Merge branch 'master' of github.com:jasenfinch/mzAnnotation

aberHRML · Apr 29, 2021 · 8efd211 · 8efd211
2 parents 5913cc6 + 8806aee
commit 8efd211
Show file tree

Hide file tree

Showing 50 changed files with 177 additions and 168 deletions.
diff --git a/.github/workflows/R-CMD-check.yaml b/.github/workflows/R-CMD-check.yaml
@@ -21,8 +21,8 @@ jobs:
       fail-fast: false
       matrix:
         config:
-          - {os: windows-latest, r: 'release'}
-          - {os: macOS-latest, r: 'release'}
+          # - {os: windows-latest, r: 'release'}
+          # - {os: macOS-latest, r: 'release'}
           - {os: ubuntu-20.04, r: 'release', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           - {os: ubuntu-20.04, r: 'devel', rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
 

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: mzAnnotation
 Title: Signal Annotation Tools for High Resolution Metabolomics
-Version: 1.7.3
+Version: 1.7.4
 Authors@R: 
     person(given = "Jasen",
            family = "Finch",
@@ -39,7 +39,6 @@ Collate: allGenerics.R
     calcAdducts.R
     calcM.R
     calcMZ.R
-    calculateMs.R
     checks.R
     convert.R
     data.R

diff --git a/NAMESPACE b/NAMESPACE
@@ -42,6 +42,7 @@ importFrom(dplyr,contains)
 importFrom(dplyr,everything)
 importFrom(dplyr,filter)
 importFrom(dplyr,group_by)
+importFrom(dplyr,inner_join)
 importFrom(dplyr,left_join)
 importFrom(dplyr,mutate)
 importFrom(dplyr,rename)
@@ -62,6 +63,7 @@ importFrom(purrr,map_chr)
 importFrom(purrr,map_dbl)
 importFrom(purrr,map_df)
 importFrom(purrr,map_int)
+importFrom(stats,setNames)
 importFrom(stringr,str_c)
 importFrom(stringr,str_extract)
 importFrom(stringr,str_replace)
@@ -71,7 +73,10 @@ importFrom(tibble,as_tibble)
 importFrom(tibble,deframe)
 importFrom(tibble,rowid_to_column)
 importFrom(tibble,tibble)
+importFrom(tidyr,drop_na)
+importFrom(tidyr,expand_grid)
 importFrom(tidyr,gather)
+importFrom(tidyr,spread)
 importFrom(utils,combn)
 importFrom(utils,getFromNamespace)
 useDynLib(mzAnnotation)
diff --git a/R/calculateMs.R b/R/calculateMs.R
diff --git a/R/ionisationProducts.R b/R/ionisationProducts.R
@@ -4,7 +4,7 @@
 #' @param adductTable table of adduct rules. Defaults to adducts()
 #' @examples 
 #' ionisationProducts(aminoAcids$SMILES[1])
-#' @importFrom dplyr ungroup
+#' @importFrom dplyr ungroup rowwise
 #' @export
 
 ionisationProducts <- function(SMILES,adductTable = adducts()){

diff --git a/R/mzAnnotation.R b/R/mzAnnotation.R
@@ -8,5 +8,6 @@ globalVariables(c('Name','ID','MF','Accurate Mass','Smile 1','Adduct',
                   'Theoretical m/z','True','desc','m/z','Adducts',
                   'Negative_Charge','Positive_Charge','SMILES','Total_Charge',
                   'NHH','COO','ACCESSION_ID','Accurate_Mass','Measured m/z',
-                  'HBA1','TPSA','.','Possible','Rule','x'
+                  'HBA1','TPSA','.','Possible','Rule','x','Transformation','ID1',
+                  'ID2','M','M1','M2','m/z1','m/z2','fill'
 ))
diff --git a/R/relationshipCalculator.R b/R/relationshipCalculator.R
@@ -2,61 +2,113 @@
 #' @description adduct, isotope and biotransfromation calculation.
 #' @param mz numeric \code{vector} of accurate m/z
 #' @param limit limit of deviation for thresholding associations. Defaults to 0.001
-#' @param modes character vector of ionisation modes of input mz 
-#' @param adducts character vector of adducts to use. If \code{NULL} all available adducts will be used. If \code{modes} is not \code{NULL}, this should be named list, the names denoting the adduct aquisition modes.
+#' @param adducts character vector of adducts names to use
 #' @param isotopes character vector of isotopes to use.
 #' @param transformations character vector of transformations to use
 #' @param adductTable table containing adduct formation rules. Defaults to \code{\link{adducts}()}.
 #' @param isotopeTable table containing isotope rules. Defaults to \code{\link{isotopes}()}.
 #' @param transformationTable table containing transformation rules. Defaults to \code{\link{transformations}()}.
+#' @examples 
+#' relationshipCalculator(c(132.03023,168.00691))
 #' @author Jasen Finch
 #' @export
 #' @importFrom utils combn
-#' @importFrom dplyr left_join contains
+#' @importFrom dplyr left_join contains inner_join
 #' @importFrom stringr str_c
-#' @examples 
-#' relationshipCalculator(c(132.03023,168.00691))
-#' 
-#' ## with modes declared
-#' relationshipCalculator(c(132.03023,172.00067),
-#'                       modes = c('n','p'),
-#'                       adducts = list(n = c("[M-H]1-","[M+Cl]1-","[M+K-2H]1-"), 
-#'                                      p = c('[M+H]1+','[M+K]1+','[M+Na]1+')))
+#' @importFrom tidyr expand_grid spread drop_na
+#' @importFrom tibble rowid_to_column tibble
+#' @importFrom stats setNames
 
