d3b-center · komalsrathi · Oct 28, 2024 · Jun 20, 2024 · Jun 20, 2024 · Aug 18, 2024
diff --git a/analyses/tp53_nf1_score/00-tp53-nf1-alterations.R b/analyses/tp53_nf1_score/00-tp53-nf1-alterations.R
@@ -71,10 +71,10 @@ keep_columns <- c("Chromosome",
                   "Tumor_Sample_Barcode",
                   "Hugo_Symbol")
 
-tumoronly_snv <- data.table::fread(snvTumorOnlyFile, select = keep_columns) %>%
+tumoronly_snv <- data.table::fread(snvTumorOnlyFile, select = keep_columns, tmpdir = scratch_dir) %>%
   dplyr::rename("Kids_First_Biospecimen_ID" = "Tumor_Sample_Barcode") 
 
-consensus_snv <- data.table::fread(snvConsensusFile, select = keep_columns) %>%
+consensus_snv <- data.table::fread(snvConsensusFile, select = keep_columns, tmpdir = scratch_dir) %>%
   dplyr::rename("Kids_First_Biospecimen_ID" = "Tumor_Sample_Barcode") %>%
   bind_rows(tumoronly_snv)
 
@@ -126,7 +126,7 @@ tp53_coding <- coding_consensus_snv %>%
 # subset to TP53 cnv loss and format to tp53_coding file format
 tp53_loss<-cnvConsensus %>% 
   filter(gene_symbol == "TP53",
-         status == "Loss") %>%
+         status == "loss") %>%
   dplyr::rename("Tumor_Sample_Barcode" = "Kids_First_Biospecimen_ID",
                 "Variant_Classification" = "status",
                 "Hugo_Symbol" =  "gene_symbol")
@@ -145,7 +145,7 @@ nf1_coding <- coding_consensus_snv %>%
 # subset to NF1 loss and format to nf1_coding file format
 nf1_loss<-cnvConsensus %>% 
   filter(gene_symbol == "NF1",
-         status == "Loss") %>%
+         status == "loss") %>%
   dplyr::rename("Tumor_Sample_Barcode" = "Kids_First_Biospecimen_ID",
                 "Variant_Classification" = "status",
                 "Hugo_Symbol" =  "gene_symbol")

diff --git a/analyses/tp53_nf1_score/02-qc-rna_expression_score.nb.html b/analyses/tp53_nf1_score/02-qc-rna_expression_score.nb.html
diff --git a/analyses/tp53_nf1_score/03-tp53-cnv-loss-domain.Rmd b/analyses/tp53_nf1_score/03-tp53-cnv-loss-domain.Rmd
@@ -134,7 +134,7 @@ annotated_cn <- data.frame(
 ) %>%
   dplyr::distinct() %>%
   # select loss that overlaps the TP53 core domains 
-  dplyr::filter(status=="Loss") %>%
+  dplyr::filter(status=="loss") %>%
   dplyr::group_by(biospecimen_id,copy_number) %>%
   # summarise domain NAME per biospecimen_id TP53 loss
   dplyr::summarise(

diff --git a/analyses/tp53_nf1_score/03-tp53-cnv-loss-domain.nb.html b/analyses/tp53_nf1_score/03-tp53-cnv-loss-domain.nb.html
diff --git a/analyses/tp53_nf1_score/04-tp53-sv-loss.Rmd b/analyses/tp53_nf1_score/04-tp53-sv-loss.Rmd
@@ -24,6 +24,7 @@ library("tidyverse")
 
 # rootdir
 root_dir <- rprojroot::find_root(rprojroot::has_dir(".git"))
+scratch_dir <- file.path(root_dir, "scratch")
 data_dir <- file.path(root_dir, "data")
 results_dir <- file.path(
   root_dir,
@@ -40,7 +41,7 @@ if (!dir.exists(results_dir)) {
 ### Input files
 ```{r}
 putative_onco_fusion <- read_rds(file.path(data_dir, "Hope-fusion-putative-oncogenic.rds"))
