morinlab · lklossok · May 13, 2025 · May 13, 2025 · May 14, 2025 · May 14, 2025
diff --git a/.RData b/.RData
diff --git a/.Rhistory b/.Rhistory
@@ -0,0 +1,5 @@
+setwd("/home/lklossok/Morin_Lab/GAMBLR.predict")
+devtools::load_all()
+devtools::document()
+devtools::load_all()
+q()
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -15,7 +15,7 @@ Description: Collection of functions and helpers to classify different B-cell ly
 License: MIT + file LICENSE
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.2
 Depends:
     R (>= 3.5.0)
 LazyData: true

diff --git a/NAMESPACE b/NAMESPACE
@@ -1,22 +1,55 @@
 # Generated by roxygen2: do not edit by hand
 
+export(DLBCLone_KNN)
+export(DLBCLone_KNN_predict)
+export(DLBCLone_load_optimized)
 export(DLBCLone_optimize_params)
+export(DLBCLone_predict_mixture_model)
+export(DLBCLone_save_optimized)
+export(DLBCLone_summarize_model)
+export(DLBCLone_train_mixture_model)
 export(DLBCLone_train_test_plot)
+export(assemble_genetic_features)
+export(basic_umap_scatterplot)
 export(classify_bl)
 export(classify_dlbcl)
 export(classify_fl)
 export(complete_missing_from_matrix)
 export(construct_reduced_winning_version)
+export(make_alluvial)
 export(make_and_annotate_umap)
+export(make_neighborhood_plot)
+export(make_umap_scatterplot)
 export(massage_matrix_for_clustering)
-export(predict_single_sample)
+export(optimize_outgroup)
+export(optimize_purity)
+export(predict_single_sample_DLBCLone)
+export(prepare_single_sample_DLBCLone)
+export(process_votes)
+export(report_accuracy)
+export(stacked_bar_plot)
+export(summarize_all_ssm_status)
 export(tabulate_ssm_status)
 export(weighted_knn_predict_with_conf)
+import(ComplexHeatmap)
+import(FNN)
 import(GAMBLR.data)
 import(GAMBLR.helpers)
+import(caret)
+import(circlize)
 import(dplyr)
+import(ggExtra)
+import(ggalluvial)
+import(ggplot2)
+import(ggrepel)
+import(ggside)
+import(grid)
+import(mclust)
+import(purrr)
 import(randomForest, except = c("combine"))
 import(readr)
+import(rlang)
+import(stringr)
 import(tibble)
 import(tidyr)
 import(tidyselect)

diff --git a/R/dlbclass.R b/R/dlbclass.R
@@ -28,13 +28,16 @@ construct_reduced_winning_version <- function(mutations_file = "inst/extdata/DLB
       stop("Please provide either a mutations file or a mutation_data data frame.")
     }
   }else{
-    mutation_data = read.table(mutations,sep="\t",row.names = 1,header=1) 
+    mutation_data = read.table(mutations_file,sep="\t",row.names = 1,header=1) 
   }
 
 
   # Transpose data if 'MYD88' is in row names
   if ("MYD88" %in% rownames(mutation_data)) {
-    mutation_data <- t(mutation_data) %>% as.data.frame() %>% column_to_rownames("sample_id")
+    mutation_data <- t(mutation_data) %>% as.data.frame() 
+    #rownames(mutation_data) <- NULL
+    #print(head(mutation_data))
+    #mutation_data = mutation_data %>% column_to_rownames("sample_id")
   }
   mutation_data = mutation_data %>% dplyr::select(-any_of(c("PLOIDY","PURITY","COO")),-ends_with("CCF"))
   #print(colnames(mutation_data))
@@ -72,34 +75,72 @@ construct_reduced_winning_version <- function(mutations_file = "inst/extdata/DLB
   #mutation_data <- mutation_data[, !colnames(mutation_data) %in% genes_to_drop]
 