+relationshipCalculator <- function(mz, limit = 0.001, adducts = c("[M-H]1-","[M+Cl]1-","[M+K-2H]1-"), isotopes = NA, transformations = NA, adductTable = adducts(), isotopeTable = isotopes(), transformationTable = transformations()){
+
+  Ms <- expand_grid(`m/z` = mz,
+                    Adduct = adducts,
+                    Isotope = isotopes,
+                    Transformation = transformations) %>% 
+    mutate(M = calculateMs(`m/z`,Adduct,Isotope,Transformation)) %>% 
+    rowid_to_column(var = 'ID')
+
+  relationships <- expand_grid(ID1 = Ms$ID,
+                               ID2 = Ms$ID) %>%
+    filter(ID1 != ID2) %>% 
+  left_join(Ms %>% 
+              select(ID1 = ID,M1 = M),
+            by = 'ID1') %>% 
+    left_join(Ms %>% 
+                select(ID2 = ID,M2 = M),
+              by = 'ID2') %>% 
+    mutate(Error = abs(M1 - M2)) %>% 
+    filter(Error <= limit) %>% 
+    left_join(Ms %>% 
+                setNames(str_c(names(.),'1')),
+              by = c("ID1", "M1")) %>% 
+    left_join(Ms %>% 
+                setNames(str_c(names(.),'2')),
+              by = c("ID2", "M2")) %>%
+    filter(`m/z1` != `m/z2`) %>% 
+    select(contains('ID'),
+           contains('m/z'),
+           contains('Adduct'),
+           contains('Isotope'),
+           contains('Transformation'),Error)
+
+  unique_rel <- relationships %>% 
+    select(contains('ID')) %>% 
+    mutate(fill = 1) %>%
+    spread(ID2,fill) %>%
+    {
+      id1 <- select(., ID1)
+      . <- select(.,-ID1)
+
+      .[lower.tri(.)] <- NA
+      . <- bind_cols(.,id1)
+      .
+    } %>%
+    gather(ID2,fill,-ID1) %>%
+    drop_na() %>%
+    select(-fill) %>% 
+    mutate(ID2 = as.numeric(ID2))
+
+  relationships <- relationships %>% 
+    inner_join(unique_rel,
+                     by = c("ID1", "ID2")) %>% 
+    select(-contains('ID'))
+
+  return(relationships)
+}
 