-manta_sv <- data.table::fread(file.path(data_dir, "Hope-sv-manta.tsv.gz")) 
+manta_sv <- data.table::fread(file.path(data_dir, "Hope-sv-manta.tsv.gz"), tmpdir = scratch_dir) 
 rna_expr <- readRDS(file.path(data_dir, "Hope-and-CPTAC-GBM-gene-expression-rsem-tpm-collapsed.rds"))
 clinical<-read_tsv(file.path(data_dir,"Hope-GBM-histologies-base.tsv"))
 

diff --git a/analyses/tp53_nf1_score/04-tp53-sv-loss.nb.html b/analyses/tp53_nf1_score/04-tp53-sv-loss.nb.html
diff --git a/analyses/tp53_nf1_score/05-tp53-altered-annotation.Rmd b/analyses/tp53_nf1_score/05-tp53-altered-annotation.Rmd
@@ -34,6 +34,7 @@ library("broom")
 
 # rootdir
 root_dir <- rprojroot::find_root(rprojroot::has_dir(".git"))
+scratch_dir <- file.path(root_dir, "scratch")
 data_dir <- file.path(root_dir, "data")
 
 input_dir <- file.path(root_dir,
@@ -133,7 +134,8 @@ consensus_tp53_snv_indel <- data.table::fread(
          "Variant_Classification",
          "Tumor_Sample_Barcode",
          "SYMBOL",
-         "HGVSp_Short")) %>%
+         "HGVSp_Short"),
+  tmpdir = scratch_dir) %>%
   rename("Kids_First_Biospecimen_ID" = "Tumor_Sample_Barcode") %>%
   rename(Hugo_Symbol = SYMBOL) %>%
   filter(Hugo_Symbol == "TP53") %>%

diff --git a/analyses/tp53_nf1_score/05-tp53-altered-annotation.nb.html b/analyses/tp53_nf1_score/05-tp53-altered-annotation.nb.html
diff --git a/analyses/tp53_nf1_score/06-evaluate-classifier.py b/analyses/tp53_nf1_score/06-evaluate-classifier.py
@@ -151,7 +151,10 @@ def get_roc_plot(scores_df, gene, outputfilename, color):
         sample_status, sample_score, drop_intermediate=False
     )
     precision_pbta, recall_pbta, _ = precision_recall_curve(sample_status, sample_score)
-    auroc_pbta = roc_auc_score(sample_status, sample_score)
+    try:
+        auroc_pbta = roc_auc_score(sample_status, sample_score)
+    except ValueError:
+        auroc_pbta = 0
     aupr_pbta = average_precision_score(sample_status, sample_score)
 
     # Obtain Shuffled Metrics
@@ -161,7 +164,10 @@ def get_roc_plot(scores_df, gene, outputfilename, color):
     precision_shuff, recall_shuff, _ = precision_recall_curve(
         sample_status, shuffle_score
     )
-    auroc_shuff = roc_auc_score(sample_status, shuffle_score)
+    try:
+        auroc_shuff = roc_auc_score(sample_status, shuffle_score)
+    except ValueError:
+        auroc_shuff = 0
     aupr_shuff = average_precision_score(sample_status, shuffle_score)
 
     roc_df = (

diff --git a/analyses/tp53_nf1_score/__pycache__/utils.cpython-310.pyc b/analyses/tp53_nf1_score/__pycache__/utils.cpython-310.pyc
diff --git a/analyses/tp53_nf1_score/plots/HR_DGM.png b/analyses/tp53_nf1_score/plots/HR_DGM.png
diff --git a/analyses/tp53_nf1_score/plots/HR_DGM_tp53_interaction.png b/analyses/tp53_nf1_score/plots/HR_DGM_tp53_interaction.png
diff --git a/analyses/tp53_nf1_score/plots/HR_HGG_WT.png b/analyses/tp53_nf1_score/plots/HR_HGG_WT.png
