preparing for release

c1au6i0 · Jan 1, 2025 · 14a77e1 · 14a77e1
1 parent 31e2627
commit 14a77e1
Show file tree

Hide file tree

Showing 23 changed files with 330 additions and 198 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: extractox
 Title: Extract Tox Info from Various Databases
-Version: 0.1.9001
+Version: 0.1.9003
 Authors@R: c(
     person("Claudio", "Zanettini", , "[email protected]", role = c("aut", "cre", "cph"),
            comment = c(ORCID = "0000-0001-5043-8033")),
@@ -12,9 +12,11 @@ Description: Extract toxicological and chemical information from databases
     Comparative Toxicogenomics Database <https://ctdbase.org/>, the
     Integrated Chemical Environment <https://ice.ntp.niehs.nih.gov/>, the
     Integrated Risk Information System <https://cfpub.epa.gov/ncea/iris/>,
+    Provisional Peer-Reviewed Toxicity Values
+    <https://www.epa.gov/pprtv/provisional-peer-reviewed-toxicity-values-pprtvs-assessments>,
     the CompTox Chemicals Dashboard Resource Hub
     <https://www.epa.gov/comptox-tools/comptox-chemicals-dashboard-resource-hub>,
-    and PubChem <https://pubchem.ncbi.nlm.nih.gov/>.
+    PubChem <https://pubchem.ncbi.nlm.nih.gov/>, and others.
 License: MIT + file LICENSE
 URL: https://github.com/c1au6i0/extractox,
     https://c1au6i0.github.io/extractox/

diff --git a/R/cache.R b/R/cache.R
@@ -59,7 +59,6 @@ save_to_cache <- function(dat, file_name, verbose = FALSE) {
 #' @keywords internal
 #' @noRd
 read_from_cache <- function(file_name, verbose = FALSE) {
-
   if (base::missing(file_name)) {
     cli::cli_abort("The argument {.field {file_name}} is required.")
   }
@@ -95,7 +94,6 @@ read_from_cache <- function(file_name, verbose = FALSE) {
 #' with_extr_sandbox(Sys.getenv("R_USER_CACHE_DIR"))
 #' with_extr_sandbox(tools::R_user_dir("extractox", "cache"))
 with_extr_sandbox <- function(code, temp_dir = tempdir()) {
-
   if (base::missing(code)) {
     cli::cli_abort("The argument {.field {file_name}} is required.")
   }

diff --git a/R/extr_ice.R b/R/extr_ice.R
@@ -49,7 +49,8 @@ extr_ice <- function(casrn,
       httr2::request(base_url) |>
         httr2::req_retry(max_tries = 2, backoff = ~3) |>
         httr2::req_body_json(list(chemids = casrn, assays = assays),
-                             auto_unbox = FALSE) |>
+          auto_unbox = FALSE
+        ) |>
         httr2::req_options(!!!libcurl_opt) |>
         httr2::req_perform()
     },
@@ -69,8 +70,10 @@ extr_ice <- function(casrn,
     "reference_url", "dtxsid", "substance_name", "pubmed_id"
   )
 
-  out <- stats::setNames(as.data.frame(matrix(ncol = length(col_names), nrow = 0)),
-                         col_names)
+  out <- stats::setNames(
+    as.data.frame(matrix(ncol = length(col_names), nrow = 0)),
+    col_names
+  )
 
   # Parse the JSON content
   content <- tryCatch(

diff --git a/R/extr_pprtv.R b/R/extr_pprtv.R
@@ -22,6 +22,7 @@
 #'   This is was introduced for debugging purposes.
 #' @return A data frame with extracted information matching the specified
 #'   identifiers, or NULL if no matches are found.
+#' @seealso \href{https://www.epa.gov/pprtv/provisional-peer-reviewed-toxicity-values-pprtvs-assessments}{EPA PPRTVs}
 #' @export
 #' @examples
 #' \donttest{

diff --git a/R/extr_tox.R b/R/extr_tox.R
@@ -59,16 +59,20 @@ extr_tox <- function(casrn, verbose = TRUE, force = TRUE) {
 
   iris_filt <- extr_iris(casrn = casrn, verbose = verbose)
 
-  extracted_monographs <- extr_monograph(ids = casrn, search_type = "casrn",
-                                         verbose = verbose)
+  extracted_monographs <- extr_monograph(
+    ids = casrn, search_type = "casrn",
+    verbose = verbose
+  )
 
   extracted_pprtv <- extr_pprtv(ids = casrn, verbose = verbose)
 
-  list_1 <- list(who_iarc_monographs = extracted_monographs,
-                 pprtv = extracted_pprtv,
-                 ghs_dat = ghs_dat,
-                 iris = iris_filt,
-                 ice = ice_dat)
+  list_1 <- list(
+    who_iarc_monographs = extracted_monographs,
+    pprtv = extracted_pprtv,
+    ghs_dat = ghs_dat,
+    iris = iris_filt,
+    ice = ice_dat
+  )
   out <- c(list_1, comptox_list)
   out
 }
diff --git a/R/other.R b/R/other.R
@@ -21,10 +21,12 @@ ice_assays <- function() {
     )
 
