final polish and changelog

sigven · May 31, 2024 · 8cf42c7 · 8cf42c7
1 parent 9af4298
commit 8cf42c7
Show file tree

Hide file tree

Showing 12 changed files with 209 additions and 158 deletions.
diff --git a/R/main.R b/R/main.R
@@ -437,12 +437,18 @@ write_cpsr_output <- function(report,
     }
 
     if(NROW(report$content$snv_indel$callset$variant$bm) > 0){
+
+      bm_excel <- report$content$snv_indel$callset$variant$bm |>
+        dplyr::mutate(
+          BM_MOLECULAR_PROFILE = pcgrr::strip_html(
+            .data$BM_MOLECULAR_PROFILE))
+
       workbook <- workbook |>
         openxlsx2::wb_add_worksheet(sheet = "BIOMARKER_EVIDENCE") |>
         openxlsx2::wb_add_data_table(
           sheet = "BIOMARKER_EVIDENCE",
           x = dplyr::select(
-            report$content$snv_indel$callset$variant$bm,
+            bm_excel,
             dplyr::any_of(
               cpsr::col_format_output[['xlsx_biomarker']])),
           start_row = 1,

diff --git a/data-raw/data-raw.R b/data-raw/data-raw.R
@@ -181,15 +181,15 @@ col_format_output[['html_bm']] <-
     'PROTEIN_CHANGE',
     'CONSEQUENCE',
     'BM_EVIDENCE_LEVEL',
+    'BM_MOLECULAR_PROFILE',
+    'BM_REFERENCE',
     'GENOTYPE',
     "DP_CONTROL",
     'BM_CANCER_TYPE',
     'BM_DISEASE_ONTOLOGY_ID',
     'BM_PRIMARY_SITE',
     'BM_CLINICAL_SIGNIFICANCE',
     'BM_THERAPEUTIC_CONTEXT',
-    'BM_REFERENCE',
-    'BM_MOLECULAR_PROFILE_NAME',
     'BM_RATING',
     'BM_EVIDENCE_TYPE',
     'BM_EVIDENCE_DIRECTION',
@@ -319,7 +319,7 @@ col_format_output[['xlsx_biomarker']] <-
     "BM_THERAPEUTIC_CONTEXT",
     "BM_CITATION",
     "BM_RATING",
-    "BM_MOLECULAR_PROFILE_NAME",
+    "BM_MOLECULAR_PROFILE",
     "BM_EVIDENCE_TYPE",
     "BM_EVIDENCE_LEVEL",
     "BM_EVIDENCE_DIRECTION",
@@ -373,150 +373,172 @@ acmg[["score2tier"]] <-
 
