Merge dbd1097 into a0014ff

.Rbuildignore

@@ -33,3 +33,4 @@ pkgdown/favicon/*
 vignettes/bibliography.Rmd
 vignettes/toxeval.bib
 vignettes/toxeval_orig.bib
+updateV3.R

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: toxEval
 Type: Package
 Title: Exploring Biological Relevance of Environmental Chemistry Observations
-Version: 1.1.0.9000
+Version: 2.0.0.0000
 Authors@R: c(person("Laura", "DeCicco", 
                      role = c("aut","cre"),
                      email = "ldecicco@usgs.gov",
@@ -33,7 +33,7 @@ Copyright: This software is in the public domain because it contains materials
     official USGS copyright policy at
     https://www.usgs.gov/visual-id/credit_usgs.html#copyright
 Depends:
-    R (>= 3.0)
+    R (>= 3.5.0)
 Imports:
     dplyr,
     tidyr,

NAMESPACE

@@ -30,6 +30,7 @@ export(rank_sites_DT)
 export(remove_flags)
 export(tox_boxplot_data)
 export(tox_chemicals)
+import(dplyr)
 import(ggplot2)
 import(shinydashboard)
 importFrom(grDevices,colorRampPalette)

NEWS

@@ -1,3 +1,7 @@
+toxEval 2.0.0
+===========
+* Switched to version 3 of the ToxCast database
+
 toxEval 1.0.0
 ===========
 * Initial release includes functions on incorporating

R/create_toxEval.R

@@ -177,15 +177,15 @@ summary.toxEval <- function(object, ...){
 
   if(is.null(object[["benchmarks"]])){
     ACC <- ToxCast_ACC %>%
-      dplyr::filter(CAS %in% unique(object$chem_info$CAS)) 
+      filter(CAS %in% unique(object$chem_info$CAS)) 
     bench_word <- "ToxCast"
   } else {
     ACC <- object[["benchmarks"]] 
     bench_word <- "benchmark"
   }
 
-  CAS_w_data <- ACC %>% dplyr::select(CAS) %>%
-    dplyr::distinct() %>% dplyr::pull(CAS)
+  CAS_w_data <- ACC %>% select(CAS) %>%
+    distinct() %>% pull(CAS)
 
   message(length(CAS_w_data)," chemicals have ", bench_word, " information")
   message("Chemicals returned from this function do NOT have ", bench_word, " information:")

R/endpoint_hits.R

@@ -6,8 +6,8 @@
 #' values in the table are the number of sites where the EAR exceeded the 
 #' user-defined EAR hit_threshold in that endpoint/category combination. If the 
 #' category "Chemical" is chosen, an "info" link is provided to the 
-#' chemical/endpoint information available in the "ToxCast Dashboard" 
-#' \url{https://actor.epa.gov/dashboard/}.
+#' chemical information available in the "Comptox Dashboard" 
+#' \url{https://comptox.epa.gov/dashboard/}.
 #' 
 #' The tables show slightly different results when choosing to explore data
 #' from a single site rather than all sites. The value displayed in this 
@@ -69,8 +69,8 @@ endpoint_hits_DT <- function(chemical_summary,
   if(category == "Chemical"){
     orig_names <- names(fullData)
 
-    casKey <- dplyr::select(chemical_summary, chnm, CAS) %>%
-      dplyr::distinct()
+    casKey <- select(chemical_summary, chnm, CAS) %>%
+      distinct()
 
     numeric_hits <- fullData
     hits <- sapply(fullData, function(x) as.character(x))
@@ -84,8 +84,7 @@ endpoint_hits_DT <- function(chemical_summary,
             } else{
               hit_char <- as.character(fullData[k,z])
             }
-            hits[k,z] <- paste(hit_char,createLink(cas = casKey$CAS[casKey$chnm == names(fullData)[z]],
-                                    endpoint = fullData[k,1]))
+            hits[k,z] <- paste(hit_char,createLink(cas = casKey$CAS[casKey$chnm == names(fullData)[z]]))
           }
         }
       }
@@ -149,47 +148,47 @@ endpoint_hits <- function(chemical_summary,
   fullData <- fullData_init
 
