update bundle version and lof info

pcgr/pcgr_vars.py

@@ -3,7 +3,7 @@
 from pcgr._version import __version__
 
 PCGR_VERSION = __version__
-DB_VERSION = '20240530'
+DB_VERSION = '20240610'
 
 ## MISCELLANEOUS
 NCBI_BUILD_MAF = 'GRCh38'
@@ -12,13 +12,13 @@
 RECOMMENDED_N_MUT_SIGNATURE = 200
 
 ## GENCODE
-GENCODE_VERSION = {'grch38': 45,'grch37': 19}
+GENCODE_VERSION = {'grch38': 46,'grch37': 19}
 
 ## vcfanno
 VCFANNO_MAX_PROC = 15
 
 ## VEP settings/versions
-VEP_VERSION = '111'
+VEP_VERSION = '112'
 VEP_ASSEMBLY = {'grch38': 'GRCh38','grch37': 'GRCh37'}
 VEP_MIN_FORKS = 1
 VEP_MAX_FORKS = 8

pcgr/vep.py

@@ -4,12 +4,9 @@
 import csv
 import gzip
 
-from pcgr import annoutils, utils
 from pcgr.annoutils import assign_cds_exon_intron_annotations
 from pcgr import pcgr_vars
-from pcgr.utils import getlogger
-
-
+from pcgr.utils import getlogger, check_file_exists, get_perl_exports
 
 def get_vep_command(file_paths, conf_options, input_vcf, output_vcf, debug = False):
 
@@ -21,14 +18,9 @@ def get_vep_command(file_paths, conf_options, input_vcf, output_vcf, debug = Fal
         file_paths['refdata_assembly_dir'],
         'misc','fasta','assembly',
         f'Homo_sapiens.{pcgr_vars.VEP_ASSEMBLY[genome_assembly]}.dna.primary_assembly.fa.gz')
-    ancestor_assembly = os.path.join(
-        file_paths['refdata_assembly_dir'],
-        'misc','fasta','ancestor',
-        f'human_ancestor.fa.gz')
 
     logger = getlogger('check-fasta-files')
-    utils.check_file_exists(fasta_assembly, logger = logger)
-    utils.check_file_exists(ancestor_assembly, logger = logger)
+    check_file_exists(fasta_assembly, logger = logger)
 
     plugins_in_use = "NearestExonJB"
 
@@ -58,7 +50,7 @@ def get_vep_command(file_paths, conf_options, input_vcf, output_vcf, debug = Fal
         gencode_set_in_use = "GENCODE - basic transcript set (--gencode_basic)"
 
     # Compose full VEP command
-    vep_main_command = f'{utils.get_perl_exports()} && vep --input_file {input_vcf} --output_file {output_vcf} {vep_options}'
+    vep_main_command = f'{get_perl_exports()} && vep --input_file {input_vcf} --output_file {output_vcf} {vep_options}'
     vep_bgzip_command = f'bgzip -f -c {output_vcf} > {output_vcf_gz}'
     vep_tabix_command = f'tabix -f -p vcf {output_vcf_gz}'
     if debug:
@@ -71,7 +63,6 @@ def get_vep_command(file_paths, conf_options, input_vcf, output_vcf, debug = Fal
     vep_cmd['gencode_set_in_use'] = gencode_set_in_use
     vep_cmd['plugins_in_use'] = plugins_in_use
     vep_cmd['fasta_assembly'] = fasta_assembly
-    #vep_cmd['GENCODE_VERSION'] = 'release ' + str(pcgr_vars.GENCODE_VERSION[genome_assembly])
 
     return(vep_cmd)
 

pcgrr/DESCRIPTION

@@ -2,7 +2,6 @@ Package: pcgrr
 Type: Package
 Title: Personal Cancer Genome ReporteR
 Version: 1.4.1.9010
-Date: 2024-04-27
 Authors@R:
     c(person(given = "Sigve",
              family = "Nakken",