   # Aggregate specific features into vectors
-  print(grep("BCL6",colnames(mutation_data),value=T))
+
+  genes = c("BCL6","BCL2")
   BCL6_ALT <- rowSums(select(mutation_data, any_of(c("BCL6_SV","SV.BCL6", "BCL6"))), na.rm = TRUE)
-  NOTCH2_vec <- rowSums(select(mutation_data, any_of(c("NOTCH2","NOTCH2HOTSPOT", "SPEN", "DTX1"))), na.rm = TRUE)
-  M88O_vec <- rowSums(select(mutation_data, any_of(c("MYD88","MYD88.OTHER", "TNFAIP3", "TNIP1", "BCL10", "NFKBIE"))), na.rm = TRUE)
+  NOTCH2_genes <- c("NOTCH2","NOTCH2HOTSPOT", "SPEN", "DTX1")
+  genes = c(genes,NOTCH2_genes)
+  NOTCH2_vec <- rowSums(select(mutation_data, any_of(NOTCH2_genes)), na.rm = TRUE)
 
-  CD70_vec <- rowSums(select(mutation_data, any_of(c("CD70", "FAS", "CD58", "B2M", "FADD", "HLA.B","HLA-B"))), na.rm = TRUE)
+  MYD88_genes = c("MYD88","MYD88.OTHER", "TNFAIP3", "TNIP1", "BCL10", "NFKBIE")
+  genes = c(genes,MYD88_genes)
+  M88O_vec <- rowSums(select(mutation_data, any_of(MYD88_genes)), na.rm = TRUE)
 
+  CD70_genes = c("CD70", "FAS", "CD58", "B2M", "FADD", "HLA.B","HLA-B")
+  CD70_vec <- rowSums(select(mutation_data, any_of(CD70_genes)), na.rm = TRUE)
+  genes = c(genes,CD70_genes)
 
 
 
   # Additional vectors for other clusters
   #BCL2_combined <- rowSums(mutation_data[, c("BCL2", "SV.BCL2")], na.rm = TRUE)
   BCL2_combined <- rowSums(select(mutation_data, (starts_with("BCL2"))), na.rm = TRUE)
+  HIST_genes = c("HIST1H2AC","HIST1H2ACHOTSPOT", 
+                 "HIST1H1E", "HIST1H1EHOTSPOT","HIST1H1B",
+                 "HIST1H2AM","HIST1H2AMHOTSPOT", "HIST1H1C",
+                 "HIST1H1CHOTSPOT","HIST1H1D", "HIST1H1DHOTSPOT",
+                 "HIST1H2BC","HIST1H2BCHOTSPOT")
+  genes = c(genes,HIST_genes)
+  SGK1_genes <- c("SGK1", "TET2", "SGK1HOTSPOT","NFKBIA","NFKBIAHOTSPOT",
+    "STAT3","STAT3HOTSPOT", "PTPN6", "BRAF","BRAFHOTSPOT", "KRAS", "KRASHOTSPOT",
+    "CD83","CD83HOTSPOT", "SF3B1","SF3B1HOTSPOT", "CD274", "MEF2C","MEF2CHOTSPOT", "KLHL6","KLHL6HOTSPOT", "CXCR4","CXCR4HOTSPOT", "PTEN", 
+    "RAC2", "SESN3", "SOCS1","SOCS1HOTSPOT", "METAP1D")
+  DUSP2_genes <- c("DUSP2", "DUSP2HOTSPOT", "ZFP36L1","ZFP36L1HOTSPOT", "CRIP1",
+                   "ACTB", "LTB", "YY1", "PABPC1","PABPC1HOTSPOT")
 