 usethis::use_data(acmg, overwrite = T)
 usethis::use_data(col_format_output, overwrite = T)
-
-my_log4r_layout <- function(level, ...) {
-  paste0(format(Sys.time()), " - cpsr-report-generation - ",
-         level, " - ", ..., "\n", collapse = "")
-}
-
-log4r_logger <-
-  log4r::logger(
-    threshold = "INFO", appenders = log4r::console_appender(my_log4r_layout))
-
-# this gets passed on to all the log4r_* functions inside the pkg
-options("PCGRR_LOG4R_LOGGER" = log4r_logger)
-
-panel_zero <- list()
-for(build in c('grch37','grch38')){
-  ref_data <- pcgrr::load_reference_data(
-    pcgr_db_assembly_dir =
-      file.path(
-        "/Users/sigven/project_data/data/data__pcgrdb/dev/pcgrdb",
-        "20240527/data",
-        build)
-  )
-  panel_zero[[build]] <- ref_data$gene$cpg |>
-    dplyr::filter(CPG_SOURCE != "ACMG_SF") |>
-    dplyr::mutate(
-      PANEL_NAME = "CPSR superpanel of cancer predisposition genes",
-      PANEL_VERSION = "v2024_05") |>
-    dplyr::inner_join(
-      dplyr::select(ref_data$gene$gene_xref,
-                    ENTREZGENE,
-                    ENSEMBL_GENE_ID,
-                    GENE_BIOTYPE,
-                    GENENAME,
-                    TSG,
-                    TSG_SUPPORT,
-                    ONCOGENE,
-                    ONCOGENE_SUPPORT),
-      by = c("ENTREZGENE","ENSEMBL_GENE_ID")
-    ) |>
-    dplyr::rename(
-      TUMOR_SUPPRESSOR = TSG,
-      TUMOR_SUPPRESSOR_SUPPORT = TSG_SUPPORT
-    ) |>
-    dplyr::left_join(
-      dplyr::select(
-        dplyr::filter(
-          ref_data$variant$clinvar_gene_stats,
-          .data$CONFIDENCE == "min2goldstars"),
-        c("ENTREZGENE",
-          "N_TRUNC_PATH",
-          "N_NONTRUNC_PATH",
-          "N_MISSENSE_PATH",
-          "N_MISSENSE_BENIGN",
-          "BENIGN_MISSENSE_FRAC",
-          "PATH_TRUNC_FRAC")
-      ), by = "ENTREZGENE"
-    ) |>
-    dplyr::select(
-      dplyr::any_of(
-        c("ENTREZGENE",
-          "SYMBOL",
-          "GENENAME",
-          "GENE_BIOTYPE",
-          "ENSEMBL_GENE_ID",
-          "TUMOR_SUPPRESSOR",
-          "TUMOR_SUPPRESSOR_SUPPORT",
-          "ONCOGENE",
-          "ONCOGENE_SUPPORT",
-          "CPG_SOURCE",
-          "CPG_MOD",
-          "CPG_MOI",
-          "CPG_PHENOTYPES",
-          "CPG_CANCER_CUI",
-          "CPG_SYNDROME_CUI")
-      ),
-      dplyr::everything()
-    ) |>
-    dplyr::distinct()
-}
 #
-workbook <- openxlsx2::wb_workbook() |>
-  openxlsx2::wb_add_worksheet(sheet = "CPSR_SUPERPANEL.GRCH37") |>
-  openxlsx2::wb_add_worksheet(sheet = "CPSR_SUPERPANEL.GRCH38") |>
-  openxlsx2::wb_add_data_table(
-    sheet = "CPSR_SUPERPANEL.GRCH37",
-    x = panel_zero[['grch37']],
-    start_row = 1,
-    start_col = 1,
-    col_names = TRUE,
-    na.strings = "NA",
-    table_style = "TableStyleMedium15") |>
-  openxlsx2::wb_add_data_table(
-    sheet = "CPSR_SUPERPANEL.GRCH38",
-    x = panel_zero[['grch38']],
-    start_row = 1,
-    start_col = 1,
-    col_names = TRUE,
-    na.strings = "NA",
-    table_style = "TableStyleMedium16")
-
-openxlsx2::wb_save(
-  wb = workbook,
-  "pkgdown/assets/cpsr_superpanel_2024_05.xlsx",
-  overwrite = TRUE)
-
+# my_log4r_layout <- function(level, ...) {
+#   paste0(format(Sys.time()), " - cpsr-report-generation - ",
