Merge pull request #99 from Meredith-Lab/cran-release

CRAN release prep
Meredith-Lab · Feb 15, 2024 · d550389 · d550389
2 parents 237bb4f + d6cc9b1
commit d550389
Show file tree

Hide file tree

Showing 12 changed files with 138 additions and 68 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -13,3 +13,4 @@ README.Rmd
 ^pkgdown$
 ^doc$
 ^Meta$
+^cran-comments\.md$
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -11,10 +11,11 @@ Authors@R: c(
     person("S. Marshall", "Ledford", role = "ctb"),
     person("Tamás", "Stirling", role = "ctb")
   )
-Description: Use this package to calculate estimated relative volatility
-    index values for organic compounds based on functional group
-    contributions.  Calculation uses the SIMPOL.1 method (Prankow and Asher,
-    2008) or modified SIMPOL.1 method as in Meredith et al. (2023).
+Description: Calculate estimated relative volatility index values for
+    organic compounds based on functional group contributions. Calculation
+    uses the SIMPOL.1 method (Prankow and Asher, 2008)
+    <doi:10.5194/acp-8-2773-2008> or modified SIMPOL.1 method as in
+    Meredith et al. (2023) <doi:10.5194/acp-8-2773-2008>.
 License: MIT + file LICENSE
 URL: https://meredith-lab.github.io/volcalc/
 BugReports: https://github.com/Meredith-Lab/volcalc/issues
@@ -27,8 +28,8 @@ Imports:
     httr2,
     KEGGREST,
     magrittr,
-    rlang,
     purrr,
+    rlang,
     stringr,
     tibble,
     tidyr,
@@ -39,9 +40,10 @@ Suggests:
     rmarkdown,
     testthat (>= 3.0.0),
     withr
+VignetteBuilder: 
+    knitr
 biocViews: 
 Config/testthat/edition: 3
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.2.3
-VignetteBuilder: knitr
diff --git a/R/calc_vol.R b/R/calc_vol.R
@@ -40,6 +40,7 @@
 #'
 #' @export
 #' @examples
+#' \dontrun{
 #' mol_paths <- mol_example()
 #' calc_vol(mol_paths)
 #'
@@ -48,7 +49,7 @@
 #'
 #' # Return intermediate calculations
 #' calc_vol(mol_paths, return_calc_steps = TRUE)
-#' 
+#' }
 calc_vol <-
   function(input, 
            from = c("mol_path", "smiles"),
@@ -123,7 +124,9 @@ calc_vol <-
 
     #return:
     vol_df %>% 
-      dplyr::select(dplyr::all_of(c({{ from }}, "formula", "name", "rvi", "category", cols_fx, cols_calc)))
+      dplyr::select(dplyr::all_of(c(
+        {{ from }}, "formula", "name", "rvi", "category", cols_fx, cols_calc)
+      ))
 
   }
 
diff --git a/R/get_fx_groups.R b/R/get_fx_groups.R
@@ -23,7 +23,8 @@
 #' @export
 get_fx_groups <- function(compound_sdf) {
 
-  # For now at least, this code only works with SDFset objects that contain single molecules.
+  # For now at least, this code only works with SDFset objects that contain
+  # single molecules. 
   # TODO: make this function work with SDFset objects with multiple molecules?
   if (length(compound_sdf) != 1) {
     stop("SDFset objects must contain a single molecule only")
@@ -46,8 +47,11 @@ get_fx_groups <- function(compound_sdf) {
   rowname <- n <- NULL
 
   #convert counts to integer
-  groups <- groups %>% dplyr::mutate(dplyr::across(dplyr::everything(), as.integer))
-  rings <- data.frame(t(ChemmineR::rings(compound_sdf, type = "count", arom = TRUE, inner = TRUE)))
+  groups <-
+    groups %>% 
+    dplyr::mutate(dplyr::across(dplyr::everything(), as.integer))
+  rings <- 
+    data.frame(t(ChemmineR::rings(compound_sdf, type = "count", arom = TRUE, inner = TRUE)))
   atoms <- atomcount2tibble(ChemmineR::atomcount(compound_sdf))
   carbon_bond_data <- data.frame(ChemmineR::conMA(compound_sdf)[[1]]) %>%
     dplyr::select(dplyr::contains("C_")) %>%
@@ -86,7 +90,9 @@ get_fx_groups <- function(compound_sdf) {
 