-  #CREBBP_vec <- rowSums(mutation_data[, c("CREBBP", "EZH2", "KMT2D", "EP300")], na.rm = TRUE)
+  TBL1XR1_genes <- c("TBL1XR1", "PIM1", "PIM1HOTSPOT",
+                   "PRDM1","PRDM1HOTSPOT",
+                   "ETV6","ETV6HOTSPOT", "ZC3H12A",
+                   "BTG1", "BTG1HOTSPOT", "BTG2", "BTG2HOTSPOT",
+                   "IGLL5", "IGLL5HOTSPOT",
+                   "TMSB4X","TMSB4XHOTSPOT", 
+                   "GRHPR","GRHPRHOTSPOT","HLA.C","HLA-C","HLA-CHOTSPOT",
+                   "MYD88", "TOX", "LYN", 
+                   "POU2F2","POU2F2HOTSPOT",
+                   "IKZF3","IKZF3HOTSPOT", 
+                   "HLA.A", "ZFP36L1","HLA-A","HLA-AHOTSPOT",
+                   "CARD11", "CARD11HOTSPOT","SF3B1", 
+                   "HLA.B","HLA-B","HLA-BHOTSPOT", "IRF2BP2", "OSBPL10", "ATP2A2", "PIM2", "IRF4", "BCL11A", 
+                   "METAP1D", "ETS1", "CCDC27")
+  CREBBP_genes <- c("CREBBP", "EZH2", "KMT2D", "EP300")
+  genes = c(genes,SGK1_genes,DUSP2_genes,TBL1XR1_genes,CREBBP_genes)
   CREBBP_vec <- rowSums(select(mutation_data, starts_with("CREBBP"),
                                                    starts_with("EZH2"),
                                                    starts_with("KMT2D"),
                                                    starts_with("EP300")), na.rm = TRUE)
-
+  PTEN_genes = c("PTEN")
+  C1_genes = c("UBE2A", "TMEM30A", "ZEB2", "GNAI2", "X5P.AMP", "POU2F2", "IKZF3",
+               "EBF1", "LYN", "BCL7A", "CXCR4", "CCDC27", "TUBGCP5", "SMG7", "RHOA", "BTG2")
+  TP53_genes = c("TP53")
+  GNA13_genes = c("GNA13", "TNFRSF14", "MAP2K1", "MEF2B", "IRF8", "HVCN1", 
+                  "GNAI2", "MEF2C", "SOCS1", "EEF1A1", "RAC2",  
+                  "POU2AF1")
+  genes = c(genes,PTEN_genes,C1_genes,TP53_genes,GNA13_genes)
   if(include_cn){
-    C1_vec4 <- rowSums(select(mutation_data, any_of(c("UBE2A", "TMEM30A", "ZEB2", "GNAI2", "X5P.AMP", "POU2F2", "IKZF3", "X3Q28.DEL", 
-                              "EBF1", "LYN", "BCL7A", "CXCR4", "CCDC27", "TUBGCP5", "SMG7", "RHOA", "BTG2"))), na.rm = TRUE)
-        TP53_biallelic <- rowSums(mutation_data[, c("TP53", "X17P.DEL")], na.rm = TRUE)
+    C1_vec4 <- rowSums(select(mutation_data, any_of(C1_genes)), na.rm = TRUE)
+        TP53_biallelic <- rowSums(mutation_data[, TP53_genes,drop=FALSE], na.rm = TRUE)
        X21Q_AMP <- mutation_data[, "X21Q.AMP"]
-      GNA13_vec <- rowSums(mutation_data[, c("GNA13", "TNFRSF14", "MAP2K1", "MEF2B", "IRF8", "HVCN1", 
-                                "GNAI2", "MEF2C", "SOCS1", "EEF1A1", "RAC2", "X12Q.AMP", 
-                                "POU2AF1", "X6Q14.1.DEL")], na.rm = TRUE)
+      GNA13_vec <- rowSums(mutation_data[, GNA13_genes], na.rm = TRUE)
       Sum_C2_ARM <- rowSums(mutation_data[, c("X17P.DEL", "X21Q.AMP", "X11Q.AMP", "X6P.AMP", "X11P.AMP", "X6Q.DEL", "X7P.AMP", "X13Q.AMP", 
                                  "X7Q.AMP", "X3Q.AMP", "X5P.AMP", "X18P.AMP", "X3P.AMP", "X19Q.AMP", "X9Q.AMP", "X12P.AMP", "X12Q.AMP")], na.rm = TRUE)
 
