vignettes/Extending_MetMashR.Rmd
Extending_MetMashR.Rmd
The latest versions of struct and +
The latest versions of struct and MetMashR that are compatible with your current R version can be installed using BiocManager.
MetMashR
# install BiocManager if not present -if (!requireNamespace("BiocManager", quietly = TRUE)) +if (!requireNamespace("BiocManager", quietly = TRUE)) { install.packages("BiocManager") +} # install MetMashR and dependencies BiocManager::install("MetMashR")
# get annotations -AN = do_query( +AN <- do_query( context = "study", input_item = "analysis_id", input_value = "AN000465", - output_item = "metabolites")
The imported table has 747 rows and 8 columns. For brevity in this vignette we have cached the first 10 rows and stored them in the package.
We can convert the imported table into an annotation_table:
annotation_table
-AT = annotation_table(AN, id_column = NULL)
AT = annotation_table(AN, id_column = NULL)
AT <- annotation_table(data = AN, id_column = NULL)
All annotation_table objects must have an id for each row in the table. This is so that later, when examining the outputs of workflow steps, you can easily trace an annotation through the workflow. @@ -172,7 +174,7 @@
annotation_source
-.mwb_source<-setClass( +.mwb_source <- setClass( "mwb_source", - contains = c('annotation_database'), + contains = c("annotation_database"), prototype = list( - name = 'Import from Metabolomics Workbench', - libraries = 'metabolomicsWorkbenchR' + name = "Import from Metabolomics Workbench", + libraries = "metabolomicsWorkbenchR" ) )
.mwb_source<-setClass( +.mwb_source <- setClass( "mwb_source", - contains = c('annotation_database'), + contains = c("annotation_database"), prototype = list( - name = 'Import from Metabolomics Workbench', - libraries = 'metabolomicsWorkbenchR' + name = "Import from Metabolomics Workbench", + libraries = "metabolomicsWorkbenchR" ) )
.mwb_source <- setClass( "mwb_source", - contains = c('annotation_database'), + contains = c("annotation_database"), prototype = list( - name = 'Import from Metabolomics Workbench', - libraries = 'metabolomicsWorkbenchR' + name = "Import from Metabolomics Workbench", + libraries = "metabolomicsWorkbenchR" ) )
-mwb_source = function( - ...) { - +mwb_source <- function(...) { # new object - out = new_struct( - 'mwb_source', + out <- new_struct( + "mwb_source", ... ) return(out) @@ -269,24 +269,24 @@ The import method -setMethod(f = "read_database", - signature = c("mwb_source"), - definition = function(obj) { - - ## get annotations using metabolomicsWorkbenchR - # AN = do_query( - # context = "study", - # input_item = "analysis_id", - # input_value = M$analysis_id, - # output_item = "metabolites") - - ## for vignette use locally cached subset - AN = readRDS( - system.file('extdata/AN000465_subset.rds',package='MetMashR') - ) +setMethod( + f = "read_database", + signature = c("mwb_source"), + definition = function(obj) { + ## get annotations using metabolomicsWorkbenchR + # AN = do_query( + # context = "study", + # input_item = "analysis_id", + # input_value = M$analysis_id, + # output_item = "metabolites") - return(AN) - } + ## for vignette use locally cached subset + AN <- readRDS( + system.file("extdata/AN000465_subset.rds", package = "MetMashR") + ) + + return(AN) + } ) Note how we pass M$analysis id to the do_query function so that we can import annotations from @@ -300,12 +300,12 @@ Using the new source # initialise source -SRC = mwb_source( - source = 'AN000465' +SRC <- mwb_source( + source = "AN000465" ) # import -AT = read_source(SRC) +AT <- read_source(SRC)
mwb_source = function( - ...) { - +mwb_source <- function(...) { # new object - out = new_struct( - 'mwb_source', + out <- new_struct( + "mwb_source", ... ) return(out) @@ -269,24 +269,24 @@ The import method -setMethod(f = "read_database", - signature = c("mwb_source"), - definition = function(obj) { - - ## get annotations using metabolomicsWorkbenchR - # AN = do_query( - # context = "study", - # input_item = "analysis_id", - # input_value = M$analysis_id, - # output_item = "metabolites") - - ## for vignette use locally cached subset - AN = readRDS( - system.file('extdata/AN000465_subset.rds',package='MetMashR') - ) +setMethod( + f = "read_database", + signature = c("mwb_source"), + definition = function(obj) { + ## get annotations using metabolomicsWorkbenchR + # AN = do_query( + # context = "study", + # input_item = "analysis_id", + # input_value = M$analysis_id, + # output_item = "metabolites") - return(AN) - } + ## for vignette use locally cached subset + AN <- readRDS( + system.file("extdata/AN000465_subset.rds", package = "MetMashR") + ) + + return(AN) + } ) Note how we pass M$analysis id to the do_query function so that we can import annotations from @@ -300,12 +300,12 @@ Using the new source # initialise source -SRC = mwb_source( - source = 'AN000465' +SRC <- mwb_source( + source = "AN000465" ) # import -AT = read_source(SRC) +AT <- read_source(SRC)
mwb_source <- function(...) { # new object - out = new_struct( - 'mwb_source', + out <- new_struct( + "mwb_source", ... ) return(out) @@ -269,24 +269,24 @@ The import method -setMethod(f = "read_database", - signature = c("mwb_source"), - definition = function(obj) { - - ## get annotations using metabolomicsWorkbenchR - # AN = do_query( - # context = "study", - # input_item = "analysis_id", - # input_value = M$analysis_id, - # output_item = "metabolites") - - ## for vignette use locally cached subset - AN = readRDS( - system.file('extdata/AN000465_subset.rds',package='MetMashR') - ) +setMethod( + f = "read_database", + signature = c("mwb_source"), + definition = function(obj) { + ## get annotations using metabolomicsWorkbenchR + # AN = do_query( + # context = "study", + # input_item = "analysis_id", + # input_value = M$analysis_id, + # output_item = "metabolites") - return(AN) - } + ## for vignette use locally cached subset + AN <- readRDS( + system.file("extdata/AN000465_subset.rds", package = "MetMashR") + ) + + return(AN) + } ) Note how we pass M$analysis id to the do_query function so that we can import annotations from @@ -300,12 +300,12 @@ Using the new source # initialise source -SRC = mwb_source( - source = 'AN000465' +SRC <- mwb_source( + source = "AN000465" ) # import -AT = read_source(SRC) +AT <- read_source(SRC)
-setMethod(f = "read_database", - signature = c("mwb_source"), - definition = function(obj) { - - ## get annotations using metabolomicsWorkbenchR - # AN = do_query( - # context = "study", - # input_item = "analysis_id", - # input_value = M$analysis_id, - # output_item = "metabolites") - - ## for vignette use locally cached subset - AN = readRDS( - system.file('extdata/AN000465_subset.rds',package='MetMashR') - ) +setMethod( + f = "read_database", + signature = c("mwb_source"), + definition = function(obj) { + ## get annotations using metabolomicsWorkbenchR + # AN = do_query( + # context = "study", + # input_item = "analysis_id", + # input_value = M$analysis_id, + # output_item = "metabolites") - return(AN) - } + ## for vignette use locally cached subset + AN <- readRDS( + system.file("extdata/AN000465_subset.rds", package = "MetMashR") + ) + + return(AN) + } )
setMethod(f = "read_database", - signature = c("mwb_source"), - definition = function(obj) { - - ## get annotations using metabolomicsWorkbenchR - # AN = do_query( - # context = "study", - # input_item = "analysis_id", - # input_value = M$analysis_id, - # output_item = "metabolites") - - ## for vignette use locally cached subset - AN = readRDS( - system.file('extdata/AN000465_subset.rds',package='MetMashR') - ) +setMethod( + f = "read_database", + signature = c("mwb_source"), + definition = function(obj) { + ## get annotations using metabolomicsWorkbenchR + # AN = do_query( + # context = "study", + # input_item = "analysis_id", + # input_value = M$analysis_id, + # output_item = "metabolites") - return(AN) - } + ## for vignette use locally cached subset + AN <- readRDS( + system.file("extdata/AN000465_subset.rds", package = "MetMashR") + ) + + return(AN) + } )
setMethod( + f = "read_database", + signature = c("mwb_source"), + definition = function(obj) { + ## get annotations using metabolomicsWorkbenchR + # AN = do_query( + # context = "study", + # input_item = "analysis_id", + # input_value = M$analysis_id, + # output_item = "metabolites") - return(AN) - } + ## for vignette use locally cached subset + AN <- readRDS( + system.file("extdata/AN000465_subset.rds", package = "MetMashR") + ) + + return(AN) + } )
Note how we pass M$analysis id to the do_query function so that we can import annotations from @@ -300,12 +300,12 @@
M$analysis
do_query
# initialise source -SRC = mwb_source( - source = 'AN000465' +SRC <- mwb_source( + source = "AN000465" ) # import -AT = read_source(SRC)
Variable AT is the imported and cleaned annotation_database from Metabolomics Workbench and can be used as input to model_apply for other models and sequence, @@ -316,15 +316,15 @@
AT
annotation_database
model_apply
MetMashR workflow steps use the model -template from the struct +template from the struct package. Although originally intended for statistical methods, the model template is a flexible way to implement many different kinds of workflow step.
model
The struct +
The struct package provides convenience functions for “on-the-fly” implementation of new model objects. Here will will use the convenience functions to implement the first new model. Examples of this are also included in the -struct +struct package vignette.
set_struct_obj( - class_name = 'drop_empty_columns', - struct_obj = 'model', + class_name = "drop_empty_columns", + struct_obj = "model", params = character(0), - outputs = c(updated = 'annotation_source'), + outputs = c(updated = "annotation_source"), private = character(0), prototype = list( - name = 'Drop empty columns', + name = "Drop empty columns", description = paste0( - 'A workflow step that removes columns from an annotation table ', - 'where all rows are NA.'), - predicted = 'updated' + "A workflow step that removes columns from an annotation table ", + "where all rows are NA." + ), + predicted = "updated" ) )
We can now create an instance of our new model, and use the show method to display information about it.
show
-M = drop_empty_columns() +M <- drop_empty_columns() show(M) #> A "drop_empty_columns" object #> ----------------------------- @@ -375,30 +376,29 @@ Empty column removal set_obj_method( - class_name = 'drop_empty_columns', - method_name = 'model_apply', - signature = c('drop_empty_columns','annotation_source'), - definition = function(M,D) { - + class_name = "drop_empty_columns", + method_name = "model_apply", + signature = c("drop_empty_columns", "annotation_source"), + definition = function(M, D) { # search for columns of NA - W = lapply( # for each column + W <- lapply( # for each column D$data, # in the annotation table - function(x){ + function(x) { all(is.na(x)) # return TRUE if all rows are NA } ) - + # get index of columns with all rows NA - idx = which(unlist(W)) - + idx <- which(unlist(W)) + # if any found, remove from annotation table - if (length(idx)>0) { - D$data[,idx] = NULL + if (length(idx) > 0) { + D$data[, idx] <- NULL } - + # update model object - M$updated = D - + M$updated <- D + # return object return(M) } @@ -409,7 +409,7 @@ Empty column removal -M = model_apply(M,AT)
M = drop_empty_columns() +M <- drop_empty_columns() show(M) #> A "drop_empty_columns" object #> ----------------------------- @@ -375,30 +376,29 @@ Empty column removal set_obj_method( - class_name = 'drop_empty_columns', - method_name = 'model_apply', - signature = c('drop_empty_columns','annotation_source'), - definition = function(M,D) { - + class_name = "drop_empty_columns", + method_name = "model_apply", + signature = c("drop_empty_columns", "annotation_source"), + definition = function(M, D) { # search for columns of NA - W = lapply( # for each column + W <- lapply( # for each column D$data, # in the annotation table - function(x){ + function(x) { all(is.na(x)) # return TRUE if all rows are NA } ) - + # get index of columns with all rows NA - idx = which(unlist(W)) - + idx <- which(unlist(W)) + # if any found, remove from annotation table - if (length(idx)>0) { - D$data[,idx] = NULL + if (length(idx) > 0) { + D$data[, idx] <- NULL } - + # update model object - M$updated = D - + M$updated <- D + # return object return(M) } @@ -409,7 +409,7 @@ Empty column removal -M = model_apply(M,AT)
M <- drop_empty_columns() show(M) #> A "drop_empty_columns" object #> ----------------------------- @@ -375,30 +376,29 @@ Empty column removal set_obj_method( - class_name = 'drop_empty_columns', - method_name = 'model_apply', - signature = c('drop_empty_columns','annotation_source'), - definition = function(M,D) { - + class_name = "drop_empty_columns", + method_name = "model_apply", + signature = c("drop_empty_columns", "annotation_source"), + definition = function(M, D) { # search for columns of NA - W = lapply( # for each column + W <- lapply( # for each column D$data, # in the annotation table - function(x){ + function(x) { all(is.na(x)) # return TRUE if all rows are NA } ) - + # get index of columns with all rows NA - idx = which(unlist(W)) - + idx <- which(unlist(W)) + # if any found, remove from annotation table - if (length(idx)>0) { - D$data[,idx] = NULL + if (length(idx) > 0) { + D$data[, idx] <- NULL } - + # update model object - M$updated = D - + M$updated <- D + # return object return(M) } @@ -409,7 +409,7 @@ Empty column removal -M = model_apply(M,AT)
set_obj_method( - class_name = 'drop_empty_columns', - method_name = 'model_apply', - signature = c('drop_empty_columns','annotation_source'), - definition = function(M,D) { - + class_name = "drop_empty_columns", + method_name = "model_apply", + signature = c("drop_empty_columns", "annotation_source"), + definition = function(M, D) { # search for columns of NA - W = lapply( # for each column + W <- lapply( # for each column D$data, # in the annotation table - function(x){ + function(x) { all(is.na(x)) # return TRUE if all rows are NA } ) - + # get index of columns with all rows NA - idx = which(unlist(W)) - + idx <- which(unlist(W)) + # if any found, remove from annotation table - if (length(idx)>0) { - D$data[,idx] = NULL + if (length(idx) > 0) { + D$data[, idx] <- NULL } - + # update model object - M$updated = D - + M$updated <- D + # return object return(M) } @@ -409,7 +409,7 @@ Empty column removal -M = model_apply(M,AT)
-M = model_apply(M,AT)
M = model_apply(M,AT)
M <- model_apply(M, AT)
The number of columns before was:
ncol(AT$data) @@ -432,48 +432,48 @@ Suffix removal # define new model object set_struct_obj( - class_name = 'remove_suffix', - struct_obj = 'model', - params = c(clean = 'logical',column_name = 'character'), - outputs = c(updated = 'annotation_source'), + class_name = "remove_suffix", + struct_obj = "model", + params = c(clean = "logical", column_name = "character"), + outputs = c(updated = "annotation_source"), prototype = list( - name = 'Remove suffix', + name = "Remove suffix", description = paste0( - 'A workflow step that removes suffixes from molecule names by ', - 'splitting a string at the last underscore an retaining the part', - 'of the string before the underscore.'), - predicted = 'updated', + "A workflow step that removes suffixes from molecule names by ", + "splitting a string at the last underscore an retaining the part", + "of the string before the underscore." + ), + predicted = "updated", clean = FALSE, - column_name = 'V1' + column_name = "V1" ) ) # define method for new object set_obj_method( - class_name = 'remove_suffix', - method_name = 'model_apply', - signature = c('remove_suffix','annotation_source'), - definition = function(M,D) { - + class_name = "remove_suffix", + method_name = "model_apply", + signature = c("remove_suffix", "annotation_source"), + definition = function(M, D) { # get list of molecule names - x = D$data[[M$column_name]] - + x <- D$data[[M$column_name]] + # split string at last underscore - s = strsplit(x, "_(?!.*_)", perl=TRUE) - + s <- strsplit(x, "_(?!.*_)", perl = TRUE) + # get left hand side - s = lapply(s,'[',1) - + s <- lapply(s, "[", 1) + # if clean replace existing column, otherwise new column if (M$clean) { - D$data[[M$column_name]] = unlist(s) + D$data[[M$column_name]] <- unlist(s) } else { - D$data$name.fixed = unlist(x) + D$data$name.fixed <- unlist(x) } - + # update model object - M$updated = D - + M$updated <- D + # return object return(M) } @@ -515,15 +515,18 @@ Metabolite mashing # refmet -refmet = mwb_refmet_database() +refmet <- mwb_refmet_database() + # pubchem caches -pubchem_cid_cache = rds_database( - source = system.file('cached/pubchem_cid_cache.rds', - package='MetMashR') +pubchem_cid_cache <- rds_database( + source = system.file("cached/pubchem_cid_cache.rds", + package = "MetMashR" + ) ) -pubchem_smile_cache = rds_database( - source = system.file('cached/pubchem_smiles_cache.rds', - package='MetMashR') +pubchem_smile_cache <- rds_database( + source = system.file("cached/pubchem_smiles_cache.rds", + package = "MetMashR" + ) )