   amide_primary_pattern <- "[CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H2]"
   amide_secondary_pattern <- "[CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H1][#6;!$(C=[O,N,S])]"
-  amide_tertiary_pattern <- "[CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])]"
+  amide_tertiary_pattern <- 
+    "[CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3H0]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])]"
+
   # amide_total_pattern <- "[CX3;$([R0][#6]),$([H1R0])](=[OX1])[#7X3;$([H2]),$([H1][#6;!$(C=[O,N,S])]),$([#7]([#6;!$(C=[O,N,S])])[#6;!$(C=[O,N,S])])]"
 
   carbonylperoxynitrate_pattern <- "*C(=O)OO[N+1](=O)[O-1]"
@@ -95,12 +101,17 @@ get_fx_groups <- function(compound_sdf) {
   carbonylperoxyacid_pattern <- "[CX3;$([R0][#6]),$([H1R0])](=[OX1])[OX2][$([OX2H]),$([OX1-])]" 
   nitroester_pattern <- "C(=O)(OC)C~[NX3](-,=[OX1])-,=[OX1]" 
   # This captures OH groups on a ring that also has a nitro group (para, ortho, or meta).  Need to correct aromatic hydroxyl count later.
-  nitrophenol_pattern <- "[OX2H][$(c1ccccc1[$([NX3](=O)=O),$([NX3+](=O)[O-])]),$(c1cccc(c1)[$([NX3](=O)=O),$([NX3+](=O)[O-])]),$(c1ccc(cc1)[$([NX3](=O)=O),$([NX3+](=O)[O-])])]"
-  phosphoric_acid_pattern <- "[$(P(=[OX1])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)]),$([P+]([OX1-])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)])]"
-  phosphoric_ester_pattern <- "[$(P(=[OX1])([OX2][#6])([$([OX2H]),$([OX1-]),$([OX2][#6])])[$([OX2H]),$([OX1-]),$([OX2][#6]),$([OX2]P)]),$([P+]([OX1-])([OX2][#6])([$([OX2H]),$([OX1-]),$([OX2][#6])])[$([OX2H]),$([OX1-]),$([OX2][#6]),$([OX2]P)])]"
-  sulfate_pattern <- "[$([#16X4](=[OX1])(=[OX1])([OX2H,OX1H0-])[OX2][#6]),$([#16X4+2]([OX1-])([OX1-])([OX2H,OX1H0-])[OX2][#6])]"
+  nitrophenol_pattern <- 
+    "[OX2H][$(c1ccccc1[$([NX3](=O)=O),$([NX3+](=O)[O-])]),$(c1cccc(c1)[$([NX3](=O)=O),$([NX3+](=O)[O-])]),$(c1ccc(cc1)[$([NX3](=O)=O),$([NX3+](=O)[O-])])]"
+  phosphoric_acid_pattern <-
+    "[$(P(=[OX1])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)]),$([P+]([OX1-])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)])]"
+  phosphoric_ester_pattern <-
+    "[$(P(=[OX1])([OX2][#6])([$([OX2H]),$([OX1-]),$([OX2][#6])])[$([OX2H]),$([OX1-]),$([OX2][#6]),$([OX2]P)]),$([P+]([OX1-])([OX2][#6])([$([OX2H]),$([OX1-]),$([OX2][#6])])[$([OX2H]),$([OX1-]),$([OX2][#6]),$([OX2]P)])]"
+  sulfate_pattern <-
+    "[$([#16X4](=[OX1])(=[OX1])([OX2H,OX1H0-])[OX2][#6]),$([#16X4+2]([OX1-])([OX1-])([OX2H,OX1H0-])[OX2][#6])]"
   #sulfonate groups; sulfonate ions, and conjugate acid, sulfonic acids
-  sulfonate_pattern <- "[#16X4](=[OX1])(=[OX1])([#6])[*$([O-1]),*$([OH1]),*$([OX2H0])]"
+  sulfonate_pattern <-
+    "[#16X4](=[OX1])(=[OX1])([#6])[*$([O-1]),*$([OH1]),*$([OX2H0])]"
   thiol_pattern <- "[#16X2H]"
   carbothioester_pattern <- "S([#6])[CX3](=O)[#6]"
 