+#          level, " - ", ..., "\n", collapse = "")
+# }
 #
-panel_zero_display <- panel_zero$grch38 |>
-  dplyr::select(
-    c("ENTREZGENE",
-      "SYMBOL",
-      "ENTREZGENE",
-      "ENSEMBL_GENE_ID",
-      "GENENAME",
-      "CPG_PHENOTYPES",
-      "CPG_MOI",
-      "CPG_MOD",
-      "CPG_SOURCE",
-    )
-  ) |>
-  dplyr::mutate(
-    CPG_SOURCE = stringr::str_replace_all(
-      CPG_SOURCE, "&", ", "
-    )) |>
-  dplyr::mutate(
-    CPG_SOURCE = stringr::str_replace_all(
-      CPG_SOURCE, "ACMG_SF", ""
-    )
-  ) |>
-  dplyr::mutate(
-    GENE = paste0(
-      "<a href='https://www.ncbi.nlm.nih.gov/gene/",
-      .data$ENTREZGENE,
-      "' target='_blank'>",
-      .data$SYMBOL, "</a>"
-    )
-  ) |>
-  dplyr::select(
-    c("GENE","ENTREZGENE","ENSEMBL_GENE_ID",
-      "CPG_MOD", "CPG_MOI", "GENENAME",
-      "CPG_SOURCE", "CPG_PHENOTYPES")
-  )
+# log4r_logger <-
+#   log4r::logger(
+#     threshold = "INFO", appenders = log4r::console_appender(my_log4r_layout))
+#
+# # this gets passed on to all the log4r_* functions inside the pkg
+# options("PCGRR_LOG4R_LOGGER" = log4r_logger)
+#
+# panel_zero <- list()
+# for(build in c('grch37','grch38')){
+#   ref_data <- pcgrr::load_reference_data(
+#     pcgr_db_assembly_dir =
+#       file.path(
+#         "/Users/sigven/project_data/data/data__pcgrdb/dev/pcgrdb",
+#         "20240530/data",
+#         build),
+#     genome_assembly = build
+#   )
+#
+#   set1 <- ref_data$gene$cpg |>
+#     dplyr::filter(CPG_SOURCE != "ACMG_SF") |>
+#     dplyr::filter(!is.na(ENSEMBL_GENE_ID)) |>
+#     dplyr::inner_join(
+#       dplyr::select(ref_data$gene$gene_xref,
+#                     ENTREZGENE,
+#                     ENSEMBL_GENE_ID,
+#                     GENE_BIOTYPE,
+#                     GENENAME,
+#                     TSG,
+#                     TSG_SUPPORT,
+#                     ONCOGENE,
+#                     ONCOGENE_SUPPORT),
+#       by = c("ENTREZGENE","ENSEMBL_GENE_ID")
+#     )
+#
+#   set2 <- ref_data$gene$cpg |>
+#     dplyr::filter(CPG_SOURCE != "ACMG_SF") |>
+#     dplyr::filter(is.na(ENSEMBL_GENE_ID)) |>
+#     dplyr::select(-c("ENSEMBL_GENE_ID")) |>
+#     dplyr::inner_join(
+#       dplyr::select(ref_data$gene$gene_xref,
+#                     ENTREZGENE,
+#                     ENSEMBL_GENE_ID,
+#                     GENE_BIOTYPE,
+#                     GENENAME,
+#                     TSG,
+#                     TSG_SUPPORT,
+#                     ONCOGENE,
+#                     ONCOGENE_SUPPORT),
+#       by = c("ENTREZGENE")
+#     )
+#
+#   panel_zero[[build]] <- dplyr::bind_rows(set1, set2) |>
+#     dplyr::mutate(
+#       PANEL_NAME = "CPSR superpanel of cancer predisposition genes",
+#       PANEL_VERSION = "v2024_05") |>
+#     dplyr::rename(
+#       TUMOR_SUPPRESSOR = TSG,
+#       TUMOR_SUPPRESSOR_SUPPORT = TSG_SUPPORT
+#     ) |>
+#     dplyr::left_join(
+#       dplyr::select(
+#         dplyr::filter(
+#           ref_data$variant$clinvar_gene_stats,
+#           .data$CONFIDENCE == "min2goldstars"),
+#         c("ENTREZGENE",
+#           "N_TRUNC_PATH",
+#           "N_NONTRUNC_PATH",
+#           "N_MISSENSE_PATH",
+#           "N_MISSENSE_BENIGN",
+#           "BENIGN_MISSENSE_FRAC",