 
-  ice_invivo_sensitization <- c("Human Maximization Test",
-                                "Human Repeat Insult Patch Test",
-                                "LLNA",
-                                "Guinea Pig Maximization/Buehler")
+  ice_invivo_sensitization <- c(
+    "Human Maximization Test",
+    "Human Repeat Insult Patch Test",
+    "LLNA",
+    "Guinea Pig Maximization/Buehler"
+  )
 
   ice_invivo_irritation <- c(
     "Draize Skin Irritation/Corrosion Test",

diff --git a/R/utils.R b/R/utils.R
@@ -85,7 +85,7 @@ download_db <- function(url,
 #' @param col_names Column names to be used when creating a new dataframe in case of no matches.
 #' @param chemical_col The name of the column in dat where chemical names are stored.
 #' @return A dataframe with search results.
-#' @internal
+#' @keywords internal
 #'
 #' @details This function is used in `extr_pprtv` and `extr_monograph`.
 #'

diff --git a/README.Rmd b/README.Rmd
@@ -69,7 +69,7 @@ extr_ice_assay_names("Rat Acute") # keep empty to retrieve all
 ```
 
 
-### IRIS
+### EPA IRIS
 
 The IRIS database is managed by the EPA and contains information on the health effects of exposure to various substances found in the environment. It provides qualitative and quantitative health risk information.
 
@@ -81,6 +81,19 @@ names(iris_info)
 ```
 
 
+### EPA PPRTVs
+
+The `extr_pprtv` function allows you to extract data for specified identifiers (CASRN or chemical names) from the EPA's Provisional Peer-Reviewed Toxicity Values (PPRTVs) database. This function retrieves and processes data, with options to use cached files or force a fresh download if necessary.
+
+```{r}
+# Example usage to extract data for a specific CASRN
+extr_pprtv(ids = "107-02-8", search_type = "casrn", verbose = TRUE)
+
+# Example usage to extract data for a chemical name
+extr_pprtv(ids = "Acrolein", search_type = "name", verbose = TRUE, force = FALSE)
+```
+
+
 ### CompTox
 
 The CompTox Chemistry Dashboard, managed by the EPA, provides access to data on chemical structures, properties, and associated bioactivity data. It integrates data from various sources to support chemical safety assessments.
@@ -99,7 +112,6 @@ The IARC Monographs database is managed by the World Health Organization (WHO) I
 
 The functione `extr_monograph` provides access to the WHO IARC Monographs database and accepts queries using CASRN or the names of chemicals.
 
-
 ```{r}
 dat <- extr_monograph(search_type = "casrn", ids = c("105-74-8", "120-58-1"))
 str(dat)
@@ -109,6 +121,32 @@ dat2 <- extr_monograph(search_type = "name", ids = c("Aloe", "Schistosoma", "Sty
 ```
 
 
+###  PubChem Database
+
+PubChem is an open chemistry database at the NIH. It provides information on chemical structures, identifiers, chemical and physical properties, biological activities, safety and toxicity information, patents, literature citations, and more.
+
+A series of functions that rely on the `webchem` package are used to extract chemical information, Globally Harmonized System (`GHS`) classification data, or flavor classification from PubChem.
+
+The function `extr_chem_info` retrieves chemical information of IUPAC-named chemicals. A warning is displayed if the chemical is not found.
+
+```{r}
+chem_info <- extr_chem_info(IUPAC_names = c("Formaldehyde", "Aflatoxin B1"))
+names(chem_info)
+```
+
+
+Two functions are used to extract specific sections of PubChem chemical information using CASRN:
+
+- `extr_pubchem_ghs` extracts Globally Harmonized System (GHS) codes.
+- `extr_pubchem_fema` extracts flavor profile data.
+
+
+```{r}
+ghs_info <- extr_pubchem_ghs(casrn = c("50-00-0", "64-17-5"))
+fema_info <- extr_pubchem_fema(casrn = c("50-00-0", "123-68-2"))
+```
+
+
 ### Tox Info
 
 The function `extr_tox` is a wrapper used to call all the above-mentioned functions and retrieve a list of dataframes.
@@ -166,31 +204,6 @@ tetramer_data <- extr_tetramer(
 names(tetramer_data)
 ```
 
-###  PubChem Database
-
-PubChem is an open chemistry database at the NIH. It provides information on chemical structures, identifiers, chemical and physical properties, biological activities, safety and toxicity information, patents, literature citations, and more.
-
-A series of functions that rely on the `webchem` package are used to extract chemical information, Globally Harmonized System (`GHS`) classification data, or flavor classification from PubChem.
-
-The function `extr_chem_info` retrieves chemical information of IUPAC-named chemicals. A warning is displayed if the chemical is not found.
-
-```{r}
-chem_info <- extr_chem_info(IUPAC_names = c("Formaldehyde", "Aflatoxin B1"))
-names(chem_info)
-```
-
-
-Two functions are used to extract specific sections of PubChem chemical information using CASRN:
-
-- `extr_pubchem_ghs` extracts Globally Harmonized System (GHS) codes.
-- `extr_pubchem_fema` extracts flavor profile data.
-
-
-```{r}
-ghs_info <- extr_pubchem_ghs(casrn = c("50-00-0", "64-17-5"))
-fema_info <- extr_pubchem_fema(casrn = c("50-00-0", "123-68-2"))
-```
-
 
 ## Important Note for Linux Users
 

diff --git a/man/extr_casrn_from_cid.Rd b/man/extr_casrn_from_cid.Rd
diff --git a/man/extr_chem_info.Rd b/man/extr_chem_info.Rd