diff --git a/README.Rmd b/README.Rmd
@@ -17,7 +17,7 @@ knitr::opts_chunk$set(
 
 <!-- badges: start -->
 
-[![R-CMD-check](https://github.com/Meredith-Lab/volcalc/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/Meredith-Lab/volcalc/actions/workflows/R-CMD-check.yaml) [![latest-DOI](https://zenodo.org/badge/425022983.svg)](https://zenodo.org/badge/latestdoi/425022983) [![manuscript-DOI](https://img.shields.io/badge/DOI-10.3389/fmicb.2023.1267234-32a859.svg)](https://doi.org/10.3389/fmicb.2023.1267234) [![Project Status: Active -- The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active) [![Codecov test coverage](https://codecov.io/gh/Meredith-Lab/volcalc/branch/master/graph/badge.svg)](https://app.codecov.io/gh/Meredith-Lab/volcalc?branch=master) [![volcalc status badge](https://cct-datascience.r-universe.dev/badges/volcalc)](https://cct-datascience.r-universe.dev/volcalc)
+[![R-CMD-check](https://github.com/Meredith-Lab/volcalc/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/Meredith-Lab/volcalc/actions/workflows/R-CMD-check.yaml) [![latest-DOI](https://zenodo.org/badge/425022983.svg)](https://zenodo.org/badge/latestdoi/425022983) [![manuscript-DOI](https://img.shields.io/badge/DOI-10.3389/fmicb.2023.1267234-32a859.svg)](https://doi.org/10.3389/fmicb.2023.1267234) [![Project Status: Active -- The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active) [![Codecov test coverage](https://codecov.io/gh/Meredith-Lab/volcalc/branch/master/graph/badge.svg)](https://app.codecov.io/gh/Meredith-Lab/volcalc?branch=master) [![volcalc status badge](https://cct-datascience.r-universe.dev/badges/volcalc)](https://cct-datascience.r-universe.dev/volcalc) [![CRAN status](https://www.r-pkg.org/badges/version/volcalc)](https://CRAN.R-project.org/package=volcalc)
 
 <!-- badges: end -->
 
@@ -26,12 +26,18 @@ knitr::opts_chunk$set(
 The `volcalc` package allows you to automate calculating estimates of volatility for chemical compounds.
 
 `volcalc` supports "group contribution" methods for estimating volatility that rely on molecular properties such as molecular weight, numbers of certain atoms, and counts of certain functional groups.
-Currently, the only methods implemented are SIMPOL.1 (Pankow & Asher 2008) and a modified version used in Meredith et al. (2023).
+Currently, the only methods implemented are SIMPOL.1 ([Pankow & Asher 2008](https://doi.org/10.5194/acp-8-2773-2008)) and a modified version used in [Meredith et al. (2023)](https://doi.org/10.3389/fmicb.2023.1267234).
 
 `volcalc` works with either .mol files or [SMILES](https://en.wikipedia.org/wiki/Simplified_molecular-input_line-entry_system) strings as input, and supports downloading .mol files directly from [KEGG](https://www.kegg.jp/).
 