# define new model object set_struct_obj( - class_name = 'remove_suffix', - struct_obj = 'model', - params = c(clean = 'logical',column_name = 'character'), - outputs = c(updated = 'annotation_source'), + class_name = "remove_suffix", + struct_obj = "model", + params = c(clean = "logical", column_name = "character"), + outputs = c(updated = "annotation_source"), prototype = list( - name = 'Remove suffix', + name = "Remove suffix", description = paste0( - 'A workflow step that removes suffixes from molecule names by ', - 'splitting a string at the last underscore an retaining the part', - 'of the string before the underscore.'), - predicted = 'updated', + "A workflow step that removes suffixes from molecule names by ", + "splitting a string at the last underscore an retaining the part", + "of the string before the underscore." + ), + predicted = "updated", clean = FALSE, - column_name = 'V1' + column_name = "V1" ) ) # define method for new object set_obj_method( - class_name = 'remove_suffix', - method_name = 'model_apply', - signature = c('remove_suffix','annotation_source'), - definition = function(M,D) { - + class_name = "remove_suffix", + method_name = "model_apply", + signature = c("remove_suffix", "annotation_source"), + definition = function(M, D) { # get list of molecule names - x = D$data[[M$column_name]] - + x <- D$data[[M$column_name]] + # split string at last underscore - s = strsplit(x, "_(?!.*_)", perl=TRUE) - + s <- strsplit(x, "_(?!.*_)", perl = TRUE) + # get left hand side - s = lapply(s,'[',1) - + s <- lapply(s, "[", 1) + # if clean replace existing column, otherwise new column if (M$clean) { - D$data[[M$column_name]] = unlist(s) + D$data[[M$column_name]] <- unlist(s) } else { - D$data$name.fixed = unlist(x) + D$data$name.fixed <- unlist(x) } - + # update model object - M$updated = D - + M$updated <- D + # return object return(M) } @@ -515,15 +515,18 @@ Metabolite mashing # refmet -refmet = mwb_refmet_database() +refmet <- mwb_refmet_database() + # pubchem caches -pubchem_cid_cache = rds_database( - source = system.file('cached/pubchem_cid_cache.rds', - package='MetMashR') +pubchem_cid_cache <- rds_database( + source = system.file("cached/pubchem_cid_cache.rds", + package = "MetMashR" + ) ) -pubchem_smile_cache = rds_database( - source = system.file('cached/pubchem_smiles_cache.rds', - package='MetMashR') +pubchem_smile_cache <- rds_database( + source = system.file("cached/pubchem_smiles_cache.rds", + package = "MetMashR" + ) )
# refmet -refmet = mwb_refmet_database() +refmet <- mwb_refmet_database() + # pubchem caches -pubchem_cid_cache = rds_database( - source = system.file('cached/pubchem_cid_cache.rds', - package='MetMashR') +pubchem_cid_cache <- rds_database( + source = system.file("cached/pubchem_cid_cache.rds", + package = "MetMashR" + ) ) -pubchem_smile_cache = rds_database( - source = system.file('cached/pubchem_smiles_cache.rds', - package='MetMashR') +pubchem_smile_cache <- rds_database( + source = system.file("cached/pubchem_smiles_cache.rds", + package = "MetMashR" + ) )
In practice it is better to create your own cache using e.g. rds_database, sql_database or other @@ -531,41 +534,46 @@
rds_database
sql_database
# prepare sequence -M = import_source() + +M <- import_source() + drop_empty_columns() + remove_suffix( clean = TRUE, - column_name = 'metabolite_name') + + column_name = "metabolite_name" + ) + database_lookup( - query_column = 'refmet_name', - database_column = 'name', + query_column = "refmet_name", + database_column = "name", database = refmet, - suffix = '_mwb', - include = 'pubchem_cid') + + suffix = "_mwb", + include = "pubchem_cid" + ) + pubchem_compound_lookup( - query_column = 'metabolite_name', - search_by = 'name', - suffix = '_pc', - output = 'cids', - records = 'best', + query_column = "metabolite_name", + search_by = "name", + suffix = "_pc", + output = "cids", + records = "best", delay = 0.2, - cache = pubchem_cid_cache) + - combine_columns( - column_names = c('pubchem_cid_mwb','CID_pc'), - output_name = 'pubchem_cid', - source_name = 'pubchem_cid_source', - source_tags = c('mwb','pc'), - clean = TRUE) + + cache = pubchem_cid_cache + ) + + prioritise_columns( + column_names = c("pubchem_cid_mwb", "CID_pc"), + output_name = "pubchem_cid", + source_name = "pubchem_cid_source", + source_tags = c("mwb", "pc"), + clean = TRUE + ) + pubchem_property_lookup( - query_column = 'pubchem_cid', - search_by = 'cid', - suffix = '', - property = 'CanonicalSMILES', + query_column = "pubchem_cid", + search_by = "cid", + suffix = "", + property = "CanonicalSMILES", delay = 0.2, - cache = pubchem_smile_cache) + cache = pubchem_smile_cache + ) # apply sequence -M = model_apply(M,mwb_source(source = 'AN000465'))
Note that because the first step in the workflow is to import data from Metabolomics Workbench, we only need to provide an empty annotation_table as input to model_apply as it will be @@ -575,8 +583,8 @@
# prepare chart -C = openbabel_structure( - smiles_column = 'CanonicalSMILES', +C <- openbabel_structure( + smiles_column = "CanonicalSMILES", row_index = 1, scale_to_fit = FALSE, view_port = 400, @@ -584,14 +592,14 @@ Metabolite mashing) # loop over some records and plot some of the molecules -G = list() -x=1 -for (k in c(3,5)) { - C$row_index = k - G[[x]]=chart_plot(C,predicted(M)) - x=x+1 +G <- list() +x <- 1 +for (k in c(3, 5)) { + C$row_index <- k + G[[x]] <- chart_plot(C, predicted(M)) + x <- x + 1 } -cowplot::plot_grid(plotlist = G,nrow=1,labels='AUTO')
sessionInfo() -#> R version 4.3.2 (2023-10-31) -#> Platform: x86_64-pc-linux-gnu (64-bit) -#> Running under: Ubuntu 22.04.3 LTS +#> R Under development (unstable) (2024-03-13 r86113) +#> Platform: x86_64-pc-linux-gnu +#> Running under: Ubuntu 22.04.4 LTS #> #> Matrix products: default #> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 @@ -633,57 +641,58 @@ Session Info#> [1] stats graphics grDevices utils datasets methods base #> #> other attached packages: -#> [1] ggplot2_3.4.4 metabolomicsWorkbenchR_1.12.0 -#> [3] MetMashR_0.1.0 struct_1.14.0 -#> [5] BiocStyle_2.30.0 +#> [1] ggplot2_3.5.0 metabolomicsWorkbenchR_1.13.0 +#> [3] MetMashR_0.99.0 struct_1.15.4 +#> [5] BiocStyle_2.31.0 #> #> loaded via a namespace (and not attached): -#> [1] tidyselect_1.2.0 farver_2.1.1 -#> [3] dplyr_1.1.4 bitops_1.0-7 -#> [5] fastmap_1.1.1 RCurl_1.98-1.14 -#> [7] digest_0.6.34 lifecycle_1.0.4 -#> [9] sf_1.0-15 rsvg_2.6.0 -#> [11] magrittr_2.0.3 compiler_4.3.2 -#> [13] rlang_1.1.3 sass_0.4.8 -#> [15] tools_4.3.2 utf8_1.2.4 -#> [17] yaml_2.3.8 data.table_1.14.10 -#> [19] knitr_1.45 labeling_0.4.3 -#> [21] S4Arrays_1.2.0 ontologyIndex_2.11 -#> [23] classInt_0.4-10 DelayedArray_0.28.0 -#> [25] plyr_1.8.9 abind_1.4-5 -#> [27] KernSmooth_2.23-22 withr_3.0.0 -#> [29] purrr_1.0.2 BiocGenerics_0.48.1 -#> [31] desc_1.4.3 grid_4.3.2 -#> [33] stats4_4.3.2 fansi_1.0.6 -#> [35] e1071_1.7-14 colorspace_2.1-0 -#> [37] scales_1.3.0 MultiAssayExperiment_1.28.0 -#> [39] SummarizedExperiment_1.32.0 cli_3.6.2 -#> [41] rmarkdown_2.25 crayon_1.5.2 -#> [43] ragg_1.2.7 generics_0.1.3 -#> [45] httr_1.4.7 DBI_1.2.1 -#> [47] cachem_1.0.8 proxy_0.4-27 -#> [49] stringr_1.5.1 zlibbioc_1.48.0 -#> [51] ggthemes_5.0.0 BiocManager_1.30.22 -#> [53] XVector_0.42.0 matrixStats_1.2.0 -#> [55] vctrs_0.6.5 Matrix_1.6-5 -#> [57] jsonlite_1.8.8 bookdown_0.37 -#> [59] IRanges_2.36.0 S4Vectors_0.40.2 -#> [61] magick_2.8.2 systemfonts_1.0.5 -#> [63] jquerylib_0.1.4 units_0.8-5 -#> [65] glue_1.7.0 pkgdown_2.0.7 -#> [67] ChemmineOB_1.40.0 cowplot_1.1.2 -#> [69] stringi_1.8.3 gtable_0.3.4 -#> [71] GenomeInfoDb_1.38.5 GenomicRanges_1.54.1 -#> [73] munsell_0.5.0 tibble_3.2.1 -#> [75] pillar_1.9.0 htmltools_0.5.7 -#> [77] GenomeInfoDbData_1.2.11 R6_2.5.1 -#> [79] textshaping_0.3.7 evaluate_0.23 -#> [81] lattice_0.22-5 Biobase_2.62.0 -#> [83] highr_0.10 memoise_2.0.1 -#> [85] bslib_0.6.1 class_7.3-22 -#> [87] Rcpp_1.0.12 SparseArray_1.2.3 -#> [89] xfun_0.41 fs_1.6.3 -#> [91] MatrixGenerics_1.14.0 pkgconfig_2.0.3
Site built with pkgdown 2.0.7.
Site built with pkgdown 2.0.7.9000.
vignettes/annotate_mixtures.Rmd
annotate_mixtures.Rmd
# prepare workflow -M = import_source() + +M <- import_source() + add_labels( labels = c( - assay = 'placeholder', # will be replaced later - source_name = 'CD' - ))+ + assay = "placeholder", # will be replaced later + source_name = "CD" + ) + ) + filter_labels( - column_name = 'compound_match', - labels = 'Full match', - mode = 'include')+ + column_name = "compound_match", + labels = "Full match", + mode = "include" + ) + filter_labels( - column_name = 'compound_match', - labels = 'Full match', - mode = 'include') + + column_name = "compound_match", + labels = "Full match", + mode = "include" + ) + filter_range( - column_name = 'library_ppm_diff', + column_name = "library_ppm_diff", upper_limit = 2, lower_limit = -2, - equal_to = FALSE) + + equal_to = FALSE + ) + combine_records( - group_by = c('compound','ion'), + group_by = c("compound", "ion"), default_fcn = .select_max( - max_col = 'mzcloud_score', + max_col = "mzcloud_score", keep_NA = FALSE, use_abs = TRUE - ) + ) ) # place to store results -CD = list() -for (assay in c('HILIC_NEG','HILIC_POS','LIPIDS_NEG','LIPIDS_POS')) { +CD <- list() +for (assay in c("HILIC_NEG", "HILIC_POS", "LIPIDS_NEG", "LIPIDS_POS")) { # prepare source - AT = cd_source( + AT <- cd_source( source = c( system.file( - paste0('extdata/MTox/CD/',assay,'.xlsx'), - package = 'MetMashR'), + paste0("extdata/MTox/CD/", assay, ".xlsx"), + package = "MetMashR" + ), system.file( - paste0('extdata/MTox/CD/',assay,'_comp.xlsx'), - package = 'MetMashR')), - tag = paste0('CD_',assay)) - + paste0("extdata/MTox/CD/", assay, "_comp.xlsx"), + package = "MetMashR" + ) + ), + tag = paste0("CD_", assay) + ) + # update labels in workflow - M[2]$labels$assay = assay - + M[2]$labels$assay <- assay + # apply workflow to source - CD[[assay]] = model_apply(M,AT) + CD[[assay]] <- model_apply(M, AT) }
The CD variable is now a list containing the workflow for each assay.
CD
The HILIC_NEG table is shown below.
MetMashR workflows store the output after each step. We +
MetMashR workflows store the output after each step. We can use this to explore the impact of different workflow steps. For example, we can display the different compound matched present before and after filtering as pie charts.
First, we create the pie chart object and specify some parameters.
-C = annotation_pie_chart( - factor_name = 'compound_match', +C <- annotation_pie_chart( + factor_name = "compound_match", label_rotation = FALSE, - label_location = 'outside', + label_location = "outside", legend = TRUE, - label_type = 'percent', + label_type = "percent", centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" )
C = annotation_pie_chart( - factor_name = 'compound_match', +C <- annotation_pie_chart( + factor_name = "compound_match", label_rotation = FALSE, - label_location = 'outside', + label_location = "outside", legend = TRUE, - label_type = 'percent', + label_type = "percent", centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" )
C <- annotation_pie_chart( + factor_name = "compound_match", label_rotation = FALSE, - label_location = 'outside', + label_location = "outside", legend = TRUE, - label_type = 'percent', + label_type = "percent", centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" )
Now we create the plots using chart_plot and add some additional settings using ggplot2, and arrange the plots @@ -286,26 +295,29 @@
chart_plot
ggplot2
HILIC_NEG[3]
# plot individual charts -g1 = chart_plot(C,predicted(CD$HILIC_NEG[3])) + - ggtitle('Compound matches\nafter filtering') + - theme(plot.title = element_text(hjust = 0.5)) +g1 <- chart_plot(C, predicted(CD$HILIC_NEG[3])) + + ggtitle("Compound matches\nafter filtering") + + theme(plot.title = element_text(hjust = 0.5)) -g2 = chart_plot(C,predicted(CD$HILIC_NEG[2])) + - ggtitle('Compound matches\nbefore filtering') + - theme(plot.title = element_text(hjust = 0.5)) +g2 <- chart_plot(C, predicted(CD$HILIC_NEG[2])) + + ggtitle("Compound matches\nbefore filtering") + + theme(plot.title = element_text(hjust = 0.5)) # get legend -leg = cowplot::get_legend(g2) +leg <- cowplot::get_legend(g2) +#> Warning in get_plot_component(plot, "guide-box"): Multiple components found; +#> returning the first one. To return all, use `return_all = TRUE`. # layout cowplot::plot_grid( - g2+theme(legend.position = 'none'), - g1+theme(legend.position = 'none'), + g2 + theme(legend.position = "none"), + g1 + theme(legend.position = "none"), leg, - nrow=1, - rel_widths = c(1,1,0.5))
It is clear from these plots that the filter has removed all annotations without a “full match”.
-C = annotation_histogram( - factor_name = 'library_ppm_diff',vline = c(-2,2) +C <- annotation_histogram( + factor_name = "library_ppm_diff", vline = c(-2, 2) ) -G=list() -G$HILIC_NEG = chart_plot(C,predicted(CD$HILIC_NEG[2])) -G$HILIC_POS = chart_plot(C,predicted(CD$HILIC_POS[3])) +G <- list() +G$HILIC_NEG <- chart_plot(C, predicted(CD$HILIC_NEG[2])) +G$HILIC_POS <- chart_plot(C, predicted(CD$HILIC_POS[3])) -cowplot::plot_grid(plotlist=G,labels=c('HILIC_NEG','HILIC_POS'))
C = annotation_histogram( - factor_name = 'library_ppm_diff',vline = c(-2,2) +C <- annotation_histogram( + factor_name = "library_ppm_diff", vline = c(-2, 2) ) -G=list() -G$HILIC_NEG = chart_plot(C,predicted(CD$HILIC_NEG[2])) -G$HILIC_POS = chart_plot(C,predicted(CD$HILIC_POS[3])) +G <- list() +G$HILIC_NEG <- chart_plot(C, predicted(CD$HILIC_NEG[2])) +G$HILIC_POS <- chart_plot(C, predicted(CD$HILIC_POS[3])) -cowplot::plot_grid(plotlist=G,labels=c('HILIC_NEG','HILIC_POS'))
C <- annotation_histogram( + factor_name = "library_ppm_diff", vline = c(-2, 2) ) -G=list() -G$HILIC_NEG = chart_plot(C,predicted(CD$HILIC_NEG[2])) -G$HILIC_POS = chart_plot(C,predicted(CD$HILIC_POS[3])) +G <- list() +G$HILIC_NEG <- chart_plot(C, predicted(CD$HILIC_NEG[2])) +G$HILIC_POS <- chart_plot(C, predicted(CD$HILIC_POS[3])) -cowplot::plot_grid(plotlist=G,labels=c('HILIC_NEG','HILIC_POS'))
Note that we plotted the distribution based on the step before filtering by range, and set the vertical red lines equal to the range @@ -352,44 +364,49 @@
# prepare workflow -M = import_source() + +M <- import_source() + add_labels( labels = c( - assay = 'placeholder', # will be replaced later - source_name = 'LS' - ))+ + assay = "placeholder", # will be replaced later + source_name = "LS" + ) + ) + filter_labels( - column_name = 'Grade', - labels = c('A','B'), - mode = 'include') + + column_name = "Grade", + labels = c("A", "B"), + mode = "include" + ) + filter_labels( - column_name = 'Grade', - labels = c('A','B'), - mode = 'include') + + column_name = "Grade", + labels = c("A", "B"), + mode = "include" + ) + combine_records( - group_by = c('LipidIon'), + group_by = c("LipidIon"), default_fcn = .select_min( - min_col = 'library_ppm_diff', + min_col = "library_ppm_diff", keep_NA = FALSE, use_abs = TRUE - ) + ) ) # place to store results -LS = list() -for (assay in c('HILIC_NEG','HILIC_POS','LIPIDS_NEG','LIPIDS_POS')) { +LS <- list() +for (assay in c("HILIC_NEG", "HILIC_POS", "LIPIDS_NEG", "LIPIDS_POS")) { # prepare source - AT = ls_source( + AT <- ls_source( source = system.file( - paste0('extdata/MTox/LS/MTox_2023_',assay,'.txt'), - package = 'MetMashR'), - tag = paste0('LS_',assay)) - + paste0("extdata/MTox/LS/MTox_2023_", assay, ".txt"), + package = "MetMashR" + ), + tag = paste0("LS_", assay) + ) + # update labels in workflow - M[2]$labels$assay = assay - + M[2]$labels$assay <- assay + # apply workflow to source - LS[[assay]] = model_apply(M,AT) + LS[[assay]] <- model_apply(M, AT) }
The LS variable is now a list containing the workflow for each assay.
LS
The LIPIDS_NEG table is shown below.
MetMashR workflows store the output after each step. We can use this to explore the impact of different workflow steps. For example, we can display the different Grades present before and after filtering as pie charts.
