Merge pull request #82 from umccr/patch1-pd

Grab correct cancer gene panel somatic_panel-v24.03.0.tsv
umccr · Aug 20, 2024 · 1226f7a · 1226f7a
2 parents c16f9a2 + cead7f1
commit 1226f7a
Show file tree

Hide file tree

Showing 16 changed files with 73 additions and 1,330 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -2,7 +2,7 @@
 # R specific hooks: https://github.com/lorenzwalthert/precommit
 repos:
 -   repo: https://github.com/lorenzwalthert/precommit
-    rev: v0.3.2
+    rev: v0.4.3
     hooks:
     -   id: style-files
         args: [--style_pkg=styler, --style_fun=tidyverse_style]
@@ -14,7 +14,7 @@ repos:
     -   id: use-tidy-description
     -   id: readme-rmd-rendered
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    rev: v4.6.0
     hooks:
     -   id: check-added-large-files
         args: ['--maxkb=200']

diff --git a/R/purple.R b/R/purple.R
@@ -51,7 +51,7 @@ purple_cnv_som_gene_read <- function(x) {
 #'
 #' @examples
 #' x <- system.file("extdata/purple/purple.cnv.gene.tsv", package = "gpgr")
-#' g <- system.file("extdata/ref/umccr_cancer_genes_v24.03.0.tsv", package = "gpgr")
+#' g <- system.file("extdata/ref/somatic_panel-v24.03.0.tsv", package = "gpgr")
 #' (pp <- purple_cnv_som_gene_process(x, g))
 #' @testexamples
 #' expect_equal(colnames(pp$tab)[ncol(pp$tab)], "minRegSupportStartEndMethod")
@@ -60,11 +60,11 @@ purple_cnv_som_gene_read <- function(x) {
 purple_cnv_som_gene_process <- function(x, g = NULL) {
   purple_cnv_gene <- purple_cnv_som_gene_read(x)
   if (is.null(g)) {
-    g <- system.file("extdata/ref/umccr_cancer_genes_v24.03.0.tsv", package = "gpgr")
+    g <- system.file("extdata/ref/somatic_panel-v24.03.0.tsv", package = "gpgr")
   }
   genes <-
     readr::read_tsv(g, col_types = readr::cols(
-      ensembl_gene_symbol = "c", oncogene = "l", tumorsuppressor = "l"
+      ensembl_gene_symbol = "c", oncogene = "l", tsgene = "l"
     )) |>
     dplyr::select(symbol = "ensembl_gene_symbol", "oncogene", "tsgene")
   oncogenes <- genes |>

diff --git a/R/sv.R b/R/sv.R
@@ -186,7 +186,7 @@ join_breakpoint_entries <- function(x) {
   # Group by GRIDSS identifier (clipping trailing h/o [h: High, o: lOwer])
   bps <- x |>
     tidyr::separate("ID", into = c("BND_group", "BND_mate"), sep = -1, convert = TRUE, remove = FALSE) |>
-    dplyr::group_by(BND_group)
+    dplyr::group_by(.data$BND_group)
 
   # Set a sequential breakpoint identifier
   bps_groups <- bps |> dplyr::n_groups()

diff --git a/README.Rmd b/README.Rmd
@@ -47,10 +47,10 @@ conda install r-gpgr -c umccr -c conda-forge -c bioconda
   (<https://github.com/hartwigmedical/hmftools/tree/master/purple>).
   See vignette at <https://umccr.github.io/gpgr/articles/purple.html>.
 
-### 🐍 umccrise {#id_-umccrise}
+### sash {#id_-sash}
 
-- Generate a HTML report with results from the `umccrise` DRAGEN tumor/normal
-  post-processing workflow from UMCCR - <https://github.com/umccr/umccrise>.
+- Generate a HTML report with results from the `sash` WGS post-processing workflow
+   - <https://github.com/scwatts/sash>.
   See the [CLI](#cli) section below for options.
 
 ## 🥳 Developers {#id_-developers}

diff --git a/README.md b/README.md
@@ -1,11 +1,10 @@
 
 - [📚 gpgr - Genomics Platform Group
-  Reporting](#-gpgr---genomics-platform-group-reporting)
+  Reporting](#books-gpgr---genomics-platform-group-reporting)
   - [Installation](#installation)
   - [Main modules](#main-modules)
-    - [🕸 LINX](#id_-linx)
     - [🔮 PURPLE](#id_-purple)
-    - [🐍 umccrise](#id_-umccrise)
+    - [sash](#id_-sash)
   - [🥳 Developers](#id_-developers)
   - [💻 CLI](#id_-cli)
 
