validation in place

still lots of NA vals
PNNL-CompBio · Jul 19, 2024 · 3cb8f7d · 3cb8f7d
1 parent 2ac87a6
commit 3cb8f7d
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 11 deletions.
diff --git a/exposome/exposome_summary_stats.R b/exposome/exposome_summary_stats.R
@@ -155,7 +155,7 @@ sg.stats <- sig.genes%>%
   dplyr::select(-Project)|>
   dplyr::rename(Project=friendlyName)|>
     dplyr::select(Project,cas_number,Conc,Link,nGenes,Chemical_ID)|>
-        mutate(concentration=as.numeric(stringr::str_replace(conc,'uM','')))|>
+        mutate(concentration=as.numeric(stringr::str_replace(Conc,'uM','')))|>
     dplyr::select(-Conc)
 
 

diff --git a/sampleChemMapping/mapSamplesToChems.R b/sampleChemMapping/mapSamplesToChems.R
@@ -26,9 +26,12 @@ required_sample_columns<-c("ClientName","SampleNumber","date_sampled","sample_ma
                            "LocationLon","LocationName","LocationAlternateDescription",
                            "AlternateName","cas_number","date_sample_start",
                            "measurement_value","measurement_value_qualifier","measurement_value_unit",
-                           "measurement_value_molar","measurement_value_molar_unit",
-                           "water_concentration","water_concentration_qualifier","water_concentration_unit",
-                           "water_concentration_molar","water_concentration_molar_unit")
+                           "measurement_value_molar","measurement_value_molar_unit")
+
+#we need to rename the water columns
+new_sample_columns=c(environment_concentration="water_concentration",environment_concentration_qualifier='water_concentration_qualifier',
+                        environment_concentration_unit='water_concentration_unit',environment_concentration_molar='water_concentration_molar',
+                        environment_concentration_molar_unit='water_concentration_molar_unit')
 
 ##required for comptox-derived mapping files
 required_comptox_columns <- c("INPUT","DTXSID","PREFERRED_NAME","INCHIKEY","SMILES","MOLECULAR_FORMULA",
@@ -38,8 +41,8 @@ required_comptox_columns <- c("INPUT","DTXSID","PREFERRED_NAME","INCHIKEY","SMIL
 ##output tables
 sample_chem_columns <-c('Sample_ID','Chemical_ID',"measurement_value","measurement_value_qualifier","measurement_value_unit",
                            "measurement_value_molar","measurement_value_molar_unit",
-                           "water_concentration","water_concentration_qualifier","water_concentration_unit",
-                           "water_concentration_molar","water_concentration_molar_unit")
+                           "environment_concentration","environment_concentration_qualifier","environment_concentration_unit",
+                           "environment_concentration_molar","environment_concentration_molar_unit")
 
 samp_columns <-c("Sample_ID","ClientName","SampleNumber","date_sampled","sample_matrix","technology",
                 "projectName","SampleName","LocationLat","projectLink",
@@ -309,19 +312,21 @@ buildSampleData<-function(fses_files, #files from barton that contain sample inf
                           sampIds, #new ids for samples
                           sampMapping){  ##mapping for sample names to clean up
     ##New data provided by michael
- #  print(fses_files)
+                                        #  print(fses_files)
+
     sampChem<-do.call(rbind,lapply(fses_files,function(fs){
  #      print(fs)
 #    fses1<-subset(sampTab,name=='fses1')[['location']]
         sc <- rio::import(fs)|>#paste0(data.dir,'/fses/fses_data_for_pnnl_4-27-2021.csv'))%>%
                                         #  sampChem<-read.csv(paste0(data.dir,'/pnnl_bioassay_sample_query_1-14-2021.csv'))%>%
-            dplyr::select(all_of(required_sample_columns))%>%
+            dplyr::select(all_of(c(required_sample_columns,unlist(new_sample_columns))))%>% #TODO: change original file to use new names
+#            dplyr::rename(new_sample_columns)|>  ##REMOVE this once we have new names
             subset(SampleNumber!='None')%>%
             subset(cas_number!='NULL')%>%
-            mutate(water_concentration_molar=stringr::str_replace_all(water_concentration_molar,'BLOD|NULL|nc:BDL',"0"))%>%
+            mutate(environment_concentration_molar=stringr::str_replace_all(environment_concentration_molar,'BLOD|NULL|nc:BDL',"0"))%>%
             mutate(measurement_value_molar=stringr::str_replace_all(measurement_value_molar,'BLOD|NULL|BDL',"0"))%>%
-            mutate(water_concentration=stringr::str_replace_all(water_concentration,'BLOD|NULL|BDL',"0"))%>%
-                                        # subset(water_concentration_molar!='0.0')%>%
+            mutate(environment_concentration=stringr::str_replace_all(environment_concentration,'BLOD|NULL|BDL',"0"))%>%
+                                        # subset(environment_concentration_molar!='0.0')%>%
             subset(!measurement_value_molar%in%c('0'))%>%
             subset(!measurement_value%in%c("0","NULL",""))#%>%
 #        select(-c(Sample_ID))#,Chemical_ID)) ##These two are added in the 4/27 version of the file