-C = annotation_pie_chart( - factor_name = 'Grade', +C <- annotation_pie_chart( + factor_name = "Grade", label_rotation = FALSE, - label_location = 'outside', - label_type = 'percent', + label_location = "outside", + label_type = "percent", legend = FALSE, centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" ) -g1 = chart_plot(C,predicted(LS$LIPIDS_NEG)) + - ggtitle('Grades after filtering') + +g1 <- chart_plot(C, predicted(LS$LIPIDS_NEG)) + + ggtitle("Grades after filtering") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) -g2 = chart_plot(C,predicted(LS$LIPIDS_NEG[1])) + - ggtitle('Grades before filtering') + +g2 <- chart_plot(C, predicted(LS$LIPIDS_NEG[1])) + + ggtitle("Grades before filtering") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) -cowplot::plot_grid(g2,g1,nrow=1,align='v')
C = annotation_pie_chart( - factor_name = 'Grade', +C <- annotation_pie_chart( + factor_name = "Grade", label_rotation = FALSE, - label_location = 'outside', - label_type = 'percent', + label_location = "outside", + label_type = "percent", legend = FALSE, centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" ) -g1 = chart_plot(C,predicted(LS$LIPIDS_NEG)) + - ggtitle('Grades after filtering') + +g1 <- chart_plot(C, predicted(LS$LIPIDS_NEG)) + + ggtitle("Grades after filtering") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) -g2 = chart_plot(C,predicted(LS$LIPIDS_NEG[1])) + - ggtitle('Grades before filtering') + +g2 <- chart_plot(C, predicted(LS$LIPIDS_NEG[1])) + + ggtitle("Grades before filtering") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) -cowplot::plot_grid(g2,g1,nrow=1,align='v')
C <- annotation_pie_chart( + factor_name = "Grade", label_rotation = FALSE, - label_location = 'outside', - label_type = 'percent', + label_location = "outside", + label_type = "percent", legend = FALSE, centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" ) -g1 = chart_plot(C,predicted(LS$LIPIDS_NEG)) + - ggtitle('Grades after filtering') + +g1 <- chart_plot(C, predicted(LS$LIPIDS_NEG)) + + ggtitle("Grades after filtering") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) -g2 = chart_plot(C,predicted(LS$LIPIDS_NEG[1])) + - ggtitle('Grades before filtering') + +g2 <- chart_plot(C, predicted(LS$LIPIDS_NEG[1])) + + ggtitle("Grades before filtering") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) -cowplot::plot_grid(g2,g1,nrow=1,align='v')
# prepare chart object -C = annotation_venn_chart( - factor_name = 'compound', - line_colour = 'white', - fill_colour = '.group', +C <- annotation_venn_chart( + factor_name = "compound", + line_colour = "white", + fill_colour = ".group", legend = TRUE, labels = FALSE ) ## plot # get all CD tables -cd = lapply(CD,predicted) -g1 = chart_plot(C,cd) + ggtitle('Compounds in CD per assay') +cd <- lapply(CD, predicted) +g1 <- chart_plot(C, cd) + ggtitle("Compounds in CD per assay") # get all LS tables -C$factor_name = 'LipidName' -ls = lapply(LS,predicted) -g2 = chart_plot(C,ls) + ggtitle('Compounds in LS per assay') +C$factor_name <- "LipidName" +ls <- lapply(LS, predicted) +g2 <- chart_plot(C, ls) + ggtitle("Compounds in LS per assay") # layout -cowplot::plot_grid(g1,g2,nrow=2)
The diagram for CD shows the largest amount of overlap is between assays with the same ion mode.
# get all the cleaned annotation tables in one list -all_source_tables = lapply(c(CD,LS),predicted) +all_source_tables <- lapply(c(CD, LS), predicted) # prepare to merge -combine_workflow = +combine_workflow <- combine_sources( source_list = all_source_tables, - tag_ids = TRUE, matching_columns = c( - name = 'LipidName', - name = 'compound', - adduct= 'ion', - adduct = 'LipidIon'), - keep_cols = '.all', - source_col = 'annotation_table', + name = "LipidName", + name = "compound", + adduct = "ion", + adduct = "LipidIon" + ), + keep_cols = ".all", + source_col = "annotation_table", exclude_cols = NULL, - tag = 'combined' - ) + tag = "combined" + ) # merge -combine_workflow = model_apply(combine_workflow,lcms_table()) +combine_workflow <- model_apply(combine_workflow, lcms_table()) # show predicted(combine_workflow) -#> A "cd_source" object -#> -------------------- -#> name: Combined annotation source -#> description: This annotation_source object was generated by combining two other sources. -#> input params: sheets +#> A "annotation_source" object +#> ---------------------------- +#> name: combined +#> description: A source created by combining two or more sources +#> input params: tag, data, source #> annotations: 912 rows x 28 columns
Now that the tables have been combined we can explore the table using charts. For example, we visualise the number of annotations for each assay from both sources.
-C = annotation_pie_chart( - factor_name = 'assay', +C <- annotation_pie_chart( + factor_name = "assay", label_rotation = FALSE, - label_location = 'outside', - label_type = 'percent', - legend = TRUE , + label_location = "outside", + label_type = "percent", + legend = TRUE, centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" ) -chart_plot(C,predicted(combine_workflow)) + - ggtitle('Annotations per assay') + +chart_plot(C, predicted(combine_workflow)) + + ggtitle("Annotations per assay") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) + - guides(fill=guide_legend(title="Assay"))
C = annotation_pie_chart( - factor_name = 'assay', +C <- annotation_pie_chart( + factor_name = "assay", label_rotation = FALSE, - label_location = 'outside', - label_type = 'percent', - legend = TRUE , + label_location = "outside", + label_type = "percent", + legend = TRUE, centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" ) -chart_plot(C,predicted(combine_workflow)) + - ggtitle('Annotations per assay') + +chart_plot(C, predicted(combine_workflow)) + + ggtitle("Annotations per assay") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) + - guides(fill=guide_legend(title="Assay"))
C <- annotation_pie_chart( + factor_name = "assay", label_rotation = FALSE, - label_location = 'outside', - label_type = 'percent', - legend = TRUE , + label_location = "outside", + label_type = "percent", + legend = TRUE, centre_radius = 0.5, - centre_label = '.total' + centre_label = ".total" ) -chart_plot(C,predicted(combine_workflow)) + - ggtitle('Annotations per assay') + +chart_plot(C, predicted(combine_workflow)) + + ggtitle("Annotations per assay") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) + - guides(fill=guide_legend(title="Assay"))
In this next example we compare the number of annotations from each source.
# change to plot source_name column -C$factor_name = 'source_name' -chart_plot(C,predicted(combine_workflow)) + - ggtitle('Annotations per source') + +C$factor_name <- "source_name" +chart_plot(C, predicted(combine_workflow)) + + ggtitle("Annotations per source") + theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm")) + - guides(fill=guide_legend(title="Source"))
# import cached results -inchikey_cache = rds_database( +inchikey_cache <- rds_database( source = file.path( - system.file('cached',package='MetMashR'), - 'pubchem_inchikey_mtox_cache.rds'), - .writable = FALSE + system.file("cached", package = "MetMashR"), + "pubchem_inchikey_mtox_cache.rds" + ) ) -id_workflow = +id_workflow <- pubchem_property_lookup( - query_column = 'name', - search_by = 'name', - suffix = '', - property = 'InChIKey', - records = 'best', + query_column = "name", + search_by = "name", + suffix = "", + property = "InChIKey", + records = "best", cache = inchikey_cache ) -id_workflow = model_apply(id_workflow,predicted(combine_workflow))
# prepare cached results for vignette -inchikey_cache2 = rds_database( +inchikey_cache2 <- rds_database( source = file.path( - system.file('cached',package='MetMashR'), - 'pubchem_inchikey_mtox_cache2.rds'), - .writable = FALSE + system.file("cached", package = "MetMashR"), + "pubchem_inchikey_mtox_cache2.rds" + ) ) -inchikey_cache3 = rds_database( +inchikey_cache3 <- rds_database( source = file.path( - system.file('cached',package='MetMashR'), - 'pubchem_inchikey_mtox_cache3.rds'), - .writable=FALSE + system.file("cached", package = "MetMashR"), + "pubchem_inchikey_mtox_cache3.rds" + ) ) -N = normalise_strings( - search_column = 'name', - output_column = 'normalised_name', +N <- normalise_strings( + search_column = "name", + output_column = "normalised_name", dictionary = c( # custom dictionary list( # replace "NP" with "Compound NP" - list(pattern = '^NP-',replace = 'Compound NP-'), + list(pattern = "^NP-", replace = "Compound NP-"), # replace ? with NA, since this is ambiguous - list(pattern = '?',replace = NA,fixed=TRUE), - # remove terms in trailing brackets e.g." (ATP)" - list(pattern = '\\ \\([^\\)]*\\)$',replace = ''), + list(pattern = "?", replace = NA, fixed = TRUE), + # remove terms in trailing brackets e.g." (ATP)" + list(pattern = "\\ \\([^\\)]*\\)$", replace = ""), # replace known abbreviations - list(pattern = '(+/-)9-HpODE', - replace = '9-hydroperoxy-10E,12Z-octadecadienoic acid', - fixed = TRUE), - list(pattern = '(+/-)19(20)-DiHDPA', - replace = '19,20-dihydroxy-4Z,7Z,10Z,13Z,16Z-docosapentaenoic acid', - fixed = TRUE) + list( + pattern = "(+/-)9-HpODE", + replace = "9-hydroperoxy-10E,12Z-octadecadienoic acid", + fixed = TRUE + ), + list( + pattern = "(+/-)19(20)-DiHDPA", + replace = "19,20-dihydroxy-4Z,7Z,10Z,13Z,16Z-docosapentaenoic acid", + fixed = TRUE + ) ), # replace greek characters .greek_dictionary, # remove racemic properties .racemic_dictionary - )) + + ) +) + pubchem_property_lookup( - query_column = 'normalised_name', - search_by = 'name', - suffix = '_norm', - property = 'InChIKey', - records = 'best', - cache = inchikey_cache2) + + query_column = "normalised_name", + search_by = "name", + suffix = "_norm", + property = "InChIKey", + records = "best", + cache = inchikey_cache2 + ) + opsin_lookup( - query_column = 'normalised_name', - suffix = '_opsin', - output = 'stdinchikey', + query_column = "normalised_name", + suffix = "_opsin", + output = "stdinchikey", cache = inchikey_cache3 ) + - combine_columns( - column_names = c('stdinchikey_opsin','InChIKey_norm','InChIKey'), - output_name = 'inchikey', - source_name = 'inchikey_source', + prioritise_columns( + column_names = c("stdinchikey_opsin", "InChIKey_norm", "InChIKey"), + output_name = "inchikey", + source_name = "inchikey_source", clean = TRUE ) -N = model_apply(N,predicted(id_workflow))
We can explore the impact of these workflow steps using Venn and Pie charts to compare the results before/after the workflow.
In this Venn diagram we show the overlap between the InChIKey @@ -709,17 +732,19 @@
# venn inchikey columns -C = annotation_venn_chart( - factor_name = c('InChIKey','InChIKey_norm','stdinchikey_opsin'), - line_colour = 'white', - fill_colour = '.group', +C <- annotation_venn_chart( + factor_name = c("InChIKey", "InChIKey_norm", "stdinchikey_opsin"), + line_colour = "white", + fill_colour = ".group", legend = TRUE, labels = FALSE ) -chart_plot(C,predicted(N[3]))+ - guides(fill = guide_legend(title='Source'), - colour = guide_legend(title = 'Source')) + - theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm"))
In the next chart we visualise the proportion of annotations from each query, after prioritisation and merging has taken place.
# pie source of inchikey -C = annotation_pie_chart( - factor_name = 'inchikey_source', +C <- annotation_pie_chart( + factor_name = "inchikey_source", label_rotation = FALSE, - label_location = 'outside', - label_type = 'percent', + label_location = "outside", + label_type = "percent", legend = TRUE, centre_radius = 0.5, - centre_label = '.total', + centre_label = ".total", count_na = TRUE ) -chart_plot(C,predicted(N)) + - guides(fill = guide_legend(title='Source'), - colour = guide_legend(title = 'Source'))+ - theme(plot.margin = unit(c(1, 1.5, 1, 1.5), "cm"))
To keep the records with the highest confidence identifiers We can remove the annotations based on the name query using the filter_labels object.
name
filter_labels
# prepare workflow -FL = filter_labels( - column_name = 'inchikey_source', - labels='InChIKey', - mode='exclude') +FL <- filter_labels( + column_name = "inchikey_source", + labels = "InChIKey", + mode = "exclude" +) # apply -FF = model_apply(FL,predicted(N)) +FF <- model_apply(FL, predicted(N)) # print summary predicted(FF) -#> A "cd_source" object -#> -------------------- -#> name: Combined annotation source -#> description: This annotation_source object was generated by combining two other sources. -#> input params: sheets +#> A "annotation_source" object +#> ---------------------------- +#> name: combined +#> description: A source created by combining two or more sources +#> input params: tag, data, source #> annotations: 465 rows x 33 columns
# prepare object -R = rds_database( +R <- rds_database( source = file.path( - system.file('extdata',package='MetMashR'), - 'standard_mixtures.rds' + system.file("extdata", package = "MetMashR"), + "standard_mixtures.rds" ), .writable = FALSE ) # read -R = read_source(R)
The standards table contains a list of metabolites and the the +R <- read_source(R) +
The standards table contains a list of metabolites and the the mixture they were included in. It also contains some manually curated data providing m/z and retention time of the metabolite, which assay it was observed in and the adduct.
# convert standard mixtures to source, then get inchikey from MTox700+ -SM = import_source() + +SM <- import_source() + filter_na( - column_name = 'rt') + + column_name = "rt" + ) + filter_na( - column_name = 'median_ms2_scans') + + column_name = "median_ms2_scans" + ) + filter_na( - column_name = 'mzcloud_id') + + column_name = "mzcloud_id" + ) + filter_range( - column_name = 'median_ms2_scans', + column_name = "median_ms2_scans", upper_limit = Inf, lower_limit = 0, - equal_to = TRUE) + + equal_to = TRUE + ) + database_lookup( - query_column = 'hmdb_id', - database_column = 'hmdb_id', + query_column = "hmdb_id", + database_column = "hmdb_id", database = MTox700plus_database(), - include = 'inchikey', - suffix = '', - not_found = NA) + + include = "inchikey", + suffix = "", + not_found = NA + ) + id_counts( - id_column = 'inchikey', - count_column = 'inchikey_count', + id_column = "inchikey", + count_column = "inchikey_count", count_na = FALSE ) # apply -SM = model_apply(SM,R)
In this next plot we show the overlap in standards for each assay detected by manual observation.
-C = annotation_venn_chart( - factor_name = 'inchikey', - group_column = 'ion_mode', - line_colour = 'white', - fill_colour = '.group', +C <- annotation_venn_chart( + factor_name = "inchikey", + group_column = "ion_mode", + line_colour = "white", + fill_colour = ".group", legend = TRUE, labels = FALSE ) ## plot -chart_plot(C,predicted(SM))
C = annotation_venn_chart( - factor_name = 'inchikey', - group_column = 'ion_mode', - line_colour = 'white', - fill_colour = '.group', +C <- annotation_venn_chart( + factor_name = "inchikey", + group_column = "ion_mode", + line_colour = "white", + fill_colour = ".group", legend = TRUE, labels = FALSE ) ## plot -chart_plot(C,predicted(SM))
C <- annotation_venn_chart( + factor_name = "inchikey", + group_column = "ion_mode", + line_colour = "white", + fill_colour = ".group", legend = TRUE, labels = FALSE ) ## plot -chart_plot(C,predicted(SM))
Here we plot a venn diagram showing the overlap in identifiers.
# get processed data -AN = predicted(FF) -AN$tag = 'Annotations' -sM = predicted(SM) -sM$tag = 'Standards' +AN <- predicted(FF) +AN$tag <- "Annotations" +sM <- predicted(SM) +sM$tag <- "Standards" # prepare chart -C = annotation_venn_chart( - factor_name = 'inchikey', - line_colour = 'white', - fill_colour = '.group' +C <- annotation_venn_chart( + factor_name = "inchikey", + line_colour = "white", + fill_colour = ".group" ) # plot -chart_plot(C,sM,AN)+ggtitle('All assays, all sources')
It can been seen that there is a large number of annotations not present in the standard. These are false positives.
-G =list() -VV = list() -for (k in c('HILIC_NEG','HILIC_POS','LIPIDS_NEG','LIPIDS_POS')) { - wf = filter_labels( - column_name = 'assay', +G <- list() +VV <- list() +for (k in c("HILIC_NEG", "HILIC_POS", "LIPIDS_NEG", "LIPIDS_POS")) { + wf <- filter_labels( + column_name = "assay", labels = k, - mode = 'include') - wf1 = model_apply(wf,AN) - wf$column_name = 'ion_mode' - wf2 = model_apply(wf,sM) - G[[k]]=chart_plot(C,predicted(wf2),predicted(wf1)) - - V = filter_venn( - factor_name = 'inchikey', + mode = "include" + ) + wf1 <- model_apply(wf, AN) + wf$column_name <- "ion_mode" + wf2 <- model_apply(wf, sM) + G[[k]] <- chart_plot(C, predicted(wf2), predicted(wf1)) + + V <- filter_venn( + factor_name = "inchikey", tables = list(predicted(wf1)), - levels = 'Standards/Annotations', - mode = 'include' + levels = "Standards/Annotations", + mode = "include" ) - V = model_apply(V,predicted(wf2)) - VV[[k]] = predicted(V) - VV[[k]]$tag = k + V <- model_apply(V, predicted(wf2)) + VV[[k]] <- predicted(V) + VV[[k]]$tag <- k } -r1=cowplot::plot_grid( - plotlist = G,nrow = 2 , - labels = c('HILIC_NEG','HILIC_POS','LIPIDS_NEG','LIPIDS_POS')) +r1 <- cowplot::plot_grid( + plotlist = G, nrow = 2, + labels = c("HILIC_NEG", "HILIC_POS", "LIPIDS_NEG", "LIPIDS_POS") +) -cowplot::plot_grid(r1,chart_plot(C,VV),nrow=2,rel_heights = c(1,0.5))
G =list() -VV = list() -for (k in c('HILIC_NEG','HILIC_POS','LIPIDS_NEG','LIPIDS_POS')) { - wf = filter_labels( - column_name = 'assay', +G <- list() +VV <- list() +for (k in c("HILIC_NEG", "HILIC_POS", "LIPIDS_NEG", "LIPIDS_POS")) { + wf <- filter_labels( + column_name = "assay", labels = k, - mode = 'include') - wf1 = model_apply(wf,AN) - wf$column_name = 'ion_mode' - wf2 = model_apply(wf,sM) - G[[k]]=chart_plot(C,predicted(wf2),predicted(wf1)) - - V = filter_venn( - factor_name = 'inchikey', + mode = "include" + ) + wf1 <- model_apply(wf, AN) + wf$column_name <- "ion_mode" + wf2 <- model_apply(wf, sM) + G[[k]] <- chart_plot(C, predicted(wf2), predicted(wf1)) + + V <- filter_venn( + factor_name = "inchikey", tables = list(predicted(wf1)), - levels = 'Standards/Annotations', - mode = 'include' + levels = "Standards/Annotations", + mode = "include" ) - V = model_apply(V,predicted(wf2)) - VV[[k]] = predicted(V) - VV[[k]]$tag = k + V <- model_apply(V, predicted(wf2)) + VV[[k]] <- predicted(V) + VV[[k]]$tag <- k } -r1=cowplot::plot_grid( - plotlist = G,nrow = 2 , - labels = c('HILIC_NEG','HILIC_POS','LIPIDS_NEG','LIPIDS_POS')) +r1 <- cowplot::plot_grid( + plotlist = G, nrow = 2, + labels = c("HILIC_NEG", "HILIC_POS", "LIPIDS_NEG", "LIPIDS_POS") +) -cowplot::plot_grid(r1,chart_plot(C,VV),nrow=2,rel_heights = c(1,0.5))
G <- list() +VV <- list() +for (k in c("HILIC_NEG", "HILIC_POS", "LIPIDS_NEG", "LIPIDS_POS")) { + wf <- filter_labels( + column_name = "assay", labels = k, - mode = 'include') - wf1 = model_apply(wf,AN) - wf$column_name = 'ion_mode' - wf2 = model_apply(wf,sM) - G[[k]]=chart_plot(C,predicted(wf2),predicted(wf1)) - - V = filter_venn( - factor_name = 'inchikey', + mode = "include" + ) + wf1 <- model_apply(wf, AN) + wf$column_name <- "ion_mode" + wf2 <- model_apply(wf, sM) + G[[k]] <- chart_plot(C, predicted(wf2), predicted(wf1)) + + V <- filter_venn( + factor_name = "inchikey", tables = list(predicted(wf1)), - levels = 'Standards/Annotations', - mode = 'include' + levels = "Standards/Annotations", + mode = "include" ) - V = model_apply(V,predicted(wf2)) - VV[[k]] = predicted(V) - VV[[k]]$tag = k + V <- model_apply(V, predicted(wf2)) + VV[[k]] <- predicted(V) + VV[[k]]$tag <- k } -r1=cowplot::plot_grid( - plotlist = G,nrow = 2 , - labels = c('HILIC_NEG','HILIC_POS','LIPIDS_NEG','LIPIDS_POS')) +r1 <- cowplot::plot_grid( + plotlist = G, nrow = 2, + labels = c("HILIC_NEG", "HILIC_POS", "LIPIDS_NEG", "LIPIDS_POS") +) -cowplot::plot_grid(r1,chart_plot(C,VV),nrow=2,rel_heights = c(1,0.5))
The majority of the standards were correctly annotated in the HILIC_NEG assay.