@@ -37,28 +36,19 @@ conda install r-gpgr -c umccr -c conda-forge -c bioconda
 
 ## Main modules
 
-### 🕸 LINX
-
-- Generate a HTML report with results from the `LINX` structural variant
-  visualisation tool from the Hartwig Medical Foundation
-  (<https://github.com/hartwigmedical/hmftools/tree/master/linx>). See
-  the [CLI](#cli) section below for options.
-- For useful functions for reading/processing `LINX` results, see the
-  vignette at <https://umccr.github.io/gpgr/articles/linx.html>.
-
 ### 🔮 PURPLE
 
 - Read and process output files from the `PURPLE` purity/copy number
   estimator tool from the Hartwig Medical Foundation
   (<https://github.com/hartwigmedical/hmftools/tree/master/purple>). See
   vignette at <https://umccr.github.io/gpgr/articles/purple.html>.
 
-### 🐍 umccrise
+### sash
 
-- Generate a HTML report with results from the `umccrise` DRAGEN
-  tumor/normal post-processing workflow from UMCCR -
-  <https://github.com/umccr/umccrise>. See the [CLI](#cli) section below
-  for options.
+- Generate a HTML report with results from the `sash` WGS
+  post-processing workflow
+  - <https://github.com/scwatts/sash>. See the [CLI](#cli) section below
+    for options.
 