diff --git a/analyses/tp53_nf1_score/plots/HR_broad_mol_subtype.png b/analyses/tp53_nf1_score/plots/HR_broad_mol_subtype.png
diff --git a/analyses/tp53_nf1_score/plots/HR_mol_subtype_without_tp53.png b/analyses/tp53_nf1_score/plots/HR_mol_subtype_without_tp53.png
diff --git a/analyses/tp53_nf1_score/plots/HR_molecular_subtype.png b/analyses/tp53_nf1_score/plots/HR_molecular_subtype.png
diff --git a/analyses/tp53_nf1_score/plots/KM_binned_age.pdf b/analyses/tp53_nf1_score/plots/KM_binned_age.pdf
diff --git a/analyses/tp53_nf1_score/plots/KM_binned_tp53.pdf b/analyses/tp53_nf1_score/plots/KM_binned_tp53.pdf
diff --git a/analyses/tp53_nf1_score/plots/KM_broad_mol.pdf b/analyses/tp53_nf1_score/plots/KM_broad_mol.pdf
diff --git a/analyses/tp53_nf1_score/plots/KM_mol_subtype_without_tp53.pdf b/analyses/tp53_nf1_score/plots/KM_mol_subtype_without_tp53.pdf
diff --git a/analyses/tp53_nf1_score/plots/KM_race.pdf b/analyses/tp53_nf1_score/plots/KM_race.pdf
diff --git a/analyses/tp53_nf1_score/plots/KM_reported_gender.pdf b/analyses/tp53_nf1_score/plots/KM_reported_gender.pdf
diff --git a/analyses/tp53_nf1_score/plots/exome_capture_TP53_roc.png b/analyses/tp53_nf1_score/plots/exome_capture_TP53_roc.png
diff --git a/analyses/tp53_nf1_score/plots/polya_TP53_roc.png b/analyses/tp53_nf1_score/plots/polya_TP53_roc.png
diff --git a/analyses/tp53_nf1_score/plots/polya_stranded_TP53_roc.png b/analyses/tp53_nf1_score/plots/polya_stranded_TP53_roc.png
diff --git a/analyses/tp53_nf1_score/plots/stranded_TP53_roc.png b/analyses/tp53_nf1_score/plots/stranded_TP53_roc.png
diff --git a/...es/tp53_nf1_score/results/DGM_score+reported_gender+molecular_subtype*tp53+binned_age.RDS b/...es/tp53_nf1_score/results/DGM_score+reported_gender+molecular_subtype*tp53+binned_age.RDS
diff --git a/analyses/tp53_nf1_score/results/DGM_score+reported_gender+molecular_subtype+binned_age.RDS b/analyses/tp53_nf1_score/results/DGM_score+reported_gender+molecular_subtype+binned_age.RDS
diff --git a/...es/tp53_nf1_score/results/HGG_H3WT_score+reported_gender+molecular_subtype+binned_age.RDS b/...es/tp53_nf1_score/results/HGG_H3WT_score+reported_gender+molecular_subtype+binned_age.RDS
diff --git a/analyses/tp53_nf1_score/results/TP53_NF1_snv_alteration.tsv b/analyses/tp53_nf1_score/results/TP53_NF1_snv_alteration.tsv
@@ -80,33 +80,33 @@ chr17	7667335	7667335	+	3'Flank	BS_E4N5C9JF	TP53
 chr17	7674221	7674221	+	Missense_Mutation	BS_E4N5C9JF	TP53
 chr17	7674894	7674894	+	Nonsense_Mutation	BS_WPCBK1EG	TP53
 chr17	7673718	7673803	+	Frame_Shift_Del	BS_JZ40GV74	TP53
-chr17	7535526	7676778	NA	Loss	BS_46TXYD8H	TP53
-chr17	113850	18444459	NA	Loss	BS_P0QJ1QAH	TP53
-chr17	7013006	7682675	NA	Loss	BS_DFTX5Q9V	TP53
-chr17	342848	21288960	NA	Loss	BS_823V5X6Z	TP53
-chr17	2884630	11599420	NA	Loss	BS_JZ40GV74	TP53
-chr17	127638	21882826	NA	Loss	BS_GCG2PKQA	TP53
-chr17	7672479	7673490	NA	Loss	BS_81SVXT4D	TP53