In the next plot we compare the overlap in InChIKey for each source.
-G=list() -for (k in c('CD','LS')) { - wf = filter_labels( - column_name = 'source_name', +G <- list() +for (k in c("CD", "LS")) { + wf <- filter_labels( + column_name = "source_name", labels = k, - mode = 'include') - wf1 = model_apply(wf,AN) - - G[[k]]=chart_plot(C,sM,predicted(wf1)) + mode = "include" + ) + wf1 <- model_apply(wf, AN) + + G[[k]] <- chart_plot(C, sM, predicted(wf1)) } -cowplot::plot_grid(plotlist = G,nrow = 1,labels = c('CD','LS'))
G=list() -for (k in c('CD','LS')) { - wf = filter_labels( - column_name = 'source_name', +G <- list() +for (k in c("CD", "LS")) { + wf <- filter_labels( + column_name = "source_name", labels = k, - mode = 'include') - wf1 = model_apply(wf,AN) - - G[[k]]=chart_plot(C,sM,predicted(wf1)) + mode = "include" + ) + wf1 <- model_apply(wf, AN) + + G[[k]] <- chart_plot(C, sM, predicted(wf1)) } -cowplot::plot_grid(plotlist = G,nrow = 1,labels = c('CD','LS'))
G <- list() +for (k in c("CD", "LS")) { + wf <- filter_labels( + column_name = "source_name", labels = k, - mode = 'include') - wf1 = model_apply(wf,AN) - - G[[k]]=chart_plot(C,sM,predicted(wf1)) + mode = "include" + ) + wf1 <- model_apply(wf, AN) + + G[[k]] <- chart_plot(C, sM, predicted(wf1)) } -cowplot::plot_grid(plotlist = G,nrow = 1,labels = c('CD','LS'))
sessionInfo() -#> R version 4.3.2 (2023-10-31) -#> Platform: x86_64-pc-linux-gnu (64-bit) -#> Running under: Ubuntu 22.04.3 LTS +#> R Under development (unstable) (2024-03-13 r86113) +#> Platform: x86_64-pc-linux-gnu +#> Running under: Ubuntu 22.04.4 LTS #> #> Matrix products: default #> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 @@ -960,63 +996,59 @@ Session Info#> [1] stats graphics grDevices utils datasets methods base #> #> other attached packages: -#> [1] DT_0.31 dplyr_1.1.4 structToolbox_1.14.0 -#> [4] ggplot2_3.4.4 MetMashR_0.1.0 struct_1.14.0 -#> [7] BiocStyle_2.30.0 +#> [1] DT_0.32 dplyr_1.1.4 structToolbox_1.15.1 +#> [4] ggplot2_3.5.0 MetMashR_0.99.0 struct_1.15.4 +#> [7] BiocStyle_2.31.0 #> #> loaded via a namespace (and not attached): -#> [1] DBI_1.2.1 bitops_1.0-7 -#> [3] gridExtra_2.3 rlang_1.1.3 -#> [5] magrittr_2.0.3 matrixStats_1.2.0 -#> [7] e1071_1.7-14 compiler_4.3.2 -#> [9] RSQLite_2.3.4 systemfonts_1.0.5 -#> [11] vctrs_0.6.5 stringr_1.5.1 -#> [13] pkgconfig_2.0.3 crayon_1.5.2 -#> [15] fastmap_1.1.1 dbplyr_2.4.0 -#> [17] XVector_0.42.0 ellipsis_0.3.2 -#> [19] labeling_0.4.3 utf8_1.2.4 -#> [21] rmarkdown_2.25 ragg_1.2.7 -#> [23] purrr_1.0.2 bit_4.0.5 -#> [25] xfun_0.41 zlibbioc_1.48.0 -#> [27] cachem_1.0.8 GenomeInfoDb_1.38.5 -#> [29] jsonlite_1.8.8 RVenn_1.1.0 -#> [31] blob_1.2.4 highr_0.10 -#> [33] DelayedArray_0.28.0 R6_2.5.1 -#> [35] bslib_0.6.1 stringi_1.8.3 -#> [37] GenomicRanges_1.54.1 jquerylib_0.1.4 -#> [39] Rcpp_1.0.12 bookdown_0.37 -#> [41] SummarizedExperiment_1.32.0 knitr_1.45 -#> [43] IRanges_2.36.0 Matrix_1.6-5 -#> [45] tidyselect_1.2.0 abind_1.4-5 -#> [47] yaml_2.3.8 ggVennDiagram_1.5.0 -#> [49] curl_5.2.0 lattice_0.22-5 -#> [51] tibble_3.2.1 plyr_1.8.9 -#> [53] Biobase_2.62.0 withr_3.0.0 -#> [55] evaluate_0.23 ontologyIndex_2.11 -#> [57] desc_1.4.3 sf_1.0-15 -#> [59] units_0.8-5 proxy_0.4-27 -#> [61] BiocFileCache_2.10.1 zip_2.3.0 -#> [63] filelock_1.0.3 pillar_1.9.0 -#> [65] BiocManager_1.30.22 MatrixGenerics_1.14.0 -#> [67] KernSmooth_2.23-22 stats4_4.3.2 -#> [69] generics_0.1.3 sp_2.1-2 -#> [71] RCurl_1.98-1.14 S4Vectors_0.40.2 -#> [73] munsell_0.5.0 scales_1.3.0 -#> [75] class_7.3-22 glue_1.7.0 -#> [77] tools_4.3.2 openxlsx_4.2.5.2 -#> [79] fs_1.6.3 cowplot_1.1.2 -#> [81] grid_4.3.2 crosstalk_1.2.1 -#> [83] colorspace_2.1-0 GenomeInfoDbData_1.2.11 -#> [85] cli_3.6.2 textshaping_0.3.7 -#> [87] fansi_1.0.6 ggthemes_5.0.0 -#> [89] S4Arrays_1.2.0 gtable_0.3.4 -#> [91] sass_0.4.8 digest_0.6.34 -#> [93] BiocGenerics_0.48.1 classInt_0.4-10 -#> [95] SparseArray_1.2.3 htmlwidgets_1.6.4 -#> [97] farver_2.1.1 memoise_2.0.1 -#> [99] htmltools_0.5.7 pkgdown_2.0.7 -#> [101] lifecycle_1.0.4 httr_1.4.7 -#> [103] bit64_4.0.5
TODO
This study consists of LCMS peak tables of HILIC_POS and LIPIDS_POS +assays collected from samples of Daphnia magna. In this section +we import the tables of data for the MS1 peaks recorded for each sample. +We will use this data in a workflows to align the MS2 annotations with +the MS1 peaks. In practice there might be accompanying statistics +e.g. t-test p-values indicating the importance of a features for a +study. For brevity in this vignette we only import peak quality +information, in the form of Relative Standard Deviations (RSD).
Here, we import the MS1 level feature meta data for each assay and +store it as a data.frame that we use later on in the workflow.
# import HILIC_POS -HP = openxlsx::read.xlsx( - system.file("extdata/daphnia/daphnia_example.xlsx", - package = 'MetMashR'), - sheet='HILIC_POS', - rowNames=FALSE, - colNames=TRUE) +HP <- openxlsx::read.xlsx( + system.file("extdata/daphnia/daphnia_example.xlsx", + package = "MetMashR" + ), + sheet = "HILIC_POS", + rowNames = FALSE, + colNames = TRUE +) # rename columns -colnames(HP)[1] = 'id' +colnames(HP)[1] <- "id" # append assay to feature id -HP$id = paste0('HILIC_POS_',HP$id) +HP$id <- paste0("HILIC_POS_", HP$id) # convert some columns to numeric -HP$rsd_qc=as.numeric(HP$rsd_qc) -HP$rsd_sample=as.numeric(HP$rsd_sample) +HP$rsd_qc <- as.numeric(HP$rsd_qc) +HP$rsd_sample <- as.numeric(HP$rsd_sample) # import LIPIDS_POS -LP = openxlsx::read.xlsx( - system.file("extdata/daphnia/daphnia_example.xlsx", - package = 'MetMashR'), - sheet='LIPIDS_POS', - rowNames=FALSE, - colNames=TRUE) +LP <- openxlsx::read.xlsx( + system.file("extdata/daphnia/daphnia_example.xlsx", + package = "MetMashR" + ), + sheet = "LIPIDS_POS", + rowNames = FALSE, + colNames = TRUE +) # rename columns -colnames(LP)[1] = 'id' +colnames(LP)[1] <- "id" # append assay to feature id -LP$id = paste0('LIPIDS_POS_',LP$id) +LP$id <- paste0("LIPIDS_POS_", LP$id) # convert some columns to numeric -LP$rsd_qc=as.numeric(LP$rsd_qc) -LP$rsd_sample=as.numeric(LP$rsd_sample)
-cd_workflow = +cd_workflow <- # import source import_source() + - + # add useful labels add_labels( labels = list( - source_name = 'CD', - assay = 'placeholder')) + # placeholder replaced later - + source_name = "CD", + assay = "placeholder" + ) + ) + # placeholder replaced later + # filter low quality filter_labels( - column_name = 'compound_match', - labels = 'Full match', - mode = 'include') + - + column_name = "compound_match", + labels = "Full match", + mode = "include" + ) + + # resolve duplicates combine_records( - group_by = c('compound','ion'), + group_by = c("compound", "ion"), default_fcn = .select_max( - max_col = 'mzcloud_score', + max_col = "mzcloud_score", keep_NA = FALSE, use_abs = TRUE - )) + + ) + ) + # match MS1 to MS2 mzrt_match( variable_meta = HP, - mz_column = 'mz', - rt_column = 'rt', + mz_column = "mz", + rt_column = "rt", ppm_window = 5, rt_window = 20, - id_column = 'id' + id_column = "id" ) + - + # ppm difference MS1 vs library calc_ppm_diff( - obs_mz_column = 'mz_match', - ref_mz_column = 'theoretical_mz', - out_column = 'ms1_lib_ppm_diff' - )
cd_workflow = +cd_workflow <- # import source import_source() + - + # add useful labels add_labels( labels = list( - source_name = 'CD', - assay = 'placeholder')) + # placeholder replaced later - + source_name = "CD", + assay = "placeholder" + ) + ) + # placeholder replaced later + # filter low quality filter_labels( - column_name = 'compound_match', - labels = 'Full match', - mode = 'include') + - + column_name = "compound_match", + labels = "Full match", + mode = "include" + ) + + # resolve duplicates combine_records( - group_by = c('compound','ion'), + group_by = c("compound", "ion"), default_fcn = .select_max( - max_col = 'mzcloud_score', + max_col = "mzcloud_score", keep_NA = FALSE, use_abs = TRUE - )) + + ) + ) + # match MS1 to MS2 mzrt_match( variable_meta = HP, - mz_column = 'mz', - rt_column = 'rt', + mz_column = "mz", + rt_column = "rt", ppm_window = 5, rt_window = 20, - id_column = 'id' + id_column = "id" ) + - + # ppm difference MS1 vs library calc_ppm_diff( - obs_mz_column = 'mz_match', - ref_mz_column = 'theoretical_mz', - out_column = 'ms1_lib_ppm_diff' - )
cd_workflow <- # import source import_source() + - + # add useful labels add_labels( labels = list( - source_name = 'CD', - assay = 'placeholder')) + # placeholder replaced later - + source_name = "CD", + assay = "placeholder" + ) + ) + # placeholder replaced later + # filter low quality filter_labels( - column_name = 'compound_match', - labels = 'Full match', - mode = 'include') + - + column_name = "compound_match", + labels = "Full match", + mode = "include" + ) + + # resolve duplicates combine_records( - group_by = c('compound','ion'), + group_by = c("compound", "ion"), default_fcn = .select_max( - max_col = 'mzcloud_score', + max_col = "mzcloud_score", keep_NA = FALSE, use_abs = TRUE - )) + + ) + ) + # match MS1 to MS2 mzrt_match( variable_meta = HP, - mz_column = 'mz', - rt_column = 'rt', + mz_column = "mz", + rt_column = "rt", ppm_window = 5, rt_window = 20, - id_column = 'id' + id_column = "id" ) + - + # ppm difference MS1 vs library calc_ppm_diff( - obs_mz_column = 'mz_match', - ref_mz_column = 'theoretical_mz', - out_column = 'ms1_lib_ppm_diff' - )
We need to apply this workflow to each assay. For convenience we store the sources for each assay in a list.
# prepare sources -cd_sources = list( +cd_sources <- list( HILIC_POS = cd_source( source = c( system.file( - 'extdata/daphnia/HILIC_POS_EL_CD.xlsx', - package = 'MetMashR'), + "extdata/daphnia/HILIC_POS_EL_CD.xlsx", + package = "MetMashR" + ), system.file( - 'extdata/daphnia/HILIC_POS_EL_CD_comp.xlsx', - package = 'MetMashR')), - sheets = c('Compounds','Compounds') + "extdata/daphnia/HILIC_POS_EL_CD_comp.xlsx", + package = "MetMashR" + ) + ), + sheets = c("Compounds", "Compounds") ), LIPIDS_POS = cd_source( source = c( system.file( - 'extdata/daphnia/LIPIDS_POS_EL_CD.xlsx', - package = 'MetMashR'), + "extdata/daphnia/LIPIDS_POS_EL_CD.xlsx", + package = "MetMashR" + ), system.file( - 'extdata/daphnia/LIPIDS_POS_EL_CD_comp.xlsx', - package = 'MetMashR')), - sheets = c('Compounds','Compounds') + "extdata/daphnia/LIPIDS_POS_EL_CD_comp.xlsx", + package = "MetMashR" + ) + ), + sheets = c("Compounds", "Compounds") ) )
Now we are ready to apply the workflow to the sources. Note that @@ -242,17 +266,17 @@
# place to store results -CD = list() +CD <- list() # set labels -cd_workflow[2]$labels$assay='HILIC_POS' +cd_workflow[2]$labels$assay <- "HILIC_POS" # apply workflow -CD$HILIC_POS = model_apply(cd_workflow,cd_sources$HILIC_POS) +CD$HILIC_POS <- model_apply(cd_workflow, cd_sources$HILIC_POS) # set labels -cd_workflow[2]$labels$assay='LIPIDS_POS' +cd_workflow[2]$labels$assay <- "LIPIDS_POS" # apply workflow -CD$LIPIDS_POS = model_apply(cd_workflow,cd_sources$LIPIDS_POS)
# MS2 vs library -C = annotation_histogram( - factor_name = 'library_ppm_diff', - vline = c(-5,5) +C <- annotation_histogram( + factor_name = "library_ppm_diff", + vline = c(-5, 5) ) -g1 = chart_plot(C,predicted(CD$HILIC_POS)) + ggtitle('MS2 vs library') +g1 <- chart_plot(C, predicted(CD$HILIC_POS)) + ggtitle("MS2 vs library") # MS1 vs library -C = annotation_histogram( - factor_name = 'ms1_lib_ppm_diff', - vline = c(-5,5) +C <- annotation_histogram( + factor_name = "ms1_lib_ppm_diff", + vline = c(-5, 5) ) -g2 = chart_plot(C,predicted(CD$HILIC_POS)) + ggtitle('MS1 vs library') +g2 <- chart_plot(C, predicted(CD$HILIC_POS)) + ggtitle("MS1 vs library") # layout -cowplot::plot_grid(g1,g2,nrow=1)
The ppm and retention time differences between the MS1 and MS2 features (peaks) can also be indicative of analytical problems.
# prepare chart -C = annotation_histogram2d( - factor_name = c('ppm_match_diff_an','rt_match_diff'), +C <- annotation_histogram2d( + factor_name = c("ppm_match_diff_an", "rt_match_diff"), bins = 30 ) -chart_plot(C,predicted(CD$HILIC_POS))
The LIPID_POS assay (not shown) only has 2 matches, so the chart is not informative for that assay.
