adding team data for initial romopomics processing

.Rhistory

@@ -1,3 +1,165 @@
+] %>%
+.[,.(Nades = length(unique(ade))),gene] %>%
+merge(
+obs_vs_random_cor_dts[,.(Ntotalades = length(unique(ade))),gene],
+by="gene"
+) %>%
+.[,.(Nades,Ntotalades,
+null = binom.test(Nades,Ntotalades,alternative = "g")$null.value,
+est = binom.test(Nades,Ntotalades,alternative = "g")$estimate,
+pvalue = binom.test(Nades,Ntotalades,alternative = "g")$p.value),
+gene]
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+] %>%
+.[,.(Nades = length(unique(ade))),gene] %>%
+merge(
+obs_vs_random_cor_dts[,.(Ntotalades = length(unique(ade))),gene],
+by="gene"
+) %>%
+.[,.(Nades,Ntotalades,
+null = binom.test(Nades,Ntotalades,alternative = "g")$null.value,
+lwr = binom.test(Nades,Ntotalades,alternative = "g")$conf.int[1],
+est = binom.test(Nades,Ntotalades,alternative = "g")$estimate,
+upr = binom.test(Nades,Ntotalades,alternative = "g")$conf.int[2],
+pvalue = binom.test(Nades,Ntotalades,alternative = "g")$p.value),
+gene]
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+] %>%
+.[,.(Nades = length(unique(ade))),gene] %>%
+merge(
+obs_vs_random_cor_dts[,.(Ntotalades = length(unique(ade))),gene],
+by="gene"
+) %>%
+.[,.(Nades,Ntotalades,
+null = binom.test(Nades,Ntotalades,alternative = "g")$null.value,
+lwr = binom.test(Nades,Ntotalades,alternative = "g")$conf.int[1],
+est = binom.test(Nades,Ntotalades,alternative = "g")$estimate,
+upr = binom.test(Nades,Ntotalades,alternative = "g")$conf.int[2],
+pvalue = binom.test(Nades,Ntotalades,alternative = "g")$p.value),
+gene]
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+] %>%
+.[,.(Nprobes = length(unique(PROBEID))),gene] %>%
+merge(
+obs_vs_random_cor_dts[,.(Ntotalprobes = length(unique(PROBEID))),gene],
+by="gene"
+) %>% .[Nprobes==Ntotalprobes,gene]
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+] %>%
+.[,.(Nades = length(unique(ade))),gene] %>%
+merge(
+obs_vs_random_cor_dts[,.(Ntotalades = length(unique(ade))),gene],
+by="gene"
+) %>%
+.[,.(Nades,Ntotalades,
+null = binom.test(Nades,Ntotalades,alternative = "g")$null.value,
+lwr = binom.test(Nades,Ntotalades,alternative = "g")$conf.int[1],
+est = binom.test(Nades,Ntotalades,alternative = "g")$estimate,
+upr = binom.test(Nades,Ntotalades,alternative = "g")$conf.int[2],
+pvalue = binom.test(Nades,Ntotalades,alternative = "g")$p.value),
+gene]
+plot_drug_events(dts[database=="covariate_adjusted" & ade %in% obs_vs_random_cor_dts[
+gene=="CYP2C8" &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade,unique(ade)
+]])
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+]
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+] %>%
+.[,.(Nprobes = length(unique(PROBEID))),gene]
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+] %>%
+.[,.(Nprobes = length(unique(PROBEID))),gene] %>%
+merge(
+obs_vs_random_cor_dts[,.(Ntotalprobes = length(unique(PROBEID))),gene],
+by="gene"
+)
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+] %>%
+.[,.(Nades = length(unique(ade))),gene] %>%
+merge(
+obs_vs_random_cor_dts[,.(Ntotalades = length(unique(ade))),gene],
+by="gene"
+) %>%
+.[,.(Nades,Ntotalades,
+null = binom.test(Nades,Ntotalades,alternative = "g")$null.value,
+lwr = binom.test(Nades,Ntotalades,alternative = "g")$conf.int[1],
+est = binom.test(Nades,Ntotalades,alternative = "g")$estimate,
+upr = binom.test(Nades,Ntotalades,alternative = "g")$conf.int[2],
+pvalue = binom.test(Nades,Ntotalades,alternative = "g")$p.value),
+gene]
+gene_candidates <-
+obs_vs_random_cor_dts[
+gene %in% predicted_genes &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade
+] %>%
+.[,.(Nprobes = length(unique(PROBEID))),gene] %>%
