Add metrics Zcg, nO2g, and nH2Og

DESCRIPTION

@@ -1,6 +1,6 @@
-Date: 2024-03-16
+Date: 2024-03-22
 Package: canprot
-Version: 1.1.2-40
+Version: 1.1.2-41
 Title: Chemical Analysis of Proteins
 Authors@R: c(
     person("Jeffrey", "Dick", email = "[email protected]", role = c("aut", "cre"),

NAMESPACE

@@ -29,7 +29,9 @@ export(
 # 20240309
 "SV",
 # 20240310 moved from chem16S
-"add_hull"
+"add_hull",
+# 20240317
+"Zcg", "nO2g", "nH2Og"
 )
 
 # Imports from default packages

R/cplab.R

@@ -15,11 +15,14 @@ cplab <- list(
   V0 = quote("Volume per residue (cm" ^ 3 ~ "mol" ^ -1 * ")"),
   pV0 = quote("Volume per protein (cm" ^ 3 ~ "mol" ^ -1 * ")"),
   V0g = quote("Specific volume (cm" ^ 3 ~ "g" ^ -1 * ")"),
-  Density = quote("Density (g" ^ -1 ~ "cm" ^ -3 * ")"),
+  Density = quote("Density (g" ~ "cm" ^ -3 * ")"),
   S0 = quote("Entropy per residue (J K" ^ -1 ~ "mol" ^ -1 * ")"),
   pS0 = quote("Entropy per protein (J K" ^ -1 ~ "mol" ^ -1 * ")"),
   S0g = quote("Specific entropy (J K" ^ -1 ~ "g" ^ -1 * ")"),
   SV = quote("Entropy density (J K" ^ -1 ~ "cm" ^ -3 * ")"),
+  Zcg = quote("Specific" ~ italic(Z)[C]),
+  nH2Og = quote("Specific" ~ italic(n)[H[2]*O]),
+  nO2g = quote("Specific" ~ italic(n)[O[2]]),
   HC = "H/C",
   NC = "N/C",
   OC = "O/C",

R/metrics.R

@@ -402,25 +402,41 @@ SC <- function(AAcomp, ...) {
 }
 
 # Density 20240304
-Density <- function(AAcomp, terminal_H2O = 0, ...) {
-  MW(AAcomp, terminal_H2O = 0, ...) / V0(AAcomp, terminal_H2O = 0, ...)
+Density <- function(AAcomp, ...) {
+  MW(AAcomp, ...) / V0(AAcomp, ...)
 }
 
 # Specific volume 20240308
-V0g <- function(AAcomp, terminal_H2O = 0, ...) {
-  V0(AAcomp, terminal_H2O = 0, ...) / MW(AAcomp, terminal_H2O = 0, ...)
+V0g <- function(AAcomp, ...) {
+  V0(AAcomp, ...) / MW(AAcomp, ...)
 }
 
 # Specific entropy 20240308
-S0g <- function(AAcomp, terminal_H2O = 0, ...) {
-  S0(AAcomp, terminal_H2O = 0, ...) / MW(AAcomp, terminal_H2O = 0, ...)
+S0g <- function(AAcomp, ...) {
+  S0(AAcomp, ...) / MW(AAcomp, ...)
 }
 
 # Entropy density 20240309
-SV <- function(AAcomp, terminal_H2O = 0, ...) {
-  S0(AAcomp, terminal_H2O = 0, ...) / V0(AAcomp, terminal_H2O = 0, ...)
+SV <- function(AAcomp, ...) {
+  S0(AAcomp, ...) / V0(AAcomp, ...)
 }
 
+# Specific Zc 20240317
+Zcg <- function(AAcomp, ...) {
+  Zc(AAcomp, ...) / MW(AAcomp, ...)
+}
+
+# Specific nO2 20240317
+nO2g <- function(AAcomp, ...) {
+  nO2(AAcomp, ...) / MW(AAcomp, ...)
+}
+
+# Specific nH2O 20240317
+nH2Og <- function(AAcomp, ...) {
+  nH2O(AAcomp, ...) / MW(AAcomp, ...)
+}
+
+
 # Metabolic cost 20211220
 # Moved from JMDplots/evdevH2O.R to canprot 20240304
 Cost <- function(AAcomp, ...) {

inst/tinytest/test-metrics.R

@@ -75,9 +75,15 @@ info <- "Metrics don't change"
 AA <- structure(list(Ala = 1, Cys = 1, Asp = 1, Glu = 1, Phe = 1, Gly = 1, His = 1, Ile = 1, Lys = 1, Leu = 1,
                      Met = 1, Asn = 1, Pro = 1, Gln = 1, Arg = 1, Ser = 1, Thr = 1, Val = 1, Trp = 1, Tyr = 1), row.names = 6L, class = "data.frame")
 metrics <- names(cplab)
-ref_values <- c(-0.074766, -1.14, -0.655, -0.49, 6.74, 118.886024, 2395.73576,
-  86.785, 1742.989, 0.729985, 1.369891, 35.511, 729.19, 0.298698,
-  0.409184, 1.46729, 0.271028, 0.271028, 0.018692, 20, 27.36, 29.075,
-  7.75, 221.25, 228.05, 47.175)
+ref_values <- c(
+  -0.074766, -1.14, -0.655, -0.49,       # Zc, nH2O, nO2, GRAVY
+  6.74, 118.886024, 2395.73576,          # pI, MW, pMW
+  86.785, 1742.989, 0.729985, 1.369891,  # V0, pV0, V0g, Density
+  35.511, 729.19, 0.298698, 0.409184,    # S0, pS0, S0g, SV
+  -0.000629, -0.009589, -0.005509,       # ZCg, nH2Og, nO2g
+  1.46729, 0.271028, 0.271028, 0.018692, # HC, NC, OC, SC
+  20, 27.36, 29.075, 7.75,               # plength, Cost, RespiratoryCost, FermentativeCost
+  221.25, 228.05, 47.175                 # B20Cost, Y20Cost, H11Cost
+)
 calc_values <- as.numeric(round(sapply(metrics, function(metric) get(metric)(AA)), 6))
 expect_equal(calc_values, ref_values)