   if(category == "Chemical"){
-    chemical_summary <- dplyr::mutate(chemical_summary, category = chnm)
+    chemical_summary <- mutate(chemical_summary, category = chnm)
   } else if (category == "Chemical Class"){
-    chemical_summary <- dplyr::mutate(chemical_summary, category = Class)
+    chemical_summary <- mutate(chemical_summary, category = Class)
   } else {
-    chemical_summary <- dplyr::mutate(chemical_summary, category = Bio_category)
+    chemical_summary <- mutate(chemical_summary, category = Bio_category)
   }
 
   if(length(unique(chemical_summary$site)) > 1){
 
     if(!sum_logic){
       fullData <- chemical_summary %>%
-        dplyr::group_by(site, category, endPoint, date) %>%
-        dplyr::summarize(sumEAR = max(EAR)) %>%
-        dplyr::group_by(site, category, endPoint) %>%
-        dplyr::summarize(meanEAR = ifelse(mean_logic, mean(sumEAR),max(sumEAR))) %>%
-        dplyr::group_by(category, endPoint) %>%
-        dplyr::summarize(nSites = sum(meanEAR > hit_threshold)) %>%
+        group_by(site, category, endPoint, date) %>%
+        summarize(sumEAR = max(EAR)) %>%
+        group_by(site, category, endPoint) %>%
+        summarize(meanEAR = ifelse(mean_logic, mean(sumEAR),max(sumEAR))) %>%
+        group_by(category, endPoint) %>%
+        summarize(nSites = sum(meanEAR > hit_threshold)) %>%
         tidyr::spread(category, nSites)       
     } else {
       fullData <- chemical_summary %>%
-        dplyr::group_by(site, category, endPoint, date) %>%
-        dplyr::summarize(sumEAR = sum(EAR)) %>%
-        dplyr::group_by(site, category, endPoint) %>%
-        dplyr::summarize(meanEAR = ifelse(mean_logic, mean(sumEAR),max(sumEAR))) %>%
-        dplyr::group_by(category, endPoint) %>%
-        dplyr::summarize(nSites = sum(meanEAR > hit_threshold)) %>%
+        group_by(site, category, endPoint, date) %>%
+        summarize(sumEAR = sum(EAR)) %>%
+        group_by(site, category, endPoint) %>%
+        summarize(meanEAR = ifelse(mean_logic, mean(sumEAR),max(sumEAR))) %>%
+        group_by(category, endPoint) %>%
+        summarize(nSites = sum(meanEAR > hit_threshold)) %>%
         tidyr::spread(category, nSites)      
     }
 
   } else {
     if(!sum_logic){
       fullData <- chemical_summary %>%
-        dplyr::group_by(category, endPoint) %>%
-        dplyr::summarise(nSites = sum(EAR > hit_threshold)) %>%
+        group_by(category, endPoint) %>%
+        summarise(nSites = sum(EAR > hit_threshold)) %>%
         tidyr::spread(category, nSites)        
     } else {
       fullData <- chemical_summary %>%
-        dplyr::group_by(category, endPoint, date) %>%
-        dplyr::summarize(sumEAR = sum(EAR)) %>%
-        dplyr::group_by(category, endPoint) %>%
-        dplyr::summarise(nSites = sum(sumEAR > hit_threshold)) %>%
+        group_by(category, endPoint, date) %>%
+        summarize(sumEAR = sum(EAR)) %>%
+        group_by(category, endPoint) %>%
+        summarise(nSites = sum(sumEAR > hit_threshold)) %>%
         tidyr::spread(category, nSites)      
     }
   }
@@ -217,10 +216,9 @@ endpoint_hits <- function(chemical_summary,
 #' 
 #' Create links
 #' @param cas character
-#' @param endpoint character
 #' @param hits character
 #' @export
 #' @keywords internal
-createLink <- function(cas, endpoint) {
-  paste0('<a href="http://actor.epa.gov/dashboard/#selected/',cas,"+",endpoint,'" target="_blank">&#9432;</a>')
+createLink <- function(cas) {
+  paste0('<a href="https://comptox.epa.gov/dashboard/dsstoxdb/results?search=',cas,'#invitrodb-bioassays-toxcast-tox21" target="_blank">&#9432;</a>')
 }