-chr17	3307018	7893426	NA	Loss	BS_80078QDG	TP53
-chr17	110880	18444888	NA	Loss	BS_85Q5P8GF	TP53
-chr17	7555845	8037810	NA	Loss	BS_WJB33V17	TP53
-chr17	7475776	7784832	NA	Loss	BS_3NX3RBCX	TP53
-chr17	5488076	7985784	NA	Loss	BS_96S0VQBN	TP53
-chr17	139198	14929426	NA	Loss	BS_QJ58E1KY	TP53
-chr17	317504	21290368	NA	Loss	BS_823V5X6Z	TP53
-chr17	7660784	7663541	NA	Loss	BS_Y4CC9PKT	TP53
-chr17	141841	14443995	NA	Loss	BS_QJ58E1KY	TP53
-chr17	7558144	7784832	NA	Loss	BS_3NX3RBCX	TP53
-chr17	3489788	7892680	NA	Loss	BS_80078QDG	TP53
-chr17	2884630	12145490	NA	Loss	BS_JZ40GV74	TP53
-chr17	7159864	8348466	NA	Loss	BS_3J4X955P	TP53
-chr17	6194429	7719421	NA	Loss	BS_3S64YXFJ	TP53
-chr17	7425418	7682675	NA	Loss	BS_DFTX5Q9V	TP53
-chr17	5489640	7984220	NA	Loss	BS_96S0VQBN	TP53
-chr17	7043484	8403276	NA	Loss	BS_KYVZWYMS	TP53
-chr17	315744	21289950	NA	Loss	BS_P0QJ1QAH	TP53
-chr17	317592	21290544	NA	Loss	BS_85Q5P8GF	TP53
-chr17	316056	21291234	NA	Loss	BS_GCG2PKQA	TP53
+chr17	7535526	7676778	NA	loss	BS_46TXYD8H	TP53
+chr17	113850	18444459	NA	loss	BS_P0QJ1QAH	TP53
+chr17	7013006	7682675	NA	loss	BS_DFTX5Q9V	TP53
+chr17	342848	21288960	NA	loss	BS_823V5X6Z	TP53
+chr17	2884630	11599420	NA	loss	BS_JZ40GV74	TP53
+chr17	127638	21882826	NA	loss	BS_GCG2PKQA	TP53
+chr17	7672479	7673490	NA	loss	BS_81SVXT4D	TP53
+chr17	3307018	7893426	NA	loss	BS_80078QDG	TP53
+chr17	110880	18444888	NA	loss	BS_85Q5P8GF	TP53
+chr17	7555845	8037810	NA	loss	BS_WJB33V17	TP53
+chr17	7475776	7784832	NA	loss	BS_3NX3RBCX	TP53
+chr17	5488076	7985784	NA	loss	BS_96S0VQBN	TP53
+chr17	139198	14929426	NA	loss	BS_QJ58E1KY	TP53
+chr17	317504	21290368	NA	loss	BS_823V5X6Z	TP53
+chr17	7660784	7663541	NA	loss	BS_Y4CC9PKT	TP53
+chr17	141841	14443995	NA	loss	BS_QJ58E1KY	TP53
+chr17	7558144	7784832	NA	loss	BS_3NX3RBCX	TP53
+chr17	3489788	7892680	NA	loss	BS_80078QDG	TP53
+chr17	2884630	12145490	NA	loss	BS_JZ40GV74	TP53
+chr17	7159864	8348466	NA	loss	BS_3J4X955P	TP53
+chr17	6194429	7719421	NA	loss	BS_3S64YXFJ	TP53
+chr17	7425418	7682675	NA	loss	BS_DFTX5Q9V	TP53
+chr17	5489640	7984220	NA	loss	BS_96S0VQBN	TP53
+chr17	7043484	8403276	NA	loss	BS_KYVZWYMS	TP53
+chr17	315744	21289950	NA	loss	BS_P0QJ1QAH	TP53
+chr17	317592	21290544	NA	loss	BS_85Q5P8GF	TP53
+chr17	316056	21291234	NA	loss	BS_GCG2PKQA	TP53
 chr17	31258363	31258372	+	Frame_Shift_Del	BS_QQP17PDQ	NF1
 chr17	31327591	31327593	+	In_Frame_Del	BS_FAZBX8AS	NF1
 chr17	31201486	31201486	+	Splice_Site	BS_79NQJZ09	NF1
@@ -154,29 +154,28 @@ chr17	31327591	31327593	+	In_Frame_Del	BS_FAZBX8AS	NF1
 chr17	31235963	31235963	+	Nonsense_Mutation	BS_B9QP40ER	NF1
 chr17	31258363	31258372	+	Frame_Shift_Del	BS_QQP17PDQ	NF1
 chr17	31169985	31169985	+	Nonsense_Mutation	BS_KYVZWYMS	NF1
-chr17	31080704	31385312	NA	Loss	BS_HBSA5CW2	NF1
-chr17	30712374	31403295	NA	Loss	BS_AYPBAHJ6	NF1
-chr17	29571542	31720689	NA	Loss	BS_DFTX5Q9V	NF1
-chr17	26561920	32615616	NA	Loss	BS_823V5X6Z	NF1
-chr17	30951410	31108735	NA	Loss	BS_JZ40GV74	NF1