+merge(
+obs_vs_random_cor_dts[,.(Ntotalprobes = length(unique(PROBEID))),gene],
+by="gene"
+) %>% .[Nprobes==Ntotalprobes,gene]
+ades <-
+obs_vs_random_cor_dts[
+gene %in% gene_candidates & gene=="CYP2C8" &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade,unique(ade)
+]
+g <- plot_drug_events(dts[database=="covariate_adjusted" & ade %in% ades]) +
+guides(
+fill=guide_legend(title="Report",title.position = "top"),
+color=guide_none()
+)
+ggsave(paste0(img_dir,basename,"drug_risk_vs_probe_expression_significant_candidate_genes_ades.png"),g,width=12,height=9)
+ades <-
+obs_vs_random_cor_dts[
+gene %in% gene_candidates & gene=="CYP2C8" &
+fdr_rprobe<0.05 & pvalue_other_ade>0.05 &
+auroc_rprobe>auroc_other_ade,unique(ade)
+]
+g <- plot_drug_events(dts[database=="covariate_adjusted" & ade %in% ades]) +
+guides(
+fill=guide_legend(title="Report",title.position = "top"),
+color=guide_none()
+)
+ggsave(paste0(img_dir,basename,"drug_risk_vs_probe_expression_significant_candidate_genes_ades.png"),g,width=12,height=9)
+dts[database=="covariate_adjusted" & ade %in% ades]
+dts[database=="covariate_adjusted" & ade %in% ades] %>% View()
+dts[database=="covariate_adjusted" & ade %in% ades]
+dts[database=="covariate_adjusted" & ade %in% ades] %>% [,.SD[1],ade]
+dts[database=="covariate_adjusted" & ade %in% ades] %>% .[,.SD[1],ade]
+dts[database=="covariate_adjusted" & ade %in% ades] %>% .[,.SD[1:7],ade]
+dts[database=="covariate_adjusted" & ade %in% ades] %>% .[,.SD[1:7],ade_name]
+g <- plot_drug_events(dts[database=="covariate_adjusted" & ade %in% ades] %>% .[,.SD[1:7],ade_name]) +
+guides(
+fill=guide_legend(title="Report",title.position = "top"),
+color=guide_none()
+)
 ggsave(paste0(img_dir,basename,"drug_risk_vs_probe_expression_significant_candidate_genes_ades.png"),g,width=12,height=9)
 obs_vs_random_cor_dts[
 gene %in% gene_candidates & gene=="CYP2C8" &
@@ -305,181 +467,27 @@ fdr_rprobe<0.05 & pvalue_other_ade>0.05] %>%
 .[,.(ade,atc_concept_name,gene)] %>%
 unique()
 drugbank_cyp_substrates[parent_key=="DB00404"]
-setwd("~/GitHub/omics_to_omop")
+pacman::p_load(tidyverse)
 #install.packages("devtools")
 devtools::install_github("ngiangre/ROMOPOmics",force=T)
 library(ROMOPOmics)
 dm_file <-
 system.file("extdata","OMOP_CDM_v6_0_custom.csv",package="ROMOPOmics",mustWork = TRUE)
 dm <-
 loadDataModel(master_table_file = dm_file)
-dm
-tail(dm)
-system.file("extdata","brca_clinical.csv",package="ROMOPOmics",mustWork = TRUE)
-read_csv("data/mock/bgdc2021.csv")
-pacman::p_load(tidyverse)
-read_csv("data/mock/bgdc2021.csv")
-list(
-"bgdc2021" =
-read_csv("data/mock/bgdc2021.csv")
-)
-mock_files  <-
-list(
-"bgdc2021" =
-read_csv("data/mock/bgdc2021.csv")
-)
-msks <-
-list(
-bgdc2021=loadModelMasks(read_csv("data/mock/mask_bgdc2021.csv"))
-)
-read_csv("data/mock/mask_bgdc2021.csv")
-list(
-"bgdc2021"=loadModelMasks(read_csv("data/mock/mask_bgdc2021.csv"))
-)
-loadModelMasks(read_csv("data/mock/mask_bgdc2021.csv"))
-loadModelMasks("data/mock/mask_bgdc2021.csv")
-msks <-
-list(
-"bgdc2021"=loadModelMasks("data/mock/mask_bgdc2021.csv")
-)
-mock_files  <-
-list(
-"bgdc2021" =
-"data/mock/bgdc2021.csv"
-)
-omop_inputs <-
-list(
-bgdc2021=
-readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-)
-msks <-
-list(
-"bgdc2021"=loadModelMasks("data/mock/mask_bgdc2021.csv")
-)
 omop_inputs <-
 list(
 bgdc2021=
 readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-)
-db_inputs   <- combineInputTables(input_table_list = omop_inputs)
-db_inputs
-omop_inputs
-msks
-readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-list(
-bgdc2021=
-readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-)
