file url: https://figshare.scilifelab.se/ndownloader/files/42061209 pac: checksum: 90c98011896647750981f091b90bf2af path: ref_data/hg19/hg19.with.mt.fasta.pac + type: file url: https://figshare.scilifelab.se/ndownloader/files/42061221 sa: checksum: 9acd60cb19c1dd8da83283348670c744 path: ref_data/hg19/hg19.with.mt.fasta.sa + type: file url: https://figshare.scilifelab.se/ndownloader/files/42061224 fuseq_wes: reference: type: folder compressed_checksum: c66a0ba6fe5b76fedf16b404f67fcda4 - path: reference_data/fuseq_wes + path: ref_data/fuseq_wes content_checksum: ensmbl_paralogs_grch37.RData: af95895660e6b09ca07ffcedcc6c7ef1 Mitelman_fusiondb.RData: e4fbf81b5b02b9fe201161d324405822 @@ -75,65 +87,77 @@ sites: checksum: 1eb85e09195f0092e389510b40765f5e path: ref_data/GNOMAD/small_exac_common_3.hg19.vcf.gz + type: file url: https://figshare.scilifelab.se/ndownloader/files/40933373 variants: checksum: 1eb85e09195f0092e389510b40765f5e path: ref_data/GNOMAD/small_exac_common_3.hg19.vcf.gz + type: file url: https://figshare.scilifelab.se/ndownloader/files/40933373 variants_tbi: checksum: fe613a305067fa746f49113b78088490 path: ref_data/GNOMAD/small_exac_common_3.hg19.vcf.gz.tbi + type: file url: https://figshare.scilifelab.se/ndownloader/files/41119760 gene_fuse: fasta: checksum: 7c1739fd43764bd5e3b9b76ce8635bf0 path: ref_data/hg19/hg19.with.mt.fasta + type: file url: https://figshare.scilifelab.se/ndownloader/files/42060171 references: fasta: checksum: 7c1739fd43764bd5e3b9b76ce8635bf0 path: ref_data/hg19/hg19.with.mt.fasta + type: file url: https://figshare.scilifelab.se/ndownloader/files/42060171 fai: checksum: 6071b578df509d097874b3e58a1a9fc6 path: ref_data/hg19/hg19.with.mt.fasta.fai + type: file url: https://figshare.scilifelab.se/ndownloader/files/42061218 dict: checksum: bfd3a82e44e749f6864084ec51119a09 path: ref_data/hg19/hg19.with.mt.fasta.dict + type: file url: https://figshare.scilifelab.se/ndownloader/files/42061359 fusioncatcher: genome_path: - path: /sw/bioinfo/FusionCatcher/1.33/bianca/fusioncatcher/data/human_v102/ - url: compressed_name: human_v102.tar.gz - - + path: human_v102/ + type: file + url: + https://figshare.scilifelab.se/ndownloader/files/42061230:5f4968cf58a28bfe661ee3d1207259c6 + https://figshare.scilifelab.se/ndownloader/files/42061233:ad677c79617e36f85592b45918a10f21 + https://figshare.scilifelab.se/ndownloader/files/42061242:b4a57d1a48b12e3302fa7d12e6ac6347 + https://figshare.scilifelab.se/ndownloader/files/42061248:1280e3204b6990b825c762ac14e4446a + star: - extra: - path: ... genome_index: - path: ref_data/star - url: https://figshare.scilifelab.se/ndownloader/files/42061278 - checksum: compressed_name: star_v2.7.10a_hg19_index.tar.gz + path: star + type: file + url: https://figshare.scilifelab.se/ndownloader/files/42061278 + star-fusion: genome_path: #path: ref_data/ctat_genome_lib_build_dir path: GRCh37_gencode_v19_CTAT_lib_Mar012021.plug-n-play.tar.gz + type: file url: https://figshare.scilifelab.se/ndownloader/files/42084318 #compressed_name: GRCh37_gencode_v19_CTAT_lib_Mar012021.plug-n-play.tar.gz vep: vep_cache: path: /sw/data/vep/107 + type: folder diff --git a/docs/includes/config.yaml b/docs/includes/config.yaml index ef9e9257..a91e3d04 100644 --- a/docs/includes/config.yaml +++ b/docs/includes/config.yaml @@ -112,20 +112,12 @@ cnvkit_diagram: cnvkit_export_seg: container: "docker://hydragenetics/cnvkit:0.9.9" -cnv_html_report: - cnv_vcf: - - annotation: cnv_loh_genes - filter: cnv_hard_filter_loh - - annotation: cnv_amp_genes - filter: cnv_hard_filter_amp - template: config/reports/cnv_report_template.html - cnvkit_scatter: container: "docker://hydragenetics/cnvkit:0.9.9" cnv_html_report: show_table: true - template_dir: config/cnv_report_template + template_dir: config/reports/cnv_report_template cnv_tsv_report: amp_cn_limit: 6.0 @@ -146,6 +138,7 @@ fastqc: filter_vcf: snv_soft_filter: "config/filters/config_soft_filter_uppsala_vep105.yaml" snv_hard_filter: "config/filters/config_hard_filter_uppsala_vep105.yaml" + snv_hard_filter_purecn: "config/filters/config_hard_filter_purecn.yaml" cnv_hard_filter_amp: "config/filters/config_hard_filter_cnv_amp.yaml" cnv_hard_filter_loh: "config/filters/config_hard_filter_cnv_loh.yaml" germline: "config/filters/config_hard_filter_germline_vep105.yaml"