Fixing v14 breaking changes (#523)

* Try skipping both poly-A steps in CI * Move up TP53 NF1 classifier step * Comment out for now * What else is broken? * Are there EPN samples? * Test fusion-summary * Reorganize config file * Fix formatting * Address circos plot related CircleCI errors * Oops left testing data file path in Co-authored-by: Candace Savonen <cansav09@gmail.com>
AlexsLemonade · Feb 7, 2020 · 8a3df18 · 8a3df18
1 parent a5dd6c1
commit 8a3df18
Show file tree

Hide file tree

Showing 7 changed files with 183 additions and 194 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -20,20 +20,47 @@ jobs:
           name: Sample Distribution Analyses
           command: ./scripts/run_in_ci.sh bash "analyses/sample-distribution-analysis/run-sample-distribution.sh"
 
+      # TODO: The data files for CI need to be fixed https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/527
+      # - run:
+      #     name: TP53 NF1 classifier run
+      #     command: OPENPBTA_POLYAPLOT=0 ./scripts/run_in_ci.sh bash "analyses/tp53_nf1_score/run_classifier.sh"  
+
       # The analysis no longer needs to be tested as it has been retired and is better covered by 'SNV Caller Analysis' below.
       #- run:
       #    name: Mutect2 vs Strelka2
       #    command: ./scripts/run_in_ci.sh Rscript -e "rmarkdown::render('analyses/mutect2-vs-strelka2/01-set-up.Rmd', clean = TRUE);
       #                                                rmarkdown::render('analyses/mutect2-vs-strelka2/02-analyze-concordance.Rmd', clean = TRUE)"
-
-      - run:
-          name: Collapse RSEM
-          command: ./scripts/run_in_ci.sh bash analyses/collapse-rnaseq/run-collapse-rnaseq.sh
+
+     ### MOLECULAR SUBTYPING ###
 
       - run:
           name: Molecular Subtyping - HGG
           command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-HGG/run-molecular-subtyping-HGG.sh
 
+      - run:
+          name: Molecular subtyping - Non-MB/Non-ATRT Embryonal tumors 
+          command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-embryonal/run-embryonal-subtyping.sh
+
+      - run:
+          name: Molecular Subtyping and Plotting - ATRT
+          command:  OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-ATRT/run-molecular-subtyping-ATRT.sh
+
+      - run:
+          name: Molecular subtyping Chordoma
+          command: ./scripts/run_in_ci.sh Rscript -e "rmarkdown::render('analyses/molecular-subtyping-chordoma/01-Subtype-chordoma.Rmd', clean = TRUE)"
+
+
+      # Deprecated - these results do not include germline calls and therefore are insufficient by subtyping
+      # - run:
+      #     name: SHH TP53 Molecular Subtyping
+      #     command: ./scripts/run_in_ci.sh Rscript -e "rmarkdown::render('analyses/molecular-subtyping-SHH-tp53/SHH-tp53-molecular-subtyping-data-prep.Rmd', clean = TRUE)"
+
+      ### END MOLECULAR SUBTYPING ###
+
+      - run:
+          name: Collapse RSEM
+          command: ./scripts/run_in_ci.sh bash analyses/collapse-rnaseq/run-collapse-rnaseq.sh
+
       - run:
           name: Immune deconvolution using xCell and MCP-Counter
           command: OPENPBTA_DECONV_METHOD="mcp_counter" ./scripts/run_in_ci.sh bash analyses/immune-deconv/run-immune-deconv.sh
@@ -85,10 +112,6 @@ jobs:
           name: Tumor mutation burden with TCGA
           command: ./scripts/run_in_ci.sh Rscript -e "rmarkdown::render('analyses/tmb-compare-tcga/compare-tmb.Rmd', clean = TRUE)"
 
-      - run:
-          name: Molecular subtyping - Non-MB/Non-ATRT Embryonal tumors 
-          command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-embryonal/run-embryonal-subtyping.sh
-
       - run:
           name: Copy number consensus
           command: ./scripts/run_in_ci.sh bash "analyses/copy_number_consensus_call/run_consensus_call.sh"
@@ -104,32 +127,19 @@ jobs:
       - run:
           name: Comparative RNASeq - generate correlation matrix - rsem-tpm.stranded
           command: ./scripts/run_in_ci.sh python3 analyses/comparative-RNASeq-analysis/01-correlation-matrix.py ../../data/pbta-gene-expression-rsem-tpm.stranded.rds --output-prefix rsem-tpm-stranded- --verbose
-
-      - run:
-          name: Molecular Subtyping and Plotting - ATRT
-          command:  OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-ATRT/run-molecular-subtyping-ATRT.sh        
-
+
       - run:
           name: Process SV file
           command: ./scripts/run_in_ci.sh Rscript analyses/sv-analysis/01-process-sv-file.R
 
       - run:
           name: Oncoprint plotting
           command: ./scripts/run_in_ci.sh bash "analyses/oncoprint-landscape/run-oncoprint.sh"
-
-      - run:
-          name: TP53 NF1 classifier run
-          command: OPENPBTA_POLYAPLOT=0 ./scripts/run_in_ci.sh bash "analyses/tp53_nf1_score/run_classifier.sh"  
 
       - run:
           name: GISTIC Plots
           command: ./scripts/run_in_ci.sh Rscript -e "rmarkdown::render('analyses/cnv-chrom-plot/gistic_plot.Rmd', clean = TRUE)"
 