+#           "PATH_TRUNC_FRAC")
+#       ), by = "ENTREZGENE"
+#     ) |>
+#     dplyr::select(
+#       dplyr::any_of(
+#         c("ENTREZGENE",
+#           "SYMBOL",
+#           "GENENAME",
+#           "GENE_BIOTYPE",
+#           "ENSEMBL_GENE_ID",
+#           "TUMOR_SUPPRESSOR",
+#           "TUMOR_SUPPRESSOR_SUPPORT",
+#           "ONCOGENE",
+#           "ONCOGENE_SUPPORT",
+#           "CPG_SOURCE",
+#           "CPG_MOD",
+#           "CPG_MOI",
+#           "CPG_PHENOTYPES",
+#           "CPG_CANCER_CUI",
+#           "CPG_SYNDROME_CUI")
+#       ),
+#       dplyr::everything()
+#     ) |>
+#     dplyr::distinct()
+# }
+# #
+# workbook <- openxlsx2::wb_workbook() |>
+#   openxlsx2::wb_add_worksheet(sheet = "CPSR_SUPERPANEL.GRCH37") |>
+#   openxlsx2::wb_add_worksheet(sheet = "CPSR_SUPERPANEL.GRCH38") |>
+#   openxlsx2::wb_add_data_table(
+#     sheet = "CPSR_SUPERPANEL.GRCH37",
+#     x = panel_zero[['grch37']],
+#     start_row = 1,
+#     start_col = 1,
+#     col_names = TRUE,
+#     na.strings = "NA",
+#     table_style = "TableStyleMedium15") |>
+#   openxlsx2::wb_add_data_table(
+#     sheet = "CPSR_SUPERPANEL.GRCH38",
+#     x = panel_zero[['grch38']],
+#     start_row = 1,
+#     start_col = 1,
+#     col_names = TRUE,
+#     na.strings = "NA",
+#     table_style = "TableStyleMedium16")
+#
+# openxlsx2::wb_save(
+#   wb = workbook,
+#   "pkgdown/assets/cpsr_superpanel_2024_05.xlsx",
+#   overwrite = TRUE)
 #
-readr::write_tsv(
-  panel_zero_display, file = "inst/extdata/panel_zero.tsv.gz",
-  na = "NA", col_names = T,quote = "none"
-)
+# #
+# panel_zero_display <- panel_zero$grch38 |>
+#   dplyr::select(
+#     c("ENTREZGENE",
+#       "SYMBOL",
+#       "ENTREZGENE",
+#       "ENSEMBL_GENE_ID",
+#       "GENENAME",
+#       "CPG_PHENOTYPES",
+#       "CPG_MOI",
+#       "CPG_MOD",
+#       "CPG_SOURCE",
+#     )
+#   ) |>
+#   dplyr::mutate(
+#     CPG_SOURCE = stringr::str_replace_all(
+#       CPG_SOURCE, "&", ", "
+#     )) |>
+#   dplyr::mutate(
+#     CPG_SOURCE = stringr::str_replace_all(
+#       CPG_SOURCE, "ACMG_SF", ""
+#     )
+#   ) |>
+#   dplyr::mutate(
+#     GENE = paste0(
+#       "<a href='https://www.ncbi.nlm.nih.gov/gene/",
+#       .data$ENTREZGENE,
+#       "' target='_blank'>",
+#       .data$SYMBOL, "</a>"
+#     )
+#   ) |>
+#   dplyr::select(
+#     c("GENE","ENTREZGENE","ENSEMBL_GENE_ID",
+#       "CPG_MOD", "CPG_MOI", "GENENAME",
+#       "CPG_SOURCE", "CPG_PHENOTYPES")
+#   )
+# #
+# readr::write_tsv(
+#   panel_zero_display, file = "inst/extdata/panel_zero.tsv.gz",
+#   na = "NA", col_names = T,quote = "none"
+# )
 
diff --git a/data/acmg.rda b/data/acmg.rda
diff --git a/data/col_format_output.rda b/data/col_format_output.rda
diff --git a/inst/extdata/panel_zero.tsv.gz b/inst/extdata/panel_zero.tsv.gz
diff --git a/inst/templates/cpsr_report.qmd b/inst/templates/cpsr_report.qmd
@@ -80,14 +80,14 @@ cat("</ul><br>")
 #| eval: !expr as.logical(cps_report$content$snv_indel$eval)
 ```
 
-<br><br>
+<br>
 
 ```{r biomarkers_cpsr} 
 #| child: 'quarto/cpsr_biomarkers.qmd'
 #| eval: !expr as.logical(cps_report$content$snv_indel$eval)
 ```
 
-<br><br>
+<br>
 
 ```{r secondary_findings_cpsr}
 #| child: 'quarto/cpsr_secondary_findings.qmd'