- -# prepare workflow -ls_workflow = - +# prepare workflow +ls_workflow <- # import raw file - import_source() + - + import_source() + + # add labels add_labels( labels = c( - assay = 'placeholder', # will be replaced later - source_name = 'LS' - ))+ + assay = "placeholder", # will be replaced later + source_name = "LS" + ) + ) + # filter by grade filter_labels( - column_name = 'Grade', - labels = c('A','B'), - mode = 'include') + - + column_name = "Grade", + labels = c("A", "B"), + mode = "include" + ) + + # resolve duplicates combine_records( - group_by = c('LipidIon'), + group_by = c("LipidIon"), default_fcn = .select_min( - min_col = 'library_ppm_diff', + min_col = "library_ppm_diff", keep_NA = FALSE, use_abs = TRUE - ) + ) ) + - + # match MS1 to MS2 mzrt_match( variable_meta = HP, - mz_column = 'mz', - rt_column = 'rt', + mz_column = "mz", + rt_column = "rt", ppm_window = 5, rt_window = 20, - id_column = 'id' + id_column = "id" ) + - + # ppm difference MS1 vs library calc_ppm_diff( - obs_mz_column = 'mz_match', - ref_mz_column = 'theor_mass', - out_column = 'ms1_lib_ppm_diff' - )
-# prepare workflow -ls_workflow = - +# prepare workflow +ls_workflow <- # import raw file - import_source() + - + import_source() + + # add labels add_labels( labels = c( - assay = 'placeholder', # will be replaced later - source_name = 'LS' - ))+ + assay = "placeholder", # will be replaced later + source_name = "LS" + ) + ) + # filter by grade filter_labels( - column_name = 'Grade', - labels = c('A','B'), - mode = 'include') + - + column_name = "Grade", + labels = c("A", "B"), + mode = "include" + ) + + # resolve duplicates combine_records( - group_by = c('LipidIon'), + group_by = c("LipidIon"), default_fcn = .select_min( - min_col = 'library_ppm_diff', + min_col = "library_ppm_diff", keep_NA = FALSE, use_abs = TRUE - ) + ) ) + - + # match MS1 to MS2 mzrt_match( variable_meta = HP, - mz_column = 'mz', - rt_column = 'rt', + mz_column = "mz", + rt_column = "rt", ppm_window = 5, rt_window = 20, - id_column = 'id' + id_column = "id" ) + - + # ppm difference MS1 vs library calc_ppm_diff( - obs_mz_column = 'mz_match', - ref_mz_column = 'theor_mass', - out_column = 'ms1_lib_ppm_diff' - )
# prepare workflow +ls_workflow <- # import raw file - import_source() + - + import_source() + + # add labels add_labels( labels = c( - assay = 'placeholder', # will be replaced later - source_name = 'LS' - ))+ + assay = "placeholder", # will be replaced later + source_name = "LS" + ) + ) + # filter by grade filter_labels( - column_name = 'Grade', - labels = c('A','B'), - mode = 'include') + - + column_name = "Grade", + labels = c("A", "B"), + mode = "include" + ) + + # resolve duplicates combine_records( - group_by = c('LipidIon'), + group_by = c("LipidIon"), default_fcn = .select_min( - min_col = 'library_ppm_diff', + min_col = "library_ppm_diff", keep_NA = FALSE, use_abs = TRUE - ) + ) ) + - + # match MS1 to MS2 mzrt_match( variable_meta = HP, - mz_column = 'mz', - rt_column = 'rt', + mz_column = "mz", + rt_column = "rt", ppm_window = 5, rt_window = 20, - id_column = 'id' + id_column = "id" ) + - + # ppm difference MS1 vs library calc_ppm_diff( - obs_mz_column = 'mz_match', - ref_mz_column = 'theor_mass', - out_column = 'ms1_lib_ppm_diff' - )
Next we prepare the LipidSearch source objects:
# prepare sources -ls_sources = list( +ls_sources <- list( HILIC_POS = ls_source( - source = + source = system.file( - 'extdata/daphnia/HILIC_POS_EL_LS.txt', - package = 'MetMashR') + "extdata/daphnia/HILIC_POS_EL_LS.txt", + package = "MetMashR" + ) ), LIPIDS_POS = ls_source( - source = + source = system.file( - 'extdata/daphnia/LIPIDS_POS_EL_LS.txt', - package = 'MetMashR') + "extdata/daphnia/LIPIDS_POS_EL_LS.txt", + package = "MetMashR" + ) ) )
Now we can apply the LipidSearch workflow to the LipidSearch sources:
# place to store results -LS = list() +LS <- list() # set labels -ls_workflow[2]$labels$assay='HILIC_POS' +ls_workflow[2]$labels$assay <- "HILIC_POS" # apply workflow -LS$HILIC_POS = model_apply(ls_workflow,ls_sources$HILIC_POS) +LS$HILIC_POS <- model_apply(ls_workflow, ls_sources$HILIC_POS) # set labels -ls_workflow[2]$labels$assay='LIPIDS_POS' +ls_workflow[2]$labels$assay <- "LIPIDS_POS" # apply workflow -LS$LIPIDS_POS = model_apply(ls_workflow,ls_sources$LIPIDS_POS)
# MS2 vs library -C = annotation_histogram( - factor_name = 'library_ppm_diff', - vline = c(-5,5) +C <- annotation_histogram( + factor_name = "library_ppm_diff", + vline = c(-5, 5) ) -g1 = chart_plot(C,predicted(LS$HILIC_POS)) + ggtitle('MS2 vs library') +g1 <- chart_plot(C, predicted(LS$HILIC_POS)) + ggtitle("MS2 vs library") # MS1 vs library -C = annotation_histogram( - factor_name = 'ms1_lib_ppm_diff', - vline = c(-5,5) +C <- annotation_histogram( + factor_name = "ms1_lib_ppm_diff", + vline = c(-5, 5) ) -g2 = chart_plot(C,predicted(LS$HILIC_POS)) + ggtitle('MS1 vs library') +g2 <- chart_plot(C, predicted(LS$HILIC_POS)) + ggtitle("MS1 vs library") # layout -cowplot::plot_grid(g1,g2,nrow=1)
We can also check for analytical issue by comparing the MS1 and MS2 ppm and retention time differences.
# prepare chart -C = annotation_histogram2d( - factor_name = c('ppm_match_diff_an','rt_match_diff'), +C <- annotation_histogram2d( + factor_name = c("ppm_match_diff_an", "rt_match_diff"), bins = 30 ) -chart_plot(C,predicted(LS$HILIC_POS))
-cache1=rds_database( - source=file.path( - system.file('cached',package='MetMashR'),'cache1.rds')) -cache2=rds_database( - source=file.path( - system.file('cached',package='MetMashR'),'cache2.rds')) -cache3=rds_database( - source=file.path( - system.file('cached',package='MetMashR'),'cache3.rds')) -cache4=rds_database( - source=file.path( - system.file('cached',package='MetMashR'),'cache4.rds'))
cache1=rds_database( - source=file.path( - system.file('cached',package='MetMashR'),'cache1.rds')) -cache2=rds_database( - source=file.path( - system.file('cached',package='MetMashR'),'cache2.rds')) -cache3=rds_database( - source=file.path( - system.file('cached',package='MetMashR'),'cache3.rds')) -cache4=rds_database( - source=file.path( - system.file('cached',package='MetMashR'),'cache4.rds'))
cache1 <- rds_database( + source = file.path( + system.file("cached", package = "MetMashR"), "cache1.rds" + ) +) +cache2 <- rds_database( + source = file.path( + system.file("cached", package = "MetMashR"), "cache2.rds" + ) +) +cache3 <- rds_database( + source = file.path( + system.file("cached", package = "MetMashR"), "cache3.rds" + ) +) +cache4 <- rds_database( + source = file.path( + system.file("cached", package = "MetMashR"), "cache4.rds" + ) +)
Next we prepare the workflow and then apply it.
-WF = +WF <- combine_sources( list( - predicted(CD$LIPIDS_POS), - predicted(LS$HILIC_POS), - predicted(LS$LIPIDS_POS)), - source_col = 'annotation_source', - keep_cols = '.all', + predicted(CD$LIPIDS_POS), + predicted(LS$HILIC_POS), + predicted(LS$LIPIDS_POS) + ), + source_col = "annotation_source", + keep_cols = ".all", matching_columns = c( - Compound = 'compound', - Compound = 'LipidName', - Ion = 'ion', - Ion = 'LipidIon', - theoretical_mz = 'theor_mass', - LipidClass = 'Class') + Compound = "compound", + Compound = "LipidName", + Ion = "ion", + Ion = "LipidIon", + theoretical_mz = "theor_mass", + LipidClass = "Class" + ) ) + normalise_strings( - search_column = 'Compound', - output_column = 'normalised_compound', + search_column = "Compound", + output_column = "normalised_compound", dictionary = c( # custom dictionary list( # replace "NP" with "Compound NP" list( - pattern = '^NP-', - replace = 'Compound NP-'), - # remove terms in trailing brackets e.g." (ATP)" + pattern = "^NP-", + replace = "Compound NP-" + ), + # remove terms in trailing brackets e.g." (ATP)" list( - pattern = '\\ \\([^\\)]*\\)$', - replace = ''), + pattern = "\\ \\([^\\)]*\\)$", + replace = "" + ), # replace known abbreviations list( - pattern = '3-Fluoro NNEI', - replace = '3-Fluoro-nnei', - fixed = TRUE), + pattern = "3-Fluoro NNEI", + replace = "3-Fluoro-nnei", + fixed = TRUE + ), list( - pattern = 'Υ-L-Glutamyl-L-glutamic acid', - replace = 'Tyr-Glu-Glu' + pattern = "Υ-L-Glutamyl-L-glutamic acid", + replace = "Tyr-Glu-Glu" ), list( - pattern = 'AcCa', - replace = 'CAR' + pattern = "AcCa", + replace = "CAR" ) ), # update tripeptides @@ -508,119 +547,121 @@ Mashing all sources / assays) ) + pubchem_property_lookup( - query_column = 'normalised_compound', - search_by = 'name', - property = 'InChIKey', - suffix = '_pubchem', + query_column = "normalised_compound", + search_by = "name", + property = "InChIKey", + suffix = "_pubchem", cache = cache1 ) + lipidmaps_lookup( - query_column = 'normalised_compound', - context = 'compound', - context_item = 'abbrev', - output_item = 'inchi_key', - suffix = '_abbrev', + query_column = "normalised_compound", + context = "compound", + context_item = "abbrev", + output_item = "inchi_key", + suffix = "_abbrev", cache = cache2 - )+ + ) + lipidmaps_lookup( - query_column = 'normalised_compound', - context = 'compound', - context_item = 'abbrev_chains', - output_item = 'inchi_key', - suffix = '_abbrevchains', + query_column = "normalised_compound", + context = "compound", + context_item = "abbrev_chains", + output_item = "inchi_key", + suffix = "_abbrevchains", cache = cache3 ) + - combine_columns( - c('InChIKey_pubchem','inchi_key_abbrev','inchi_key_abbrevchains'), - output_name = 'inchikey', - source_name = 'inchikey_src', - source_tags = c('pubchem','lm_abbrev','lm_chains'), + prioritise_columns( + column_names = c("InChIKey_pubchem", "inchi_key_abbrev", "inchi_key_abbrevchains"), + output_name = "inchikey", + source_name = "inchikey_src", + source_tags = c("pubchem", "lm_abbrev", "lm_chains"), clean = TRUE ) + classyfire_lookup( - query_column = 'inchikey', - output_items = '.all', - output_fields = '.all',suffix = '_cf', + query_column = "inchikey", + output_items = ".all", + output_fields = ".all", suffix = "_cf", cache = cache4, delay = 5 ) + database_lookup( - query_column = 'inchikey', - database_column = 'InChI.Key', + query_column = "inchikey", + database_column = "InChI.Key", database = PathBank_metabolite_database(), - include = c('Pathway.Name','Pathway.Subject','Species'), - suffix = '', + include = c("Pathway.Name", "Pathway.Subject", "Species"), + suffix = "", not_found = NA ) + add_columns( - new_columns = rbind(HP,LP), - by = c('mzrt_match_id'='id') + new_columns = rbind(HP, LP), + by = c("mzrt_match_id" = "id") ) + filter_na( - column_name = 'inchikey' + column_name = "inchikey" ) + combine_records( - group_by = 'mzrt_match_id', + group_by = "mzrt_match_id", default_fcn = .unique( - separator = ' || ') + separator = " || " + ) ) + filter_labels( - column_name = 'rsd_qc', - labels = 'NA', - mode = 'exclude' + column_name = "rsd_qc", + labels = "NA", + mode = "exclude" ) + filter_range( - column_name = 'rsd_qc', + column_name = "rsd_qc", upper_limit = 20, - lower_limit=-Inf, - equal_to=FALSE + lower_limit = -Inf, + equal_to = FALSE ) -WF = model_apply(WF,predicted(CD$HILIC_POS))
WF = +WF <- combine_sources( list( - predicted(CD$LIPIDS_POS), - predicted(LS$HILIC_POS), - predicted(LS$LIPIDS_POS)), - source_col = 'annotation_source', - keep_cols = '.all', + predicted(CD$LIPIDS_POS), + predicted(LS$HILIC_POS), + predicted(LS$LIPIDS_POS) + ), + source_col = "annotation_source", + keep_cols = ".all", matching_columns = c( - Compound = 'compound', - Compound = 'LipidName', - Ion = 'ion', - Ion = 'LipidIon', - theoretical_mz = 'theor_mass', - LipidClass = 'Class') + Compound = "compound", + Compound = "LipidName", + Ion = "ion", + Ion = "LipidIon", + theoretical_mz = "theor_mass", + LipidClass = "Class" + ) ) + normalise_strings( - search_column = 'Compound', - output_column = 'normalised_compound', + search_column = "Compound", + output_column = "normalised_compound", dictionary = c( # custom dictionary list( # replace "NP" with "Compound NP" list( - pattern = '^NP-', - replace = 'Compound NP-'), - # remove terms in trailing brackets e.g." (ATP)" + pattern = "^NP-", + replace = "Compound NP-" + ), + # remove terms in trailing brackets e.g." (ATP)" list( - pattern = '\\ \\([^\\)]*\\)$', - replace = ''), + pattern = "\\ \\([^\\)]*\\)$", + replace = "" + ), # replace known abbreviations list( - pattern = '3-Fluoro NNEI', - replace = '3-Fluoro-nnei', - fixed = TRUE), + pattern = "3-Fluoro NNEI", + replace = "3-Fluoro-nnei", + fixed = TRUE + ), list( - pattern = 'Υ-L-Glutamyl-L-glutamic acid', - replace = 'Tyr-Glu-Glu' + pattern = "Υ-L-Glutamyl-L-glutamic acid", + replace = "Tyr-Glu-Glu" ), list( - pattern = 'AcCa', - replace = 'CAR' + pattern = "AcCa", + replace = "CAR" ) ), # update tripeptides @@ -508,119 +547,121 @@ Mashing all sources / assays) ) + pubchem_property_lookup( - query_column = 'normalised_compound', - search_by = 'name', - property = 'InChIKey', - suffix = '_pubchem', + query_column = "normalised_compound", + search_by = "name", + property = "InChIKey", + suffix = "_pubchem", cache = cache1 ) + lipidmaps_lookup( - query_column = 'normalised_compound', - context = 'compound', - context_item = 'abbrev', - output_item = 'inchi_key', - suffix = '_abbrev', + query_column = "normalised_compound", + context = "compound", + context_item = "abbrev", + output_item = "inchi_key", + suffix = "_abbrev", cache = cache2 - )+ + ) + lipidmaps_lookup( - query_column = 'normalised_compound', - context = 'compound', - context_item = 'abbrev_chains', - output_item = 'inchi_key', - suffix = '_abbrevchains', + query_column = "normalised_compound", + context = "compound", + context_item = "abbrev_chains", + output_item = "inchi_key", + suffix = "_abbrevchains", cache = cache3 ) + - combine_columns( - c('InChIKey_pubchem','inchi_key_abbrev','inchi_key_abbrevchains'), - output_name = 'inchikey', - source_name = 'inchikey_src', - source_tags = c('pubchem','lm_abbrev','lm_chains'), + prioritise_columns( + column_names = c("InChIKey_pubchem", "inchi_key_abbrev", "inchi_key_abbrevchains"), + output_name = "inchikey", + source_name = "inchikey_src", + source_tags = c("pubchem", "lm_abbrev", "lm_chains"), clean = TRUE ) + classyfire_lookup( - query_column = 'inchikey', - output_items = '.all', - output_fields = '.all',suffix = '_cf', + query_column = "inchikey", + output_items = ".all", + output_fields = ".all", suffix = "_cf", cache = cache4, delay = 5 ) + database_lookup( - query_column = 'inchikey', - database_column = 'InChI.Key', + query_column = "inchikey", + database_column = "InChI.Key", database = PathBank_metabolite_database(), - include = c('Pathway.Name','Pathway.Subject','Species'), - suffix = '', + include = c("Pathway.Name", "Pathway.Subject", "Species"), + suffix = "", not_found = NA ) + add_columns( - new_columns = rbind(HP,LP), - by = c('mzrt_match_id'='id') + new_columns = rbind(HP, LP), + by = c("mzrt_match_id" = "id") ) + filter_na( - column_name = 'inchikey' + column_name = "inchikey" ) + combine_records( - group_by = 'mzrt_match_id', + group_by = "mzrt_match_id", default_fcn = .unique( - separator = ' || ') + separator = " || " + ) ) + filter_labels( - column_name = 'rsd_qc', - labels = 'NA', - mode = 'exclude' + column_name = "rsd_qc", + labels = "NA", + mode = "exclude" ) + filter_range( - column_name = 'rsd_qc', + column_name = "rsd_qc", upper_limit = 20, - lower_limit=-Inf, - equal_to=FALSE + lower_limit = -Inf, + equal_to = FALSE ) -WF = model_apply(WF,predicted(CD$HILIC_POS))
WF <- combine_sources( list( - predicted(CD$LIPIDS_POS), - predicted(LS$HILIC_POS), - predicted(LS$LIPIDS_POS)), - source_col = 'annotation_source', - keep_cols = '.all', + predicted(CD$LIPIDS_POS), + predicted(LS$HILIC_POS), + predicted(LS$LIPIDS_POS) + ), + source_col = "annotation_source", + keep_cols = ".all", matching_columns = c( - Compound = 'compound', - Compound = 'LipidName', - Ion = 'ion', - Ion = 'LipidIon', - theoretical_mz = 'theor_mass', - LipidClass = 'Class') + Compound = "compound", + Compound = "LipidName", + Ion = "ion", + Ion = "LipidIon", + theoretical_mz = "theor_mass", + LipidClass = "Class" + ) ) + normalise_strings( - search_column = 'Compound', - output_column = 'normalised_compound', + search_column = "Compound", + output_column = "normalised_compound", dictionary = c( # custom dictionary list( # replace "NP" with "Compound NP" list( - pattern = '^NP-', - replace = 'Compound NP-'), - # remove terms in trailing brackets e.g." (ATP)" + pattern = "^NP-", + replace = "Compound NP-" + ), + # remove terms in trailing brackets e.g." (ATP)" list( - pattern = '\\ \\([^\\)]*\\)$', - replace = ''), + pattern = "\\ \\([^\\)]*\\)$", + replace = "" + ), # replace known abbreviations list( - pattern = '3-Fluoro NNEI', - replace = '3-Fluoro-nnei', - fixed = TRUE), + pattern = "3-Fluoro NNEI", + replace = "3-Fluoro-nnei", + fixed = TRUE + ), list( - pattern = 'Υ-L-Glutamyl-L-glutamic acid', - replace = 'Tyr-Glu-Glu' + pattern = "Υ-L-Glutamyl-L-glutamic acid", + replace = "Tyr-Glu-Glu" ), list( - pattern = 'AcCa', - replace = 'CAR' + pattern = "AcCa", + replace = "CAR" ) ), # update tripeptides @@ -508,119 +547,121 @@ Mashing all sources / assays) ) + pubchem_property_lookup( - query_column = 'normalised_compound', - search_by = 'name', - property = 'InChIKey', - suffix = '_pubchem', + query_column = "normalised_compound", + search_by = "name", + property = "InChIKey", + suffix = "_pubchem", cache = cache1 ) + lipidmaps_lookup( - query_column = 'normalised_compound', - context = 'compound', - context_item = 'abbrev', - output_item = 'inchi_key', - suffix = '_abbrev', + query_column = "normalised_compound", + context = "compound", + context_item = "abbrev", + output_item = "inchi_key", + suffix = "_abbrev", cache = cache2 - )+ + ) + lipidmaps_lookup( - query_column = 'normalised_compound', - context = 'compound', - context_item = 'abbrev_chains', - output_item = 'inchi_key', - suffix = '_abbrevchains', + query_column = "normalised_compound", + context = "compound", + context_item = "abbrev_chains", + output_item = "inchi_key", + suffix = "_abbrevchains", cache = cache3 ) + - combine_columns( - c('InChIKey_pubchem','inchi_key_abbrev','inchi_key_abbrevchains'), - output_name = 'inchikey', - source_name = 'inchikey_src', - source_tags = c('pubchem','lm_abbrev','lm_chains'), + prioritise_columns( + column_names = c("InChIKey_pubchem", "inchi_key_abbrev", "inchi_key_abbrevchains"), + output_name = "inchikey", + source_name = "inchikey_src", + source_tags = c("pubchem", "lm_abbrev", "lm_chains"), clean = TRUE ) + classyfire_lookup( - query_column = 'inchikey', - output_items = '.all', - output_fields = '.all',suffix = '_cf', + query_column = "inchikey", + output_items = ".all", + output_fields = ".all", suffix = "_cf", cache = cache4, delay = 5 ) + database_lookup( - query_column = 'inchikey', - database_column = 'InChI.Key', + query_column = "inchikey", + database_column = "InChI.Key", database = PathBank_metabolite_database(), - include = c('Pathway.Name','Pathway.Subject','Species'), - suffix = '', + include = c("Pathway.Name", "Pathway.Subject", "Species"), + suffix = "", not_found = NA ) + add_columns( - new_columns = rbind(HP,LP), - by = c('mzrt_match_id'='id') + new_columns = rbind(HP, LP), + by = c("mzrt_match_id" = "id") ) + filter_na( - column_name = 'inchikey' + column_name = "inchikey" ) + combine_records( - group_by = 'mzrt_match_id', + group_by = "mzrt_match_id", default_fcn = .unique( - separator = ' || ') + separator = " || " + ) ) + filter_labels( - column_name = 'rsd_qc', - labels = 'NA', - mode = 'exclude' + column_name = "rsd_qc", + labels = "NA", + mode = "exclude" ) + filter_range( - column_name = 'rsd_qc', + column_name = "rsd_qc", upper_limit = 20, - lower_limit=-Inf, - equal_to=FALSE + lower_limit = -Inf, + equal_to = FALSE ) -WF = model_apply(WF,predicted(CD$HILIC_POS))
We can explore the contents of the table. Here we generate plots to visualise the number of annotations from each source.