-chr17	31108735	31605070	NA	Loss	BS_JZ40GV74	NF1
-chr17	23512743	32996449	NA	Loss	BS_GCG2PKQA	NF1
-chr17	31047576	31458000	NA	Loss	BS_ASGBEHAX	NF1
-chr17	31146709	31478770	NA	Loss	BS_1WY6405N	NF1
-chr17	30085242	31692045	NA	Loss	BS_WJB33V17	NF1
-chr17	26783064	42907788	NA	Loss	BS_AYPBAHJ6	NF1
-chr17	26951936	36152512	NA	Loss	BS_823V5X6Z	NF1
-chr17	31033464	31458000	NA	Loss	BS_ASGBEHAX	NF1
-chr17	27516273	31234093	NA	Loss	BS_QJ58E1KY	NF1
-chr17	31234093	31402364	NA	Loss	BS_QJ58E1KY	NF1
-chr17	31147092	31479153	NA	Loss	BS_1WY6405N	NF1
-chr17	30982875	31104675	NA	Loss	BS_JZ40GV74	NF1
-chr17	31104675	31604055	NA	Loss	BS_JZ40GV74	NF1
-chr17	30488458	31753722	NA	Loss	BS_DFTX5Q9V	NF1
-chr17	26966160	45573735	NA	Loss	BS_3HXCGJ4J	NF1
-chr17	30396520	31754324	NA	Loss	BS_KYVZWYMS	NF1
-chr17	26966060	32996449	NA	Loss	BS_GCG2PKQA	NF1
-NA	NA	NA	NA	NA	BS_J4E9SW51	No_TP53_NF1_alt
+chr17	31080704	31385312	NA	loss	BS_HBSA5CW2	NF1
+chr17	30712374	31403295	NA	loss	BS_AYPBAHJ6	NF1
+chr17	29571542	31720689	NA	loss	BS_DFTX5Q9V	NF1
+chr17	26561920	32615616	NA	loss	BS_823V5X6Z	NF1
+chr17	30951410	31108735	NA	loss	BS_JZ40GV74	NF1
+chr17	31108735	31605070	NA	loss	BS_JZ40GV74	NF1
+chr17	23512743	32996449	NA	loss	BS_GCG2PKQA	NF1
+chr17	31047576	31458000	NA	loss	BS_ASGBEHAX	NF1
+chr17	31146709	31478770	NA	loss	BS_1WY6405N	NF1
+chr17	30085242	31692045	NA	loss	BS_WJB33V17	NF1
+chr17	26783064	42907788	NA	loss	BS_AYPBAHJ6	NF1
+chr17	26951936	36152512	NA	loss	BS_823V5X6Z	NF1
+chr17	31033464	31458000	NA	loss	BS_ASGBEHAX	NF1
+chr17	27516273	31234093	NA	loss	BS_QJ58E1KY	NF1
+chr17	31234093	31402364	NA	loss	BS_QJ58E1KY	NF1
+chr17	31147092	31479153	NA	loss	BS_1WY6405N	NF1
+chr17	30982875	31104675	NA	loss	BS_JZ40GV74	NF1
+chr17	31104675	31604055	NA	loss	BS_JZ40GV74	NF1
+chr17	30488458	31753722	NA	loss	BS_DFTX5Q9V	NF1
+chr17	26966160	45573735	NA	loss	BS_3HXCGJ4J	NF1
+chr17	30396520	31754324	NA	loss	BS_KYVZWYMS	NF1
+chr17	26966060	32996449	NA	loss	BS_GCG2PKQA	NF1
 NA	NA	NA	NA	NA	BS_D7PRJEMD	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_7P378T0E	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_9DM8H1RX	No_TP53_NF1_alt
@@ -192,7 +191,6 @@ NA	NA	NA	NA	NA	BS_00TRPEQX	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_A0NBZQPH	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_QWS88QXE	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_V3X7YF5J	No_TP53_NF1_alt
-NA	NA	NA	NA	NA	BS_ABZ3BK38	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_NJFK43N3	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_KAD49R68	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_F064HMTP	No_TP53_NF1_alt
@@ -213,3 +211,5 @@ NA	NA	NA	NA	NA	BS_742CDKAS	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_SG37096X	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_7ZM4PG53	No_TP53_NF1_alt
 NA	NA	NA	NA	NA	BS_4MGT61BX	No_TP53_NF1_alt
+NA	NA	NA	NA	NA	BS_J4E9SW51	No_TP53_NF1_alt
+NA	NA	NA	NA	NA	BS_ABZ3BK38	No_TP53_NF1_alt