 ## 🥳 Developers
 
@@ -80,52 +70,40 @@ export PATH="${gpgr_cli}:${PATH}"
 ```
 
     gpgr.R --version
-    gpgr.R 1.4.3
+    gpgr.R 2.1.0
 
     #-----------------------------------#
     gpgr.R --help
-    usage: gpgr.R [-h] [-v] {linx,canrep} ...
+    usage: gpgr.R [-h] [-v] {canrep} ...
 
     UMCCR Genomics Platform Group Reporting
 
     positional arguments:
-      {linx,canrep}  sub-command help
-        linx         UMCCR LINX Report.
+      {canrep}       sub-command help
         canrep       UMCCR Cancer Report.
 
     options:
       -h, --help     show this help message and exit
       -v, --version  show program's version number and exit
 
-    #-----------------------------------#
-    #------- LINX Report -------#
-    gpgr.R linx --help
-    usage: gpgr.R linx [-h] --sample SAMPLE --plot PLOT --table TABLE [--out OUT]
-                       [--quiet]
-
-    options:
-      -h, --help       show this help message and exit
-      --sample SAMPLE  Sample name.
-      --plot PLOT      Path to LINX plot directory.
-      --table TABLE    Path to LINX table directory.
-      --out OUT        HTML output file name [def: linx_{sample}.html].
-      --quiet          Suppress log printing during rendering.
-
     #-----------------------------------#
     #------- Cancer Report -------#
     gpgr.R canrep --help
     usage: gpgr.R canrep [-h] --af_global AF_GLOBAL --af_keygenes AF_KEYGENES
-                         --batch_name BATCH_NAME --conda_list CONDA_LIST --img_dir
-                         IMG_DIR --key_genes KEY_GENES --somatic_snv_summary
-                         SOMATIC_SNV_SUMMARY --somatic_snv_vcf SOMATIC_SNV_VCF
+                         --batch_name BATCH_NAME [--conda_list CONDA_LIST]
+                         --img_dir IMG_DIR --key_genes KEY_GENES --oncokb_genes
+                         ONCOKB_GENES --somatic_snv_vcf SOMATIC_SNV_VCF
+                         --somatic_snv_summary SOMATIC_SNV_SUMMARY
                          --somatic_sv_tsv SOMATIC_SV_TSV --somatic_sv_vcf
                          SOMATIC_SV_VCF --purple_som_gene_cnv PURPLE_SOM_GENE_CNV
-                         --purple_som_cnv PURPLE_SOM_CNV --purple_purity
-                         PURPLE_PURITY --purple_qc PURPLE_QC --purple_som_snv_vcf
-                         PURPLE_SOM_SNV_VCF --oncoviral_present_viruses
-                         ONCOVIRAL_PRESENT_VIRUSES --oncoviral_breakpoints_tsv
-                         ONCOVIRAL_BREAKPOINTS_TSV [--out_file OUT_FILE] [--quiet]
-                         --result_outdir RESULT_OUTDIR --tumor_name TUMOR_NAME
+                         --purple_som_cnv_ann PURPLE_SOM_CNV_ANN --purple_som_cnv
+                         PURPLE_SOM_CNV --purple_purity PURPLE_PURITY --purple_qc
+                         PURPLE_QC --purple_som_snv_vcf PURPLE_SOM_SNV_VCF
+                         --virusbreakend_tsv VIRUSBREAKEND_TSV --virusbreakend_vcf
+                         VIRUSBREAKEND_VCF --dragen_hrd DRAGEN_HRD
+                         --bcftools_stats BCFTOOLS_STATS [--out_file OUT_FILE]
+                         [--quiet] --result_outdir RESULT_OUTDIR --tumor_name
+                         TUMOR_NAME
 
     options:
       -h, --help            show this help message and exit
@@ -140,16 +118,21 @@ export PATH="${gpgr_cli}:${PATH}"
       --img_dir IMG_DIR     Path to directory containing PURPLE plots.
       --key_genes KEY_GENES
                             Path to UMCCR cancer gene file.
-      --somatic_snv_summary SOMATIC_SNV_SUMMARY
-                            Path to `somatic_snv_summary.json`.
+      --oncokb_genes ONCOKB_GENES
+                            Path to OncoKB database file.
       --somatic_snv_vcf SOMATIC_SNV_VCF
                             Path to `somatic-PASS.vcf.gz` SNV VCF.
+      --somatic_snv_summary SOMATIC_SNV_SUMMARY
+                            Path to `somatic_snv_summary.json` JSON.
       --somatic_sv_tsv SOMATIC_SV_TSV
                             Path to `manta.tsv` TSV file.
       --somatic_sv_vcf SOMATIC_SV_VCF
                             Path to `manta.vcf.gz` VCF file.
       --purple_som_gene_cnv PURPLE_SOM_GENE_CNV
                             Path to `purple.cnv.gene.tsv`.
+      --purple_som_cnv_ann PURPLE_SOM_CNV_ANN
+                            Path to annotated and prioritised
+                            `purple.cnv.somatic.tsv`.
       --purple_som_cnv PURPLE_SOM_CNV
                             Path to `purple.cnv.somatic.tsv`.
       --purple_purity PURPLE_PURITY
@@ -158,10 +141,14 @@ export PATH="${gpgr_cli}:${PATH}"
                             Path to `purple.qc`.
       --purple_som_snv_vcf PURPLE_SOM_SNV_VCF
                             Path to `purple.somatic.vcf.gz`.
-      --oncoviral_present_viruses ONCOVIRAL_PRESENT_VIRUSES
-                            Path to `oncoviruses/present_viruses.txt`.
-      --oncoviral_breakpoints_tsv ONCOVIRAL_BREAKPOINTS_TSV
-                            Path to `oncoviruses/oncoviral_breakpoints.tsv`.
+      --virusbreakend_tsv VIRUSBREAKEND_TSV
+                            Path to VIRUSBreakend summary file.
+      --virusbreakend_vcf VIRUSBREAKEND_VCF
+                            Path to VIRUSBreakend VCF file.
+      --dragen_hrd DRAGEN_HRD
+                            Path to DRAGEN HRD file
+      --bcftools_stats BCFTOOLS_STATS
+                            Path to bcftools stats file
       --out_file OUT_FILE   Path to output HTML file (needs '.html' suffix) [def:
                             {tumor_name}_cancer_report.html].
       --quiet               Suppress log printing during rendering.

diff --git a/inst/extdata/purple/purple.purity.tsv.dvc b/inst/extdata/purple/purple.purity.tsv.dvc
@@ -1,5 +1,5 @@
 outs:
-- md5: b7e6e168bb07e3dc3bcab9934cda9094
-  size: 482
+- md5: 37113a19fbacef8079824f7802f8ee4d
+  size: 468
   path: purple.purity.tsv
   hash: md5
diff --git a/inst/extdata/purple/purple.qc.dvc b/inst/extdata/purple/purple.qc.dvc
@@ -1,5 +1,5 @@
 outs:
-- md5: c10f44c2a7dc2b29cd2971efc94e0b0d
-  size: 228
+- md5: 2ec1cbc0a2c173f8154de718e82afb5d
+  size: 246
   path: purple.qc
   hash: md5
diff --git a/inst/extdata/ref/.gitignore b/inst/extdata/ref/.gitignore
@@ -1 +1,2 @@
 /umccr_cancer_genes_v24.03.0.tsv
+/somatic_panel-v24.03.0.tsv
diff --git a/inst/extdata/ref/somatic_panel-v24.03.0.tsv.dvc b/inst/extdata/ref/somatic_panel-v24.03.0.tsv.dvc
@@ -0,0 +1,5 @@
+outs:
+- md5: 5ada82f5b399519a6ed34d5449a343f4
+  size: 50539
+  hash: md5
+  path: somatic_panel-v24.03.0.tsv