# pie chart of the sources of annotations -C = annotation_pie_chart( - factor_name = 'source_name', - label_location = 'outside' +C <- annotation_pie_chart( + factor_name = "source_name", + label_location = "outside" ) -chart_plot(C,predicted(WF)) + ggtitle('Annotations per source')
Next we plot a histogram of the QC-RSD values before filtering, by indexing the relevant step of the workflow.
# histogram of the rsd-qc for annotated features (before filtering) -C = annotation_histogram( - factor_name = 'rsd_qc', +C <- annotation_histogram( + factor_name = "rsd_qc", bins = 30, vline = 20 ) -chart_plot(C,predicted(WF[12])) + - ggtitle('MS1 peak QC-RSD',"Features with QC-RSD<20 were removed by the workflow.")
In this plot we present a bar chart of the different molecular classes present in the final table.
# bar chart of the superclasses -C = annotation_bar_chart( - factor_name = 'superclass.name_cf', - legend = TRUE,label_type = 'none' +C <- annotation_bar_chart( + factor_name = "superclass.name_cf", + legend = TRUE, label_type = "none" ) -chart_plot(C,predicted(WF[10])) + ggtitle('Superclasses')
Finally we use the PubChem API to generate an image of the molecular structure for one of the metabolites.
# display one of the metabolite structures -C = pubchem_widget( - query_column = 'normalised_compound', - row_index=1, - record_type = '3D-Conformer', - display = FALSE, - hide_title = FALSE, - height = '820px') +C <- pubchem_widget( + query_column = "normalised_compound", + row_index = 1, + record_type = "3D-Conformer", + display = FALSE, + hide_title = FALSE, + height = "820px" +) -chart_plot(C,predicted(WF))
sessionInfo() -#> R version 4.3.2 (2023-10-31) -#> Platform: x86_64-pc-linux-gnu (64-bit) -#> Running under: Ubuntu 22.04.3 LTS +#> R Under development (unstable) (2024-03-13 r86113) +#> Platform: x86_64-pc-linux-gnu +#> Running under: Ubuntu 22.04.4 LTS #> #> Matrix products: default #> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 @@ -652,62 +693,59 @@ Session Info#> [1] stats graphics grDevices utils datasets methods base #> #> other attached packages: -#> [1] patchwork_1.2.0 ggplot2_3.4.4 -#> [3] metabolomicsWorkbenchR_1.12.0 MetMashR_0.1.0 -#> [5] struct_1.14.0 BiocStyle_2.30.0 +#> [1] patchwork_1.2.0 ggplot2_3.5.0 +#> [3] metabolomicsWorkbenchR_1.13.0 MetMashR_0.99.0 +#> [5] struct_1.15.4 BiocStyle_2.31.0 #> #> loaded via a namespace (and not attached): -#> [1] DBI_1.2.1 bitops_1.0-7 -#> [3] gridExtra_2.3 rlang_1.1.3 -#> [5] magrittr_2.0.3 matrixStats_1.2.0 -#> [7] e1071_1.7-14 compiler_4.3.2 -#> [9] RSQLite_2.3.4 systemfonts_1.0.5 -#> [11] vctrs_0.6.5 stringr_1.5.1 -#> [13] pkgconfig_2.0.3 crayon_1.5.2 -#> [15] fastmap_1.1.1 dbplyr_2.4.0 -#> [17] XVector_0.42.0 labeling_0.4.3 -#> [19] utf8_1.2.4 rmarkdown_2.25 -#> [21] structToolbox_1.14.0 ragg_1.2.7 -#> [23] purrr_1.0.2 bit_4.0.5 -#> [25] xfun_0.41 MultiAssayExperiment_1.28.0 -#> [27] zlibbioc_1.48.0 cachem_1.0.8 -#> [29] GenomeInfoDb_1.38.5 jsonlite_1.8.8 -#> [31] blob_1.2.4 highr_0.10 -#> [33] DelayedArray_0.28.0 R6_2.5.1 -#> [35] bslib_0.6.1 stringi_1.8.3 -#> [37] GenomicRanges_1.54.1 jquerylib_0.1.4 -#> [39] Rcpp_1.0.12 bookdown_0.37 -#> [41] SummarizedExperiment_1.32.0 knitr_1.45 -#> [43] IRanges_2.36.0 Matrix_1.6-5 -#> [45] tidyselect_1.2.0 abind_1.4-5 -#> [47] yaml_2.3.8 curl_5.2.0 -#> [49] lattice_0.22-5 tibble_3.2.1 -#> [51] plyr_1.8.9 Biobase_2.62.0 -#> [53] withr_3.0.0 evaluate_0.23 -#> [55] ontologyIndex_2.11 desc_1.4.3 -#> [57] sf_1.0-15 units_0.8-5 -#> [59] proxy_0.4-27 BiocFileCache_2.10.1 -#> [61] zip_2.3.0 pillar_1.9.0 -#> [63] BiocManager_1.30.22 filelock_1.0.3 -#> [65] MatrixGenerics_1.14.0 KernSmooth_2.23-22 -#> [67] stats4_4.3.2 generics_0.1.3 -#> [69] sp_2.1-2 RCurl_1.98-1.14 -#> [71] S4Vectors_0.40.2 munsell_0.5.0 -#> [73] scales_1.3.0 class_7.3-22 -#> [75] glue_1.7.0 tools_4.3.2 -#> [77] data.table_1.14.10 openxlsx_4.2.5.2 -#> [79] fs_1.6.3 cowplot_1.1.2 -#> [81] grid_4.3.2 colorspace_2.1-0 -#> [83] GenomeInfoDbData_1.2.11 cli_3.6.2 -#> [85] textshaping_0.3.7 fansi_1.0.6 -#> [87] ggthemes_5.0.0 S4Arrays_1.2.0 -#> [89] dplyr_1.1.4 gtable_0.3.4 -#> [91] sass_0.4.8 digest_0.6.34 -#> [93] BiocGenerics_0.48.1 classInt_0.4-10 -#> [95] SparseArray_1.2.3 farver_2.1.1 -#> [97] memoise_2.0.1 htmltools_0.5.7 -#> [99] pkgdown_2.0.7 lifecycle_1.0.4 -#> [101] httr_1.4.7 bit64_4.0.5
vignettes/exploring_mtox.Rmd
exploring_mtox.Rmd
# prep object -MT = MTox700plus_database( - version = 'latest', - tag = 'MTox700+' +MT <- MTox700plus_database( + version = "latest", + tag = "MTox700+" ) # import -df = read_database(MT) +df <- read_database(MT) # show contents .DT(df)
+ + # prepare workflow that uses MTox700+ as a source -M = import_source() - trim_whitespace( - column_name = '.all', - which = 'both', - whitespace = '[\\h\\v]' - ) +M <- import_source() +trim_whitespace( + column_name = ".all", + which = "both", + whitespace = "[\\h\\v]" +) #> A "trim_whitespace" object #> -------------------------- #> name: Trim whitespace @@ -180,7 +181,7 @@ Importing the MTox700+ database#> seq_in: data # apply -M = model_apply(M,MT) +M <- model_apply(M, MT)
# prepare workflow that uses MTox700+ as a source -M = import_source() - trim_whitespace( - column_name = '.all', - which = 'both', - whitespace = '[\\h\\v]' - ) +M <- import_source() +trim_whitespace( + column_name = ".all", + which = "both", + whitespace = "[\\h\\v]" +) #> A "trim_whitespace" object #> -------------------------- #> name: Trim whitespace @@ -180,7 +181,7 @@ Importing the MTox700+ database#> seq_in: data # apply -M = model_apply(M,MT)
# prepare chart -C = openbabel_structure( - smiles_column = 'smiles', +C <- openbabel_structure( + smiles_column = "smiles", row_index = 1, scale_to_fit = FALSE, image_size = 300, - title_column = 'metabolite_name', + title_column = "metabolite_name", view_port = 400 ) # first six -G = list() +G <- list() for (k in 1:6) { # set row idx - C$row_index=k + C$row_index <- k # plot - G[[k]] = chart_plot(C,predicted(M)) + G[[k]] <- chart_plot(C, predicted(M)) } # layout -cowplot::plot_grid(plotlist = G,nrow=2)
The MTox700+ database also contains information about the structural classification of the metabolites based on ChemOnt (a chemical taxonomy) @@ -223,22 +224,22 @@
# initialise chart object -C = annotation_bar_chart( - factor_name = 'superclass', +C <- annotation_bar_chart( + factor_name = "superclass", label_rotation = TRUE, - label_location = 'outside', - label_type = 'percent', + label_location = "outside", + label_type = "percent", legend = TRUE ) # plot -g = chart_plot(C,predicted(M)) + ylim(c(0,600)) + - guides(fill=guide_legend(nrow=6,title = element_blank())) + - theme(legend.position = 'bottom',legend.margin=margin()) +g <- chart_plot(C, predicted(M)) + ylim(c(0, 600)) + + guides(fill = guide_legend(nrow = 6, title = element_blank())) + + theme(legend.position = "bottom", legend.margin = margin()) # layout -leg = cowplot::get_legend(g) -cowplot::plot_grid(g+theme(legend.position = 'none'),leg,nrow=2,rel_heights = c(75,25))
The diagram shows that less than half of the metabolites in MTox700+ are also present in the PathBank database for primary pathways.
# prepare object -X = database_lookup( - query_column = 'inchikey', +X <- database_lookup( + query_column = "inchikey", database = P$data, - database_column = 'InChI.Key', - include = c( - "PathBank.ID","Pathway.Name","Pathway.Subject","Species", - "HMDB.ID","KEGG.ID","ChEBI.ID","DrugBank.ID","SMILES"), - suffix = '' + database_column = "InChI.Key", + include = c( + "PathBank.ID", "Pathway.Name", "Pathway.Subject", "Species", + "HMDB.ID", "KEGG.ID", "ChEBI.ID", "DrugBank.ID", "SMILES" + ), + suffix = "" ) # apply -X = model_apply(X,predicted(M))
We can now visualise e.g. the subject of the pathways captured by the MTox700+ database.
-C = annotation_bar_chart( - factor_name = 'Pathway.Subject', +C <- annotation_bar_chart( + factor_name = "Pathway.Subject", label_rotation = TRUE, - label_location = 'outside', - label_type = 'percent', + label_location = "outside", + label_type = "percent", legend = TRUE ) -chart_plot(C,predicted(X))+ylim(c(0,17500))
C = annotation_bar_chart( - factor_name = 'Pathway.Subject', +C <- annotation_bar_chart( + factor_name = "Pathway.Subject", label_rotation = TRUE, - label_location = 'outside', - label_type = 'percent', + label_location = "outside", + label_type = "percent", legend = TRUE ) -chart_plot(C,predicted(X))+ylim(c(0,17500))
C <- annotation_bar_chart( + factor_name = "Pathway.Subject", label_rotation = TRUE, - label_location = 'outside', - label_type = 'percent', + label_location = "outside", + label_type = "percent", legend = TRUE ) -chart_plot(C,predicted(X))+ylim(c(0,17500))
We can see that MTox700+ largely focuses on metabolites related to Disease metabolism and general metabolism, which is concomitant with the @@ -371,33 +373,35 @@
# Number in MTox700+ nrow(predicted(M)$data) -#> [1] 1222
After combing with PathBank the number of records is:
# Number after PathBank lookup nrow(predicted(X)$data) -#> [1] 31051
Sometimes it is useful to collapse this information into a single record per metabolite. We can use the combine_records object and its helper functions to do this in a MetMashR workflow.