pcgrr/data-raw/data-raw.R

@@ -207,6 +207,7 @@ data_coltype_defs[['snv_indel_somatic_raw']] <- readr::cols_only(
   CONSEQUENCE = readr::col_character(),
   IMPACT = readr::col_character(),
   LOSS_OF_FUNCTION = readr::col_logical(),
+  LOF_FILTER = readr::col_character(),
   SPLICE_DONOR_RELEVANT = readr::col_logical(),
   NULL_VARIANT = readr::col_logical(),
   CODING_STATUS = readr::col_character(),
@@ -216,6 +217,7 @@ data_coltype_defs[['snv_indel_somatic_raw']] <- readr::cols_only(
   HGVSc = readr::col_character(),
   HGVSp = readr::col_character(),
   CDS_CHANGE = readr::col_character(),
+  CDS_RELATIVE_POSITION = readr::col_character(),
   EXON = readr::col_character(),
   EXON_AFFECTED = readr::col_character(),
   MUTATION_HOTSPOT = readr::col_character(),
@@ -306,6 +308,7 @@ data_coltype_defs[['snv_indel_germline_raw']] <- readr::cols_only(
   CONSEQUENCE = readr::col_character(),
   IMPACT = readr::col_character(),
   LOSS_OF_FUNCTION = readr::col_logical(),
+  LOF_FILTER = readr::col_character(),
   SPLICE_DONOR_RELEVANT = readr::col_logical(),
   NULL_VARIANT = readr::col_logical(),
   CODING_STATUS = readr::col_character(),
@@ -315,6 +318,7 @@ data_coltype_defs[['snv_indel_germline_raw']] <- readr::cols_only(
   HGVSc = readr::col_character(),
   HGVSp = readr::col_character(),
   CDS_CHANGE = readr::col_character(),
+  CDS_RELATIVE_POSITION = readr::col_character(),
   EXON = readr::col_character(),
   EXON_AFFECTED = readr::col_integer(),
   EXON_POSITION = readr::col_integer(),
@@ -487,6 +491,7 @@ tsv_cols[['snv_indel']] <-
     'CONSEQUENCE',
     'PFAM_DOMAIN_NAME',
     'LOSS_OF_FUNCTION',
+    'LOF_FILTER',
     'CDS_CHANGE',
     'CODING_STATUS',
     'EXONIC_STATUS',
@@ -647,6 +652,7 @@ dt_display[['snv_indel_gene_actionable']] <-
     'HGVSp',
     'PREDICTED_EFFECT',
     'LOSS_OF_FUNCTION',
+    'LOF_FILTER',
     'ONCOGENICITY',
     'ONCOGENICITY_CODE',
     'ONCOGENICITY_SCORE',
@@ -701,6 +707,8 @@ dt_display[['snv_indel_tier3']] <-
     'HGVSc',
     'HGVSp',
     'MUTATION_HOTSPOT_CANCERTYPE',
+    'LOSS_OF_FUNCTION',
+    'LOF_FILTER',
     'TCGA_FREQUENCY',
     'PREDICTED_EFFECT',
     'ONCOGENICITY_CODE',
@@ -739,6 +747,8 @@ dt_display[['tier4']] <-
     'HGVSc',
     'HGVSp',
     'PREDICTED_EFFECT',
+    'LOSS_OF_FUNCTION',
+    'LOF_FILTER',
     'REGULATORY_ANNOTATION',
     'ONCOGENICITY_CODE',
     'ONCOGENICITY_SCORE',
@@ -961,22 +971,40 @@ usethis::use_data(cosmic_sbs_signatures, overwrite = T)
 #usethis::use_data(cosmic_sbs_signatures_all, overwrite = T)
 #usethis::use_data(cosmic_sbs_signatures_no_artefacts, overwrite = T)
 