 ## Installation
 
+Install from CRAN with
+
+``` r
+install.packages("volcalc")
+```
+
 You can install the development version of `volcalc` from GitHub with
 
 ``` r
@@ -113,9 +119,9 @@ citation("volcalc")
 
 ### References
 
-Pankow, J.F., Asher, W.E., 2008.
-SIMPOL.1: a simple group contribution method for predicting vapor pressures and enthalpies of vaporization of multifunctional organic compounds.
-Atmos.
-Chem.
-Phys.
+Pankow, J.F., Asher, W.E., 2008. SIMPOL.1: a simple group contribution
+method for predicting vapor pressures and enthalpies of vaporization of
+multifunctional organic compounds. Atmos. Chem. Phys.
 <https://doi.org/10.5194/acp-8-2773-2008>
+
+Meredith, L.K., Ledford, S.M., Riemer, K., Geffre, P., Graves, K., Honeker, L.K., LeBauer, D., Tfaily, M.M., Krechmer, J., 2023. Automating methods for estimating metabolite volatility. Frontiers in Microbiology 14. <https://doi.org/10.3389/fmicb.2023.1267234>
diff --git a/README.md b/README.md
@@ -15,6 +15,8 @@ developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.re
 coverage](https://codecov.io/gh/Meredith-Lab/volcalc/branch/master/graph/badge.svg)](https://app.codecov.io/gh/Meredith-Lab/volcalc?branch=master)
 [![volcalc status
 badge](https://cct-datascience.r-universe.dev/badges/volcalc)](https://cct-datascience.r-universe.dev/volcalc)
+[![CRAN
+status](https://www.r-pkg.org/badges/version/volcalc)](https://CRAN.R-project.org/package=volcalc)
 
 <!-- badges: end -->
 
@@ -27,7 +29,9 @@ volatility for chemical compounds.
 volatility that rely on molecular properties such as molecular weight,
 numbers of certain atoms, and counts of certain functional groups.
 Currently, the only methods implemented are SIMPOL.1 ([Pankow & Asher
-2008](https://doi.org/10.5194/acp-8-2773-2008)) and a modified version used in [Meredith et al. (2023)](https://doi.org/10.3389/fmicb.2023.1267234).
+2008](https://doi.org/10.5194/acp-8-2773-2008)) and a modified version
+used in [Meredith et
+al. (2023)](https://doi.org/10.3389/fmicb.2023.1267234).
 
 `volcalc` works with either .mol files or
 [SMILES](https://en.wikipedia.org/wiki/Simplified_molecular-input_line-entry_system)
@@ -36,6 +40,12 @@ strings as input, and supports downloading .mol files directly from
 
 ## Installation
 
+Install from CRAN with
+
+``` r
+install.packages("volcalc")
+```
+
 You can install the development version of `volcalc` from GitHub with
 
 ``` r
@@ -171,5 +181,7 @@ method for predicting vapor pressures and enthalpies of vaporization of
 multifunctional organic compounds. Atmos. Chem. Phys.
 <https://doi.org/10.5194/acp-8-2773-2008>
 
-Meredith, L.K., Ledford, S.M., Riemer, K., Geffre, P., Graves, K., Honeker, L.K., LeBauer, D., Tfaily, M.M., Krechmer, J., 2023. Automating methods for estimating metabolite volatility. Frontiers in Microbiology 14. <https://doi.org/10.3389/fmicb.2023.1267234>
-
+Meredith, L.K., Ledford, S.M., Riemer, K., Geffre, P., Graves, K.,
+Honeker, L.K., LeBauer, D., Tfaily, M.M., Krechmer, J., 2023. Automating
+methods for estimating metabolite volatility. Frontiers in Microbiology
+14. <https://doi.org/10.3389/fmicb.2023.1267234>
diff --git a/cran-comments.md b/cran-comments.md
@@ -0,0 +1,13 @@
+## R CMD check results
+
+0 errors | 0 warnings | 1 note
+
+* This is a new release.
+
+The note on check is:
+
+>Package has a FOSS license but eventually depends on the following
+>  package which may restrict use:
+>    ChemmineOB
+
+ChemmineOB is an R package with the [Artistic-2.0 license](https://github.com/girke-lab/ChemmineOB/blob/master/LICENSE), which does appear to be FOSS.  Other R packages
diff --git a/man/calc_vol.Rd b/man/calc_vol.Rd
diff --git a/man/volcalc-package.Rd b/man/volcalc-package.Rd
diff --git a/tests/testthat/test-calc_vol.R b/tests/testthat/test-calc_vol.R
@@ -1,16 +1,22 @@
-test_that("volatility estimate is correct for example compound for entire workflow", {
+test_that("volatility estimate is correct", {
   ex_vol_df <- calc_vol("data/C16181.mol")
   expect_equal(round(ex_vol_df$rvi, 6), 6.975349)
 })
 