R/filter_endPoint_info.R

@@ -42,7 +42,7 @@ filter_groups <- function(ep,
   assay_source_name <- assay_component_endpoint_name <- ".dplyr"
 
   ep <- ep[,c("assay_component_endpoint_name",groupCol,"assay_source_name")] %>%
-    dplyr::rename(endPoint = assay_component_endpoint_name,
+    rename(endPoint = assay_component_endpoint_name,
            assaysFull = assay_source_name)
   names(ep)[names(ep) == groupCol] <- "groupCol"
 

R/get_ACC.R

@@ -4,12 +4,14 @@
 #' (ACC) values for specified chemicals. 
 #' 
 #' The data used in toxEval were combined from files in the 
-#' "INVITRODB_V2_LEVEL5" directory that were included in the October 2015 
+#' "INVITRODB_V3_LEVEL5" directory that were included in the October 2018 
 #' release of the ToxCast database. The function \code{get_ACC} will 
 #' convert the ACC values in the ToxCast database from units of (log \eqn{\mu}M) 
 #' to units of \eqn{\mu}g/L, and reformat the data as input to toxEval.
 #' 
-#' @param CAS Vector of CAS. 
+#' @param CAS Vector of CAS.
+#' @import dplyr
+#' 
 #' @return data frame with columns CAS, chnm, flags, endPoint, ACC, MlWt, and ACC_value
 #' @export
 #' @examples
@@ -21,22 +23,22 @@ get_ACC <- function(CAS){
   Structure_MolWt <- Substance_CASRN <- casn <- Substance_Name <- ".dplyr"
   chnm <- flags <- MlWt <- ACC_value <- casrn <- endPoint <- ".dplyr"
 
-  chem_list <- dplyr::select(tox_chemicals,
+  chem_list <- select(tox_chemicals,
                              casrn = Substance_CASRN,
-                             MlWt = Structure_MolWt) %>%
-    dplyr::filter(casrn %in% CAS) 
+                             MlWt = Structure_MolWt) 
+  chem_list <- filter(chem_list, casrn %in% CAS) 
+
+  ACC <- ToxCast_ACC 
+  ACC <- filter(ACC, CAS %in% CAS)
+  ACC <- right_join(ACC, chem_list,
+               by= c("CAS"="casrn")) 
 
-  ACC <- ToxCast_ACC %>%
-    dplyr::filter(CAS %in% CAS) %>%
-    dplyr::right_join(chem_list,
-               by= c("CAS"="casrn")) %>%
-    data.frame() %>%
-    dplyr::mutate(ACC_value = 10^ACC,
-                  ACC_value = ACC_value * MlWt) %>%
-    dplyr::filter(!is.na(ACC_value)) %>%
-    dplyr::left_join(dplyr::select(tox_chemicals, 
-                                   CAS = Substance_CASRN, 
-                                   chnm = Substance_Name), by="CAS")
+  ACC <- mutate(ACC, ACC_value = 10^ACC,
+                  ACC_value = ACC_value * MlWt) 
+  ACC <- filter(ACC, !is.na(ACC_value))
+  ACC <- left_join(ACC, select(tox_chemicals, 
+                           CAS = Substance_CASRN, 
+                           chnm = Substance_Name), by="CAS")
 
   if(any(is.na(ACC$MlWt))){
     warning("Some chemicals are missing molecular weights")