-immune_celltypes <- as.data.frame(
-  immunedeconv::cell_type_map |>
-    dplyr::filter(method_dataset == "quantiseq") |>
-    dplyr::select(method_cell_type, cell_type) |>
-    dplyr::mutate(cell_type = dplyr::if_else(
-      !is.na(cell_type) &
-        cell_type == "uncharacterized cell",
-      "Uncharacterized cell",
-      as.character(cell_type)
-    )) |>
-    dplyr::mutate(cell_type = factor(
-      cell_type, levels = cell_type)) |>
-    dplyr::distinct()
+# immune_celltypes <- as.data.frame(
+#   immunedeconv::cell_type_map |>
+#     dplyr::filter(method_dataset == "quantiseq") |>
+#     dplyr::select(method_cell_type, cell_type) |>
+#     dplyr::mutate(cell_type = dplyr::if_else(
+#       !is.na(cell_type) &
+#         cell_type == "uncharacterized cell",
+#       "Uncharacterized cell",
+#       as.character(cell_type)
+#     )) |>
+#     dplyr::mutate(cell_type = factor(
+#       cell_type, levels = cell_type)) |>
+#     dplyr::distinct()
+# )
+
+immune_celltypes2 <- data.frame(
+  method_cell_type = c("B.cells","Macrophages.M1",
+                       "Macrophages.M2","Monocytes",
+                       "Neutrophils","NK.cells",
+                       "T.cells.CD4","T.cells.CD8",
+                       "Tregs","Dendritic.cells",
+                       "Other"),
+  cell_type = c("B cell","Macrophage M1",
+                "Macrophage M2","Monocyte",
+                "Neutrophil","NK cell",
+                "T cell CD4+ (non-regulatory)",
+                "T cell CD8+",
+                "T cell regulatory (Tregs)",
+                "Myeloid dendritic cell",
+                "Uncharacterized cell")
 )
 
-usethis::use_data(immune_celltypes, overwrite = T)
+
+#usethis::use_data(immune_celltypes, overwrite = T)
 
 germline_filter_levels <-
   c("SOMATIC",

pcgrr/vignettes/annotation_resources.Rmd

@@ -4,10 +4,10 @@ output: rmarkdown::html_document
 ---
 
 ### Basic variant consequence annotation
-  * [VEP](http://www.ensembl.org/info/docs/tools/vep/index.html) - Variant Effect Predictor release 111 ([GENCODE v45](https://www.gencodegenes.org/human/) as gene reference database (v19 for grch37))
+  * [VEP](http://www.ensembl.org/info/docs/tools/vep/index.html) - Variant Effect Predictor release 112 ([GENCODE v46](https://www.gencodegenes.org/human/) as gene reference database (v19 for grch37))
 
 ###  *Insilico* predictions of effect of coding variants
-  * [dBNSFP](https://sites.google.com/site/jpopgen/dbNSFP) - database of non-synonymous functional predictions (v4.4, May 2023)
+  * [dBNSFP](https://sites.google.com/site/jpopgen/dbNSFP) - database of non-synonymous functional predictions (v4.5, November 2023)
 
 ###  Variant frequency databases
   * [gnomAD](http://exac.broadinstitute.org/) - germline variant frequencies exome-wide (r2.1, October 2018)
@@ -16,12 +16,12 @@ output: rmarkdown::html_document
   * [TCGA](https://portal.gdc.cancer.gov/) - somatic mutations discovered across 33 tumor type cohorts (release 39.0, December 2023)
 
 ### Variant databases of clinical utility
-  * [ClinVar](http://www.ncbi.nlm.nih.gov/clinvar/) - database of clinically related variants (May 2024)
-  * [CIViC](http://civic.genome.wustl.edu) - clinical interpretations of variants in cancer (May 23rd 2024)
+  * [ClinVar](http://www.ncbi.nlm.nih.gov/clinvar/) - database of clinically related variants (June 2024)
+  * [CIViC](http://civic.genome.wustl.edu) - clinical interpretations of variants in cancer (June 6th 2024)
   * [CGI](http://www.cancergenomeinterpreter.org/biomarkers) - Cancer Genome Interpreter Cancer Biomarkers Database (CGI) (October 18th 2022)
 
 ### Protein domains/functional features
-  * [UniProt/SwissProt KnowledgeBase](http://www.uniprot.org) - resource on protein sequence and functional information (2024_02)
+  * [UniProt/SwissProt KnowledgeBase](http://www.uniprot.org) - resource on protein sequence and functional information (2024_03)
   * [Pfam](http://pfam.xfam.org) - database of protein families and domains (v35.0, November 2021)
 
 ### Knowledge resources on gene and protein targets