combine_records
# prepare object -X = database_lookup( - query_column = 'inchikey', +X <- database_lookup( + query_column = "inchikey", database = P$data, - database_column = 'InChI.Key', - include = c( - "PathBank.ID","Pathway.Name","Pathway.Subject","Species", - "HMDB.ID","KEGG.ID","ChEBI.ID","DrugBank.ID","SMILES"), - suffix = '') + + database_column = "InChI.Key", + include = c( + "PathBank.ID", "Pathway.Name", "Pathway.Subject", "Species", + "HMDB.ID", "KEGG.ID", "ChEBI.ID", "DrugBank.ID", "SMILES" + ), + suffix = "" +) + combine_records( - group_by = 'inchikey', - default_fcn = .unique(' || ') + group_by = "inchikey", + default_fcn = .unique(" || ") ) # apply -X = model_apply(X,predicted(M))
We have used the .unique helper function so that records for each inchikey are combined into a single record by only retaining unique values in each field (column). If there are multiple unique @@ -407,7 +411,7 @@
.unique
# get index of metabolite -w = which(predicted(X)$data$metabolite_name=='Glycolic acid')
The pathways associated with Glycolic acid are:
# print list of pathways @@ -421,9 +425,9 @@ Session Info sessionInfo() -#> R version 4.3.2 (2023-10-31) -#> Platform: x86_64-pc-linux-gnu (64-bit) -#> Running under: Ubuntu 22.04.3 LTS +#> R Under development (unstable) (2024-03-13 r86113) +#> Platform: x86_64-pc-linux-gnu +#> Running under: Ubuntu 22.04.4 LTS #> #> Matrix products: default #> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 @@ -444,63 +448,59 @@ Session Info#> [1] stats graphics grDevices utils datasets methods base #> #> other attached packages: -#> [1] DT_0.31 dplyr_1.1.4 structToolbox_1.14.0 -#> [4] ggplot2_3.4.4 MetMashR_0.1.0 struct_1.14.0 -#> [7] BiocStyle_2.30.0 +#> [1] DT_0.32 dplyr_1.1.4 structToolbox_1.15.1 +#> [4] ggplot2_3.5.0 MetMashR_0.99.0 struct_1.15.4 +#> [7] BiocStyle_2.31.0 #> #> loaded via a namespace (and not attached): -#> [1] DBI_1.2.1 bitops_1.0-7 -#> [3] gridExtra_2.3 rlang_1.1.3 -#> [5] magrittr_2.0.3 matrixStats_1.2.0 -#> [7] e1071_1.7-14 compiler_4.3.2 -#> [9] RSQLite_2.3.4 systemfonts_1.0.5 -#> [11] vctrs_0.6.5 stringr_1.5.1 -#> [13] pkgconfig_2.0.3 crayon_1.5.2 -#> [15] fastmap_1.1.1 dbplyr_2.4.0 -#> [17] magick_2.8.2 XVector_0.42.0 -#> [19] ellipsis_0.3.2 labeling_0.4.3 -#> [21] utf8_1.2.4 rmarkdown_2.25 -#> [23] ragg_1.2.7 purrr_1.0.2 -#> [25] bit_4.0.5 xfun_0.41 -#> [27] zlibbioc_1.48.0 cachem_1.0.8 -#> [29] GenomeInfoDb_1.38.5 jsonlite_1.8.8 -#> [31] RVenn_1.1.0 blob_1.2.4 -#> [33] highr_0.10 DelayedArray_0.28.0 -#> [35] R6_2.5.1 bslib_0.6.1 -#> [37] stringi_1.8.3 GenomicRanges_1.54.1 -#> [39] jquerylib_0.1.4 Rcpp_1.0.12 -#> [41] bookdown_0.37 SummarizedExperiment_1.32.0 -#> [43] knitr_1.45 IRanges_2.36.0 -#> [45] Matrix_1.6-5 tidyselect_1.2.0 -#> [47] abind_1.4-5 yaml_2.3.8 -#> [49] ggVennDiagram_1.5.0 curl_5.2.0 -#> [51] lattice_0.22-5 tibble_3.2.1 -#> [53] Biobase_2.62.0 withr_3.0.0 -#> [55] evaluate_0.23 ontologyIndex_2.11 -#> [57] desc_1.4.3 sf_1.0-15 -#> [59] units_0.8-5 proxy_0.4-27 -#> [61] BiocFileCache_2.10.1 pillar_1.9.0 -#> [63] BiocManager_1.30.22 filelock_1.0.3 -#> [65] MatrixGenerics_1.14.0 KernSmooth_2.23-22 -#> [67] stats4_4.3.2 ChemmineOB_1.40.0 -#> [69] generics_0.1.3 sp_2.1-2 -#> [71] RCurl_1.98-1.14 S4Vectors_0.40.2 -#> [73] munsell_0.5.0 scales_1.3.0 -#> [75] class_7.3-22 glue_1.7.0 -#> [77] tools_4.3.2 fs_1.6.3 -#> [79] cowplot_1.1.2 grid_4.3.2 -#> [81] crosstalk_1.2.1 colorspace_2.1-0 -#> [83] GenomeInfoDbData_1.2.11 cli_3.6.2 -#> [85] textshaping_0.3.7 rsvg_2.6.0 -#> [87] fansi_1.0.6 ggthemes_5.0.0 -#> [89] S4Arrays_1.2.0 gtable_0.3.4 -#> [91] sass_0.4.8 digest_0.6.34 -#> [93] BiocGenerics_0.48.1 classInt_0.4-10 -#> [95] SparseArray_1.2.3 farver_2.1.1 -#> [97] htmlwidgets_1.6.4 memoise_2.0.1 -#> [99] htmltools_0.5.7 pkgdown_2.0.7 -#> [101] lifecycle_1.0.4 httr_1.4.7 -#> [103] bit64_4.0.5
sessionInfo() -#> R version 4.3.2 (2023-10-31) -#> Platform: x86_64-pc-linux-gnu (64-bit) -#> Running under: Ubuntu 22.04.3 LTS +#> R Under development (unstable) (2024-03-13 r86113) +#> Platform: x86_64-pc-linux-gnu +#> Running under: Ubuntu 22.04.4 LTS #> #> Matrix products: default #> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 @@ -444,63 +448,59 @@ Session Info#> [1] stats graphics grDevices utils datasets methods base #> #> other attached packages: -#> [1] DT_0.31 dplyr_1.1.4 structToolbox_1.14.0 -#> [4] ggplot2_3.4.4 MetMashR_0.1.0 struct_1.14.0 -#> [7] BiocStyle_2.30.0 +#> [1] DT_0.32 dplyr_1.1.4 structToolbox_1.15.1 +#> [4] ggplot2_3.5.0 MetMashR_0.99.0 struct_1.15.4 +#> [7] BiocStyle_2.31.0 #> #> loaded via a namespace (and not attached): -#> [1] DBI_1.2.1 bitops_1.0-7 -#> [3] gridExtra_2.3 rlang_1.1.3 -#> [5] magrittr_2.0.3 matrixStats_1.2.0 -#> [7] e1071_1.7-14 compiler_4.3.2 -#> [9] RSQLite_2.3.4 systemfonts_1.0.5 -#> [11] vctrs_0.6.5 stringr_1.5.1 -#> [13] pkgconfig_2.0.3 crayon_1.5.2 -#> [15] fastmap_1.1.1 dbplyr_2.4.0 -#> [17] magick_2.8.2 XVector_0.42.0 -#> [19] ellipsis_0.3.2 labeling_0.4.3 -#> [21] utf8_1.2.4 rmarkdown_2.25 -#> [23] ragg_1.2.7 purrr_1.0.2 -#> [25] bit_4.0.5 xfun_0.41 -#> [27] zlibbioc_1.48.0 cachem_1.0.8 -#> [29] GenomeInfoDb_1.38.5 jsonlite_1.8.8 -#> [31] RVenn_1.1.0 blob_1.2.4 -#> [33] highr_0.10 DelayedArray_0.28.0 -#> [35] R6_2.5.1 bslib_0.6.1 -#> [37] stringi_1.8.3 GenomicRanges_1.54.1 -#> [39] jquerylib_0.1.4 Rcpp_1.0.12 -#> [41] bookdown_0.37 SummarizedExperiment_1.32.0 -#> [43] knitr_1.45 IRanges_2.36.0 -#> [45] Matrix_1.6-5 tidyselect_1.2.0 -#> [47] abind_1.4-5 yaml_2.3.8 -#> [49] ggVennDiagram_1.5.0 curl_5.2.0 -#> [51] lattice_0.22-5 tibble_3.2.1 -#> [53] Biobase_2.62.0 withr_3.0.0 -#> [55] evaluate_0.23 ontologyIndex_2.11 -#> [57] desc_1.4.3 sf_1.0-15 -#> [59] units_0.8-5 proxy_0.4-27 -#> [61] BiocFileCache_2.10.1 pillar_1.9.0 -#> [63] BiocManager_1.30.22 filelock_1.0.3 -#> [65] MatrixGenerics_1.14.0 KernSmooth_2.23-22 -#> [67] stats4_4.3.2 ChemmineOB_1.40.0 -#> [69] generics_0.1.3 sp_2.1-2 -#> [71] RCurl_1.98-1.14 S4Vectors_0.40.2 -#> [73] munsell_0.5.0 scales_1.3.0 -#> [75] class_7.3-22 glue_1.7.0 -#> [77] tools_4.3.2 fs_1.6.3 -#> [79] cowplot_1.1.2 grid_4.3.2 -#> [81] crosstalk_1.2.1 colorspace_2.1-0 -#> [83] GenomeInfoDbData_1.2.11 cli_3.6.2 -#> [85] textshaping_0.3.7 rsvg_2.6.0 -#> [87] fansi_1.0.6 ggthemes_5.0.0 -#> [89] S4Arrays_1.2.0 gtable_0.3.4 -#> [91] sass_0.4.8 digest_0.6.34 -#> [93] BiocGenerics_0.48.1 classInt_0.4-10 -#> [95] SparseArray_1.2.3 farver_2.1.1 -#> [97] htmlwidgets_1.6.4 memoise_2.0.1 -#> [99] htmltools_0.5.7 pkgdown_2.0.7 -#> [101] lifecycle_1.0.4 httr_1.4.7 -#> [103] bit64_4.0.5
MetMashR +
MetMashR is an R package designed to facilitate the cleaning, filtering and -combining of annotations from different sources. MetMashR +combining of annotations from different sources. MetMashR defines an “annotation source” as a piece of software, proprietary or otherwise, that takes the raw input of an analytical instrument and attempts to assign molecule names to the peaks in the data, usually by -comparison to a library. MetMashR +comparison to a library. MetMashR was primarily designed for use with metabolomics data measured by LCMS (hence “metabolite” in the package name) but could be extended to include other platforms (e.g. NMR, DIMS etc.), or other analytical @@ -125,20 +125,20 @@
All of the objects defined in MetMashR -use or extend the class templates defined by the struct +
All of the objects defined in MetMashR +use or extend the class templates defined by the struct package. Although originally intended for statistics applications, the -templates in the struct +templates in the struct package have proven to be adaptable to many different scenarios and types of analysis/workflow step.
The use of struct +
The use of struct templates allows workflow steps to be applied in sequence and intermediate outputs to be retained for further analysis if required. The templates include ontology definitions for both the object and its input/output parameters. This makes the workflows more “FAIR” which is critical alongside FAIR data to making workflows repeatable, transparent and reproducible.
A general summary of extending struct +
A general summary of extending struct templates is provided in the package vignette.
The latest versions of struct and -MetMashR +
The latest versions of struct and +MetMashR that are compatible with your current R version can be installed using BiocManager.
annotation_source objects are the dataset used by all -MetMashR -workflow steps. If you have used our structToolbox +MetMashR +workflow steps. If you have used our structToolbox package before, then annotation sources used equivalently to DatasetExperiment objects, except that they hold a single data.frame of metabolite annotation data.
DatasetExperiment
data.frame
Note: -It is not the aim of MetMashR +It is not the aim of MetMashR to generate these annotations. Instead we aim to provide tools to process, filter, clean and otherwise “mash” this table of annotations generated elsewhere.
# prepare source object -AT = ls_source( +AT <- ls_source( source = system.file( - paste0('extdata/MTox/LS/MTox_2023_HILIC_POS.txt'), - package = 'MetMashR') + paste0("extdata/MTox/LS/MTox_2023_HILIC_POS.txt"), + package = "MetMashR" + ) ) # read source -AT = read_source(AT) +AT <- read_source(AT) # show info AT @@ -246,10 +248,10 @@ Annotation Databases # prepare source object -MT = MTox700plus_database() +MT <- MTox700plus_database() # read -MT = read_source(MT) +MT <- read_source(MT) # show MT @@ -260,23 +262,23 @@ Annotation Databases#> MTox700+ is a list of toxicologically relevant metabolites derived from #> publications, public databases and relevant toxicological assays. #> input params: version -#> annotations: 1222 rows x 15 columns
# prepare source object -MT = MTox700plus_database() +MT <- MTox700plus_database() # read -MT = read_source(MT) +MT <- read_source(MT) # show MT @@ -260,23 +262,23 @@ Annotation Databases#> MTox700+ is a list of toxicologically relevant metabolites derived from #> publications, public databases and relevant toxicological assays. #> input params: version -#> annotations: 1222 rows x 15 columns
annotation_database objects also have a read_database method to read the table directly to a data.frame.
read_database
# prepare source object -MT = MTox700plus_database() +MT <- MTox700plus_database() # read to data.frame -df = read_database(MT) +df <- read_database(MT) # show .DT(df)
Some annotation_database objects also have a +
Some annotation_database objects also have a write_database method, that allows you to update the table -on disk. For example, in MetMashR +on disk. For example, in MetMashR the rds_database has a write_database method. It is useful in combination with rest_api objects to cache results and reduce the number of requests to the api.
write_database
rest_api
# prepare source object -AT = ls_source( +AT <- ls_source( source = system.file( - paste0('extdata/MTox/LS/MTox_2023_HILIC_POS.txt'), - package = 'MetMashR') + paste0("extdata/MTox/LS/MTox_2023_HILIC_POS.txt"), + package = "MetMashR" + ) ) # prepare workflow -WF = import_source() +WF <- import_source() # apply workflow to annotation source -WF = model_apply(WF,AT) +WF <- model_apply(WF, AT) # show predicted(WF) @@ -359,25 +362,26 @@ Filtering / Cleaning # prepare source object -AT = ls_source( +AT <- ls_source( source = system.file( - paste0('extdata/MTox/LS/MTox_2023_HILIC_POS.txt'), - package = 'MetMashR') + paste0("extdata/MTox/LS/MTox_2023_HILIC_POS.txt"), + package = "MetMashR" + ) ) # prepare workflow -WF = +WF <- # step 1 import source from file import_source() + # step 2 filter the "Grade" column to only include "A" and "B" filter_labels( - column_name = 'Grade', - labels=c('A','B'), - mode = 'include' + column_name = "Grade", + labels = c("A", "B"), + mode = "include" ) # apply workflow to annotation source -WF = model_apply(WF,AT) +WF <- model_apply(WF, AT) # show predicted(WF) @@ -468,39 +472,40 @@ REST APIs # prepare source object -AT = ls_source( +AT <- ls_source( source = system.file( - paste0('extdata/MTox/LS/MTox_2023_HILIC_POS.txt'), - package = 'MetMashR') + paste0("extdata/MTox/LS/MTox_2023_HILIC_POS.txt"), + package = "MetMashR" + ) ) # prepare cache -TF = rds_database( +TF <- rds_database( source = tempfile() ) # prepare workflow -WF = +WF <- # step 1 import source from file import_source() + # step 2 filter the "Grade" column to only include "A" and "B" filter_labels( - column_name = 'Grade', - labels=c('A','B'), - mode = 'include' + column_name = "Grade", + labels = c("A", "B"), + mode = "include" ) + # step 3 query lipidmaps api for inchikey lipidmaps_lookup( - query_column = 'LipidName', - context = 'compound', - context_item = 'abbrev', - output_item = 'inchi_key', + query_column = "LipidName", + context = "compound", + context_item = "abbrev", + output_item = "inchi_key", cache = TF, - suffix = '' + suffix = "" ) # apply workflow to annotation source -WF = model_apply(WF,AT) +WF <- model_apply(WF, AT) # show predicted(WF) @@ -517,21 +522,21 @@ REST APIs # retrieve cache -TF = read_source(TF) +TF <- read_source(TF) # filter records with no inchikey -FI = +FI <- filter_na( - column_name = 'inchi_key' + column_name = "inchi_key" ) # apply -FI = model_apply(FI,TF) +FI <- model_apply(FI, TF) # show .DT(predicted(FI)$data)
# prepare source object -AT = ls_source( +AT <- ls_source( source = system.file( - paste0('extdata/MTox/LS/MTox_2023_HILIC_POS.txt'), - package = 'MetMashR') + paste0("extdata/MTox/LS/MTox_2023_HILIC_POS.txt"), + package = "MetMashR" + ) ) # prepare workflow -WF = +WF <- # step 1 import source from file import_source() + # step 2 filter the "Grade" column to only include "A" and "B" filter_labels( - column_name = 'Grade', - labels=c('A','B'), - mode = 'include' + column_name = "Grade", + labels = c("A", "B"), + mode = "include" ) # apply workflow to annotation source -WF = model_apply(WF,AT) +WF <- model_apply(WF, AT) # show predicted(WF) @@ -468,39 +472,40 @@ REST APIs # prepare source object -AT = ls_source( +AT <- ls_source( source = system.file( - paste0('extdata/MTox/LS/MTox_2023_HILIC_POS.txt'), - package = 'MetMashR') + paste0("extdata/MTox/LS/MTox_2023_HILIC_POS.txt"), + package = "MetMashR" + ) ) # prepare cache -TF = rds_database( +TF <- rds_database( source = tempfile() ) # prepare workflow -WF = +WF <- # step 1 import source from file import_source() + # step 2 filter the "Grade" column to only include "A" and "B" filter_labels( - column_name = 'Grade', - labels=c('A','B'), - mode = 'include' + column_name = "Grade", + labels = c("A", "B"), + mode = "include" ) + # step 3 query lipidmaps api for inchikey lipidmaps_lookup( - query_column = 'LipidName', - context = 'compound', - context_item = 'abbrev', - output_item = 'inchi_key', + query_column = "LipidName", + context = "compound", + context_item = "abbrev", + output_item = "inchi_key", cache = TF, - suffix = '' + suffix = "" ) # apply workflow to annotation source -WF = model_apply(WF,AT) +WF <- model_apply(WF, AT) # show predicted(WF) @@ -517,21 +522,21 @@ REST APIs # retrieve cache -TF = read_source(TF) +TF <- read_source(TF) # filter records with no inchikey -FI = +FI <- filter_na( - column_name = 'inchi_key' + column_name = "inchi_key" ) # apply -FI = model_apply(FI,TF) +FI <- model_apply(FI, TF) # show .DT(predicted(FI)$data)
# prepare source object -AT = ls_source( +AT <- ls_source( source = system.file( - paste0('extdata/MTox/LS/MTox_2023_HILIC_POS.txt'), - package = 'MetMashR') + paste0("extdata/MTox/LS/MTox_2023_HILIC_POS.txt"), + package = "MetMashR" + ) ) # prepare cache -TF = rds_database( +TF <- rds_database( source = tempfile() ) # prepare workflow -WF = +WF <- # step 1 import source from file import_source() + # step 2 filter the "Grade" column to only include "A" and "B" filter_labels( - column_name = 'Grade', - labels=c('A','B'), - mode = 'include' + column_name = "Grade", + labels = c("A", "B"), + mode = "include" ) + # step 3 query lipidmaps api for inchikey lipidmaps_lookup( - query_column = 'LipidName', - context = 'compound', - context_item = 'abbrev', - output_item = 'inchi_key', + query_column = "LipidName", + context = "compound", + context_item = "abbrev", + output_item = "inchi_key", cache = TF, - suffix = '' + suffix = "" ) # apply workflow to annotation source -WF = model_apply(WF,AT) +WF <- model_apply(WF, AT) # show predicted(WF) @@ -517,21 +522,21 @@ REST APIs # retrieve cache -TF = read_source(TF) +TF <- read_source(TF) # filter records with no inchikey -FI = +FI <- filter_na( - column_name = 'inchi_key' + column_name = "inchi_key" ) # apply -FI = model_apply(FI,TF) +FI <- model_apply(FI, TF) # show .DT(predicted(FI)$data)
# retrieve cache -TF = read_source(TF) +TF <- read_source(TF) # filter records with no inchikey -FI = +FI <- filter_na( - column_name = 'inchi_key' + column_name = "inchi_key" ) # apply -FI = model_apply(FI,TF) +FI <- model_apply(FI, TF) # show .DT(predicted(FI)$data)
An alternative to using rest_api objects in every +
An alternative to using rest_api objects in every workflow is to create separate workflow to generate a local database of relevant data. This database can then be used in other workflows without needing to query the api every time the workflow is run.
-custom_dict = list( +custom_dict <- list( list( pattern = "AcCa", - replace = 'CAR', + replace = "CAR", fixed = TRUE ), list( pattern = "AEA", - replace = 'NAE', + replace = "NAE", fixed = TRUE ), list( pattern = "_", - replace = '/', + replace = "/", fixed = TRUE ) )
custom_dict = list( +custom_dict <- list( list( pattern = "AcCa", - replace = 'CAR', + replace = "CAR", fixed = TRUE ), list( pattern = "AEA", - replace = 'NAE', + replace = "NAE", fixed = TRUE ), list( pattern = "_", - replace = '/', + replace = "/", fixed = TRUE ) )
custom_dict <- list( list( pattern = "AcCa", - replace = 'CAR', + replace = "CAR", fixed = TRUE ), list( pattern = "AEA", - replace = 'NAE', + replace = "NAE", fixed = TRUE ), list( pattern = "_", - replace = '/', + replace = "/", fixed = TRUE ) )
# prepare workflow -WF = +WF <- # step 1 import source from file import_source() + # step 2 filter the "Grade" column to only include "A" and "B" filter_labels( - column_name = 'Grade', - labels=c('A','B'), - mode = 'include' + column_name = "Grade", + labels = c("A", "B"), + mode = "include" ) + # step 3 normalise lipid names using the custom dictionary: normalise_strings( - search_column = 'LipidName', - output_column = 'normalised_name', - dictionary = custom_dict + search_column = "LipidName", + output_column = "normalised_name", + dictionary = custom_dict ) + # step 4 query lipidmaps api for inchikey using the names provided by LipidSearch lipidmaps_lookup( - query_column = 'LipidName', - context = 'compound', - context_item = 'abbrev', - output_item = 'inchi_key', - suffix = '_LipidName', - cache = TF + query_column = "LipidName", + context = "compound", + context_item = "abbrev", + output_item = "inchi_key", + suffix = "_LipidName", + cache = TF ) + # step 5 query lipidmaps api for inchikey using the names provided by LipidSearch lipidmaps_lookup( - query_column = 'normalised_name', - context = 'compound', - context_item = 'abbrev', - output_item = 'inchi_key', - suffix = '_normalised' + query_column = "normalised_name", + context = "compound", + context_item = "abbrev", + output_item = "inchi_key", + suffix = "_normalised" ) # apply workflow to annotation source -WF = model_apply(WF,AT) +WF <- model_apply(WF, AT) # show result table for relevant columns -.DT(predicted(WF)$data[,c('LipidName','normalised_name','inchi_key_LipidName','inchi_key_normalised')])
You can see that we obtained inchikey for more of the Lipids after +.DT(predicted(WF)$data[, c("LipidName", "normalised_name", "inchi_key_LipidName", "inchi_key_normalised")]) +
You can see that we obtained inchikey for more of the Lipids after normalising the lipid names.