@@ -109,7 +150,7 @@ construct_reduced_winning_version <- function(mutations_file = "inst/extdata/DLB
                                    "X18Q23.DEL", "X19P13.3.DEL", "X13Q34.DEL", "X7Q22.1.AMP", "X10Q23.31.DEL", "X9P24.1.AMP", 
                                    "X3Q28.AMP", "X11Q23.3.AMP", "X17Q24.3.AMP", "X3Q28.DEL", "X13Q14.2.DEL", "X18Q21.32.AMP", 
                                    "X19Q13.32.DEL", "X6P21.1.AMP", "X18Q22.2.AMP", "EP300", "ZNF423", "CD274")], na.rm = TRUE)
-      PTEN <- rowSums(mutation_data[, c("PTEN", "X10Q23.31.DEL", "X13Q14.2.DEL")], na.rm = TRUE)
+      PTEN <- rowSums(mutation_data[, PTEN_genes, drop=FALSE], na.rm = TRUE)
       Sum_C5_CNA <- rowSums(mutation_data[, c("X18Q.AMP", "X3Q.AMP", "X3P.AMP", "X19Q13.42.AMP", "X6Q21.DEL", 
                                  "X18P.AMP", "X19Q.AMP", "X8Q12.1.DEL", "X6Q14.1.DEL", "X19P13.2.DEL", 
                                  "X9P21.3.DEL", "X18Q21.32.AMP", "X18Q22.2.AMP", "X1Q42.12.DEL", "X1Q32.1.AMP", "X6P21.33.DEL")], na.rm = TRUE)
@@ -131,7 +172,7 @@ construct_reduced_winning_version <- function(mutations_file = "inst/extdata/DLB
                               starts_with("BTG2")), na.rm = TRUE)
       TP53_biallelic <- rowSums(mutation_data[, c("TP53"),drop=FALSE], na.rm = TRUE)
 
-      PTEN <- rowSums(mutation_data[, c("PTEN"),drop=FALSE], na.rm = TRUE)
+      PTEN <- rowSums(select(mutation_data,any_of(PTEN_genes)))
       #GNA13_vec <- rowSums(mutation_data[, c("GNA13", "TNFRSF14", "MAP2K1", "MEF2B", "IRF8", "HVCN1", 
       #                          "GNAI2", "MEF2C", "SOCS1", "EEF1A1", "RAC2", 
       #                          "POU2AF1")], na.rm = TRUE)
@@ -149,40 +190,12 @@ construct_reduced_winning_version <- function(mutations_file = "inst/extdata/DLB
 
   SV_MYC <- select(mutation_data, any_of(c("SV.MYC", "MYC","MYC_SV"))) %>% rowSums(na.rm = TRUE)
 
-  Hist_comp <- rowSums(select(mutation_data, any_of(c("HIST1H2AC","HIST1H2ACHOTSPOT", 
-                                                    "HIST1H1E", "HIST1H1EHOTSPOT","HIST1H1B",
-                                                     "HIST1H2AM","HIST1H2AMHOTSPOT", "HIST1H1C",
-                                                     "HIST1H1CHOTSPOT","HIST1H1D", "HIST1H1DHOTSPOT",
-                                                     "HIST1H2BC","HIST1H2BCHOTSPOT"))), na.rm = TRUE)
-  SGK1_vec <- rowSums(select(mutation_data, any_of(c("SGK1", "TET2", "SGK1HOTSPOT","NFKBIA","NFKBIAHOTSPOT",
-                              "STAT3","STAT3HOTSPOT", "PTPN6", "BRAF","BRAFHOTSPOT", "KRAS", "KRASHOTSPOT",
-                               "CD83","CD83HOTSPOT", "SF3B1","SF3B1HOTSPOT", "CD274", "MEF2C","MEF2CHOTSPOT", "KLHL6","KLHL6HOTSPOT", "CXCR4","CXCR4HOTSPOT", "PTEN", 
-                               "RAC2", "SESN3", "SOCS1","SOCS1HOTSPOT", "METAP1D"))), na.rm = TRUE)
-  #SGK1_vec <- rowSums(mutation_data[, c("SGK1", "TET2", "NFKBIA", "STAT3", "PTPN6", "BRAF", "KRAS", 
-  #                             "CD83", "SF3B1", "CD274", "MEF2C", "KLHL6", "CXCR4", "PTEN", 
-  #                             "RAC2", "SESN3", "SOCS1", "METAP1D")], na.rm = TRUE)
-  #DUSP2_vec <- rowSums(mutation_data[, c("DUSP2", "ZFP36L1", "CRIP1", "ACTB", "LTB", "YY1", "PABPC1")], na.rm = TRUE)
-  DUSP2_vec <- rowSums(select(mutation_data, any_of(c("DUSP2", "DUSP2HOTSPOT", "ZFP36L1","ZFP36L1HOTSPOT", "CRIP1", "ACTB", "LTB", "YY1", "PABPC1","PABPC1HOTSPOT"))), na.rm = TRUE)
+  Hist_comp <- rowSums(select(mutation_data, any_of(HIST_genes)), na.rm = TRUE)
+  SGK1_vec <- rowSums(select(mutation_data, any_of(SGK1_genes)), na.rm = TRUE)
+  DUSP2_vec <- rowSums(select(mutation_data, any_of(DUSP2_genes)), na.rm = TRUE)
+
 