-omop_inputs$bgdc2021$table
-omop_inputs$bgdc2021$bgdc20211_1
-mock_files$bgdc2021
-sks$bgdc2021
-msks$bgdc2021
-View(dm)
-msks <-
-list(
-"bgdc2021"=loadModelMasks("data/mock/mask_bgdc2021.csv")
-)
-list(
-bgdc2021=
-readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-)
-omop_inputs <-
-list(
-bgdc2021=
-readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-)
-combineInputTables(input_table_list = omop_inputs)
-msks <-
-list(
-"bgdc2021"=loadModelMasks("data/mock/bgdc2021_mask.csv")
-)
-omop_inputs <-
-list(
-bgdc2021=
-readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-)
-omop_inputs
-omop_inputs <-
-list(
-bgdc2021=
-readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-)
-db_inputs   <- combineInputTables(input_table_list = omop_inputs)
-db_inputs
-msks <-
-list(
-"bgdc2021"=loadModelMasks("data/mock/bgdc2021_mask.csv")
-)
-omop_inputs <-
-list(
-bgdc2021=
-readInputFile(
-input_file = mock_files$bgdc2021,
-data_model = dm,
-mask_table = msks$bgdc2021
-)
-)
-combineInputTables(input_table_list = omop_inputs)
-mock_files$bgdc2021
-msks$bgdc2021
-readInputFile(
 input_file = "data/mock/bgdc2021.csv",
 data_model = dm,
 mask_table = loadModelMasks("data/mock/bgdc2021_mask.csv")
 )
-#install.packages("devtools")
-devtools::install_github("ngiangre/ROMOPOmics",force=T)
-dm_file <-
-system.file("extdata","OMOP_CDM_v6_0_custom.csv",package="ROMOPOmics",mustWork = TRUE)
-dm <-
-loadDataModel(master_table_file = dm_file)
-dm
-readInputFile(
-input_file = "data/mock/bgdc2021.csv",
-data_model = dm,
-mask_table = loadModelMasks("data/mock/bgdc2021_mask.csv")
 )
-View(dm)
-#install.packages("devtools")
-devtools::install_github("ngiangre/ROMOPOmics",force=T)
-library(ROMOPOmics)
-dm_file <-
-system.file("extdata","OMOP_CDM_v6_0_custom.csv",package="ROMOPOmics",mustWork = TRUE)
-dm <-
-loadDataModel(master_table_file = dm_file)
+db_inputs   <- combineInputTables(input_table_list = omop_inputs)
+omop_db     <- buildSQLDBR(omop_tables = db_inputs,file.path(tempdir(),"mock.sqlite"))
+DBI::dbListTables(omop_db)
+setwd("~/GitHub/omics_to_omop")
 omop_inputs <-
 list(
 bgdc2021=
@@ -489,14 +497,7 @@ data_model = dm,
 mask_table = loadModelMasks("data/mock/bgdc2021_mask.csv")
 )
 )
-db_inputs   <- combineInputTables(input_table_list = omop_inputs)
-db_inputs
-View(dm)
-readInputFile(
-input_file = "data/mock/bgdc2021.csv",
-data_model = dm,
-mask_table = loadModelMasks("data/mock/bgdc2021_mask.csv")
-)
+DBI::dbDisconnect()
 omop_inputs <-
 list(
 bgdc2021=
@@ -506,7 +507,6 @@ data_model = dm,
 mask_table = loadModelMasks("data/mock/bgdc2021_mask.csv")
 )
 )
-combineInputTables(input_table_list = omop_inputs)
 db_inputs   <- combineInputTables(input_table_list = omop_inputs)
 omop_db     <- buildSQLDBR(omop_tables = db_inputs,file.path(tempdir(),"mock.sqlite"))
 DBI::dbListTables(omop_db)

data/Nof1.csv

@@ -0,0 +1,2 @@
+patient,tumor_type,cancer_report,cancer_report_date,specimen,mutation_1,mutation_2,mutation_1_type,mutation_2_type
+Sally,glioblastoma,MSK Impact report,2018/03/01,brain,ARID1A,ARID1B,SNP,CNV

data/Nof1_mask.csv

@@ -0,0 +1,10 @@
+alias,example1,field,table,field_idx,set_value
+patient,Sally,person_id,person,NA,NA
+tumor_type,glioblastoma,specimen_source_value,specimen,NA,NA
+cancer_report,MSK Impact report,note_title,note,NA,NA
+cancer_report_date,2018/03/01,note_date,note,NA,NA
+specimen,brain,anatomic_site_source_value,specimen,NA,NA
+mutation_1,ARID1A,variant_source_value,variation,1,NA
+mutation_2,ARID1B,variant_source_value,variation,2,NA
+mutation_1_type,SNP,variant_status_source_value,variation,1,NA
+mutation_2_type,CNV,variant_status_source_value,variation,2,NA