-      # Deprecated - these results do not include germline calls and therefore are insufficient by subtyping
-      # - run:
-      #     name: SHH TP53 Molecular Subtyping
-      #     command: ./scripts/run_in_ci.sh Rscript -e "rmarkdown::render('analyses/molecular-subtyping-SHH-tp53/SHH-tp53-molecular-subtyping-data-prep.Rmd', clean = TRUE)"
-
       - run:
           name: Gene set enrichment analysis to generate GSVA scores
           command: OPENPBTA_TESTING=1 ./scripts/run_in_ci.sh bash "analyses/gene-set-enrichment-analysis/run-gsea.sh" 
@@ -142,10 +152,6 @@ jobs:
           name: Fusion Summary
           command: OPENPBTA_TESTING=1 ./scripts/run_in_ci.sh bash "analyses/fusion-summary/run-new-analysis.sh"
 
-      - run:
-          name: Molecular subtyping Chordoma
-          command: ./scripts/run_in_ci.sh Rscript -e "rmarkdown::render('analyses/molecular-subtyping-chordoma/01-Subtype-chordoma.Rmd', clean = TRUE)"
-
       - run:
           name: Telomerase activity
           command: ./scripts/run_in_ci.sh bash analyses/telomerase-activity-prediction/RUN-telomerase-activity-prediction.sh

diff --git a/analyses/chromosomal-instability/01b-visualization-cnv-sv.Rmd b/analyses/chromosomal-instability/01b-visualization-cnv-sv.Rmd
@@ -88,11 +88,8 @@ metadata <- readr::read_tsv(file.path(data_dir, "pbta-histologies.tsv"))
 Read in the CNV data. 
 
 ```{r}
-# TODO: update file path when consensus is added to data release
 cnv_df <- data.table::fread(
-  file.path("..", 
-            "copy_number_consensus_call", 
-            "results",
+  file.path(data_dir, 
             "pbta-cnv-consensus.seg.gz"),
   data.table = FALSE
 ) 
@@ -307,7 +304,7 @@ circos_map_plot(
 ```{r}
 circos_map_transloc(transloc_df,
   add_track = FALSE, # We change this to true to add on to our already existing plot
-  sample_names = samples_for_examples[1],
+  sample_names = sample(transloc_df$biospecimen_id1, 1),
   samples_col = "biospecimen_id1",
   chr_col_1 = "chrom1", # Need to specify which column is the first and second location for each
   chr_col_2 = "chrom2",
@@ -326,7 +323,7 @@ png(file.path(plots_dir, "transloc_circos_plot.png"), width = 800, height = 800)
 # Run function per usual
 circos_map_transloc(transloc_df,
   add_track = FALSE,
-  sample_names = samples_for_examples[1],
+  sample_names = sample(transloc_df$biospecimen_id1, 1),
   samples_col = "biospecimen_id1",
   chr_col_1 = "chrom1",
   chr_col_2 = "chrom2",

diff --git a/analyses/chromosomal-instability/01b-visualization-cnv-sv.nb.html b/analyses/chromosomal-instability/01b-visualization-cnv-sv.nb.html
diff --git a/analyses/chromosomal-instability/util/circos-plots.R b/analyses/chromosomal-instability/util/circos-plots.R
@@ -135,6 +135,13 @@ circos_map_plot <- function(df,
   y_min <- min(bed_df$y_val, na.rm = TRUE)
   y_max <- max(bed_df$y_val, na.rm = TRUE)
 
+  # Can't have identical y_min and y_max, this is just so CircleCI runs even if 
+  # the subset data is wonky
+  if (y_min == y_max) {
+    y_max <- y_max + 0.001 
+    warning("ymax and ymin are identical")
+  }
+
   # Tell them only one color is allowed
   if (length(single_color) > 1) {
     warning("Only a single color is allowed for the `single_color` argument, 

diff --git a/analyses/fusion-summary/01-fusion-summary.Rmd b/analyses/fusion-summary/01-fusion-summary.Rmd
@@ -151,36 +151,28 @@ specimensUnion<- union(arribaDF$tumor_id, starfusionDF$tumor_id)
 #### Write non-MB, non-ATRT embryonal fusions to file
 
 ```{r}
-allFuseEmbry <- allFuseEmbry %>%
-  prepareOutput(specimensUnion)
+if (!running_in_ci) {
+  allFuseEmbry <- allFuseEmbry %>%
+    prepareOutput(specimensUnion)
+  allFuseEmbry %>%
+    mutate(
+      `CIC--NUTM1` = 0,
+      `MN1--BEND2` = 0
+    ) %>%
+    write_tsv(embryFile)
+}
 ```
 
-```{r}
-# Are there any missing fusions?
-setdiff(embryFuses, colnames(allFuseEmbry))
-```
+#### Write ependymoma fusions to file
 
 ```{r}
-allFuseEmbry %>%
+allFuseEpend %>%
+  prepareOutput(specimensUnion) %>%
   mutate(
-    `CIC--NUTM1` = 0,
-    `MN1--BEND2` = 0
+    `C11orf95--YAP1` = 0,
+    `LTBP3--RELA` = 0,
+    `PTEN--TAS2R1` = 0,
+    `YAP1--MAMLD2` = 0
   ) %>%
-  write_tsv(embryFile)
-```
-
-#### Write ependymoma fusions to file
-
-```{r}
-if (!running_in_ci) {
-  allFuseEpend %>%
-    prepareOutput(specimensUnion) %>%
-    mutate(
-      `C11orf95--YAP1` = 0,
-      `LTBP3--RELA` = 0,
-      `PTEN--TAS2R1` = 0,
-      `YAP1--MAMLD2` = 0
-    ) %>%
-    write_tsv(ependFile)
-}
+  write_tsv(ependFile)
 ```