man/metrics.Rd

@@ -16,6 +16,9 @@
 \alias{pS0}
 \alias{S0g}
 \alias{SV}
+\alias{Zcg}
+\alias{nH2Og}
+\alias{nO2g}
 \alias{HC}
 \alias{NC}
 \alias{OC}
@@ -43,12 +46,14 @@ Calculate chemical metrics for proteins from their amino acid compositions.
   pMW(AAcomp, terminal_H2O = 1, ...)
   V0(AAcomp, terminal_H2O = 0, ...)
   pV0(AAcomp, terminal_H2O = 1, ...)
-  V0g(AAcomp, terminal_H2O = 0, ...)
-  Density(AAcomp, terminal_H2O = 0, ...)
+  V0g(AAcomp, ...)
+  Density(AAcomp, ...)
   S0(AAcomp, terminal_H2O = 0, ...)
   pS0(AAcomp, terminal_H2O = 1, ...)
-  S0g(AAcomp, terminal_H2O = 0, ...)
-  SV(AAcomp, terminal_H2O = 0, ...)
+  S0g(AAcomp, ...)
+  SV(AAcomp, ...)
+  nH2Og(AAcomp, ...)
+  nO2g(AAcomp, ...)
   HC(AAcomp, ...)
   NC(AAcomp, ...)
   OC(AAcomp, ...)
@@ -85,14 +90,14 @@ The metrics are described below:
   This metric is independent of the choice of basis species.
   Note that \Zc is normalized by number of carbon atoms, not by number of residues.
 }
-\item{\code{nH2O}}{Stoichiometric hydration state (\nH2O).
+\item{\code{nH2O}}{Stoichiometric hydration state (\nH2O per residue).
   The available \code{basis} species are:
   \itemize{
     \item{\samp{QEC} - glutamine, glutamic acid, cysteine, \H2O, \O2 (Dick et al., 2020)}
     \item{\samp{QCa} - glutamine, cysteine, acetic acid, \H2O, \O2}
   }
 }
-\item{\code{nO2}}{Stoichiometric oxidation state (\nO2).
+\item{\code{nO2}}{Stoichiometric oxidation state (\nO2 per residue).
   The basis species also affect this calculation.
 }
 \item{\code{GRAVY}}{Grand average of hydropathy.
@@ -118,6 +123,8 @@ The metrics are described below:
 \item{\code{pS0}}{Standard molal entropy per protein.}
 \item{\code{S0g}}{Specific entropy.}
 \item{\code{SV}}{Entropy density.}
+\item{\code{nH2Og}}{\nH2O per gram.}
+\item{\code{nO2g}}{\nO2 per gram.}
 \item{\code{HC}}{H/C ratio (not counting terminal -H and -OH groups).}
 \item{\code{NC}}{N/C ratio.}
 \item{\code{OC}}{O/C ratio (not counting terminal -H and -OH groups).}

vignettes/demos.Rmd

@@ -44,7 +44,7 @@ The **canprot** functions used are:
 knitr::read_chunk("../demo/thermophiles.R")
 ```
 
-```{r thermophiles_demo_body, out.width = "100%", fig.align = "center", fig.width = 8, fig.height = 6, echo = FALSE, message = FALSE}
+```{r thermophiles_demo_body, out.width = "100%", fig.align = "center", fig.width = 8, fig.height = 6, echo = FALSE, message = FALSE, dpi = 150}
 ```
 
 The data are from @DBCS23 for methanogen genomes (amino acid composition and optimal growth temperature) and from @LLX+24 for *Nitrososphaeria* MAGs (genome assemblies and habitat and respiration types).
@@ -71,7 +71,7 @@ knitr::read_chunk("../demo/locations.R")
 ```{r locations_demo_setup, echo = FALSE}
 ```
 
-```{r locations_demo_body, out.width = "100%", fig.align = "center", fig.width = 8, fig.height = 4.5}
+```{r locations_demo_body, out.width = "100%", fig.align = "center", fig.width = 8, fig.height = 4.5, dpi = 150}
 ```
 
 The plots show carbon oxidation state (`r Zc`) and isoelectric point (pI) for human proteins in different subcellular locations.
@@ -94,7 +94,7 @@ The **canprot** functions used are:
 knitr::read_chunk("../demo/redoxins.R")
 ```
 
-```{r redoxins_demo_body, out.width = "75%", fig.align = "center", fig.width = 6, fig.height = 5, echo = FALSE, message = FALSE}
+```{r redoxins_demo_body, out.width = "75%", fig.align = "center", fig.width = 6, fig.height = 5, echo = FALSE, message = FALSE, dpi = 100}
 ```
 
 This is an *exploratory analysis* for hypothesis generation about evolutionary links between midpoint reduction potential and `r Zc` of proteins.