 test_that("returns correct columns depending on return arguments", {
   just_vol <- calc_vol("data/C16181.mol")
   with_fx <- calc_vol("data/C16181.mol", return_fx_groups = TRUE)
-  with_fx_steps <- calc_vol("data/C16181.mol", return_fx_groups = TRUE, return_calc_steps = TRUE)
-  expect_setequal(colnames(just_vol), c("mol_path", "formula", "name", "rvi", "category"))
+  with_fx_steps <-
+    calc_vol("data/C16181.mol",
+             return_fx_groups = TRUE,
+             return_calc_steps = TRUE)
+  expect_setequal(colnames(just_vol),
+                  c("mol_path", "formula", "name", "rvi", "category"))
   # just some examples here
-  expect_contains(colnames(with_fx), c(colnames(just_vol), "carbons", "carbothioesters", "fluorines"))
-  expect_contains(colnames(with_fx_steps), c(colnames(with_fx), "molecular_weight", "log_alpha", "log10_P"))
+  expect_contains(colnames(with_fx),
+                  c(colnames(just_vol), "carbons", "carbothioesters", "fluorines"))
+  expect_contains(colnames(with_fx_steps),
+                  c(colnames(with_fx), "molecular_weight", "log_alpha", "log10_P"))
 })
 
 test_that("calc_vol() works with multiple inputs", {
@@ -21,11 +27,15 @@ test_that("calc_vol() works with multiple inputs", {
 })
 
 test_that("smiles and .mol give same results", {
-  paths <- c("data/C16181.mol", "data/map00361/C00011.mol", "data/map00361/C00042.mol")
-  smiles <- c("C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)O", "O=C=O", "C(CC(=O)O)C(=O)O")
+  paths <-
+    c("data/C16181.mol",
+      "data/map00361/C00011.mol",
+      "data/map00361/C00042.mol")
+  smiles <-
+    c("C1(C(C(C(C(C1Cl)Cl)Cl)Cl)Cl)O", "O=C=O", "C(CC(=O)O)C(=O)O")
   expect_equal(
-    calc_vol(smiles, from = "smiles") %>% dplyr::select(-name, -smiles),
-    calc_vol(paths) %>% dplyr::select(-name, -mol_path)
+    calc_vol(smiles, from = "smiles") %>% dplyr::select(-name,-smiles),
+    calc_vol(paths) %>% dplyr::select(-name,-mol_path)
   )
 })
 
@@ -36,7 +46,9 @@ test_that("errors with invalid SMILES", {
 test_that("meredith and original method give different results", {
   #thiol and sulfonate groups, respectively
   # paths <- c(test_path("data/C00409.mol"), test_path("data/C03349.mol"))
-  smiles <- c("Methanethiol" = "SC", "Methyl methanesulfonate" = "COS(=O)(=O)C")
+  smiles <-
+    c("Methanethiol" = "SC",
+      "Methyl methanesulfonate" = "COS(=O)(=O)C")
   meredith <- calc_vol(smiles, from = "smiles", method = "meredith")
   simpol   <- calc_vol(smiles, from = "smiles", method = "simpol1")
   expect_true(all(meredith$rvi < simpol$rvi))

diff --git a/tests/testthat/test-get_fx_groups.R b/tests/testthat/test-get_fx_groups.R
@@ -58,7 +58,8 @@ test_that("SMARTS strings are correct", {
   expected <- test_compounds %>% dplyr::select(smiles, dplyr::all_of(common_cols))
   actual   <- test_fx_groups %>% dplyr::select(smiles, dplyr::all_of(common_cols))
 
-  # compare but ignore NAs in expected, by just overwriting them with values in actual using rows_patch()
+  # compare but ignore NAs in expected, by just overwriting them with values in
+  # actual using rows_patch()
   expect_equal(
     actual,
     dplyr::rows_patch(expected, actual)
-Original file line number
+Diff line change
@@ Expand Up / @@ -13,3 +13,4 @@ README.Rmd @@
     ^pkgdown$
     ^doc$
     ^Meta$
+    ^cran-comments\.md$