-  #TBL1XR1_vec <- rowSums(mutation_data[, c("TBL1XR1", "PIM1", "PRDM1", "ETV6", "ZC3H12A", "BTG1", "BTG2", 
-  #                                "IGLL5", "TMSB4X", "GRHPR", "HLA.C", "MYD88", "TOX", "LYN", 
-  #                                "POU2F2", "IKZF3", "HLA.A", "ZFP36L1", "CARD11", "SF3B1", 
-  #                                "HLA.B", "IRF2BP2", "OSBPL10", "ATP2A2", "PIM2", "IRF4", "BCL11A", 
-  #                                "METAP1D", "ETS1", "CCDC27")], na.rm = TRUE)
-    TBL1XR1_vec <- rowSums(select(mutation_data, any_of(c("TBL1XR1", "PIM1", "PIM1HOTSPOT",
-                                                          "PRDM1","PRDM1HOTSPOT",
-                                                          "ETV6","ETV6HOTSPOT", "ZC3H12A",
-                                                          "BTG1", "BTG1HOTSPOT", "BTG2", "BTG2HOTSPOT",
-                                  "IGLL5", "IGLL5HOTSPOT",
-                                  "TMSB4X","TMSB4XHOTSPOT", 
-                                  "GRHPR","GRHPRHOTSPOT","HLA.C","HLA-C","HLA-CHOTSPOT",
-                                  "MYD88", "TOX", "LYN", 
-                                  "POU2F2","POU2F2HOTSPOT",
-                                  "IKZF3","IKZF3HOTSPOT", 
-                                  "HLA.A", "ZFP36L1","HLA-A","HLA-AHOTSPOT",
-                                  "CARD11", "CARD11HOTSPOT","SF3B1", 
-                                  "HLA.B","HLA-B","HLA-BHOTSPOT", "IRF2BP2", "OSBPL10", "ATP2A2", "PIM2", "IRF4", "BCL11A", 
-                                  "METAP1D", "ETS1", "CCDC27"))), na.rm = TRUE)
+  TBL1XR1_vec <- rowSums(select(mutation_data, any_of(TBL1XR1_genes)), na.rm = TRUE)
 
   MYD88_L265P_CD79B <- rowSums(select(mutation_data, any_of(c("MYD88.L265P","MYD88HOTSPOT", "CD79B","CD79BHOTSPOT"))), na.rm = TRUE)
 
@@ -220,9 +233,6 @@ construct_reduced_winning_version <- function(mutations_file = "inst/extdata/DLB
       C1_vec4 = C1_vec4,
       CD70_vec = CD70_vec,
       TP53_biallelic = TP53_biallelic,
-      #X21Q_AMP = X21Q_AMP,
-      #Sum_C2_ARM = Sum_C2_ARM,
-      #Sum_C2_FOCAL = Sum_C2_FOCAL,
       BCL2_combined = BCL2_combined,
       CREBBP_vec = CREBBP_vec,
       GNA13_vec = GNA13_vec,
@@ -231,10 +241,8 @@ construct_reduced_winning_version <- function(mutations_file = "inst/extdata/DLB
       Hist_comp = Hist_comp,
       SGK1_vec = SGK1_vec,
       DUSP2_vec = DUSP2_vec,
-      #CN_2P16_1_AMP = CN_2P16_1_AMP,
       TBL1XR1_vec = TBL1XR1_vec,
       MYD88_L265P_CD79B = MYD88_L265P_CD79B
-      #Sum_C5_CNA = Sum_C5_CNA
     )
   }
 
@@ -252,5 +260,10 @@ construct_reduced_winning_version <- function(mutations_file = "inst/extdata/DLB
   return(list(reduced=reduced_data,
               full=full_data,
               no_cn=data_no_cn,
-              feature_names=list(ssm_features=ssm,hotspot_features=hotspot,cnv_features=cnv,sv_features=sv)))
+              ssm_genes = genes,
+              feature_names=list(ssm_features=ssm,
+                                 hotspot_features=hotspot,
+                                 cnv_features=cnv,
+                                 sv_features=sv
+                                 )))
 }