-relationshipCalculator <- function(mz, limit = 0.001, modes = NULL, adducts = c("[M-H]1-","[M+Cl]1-","[M+K-2H]1-"), isotopes = NULL, transformations = NULL, adductTable = adducts(), isotopeTable = isotopes(), transformationTable = transformations()){
-  if (is.null(adducts)) {
-    adducts <- adductTable$Name
-  }
-  if (!is.null(modes) & is.list(adducts)) {
-    A1 <- adducts[[modes[1]]]
-    A2 <- adducts[[modes[2]]]
-  } else {
-    A1 <- adducts
-    A2 <- adducts
+calculateMs <- function(mzs, adducts, isotopes, transformations, adductTable = adducts(), isotopeTable = isotopes(), transformationTable = transformations()){
+
+  if (!identical(length(mzs),length(adducts),length(isotopes),length(transformations))){
+    stop('Arguments mzs, adducts, isotopes, transformations should be vectors of the same length',
+         call. = FALSE) 
   }
-  isotopes <- c('NA',isotopes)
-  transformations <- c('NA',transformations)
-
-  combinations <- combn(mz,2)
-
-  combinations <- apply(combinations,2,function(x){
-    M1 <- calculateMs(x[1],A1,isotopes,transformations,adductTable,isotopeTable,transformationTable)
-    M2 <- calculateMs(x[2],A2,isotopes,transformations,adductTable,isotopeTable,transformationTable)
-
-    coms <- expand.grid(M1$ID,M2$ID)
-    colnames(coms) <- c('ID1','ID2')
-    coms <- left_join(coms,M1,by = c('ID1' = 'ID'))
-    colnames(coms)[3:ncol(coms)] <- str_c(colnames(coms)[3:ncol(coms)],'1')
-    coms <- left_join(coms,M2,by = c('ID2' = 'ID'))
-    colnames(coms)[8:ncol(coms)] <- str_c(colnames(coms)[8:ncol(coms)],'2')
-
-    coms <- mutate(coms,Error = abs(M1 - M2)) %>%
-      filter(Error <= limit) %>%
-      select(contains('m/z'),contains('Adduct'),contains('Isotope'),contains('Transformation'),Error)
-    return(coms)
-  })
-  combinations <- bind_rows(combinations) %>%
-    as_tibble()
-  return(combinations)
+
+  addRules <- adducts %>% 
+    tibble(Adduct = .) %>% 
+    left_join(adductTable ,
+              by = c('Adduct' = 'Name'))
+
+  isoRules <- isotopes %>% 
+    tibble(Isotope = .) %>% 
+    left_join(isotopeTable, by = "Isotope") %>% 
+    {
+      .$`Mass Difference`[is.na(.$`Mass Difference`)] <- 0
+      .
+    }
+
+  transRules <- transformations %>% 
+    tibble(Transformation  = .) %>% 
+    left_join(transformationTable, by = c("Transformation" = "MF Change")) %>% 
+    {
+      .$Difference[is.na(.$Difference)] <- 0
+      .
+    }
+
+  M <- ((mzs - addRules$Add) * addRules$Charge) 
+  M <- (M - isoRules$`Mass Difference`)
+  M <- M / addRules$xM
+  M <- M - transRules$Difference
+
+  return(round(M,5))
 }
diff --git a/README.md b/README.md
@@ -34,9 +34,9 @@ res <- relationshipCalculator(c(132.03023,168.00691))
 
 res
 #> # A tibble: 1 x 9
-#>   `m/z1` `m/z2` Adduct1 Adduct2 Isotope1 Isotope2 Transformation1
-#>    <dbl>  <dbl> <chr>   <chr>   <lgl>    <lgl>    <lgl>          
-#> 1   132.   168. [M-H]1- [M+Cl]… NA       NA       NA             
+#>   `m/z1` `m/z2` Adduct1 Adduct2  Isotope1 Isotope2 Transformation1
+#>    <dbl>  <dbl> <chr>   <chr>    <lgl>    <lgl>    <lgl>          
+#> 1   132.   168. [M-H]1- [M+Cl]1- NA       NA       NA             
 #> # … with 2 more variables: Transformation2 <lgl>, Error <dbl>
 ```
 
@@ -82,9 +82,9 @@ res <- PIPsearch(db = db,
                  isotope = NA)
 res
 #> # A tibble: 1 x 12
-#>      ID NAME  InChI InChIKey SMILES MF    Accurate_Mass Isotope Adduct
-#>   <int> <chr> <chr> <chr>    <chr>  <chr>         <dbl> <lgl>   <chr> 
-#> 1     4 L-As… InCh… CKLJMWT… C([C@… C4H7…          133. NA      [M-H]…
-#> # … with 3 more variables: `Measured m/z` <dbl>, `Theoretical m/z` <dbl>, `PPM
-#> #   Error` <dbl>
+#>      ID NAME   InChI       InChIKey   SMILES  MF    Accurate_Mass Isotope Adduct
+#>   <int> <chr>  <chr>       <chr>      <chr>   <chr>         <dbl> <lgl>   <chr> 
+#> 1     4 L-Asp… InChI=1S/C… CKLJMWTZI… C([C@@… C4H7…          133. NA      [M-H]…
+#> # … with 3 more variables: Measured m/z <dbl>, Theoretical m/z <dbl>,
+#> #   PPM Error <dbl>
 ```
diff --git a/docs/404.html b/docs/404.html
diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html
diff --git a/docs/authors.html b/docs/authors.html
diff --git a/docs/index.html b/docs/index.html
diff --git a/docs/news/index.html b/docs/news/index.html
diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml
@@ -2,7 +2,7 @@ pandoc: 2.11.2
 pkgdown: 1.6.1
 pkgdown_sha: ~
 articles: {}
-last_built: 2021-02-17T23:51Z
+last_built: 2021-04-29T17:14Z
 urls:
   reference: https://jasenfinch.github.io/mzAnnotation//reference
   article: https://jasenfinch.github.io/mzAnnotation//articles

diff --git a/docs/reference/MetaboliteDatabase-class.html b/docs/reference/MetaboliteDatabase-class.html
diff --git a/docs/reference/PIPsearch.html b/docs/reference/PIPsearch.html
diff --git a/docs/reference/adductTransformMF.html b/docs/reference/adductTransformMF.html