Merge pull request #33 from annemarie-sharp/main

Rename columns for clarity in study/taxon tables

Author: cmirzayi

R/describe_curation.R

@@ -42,20 +42,20 @@ createTaxonTable <- function(dat, n=10){
         fixed = TRUE
       ))
     })) %>%
-    mutate(total_signatures = sapply(metaphlan_name, function(x)
+    mutate(`Total Signatures` = sapply(metaphlan_name, function(x)
       .countTaxon(dat = dat, x = x, direction = "both"))) %>%
-    mutate(increased_signatures = sapply(metaphlan_name, function(x)
+    mutate(`Increased Signatures` = sapply(metaphlan_name, function(x)
       .countTaxon(dat = dat, x = x, direction = "increased"))) %>%
-    mutate(decreased_signatures = sapply(metaphlan_name, function(x)
+    mutate(`Decreased Signatures` = sapply(metaphlan_name, function(x)
       .countTaxon(dat = dat, x = x, direction = "decreased"))) %>%
     mutate(Taxon = gsub(".+\\|", "", output$metaphlan_name))
 
     output %>% separate(col="Taxon", into=c("Taxonomic Level", "Taxon Name"), sep="__") %>%
     mutate(`Taxonomic Level` = unname(dmap[`Taxonomic Level`])) %>%
     rowwise() %>%    
-    mutate( `Binomial Test pval` = .createBinomTestSummary(increased_signatures, total_signatures, wordy = FALSE)) %>%
+    mutate( `Binomial Test pval` = .createBinomTestSummary(`Increased Signatures`, `Total Signatures`, wordy = FALSE)) %>%
       ungroup() %>%
-    relocate(`Taxon Name`, `Taxonomic Level`, total_signatures, increased_signatures, decreased_signatures, `Binomial Test pval`)
+    relocate(`Taxon Name`, `Taxonomic Level`, `Total Signatures`, `Increased Signatures`, `Decreased Signatures`, `Binomial Test pval`)
 }
 
 .countTaxon = function(dat, x, direction = c("both", "increased", "decreased")){
@@ -115,24 +115,24 @@ createStudyTable <- function(bsdb.df, includeAlso = NULL) {
   # Core of the change is in how study IDs are generated, see function in 
   # simple.R. NB: the function also fixes DOI links as side effect, now. 
 
-  bsdb_with_StudyCodes.df <- .make_unique_study_ID(bsdb.df)
+  bsdb_with_StudyIDs.df <- .make_unique_study_ID(bsdb.df)
 
   # some dplyr-fu to summarize tables, with more recent syntax
-  study_table_fixed <- bsdb_with_StudyCodes.df %>%
-    group_by(`Study code`) %>%
+  study_table_fixed <- bsdb_with_StudyIDs.df %>%
+    group_by(`Study Identifier`) %>%
     reframe(
-      MaxCases = max(`Group 1 sample size`),
-      MaxControls = max(`Group 0 sample size`),
+      Cases = max(`Group 1 sample size`),
+      Controls = max(`Group 0 sample size`),
       across(
         all_of(
           c("Study design", "Condition", "PMID", "DOI", "URL", includeAlso)
         ),
         .fns = function(x)
           paste(unique(x), collapse = "; ")
       ),
-      N_signatures = n()
+      `Number of signatures` = n()
     ) %>%
-    relocate(N_signatures, .after = Condition)
+    relocate(`Number of signatures`, .after = Condition)
 
   return(study_table_fixed)
 }
@@ -147,10 +147,10 @@ globalVariables(
     "Study.Design",
     "Taxon Name",
     "Binomial Test pval",
-    "total_signatures",
+    "Total Signatures",
     "Abundance in Group 1",
-    "decreased_signatures",
-    "increased_signatures",
+    "Decreased Signatures",
+    "Increased Signatures",
     "Taxonomic Level",
     "metaphlan_name",
     "Freq",
@@ -164,10 +164,10 @@ globalVariables(
     "PMID",
     "URL",
     "uniqueRank",
-    "Study code",
+    "Study Identifier",
     "Group 0 sample size",
     "Group 1 sample size",
-    "N_signatures"
+    "Number of signatures"
   )
 )
 

R/simple.R

@@ -90,7 +90,7 @@ getMostFrequentTaxa <- function(dat, n=10, sig.type=c("both", "increased", "decr
 #' @param bsdb.df \code{data.frame} produced by \link[bugsigdbr]{importBugSigDB}, pre-filtered as desired
 
 .make_unique_study_ID <- function(bsdb.df){
-  bsdb_with_StudyCode <- bsdb.df %>% 
+  bsdb_with_StudyIDs <- bsdb.df %>% 
     # fix DOIs
     mutate(
       DOI =  ifelse(
@@ -107,11 +107,11 @@ getMostFrequentTaxa <- function(dat, n=10, sig.type=c("both", "increased", "decr
       # this is arbitrary, the point is to make sure you can split overlapping
       # IDs into one
       uniqueRank = as.numeric(as.factor(paste(PMID, DOI, URL, `Authors list`))),
-      `Study code` = ifelse(uniqueRank > 1, paste(BasicID, uniqueRank - 1, sep = "."), BasicID)
+      `Study Identifier` = ifelse(uniqueRank > 1, paste(BasicID, uniqueRank - 1, sep = "."), BasicID)
     ) %>% 
     ungroup() %>% 
     select(- BasicID, - uniqueRank) %>% 
-    relocate(`Study code`) 
+    relocate(`Study Identifier`) 
 
-  return(bsdb_with_StudyCode)
+  return(bsdb_with_StudyIDs)
 }