MetMashR also provides an interface to the rgoslin package to assist with Lipid annotations.
rgoslin
# prepare workflow -CR = combine_records( - group_by = 'LipidName', - default_fcn = .unique(separator='; '), +CR <- combine_records( + group_by = "LipidName", + default_fcn = .unique(separator = "; "), fcns = list( - count = .count()) + count = .count() + ) ) # apply to previous output -CR = model_apply(CR,predicted(WF)) +CR <- model_apply(CR, predicted(WF)) # show output for relevant columns -.DT(predicted(CR)$data[,c('LipidName','normalised_name','inchi_key_normalised','count')])
You can see that there is now a single record (row) for each +.DT(predicted(CR)$data[, c("LipidName", "normalised_name", "inchi_key_normalised", "count")]) +
You can see that there is now a single record (row) for each LipidName, and that the multiple inchikeys associated with that LipidName have been collapsed into a single entry separated by semicolons.
+sessionInfo() +#> R Under development (unstable) (2024-03-13 r86113) +#> Platform: x86_64-pc-linux-gnu +#> Running under: Ubuntu 22.04.4 LTS +#> +#> Matrix products: default +#> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 +#> LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.20.so; LAPACK version 3.10.0 +#> +#> locale: +#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C +#> [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8 +#> [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8 +#> [7] LC_PAPER=en_US.UTF-8 LC_NAME=C +#> [9] LC_ADDRESS=C LC_TELEPHONE=C +#> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C +#> +#> time zone: UTC +#> tzcode source: system (glibc) +#> +#> attached base packages: +#> [1] stats graphics grDevices utils datasets methods base +#> +#> other attached packages: +#> [1] DT_0.32 dplyr_1.1.4 structToolbox_1.15.1 +#> [4] ggplot2_3.5.0 MetMashR_0.99.0 struct_1.15.4 +#> [7] BiocStyle_2.31.0 +#> +#> loaded via a namespace (and not attached): +#> [1] tidyselect_1.2.1 blob_1.2.4 +#> [3] filelock_1.0.3 bitops_1.0-7 +#> [5] fastmap_1.1.1 RCurl_1.98-1.14 +#> [7] BiocFileCache_2.11.1 digest_0.6.35 +#> [9] lifecycle_1.0.4 ellipsis_0.3.2 +#> [11] RSQLite_2.3.5 magrittr_2.0.3 +#> [13] compiler_4.4.0 rlang_1.1.3 +#> [15] sass_0.4.9 tools_4.4.0 +#> [17] utf8_1.2.4 yaml_2.3.8 +#> [19] knitr_1.45 S4Arrays_1.3.6 +#> [21] htmlwidgets_1.6.4 ontologyIndex_2.12 +#> [23] bit_4.0.5 sp_2.1-3 +#> [25] curl_5.2.1 DelayedArray_0.29.9 +#> [27] plyr_1.8.9 abind_1.4-5 +#> [29] withr_3.0.0 purrr_1.0.2 +#> [31] BiocGenerics_0.49.1 desc_1.4.3 +#> [33] grid_4.4.0 stats4_4.4.0 +#> [35] fansi_1.0.6 colorspace_2.1-0 +#> [37] scales_1.3.0 SummarizedExperiment_1.33.3 +#> [39] cli_3.6.2 rmarkdown_2.26 +#> [41] crayon_1.5.2 ragg_1.3.0 +#> [43] generics_0.1.3 httr_1.4.7 +#> [45] DBI_1.2.2 cachem_1.0.8 +#> [47] stringr_1.5.1 zlibbioc_1.49.3 +#> [49] ggthemes_5.1.0 BiocManager_1.30.22 +#> [51] XVector_0.43.1 matrixStats_1.2.0 +#> [53] vctrs_0.6.5 Matrix_1.6-5 +#> [55] jsonlite_1.8.8 bookdown_0.38 +#> [57] IRanges_2.37.1 S4Vectors_0.41.5 +#> [59] bit64_4.0.5 crosstalk_1.2.1 +#> [61] systemfonts_1.0.6 jquerylib_0.1.4 +#> [63] glue_1.7.0 pkgdown_2.0.7.9000 +#> [65] cowplot_1.1.3 stringi_1.8.3 +#> [67] gtable_0.3.4 GenomeInfoDb_1.39.9 +#> [69] GenomicRanges_1.55.4 munsell_0.5.0 +#> [71] tibble_3.2.1 pillar_1.9.0 +#> [73] htmltools_0.5.7 GenomeInfoDbData_1.2.11 +#> [75] R6_2.5.1 dbplyr_2.5.0 +#> [77] textshaping_0.3.7 evaluate_0.23 +#> [79] lattice_0.22-6 Biobase_2.63.0 +#> [81] memoise_2.0.1 bslib_0.6.1 +#> [83] Rcpp_1.0.12 gridExtra_2.3 +#> [85] SparseArray_1.3.4 xfun_0.42 +#> [87] fs_1.6.3 MatrixGenerics_1.15.0 +#> [89] pkgconfig_2.0.3
sessionInfo() +#> R Under development (unstable) (2024-03-13 r86113) +#> Platform: x86_64-pc-linux-gnu +#> Running under: Ubuntu 22.04.4 LTS +#> +#> Matrix products: default +#> BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 +#> LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.20.so; LAPACK version 3.10.0 +#> +#> locale: +#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C +#> [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8 +#> [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8 +#> [7] LC_PAPER=en_US.UTF-8 LC_NAME=C +#> [9] LC_ADDRESS=C LC_TELEPHONE=C +#> [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C +#> +#> time zone: UTC +#> tzcode source: system (glibc) +#> +#> attached base packages: +#> [1] stats graphics grDevices utils datasets methods base +#> +#> other attached packages: +#> [1] DT_0.32 dplyr_1.1.4 structToolbox_1.15.1 +#> [4] ggplot2_3.5.0 MetMashR_0.99.0 struct_1.15.4 +#> [7] BiocStyle_2.31.0 +#> +#> loaded via a namespace (and not attached): +#> [1] tidyselect_1.2.1 blob_1.2.4 +#> [3] filelock_1.0.3 bitops_1.0-7 +#> [5] fastmap_1.1.1 RCurl_1.98-1.14 +#> [7] BiocFileCache_2.11.1 digest_0.6.35 +#> [9] lifecycle_1.0.4 ellipsis_0.3.2 +#> [11] RSQLite_2.3.5 magrittr_2.0.3 +#> [13] compiler_4.4.0 rlang_1.1.3 +#> [15] sass_0.4.9 tools_4.4.0 +#> [17] utf8_1.2.4 yaml_2.3.8 +#> [19] knitr_1.45 S4Arrays_1.3.6 +#> [21] htmlwidgets_1.6.4 ontologyIndex_2.12 +#> [23] bit_4.0.5 sp_2.1-3 +#> [25] curl_5.2.1 DelayedArray_0.29.9 +#> [27] plyr_1.8.9 abind_1.4-5 +#> [29] withr_3.0.0 purrr_1.0.2 +#> [31] BiocGenerics_0.49.1 desc_1.4.3 +#> [33] grid_4.4.0 stats4_4.4.0 +#> [35] fansi_1.0.6 colorspace_2.1-0 +#> [37] scales_1.3.0 SummarizedExperiment_1.33.3 +#> [39] cli_3.6.2 rmarkdown_2.26 +#> [41] crayon_1.5.2 ragg_1.3.0 +#> [43] generics_0.1.3 httr_1.4.7 +#> [45] DBI_1.2.2 cachem_1.0.8 +#> [47] stringr_1.5.1 zlibbioc_1.49.3 +#> [49] ggthemes_5.1.0 BiocManager_1.30.22 +#> [51] XVector_0.43.1 matrixStats_1.2.0 +#> [53] vctrs_0.6.5 Matrix_1.6-5 +#> [55] jsonlite_1.8.8 bookdown_0.38 +#> [57] IRanges_2.37.1 S4Vectors_0.41.5 +#> [59] bit64_4.0.5 crosstalk_1.2.1 +#> [61] systemfonts_1.0.6 jquerylib_0.1.4 +#> [63] glue_1.7.0 pkgdown_2.0.7.9000 +#> [65] cowplot_1.1.3 stringi_1.8.3 +#> [67] gtable_0.3.4 GenomeInfoDb_1.39.9 +#> [69] GenomicRanges_1.55.4 munsell_0.5.0 +#> [71] tibble_3.2.1 pillar_1.9.0 +#> [73] htmltools_0.5.7 GenomeInfoDbData_1.2.11 +#> [75] R6_2.5.1 dbplyr_2.5.0 +#> [77] textshaping_0.3.7 evaluate_0.23 +#> [79] lattice_0.22-6 Biobase_2.63.0 +#> [81] memoise_2.0.1 bslib_0.6.1 +#> [83] Rcpp_1.0.12 gridExtra_2.3 +#> [85] SparseArray_1.3.4 xfun_0.42 +#> [87] fs_1.6.3 MatrixGenerics_1.15.0 +#> [89] pkgconfig_2.0.3
Lloyd GR, Weber RJM (2024). MetMashR: Metabolite Mashing with R. -R package version 0.1.0, https://computational-metabolomics.github.io/MetMashR/. +R package version 0.99.0, https://computational-metabolomics.github.io/MetMashR/.
@Manual{, title = {MetMashR: Metabolite Mashing with R}, author = {Gavin Rhys Lloyd and Ralf Johannes Maria Weber}, year = {2024}, - note = {R package version 0.1.0}, + note = {R package version 0.99.0}, url = {https://computational-metabolomics.github.io/MetMashR/}, }
R/AnnotationDb_database.R
AnnotationDb_database.Rd
Retrieve a table from an AnnotationDb package.
AnnotationDb_database(source, table, ...)
(character) The name of an AnnotationDb package to import the specified table from. Note the package should already be installed.
(character) The name of a table to import from the specified source AnnotationDb package.
Additional slots and values passed to struct_class.
struct_class
A +AnnotationDb_database + object. This object has no output slots.
+AnnotationDb_database +
output
This object makes use of functionality from the following packages:
AnnotationDbi
A AnnotationDb_database object inherits the following struct classes: [AnnotationDb_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
AnnotationDb_database
struct
[AnnotationDb_database]
[annotation_database]
[annotation_source]
[struct_class]
Pagès H, Carlson M, Falcon S, Li N (2023). AnnotationDbi: Manipulation +of SQLite-based annotations in Bioconductor. +doi:10.18129/B9.bioc.AnnotationDbi +https://doi.org/10.18129/B9.bioc.AnnotationDbi, R package version +1.65.2, https://bioconductor.org/packages/AnnotationDbi.
AnnotationDbi::AnnotationDb
Other annotation databases: +GO_database, +annotation_database, +annotation_source, +rdata_database, +rds_cache, +rds_database
GO_database
rdata_database
rds_cache
M = AnnotationDb_database( + table = character(0), + tag = character(0), + data = data.frame(id=NA), + source = character(0)) + +
R/AnnotationDb_select_class.R
AnnotationDb_select.Rd
A wrapper around [annotationDbi::select()] that can be used to import columns from the database where the keys are provided by a column in the annotation table.
[annotationDbi::select()]
AnnotationDb_select( + database, + key_column, + key_type, + database_columns, + drop_na = TRUE, + ... +)
(character) The name of the AnnotationDbi package/object to import.
(character) The name of a column in the annotation table containing key values used to extract records from the AnnotationDbi database.
(character) The name of a column in the AnnoationDb database searched for matches to the key values.
(character) The name of columns to import from the AnnoationDb database. Special case .all can be used to get all columns.
.all
(logical) Drop NA. Allowed values are limited to the following:
"TRUE": Remove rows where all columns of the returned database are NA.
"TRUE"
"FALSE": Keep rows where all columns of the returned database are NA.
"FALSE"
The default is TRUE.
TRUE
A AnnotationDb_select object with the following output slots:
AnnotationDb_select
updated
dplyr
A AnnotationDb_select object inherits the following struct classes: [AnnotationDb_select] >> [model] >> [struct_class]
[AnnotationDb_select]
[model]
Wickham H, François R, Henry L, Müller K, Vaughan D (2023). dplyr: A +Grammar of Data Manipulation. R package version 1.1.4, +https://CRAN.R-project.org/package=dplyr.
dplyr::left_join()
AnnotationDbi::select()
M = AnnotationDb_select( + database = "", + key_column = "", + key_type = "", + database_columns = ".all", + drop_na = FALSE) + +
A BiocFileCache_database object inherits the following struct classes: BiocFileCache_database() ⭢ annotation_database() ⭢ annotation_source() ⭢ struct_class()
BiocFileCache_database
BiocFileCache_database()
annotation_database()
annotation_source()
struct_class()
A BiocFileCache_database object inherits the following struct classes: [BiocFileCache_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
[BiocFileCache_database]
Shepherd L, Morgan M (2023). BiocFileCache: Manage Files Across Sessions. doi:10.18129/B9.bioc.BiocFileCache https://doi.org/10.18129/B9.bioc.BiocFileCache, R package version -2.10.1, https://bioconductor.org/packages/BiocFileCache.
M = BiocFileCache_database( + bfc_path = NULL, + resource_name = "bfc", + bfc_fun = function(){}, + import_fun = function(){}, + offline = FALSE, + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
A CompoundDb_source object inherits the following struct classes: CompoundDb_source() ⭢ annotation_source() ⭢ struct_class()
CompoundDb_source
CompoundDb_source()
A CompoundDb_source object inherits the following struct classes: [CompoundDb_source] >> [annotation_source] >> [struct_class]
[CompoundDb_source]
M = CompoundDb_source( + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
R/go_database_class.R
GO_database.Rd
Retrieve a table from the Gene Ontology using the GO.db package.
GO.db
GO_database(source = "GO.db", table = "GOBPOFFSPRING", ...)
(character) The name of an AnnotationDb package to import the specified table from. Note the package should already be installed. The default is "GO.db".
"GO.db"
(character) The name of a table to import from the GO.db package. Allowed tables include: GOBPANCESTOR,GOBPPARENTS,GOBPCHILDREN,GOBPOFFSPRING (and their CC or MF equivalents), GOTERM, GOSYNONYM, GOOBSOLETE. The default is "GOBPOFFSPRING".
"GOBPOFFSPRING"
A +GO_database + object. This object has no output slots.
+GO_database +
A GO_database object inherits the following struct classes: [GO_database] >> [AnnotationDb_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
[GO_database]
Carlson M (2023). GO.db: A set of annotation maps describing the +entire Gene Ontology. R package version 3.18.0.
GO.db::GO()
Other annotation databases: +AnnotationDb_database, +annotation_database, +annotation_source, +rdata_database, +rds_cache, +rds_database
M = GO_database( + table = "GOBPCHILDREN", + tag = character(0), + data = data.frame(id=NA), + source = character(0)) + +
(character) The version number of the MTox700+ database to import. Available versions are listed here: https://github.com/michabohealthscience/MTox700plus/releases. version should match the tag of thr release e.g. "v1.0". For convenience version = "latest" will always retrieve the most recent release. To prevent unecessary downloads BiocFileCache is used to store a local copy. The default is "latest".
version
"v1.0"
version = "latest"
BiocFileCache
"latest"
(character) The version number of the MTox700+ database to import. Available versions are listed here: https://github.com/michabohealthscience/MTox700plus/releases. version should match the tag of the release e.g. "v1.0". For convenience version = "latest" will always retrieve the most recent release. To prevent unecessary downloads BiocFileCache is used to store a local copy. The default is "latest".
A MTox700plus_database object inherits the following struct classes: MTox700plus_database() ⭢ BiocFileCache_database() ⭢ annotation_database() ⭢ annotation_source() ⭢ struct_class()
MTox700plus_database
MTox700plus_database()
A MTox700plus_database object inherits the following struct classes: [MTox700plus_database] >> [BiocFileCache_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
[MTox700plus_database]
Wickham H (2023). httr: Tools for Working with URLs and HTTP. R package version 1.4.7, https://CRAN.R-project.org/package=httr.
Sostare E, Lawson TN, Saunders LR, Colbourne JK, Weber RJM, Sobanski T, @@ -139,7 +139,18 @@
M = MTox700plus_database( + version = "v1.0", + bfc_path = NULL, + resource_name = "bfc", + bfc_fun = function(){}, + import_fun = function(){}, + offline = FALSE, + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
R/MetMashR-package.R
MetMashR-package.Rd
A package to merge, filter sort, organise and otherwise mash together metabolite annotation tables. Metabolite annotations can be imported from multiple sources (software) and combined using workflow steps based on S4 class templates derived from the `struct` package. Other modular workflow such as filtering, merging, splitting, normalisation and rest-api queries are also included.
Useful links:
https://computational-metabolomics.github.io/MetMashR/
Report bugs at https://github.com/computational-metabolomics/MetMashR/issues
Maintainer: Gavin Rhys Lloyd g.r.lloyd@bham.ac.uk (ORCID)
Authors:
Ralf Johannes Maria Weber r.j.weber@bham.ac.uk
A PathBank_metabolite_database object inherits the following struct classes: PathBank_metabolite_database() ⭢ BiocFileCache_database() ⭢ annotation_database() ⭢ annotation_source() ⭢ struct_class()
PathBank_metabolite_database
PathBank_metabolite_database()
A PathBank_metabolite_database object inherits the following struct classes: [PathBank_metabolite_database] >> [BiocFileCache_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
[PathBank_metabolite_database]
Wishart, S D, Li, Carin, Marcu, Ana, Badran, Hasan, Pon, Allison, @@ -144,7 +144,18 @@
M = PathBank_metabolite_database( + version = "primary", + bfc_path = NULL, + resource_name = "bfc", + bfc_fun = function(){}, + import_fun = function(){}, + offline = FALSE, + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
A add_columns object inherits the following struct classes: add_columns() ⭢ model() ⭢ struct_class()
add_columns
add_columns()
model()
A add_columns object inherits the following struct classes: [add_columns] >> [model] >> [struct_class]
[add_columns]
Wickham H, François R, Henry L, Müller K, Vaughan D (2023). dplyr: A -Grammar of Data Manipulation. R package version 1.1.3, +Grammar of Data Manipulation. R package version 1.1.4, https://CRAN.R-project.org/package=dplyr.
A add_labels object inherits the following struct classes: add_labels() ⭢ model() ⭢ struct_class()
add_labels
add_labels()
A add_labels object inherits the following struct classes: [add_labels] >> [model] >> [struct_class]
[add_labels]
A annotation_pie_chart object inherits the following struct classes: annotation_pie_chart() ⭢ chart() ⭢ struct_class()
annotation_pie_chart
annotation_pie_chart()
chart()
A annotation_pie_chart object inherits the following struct classes: [annotation_pie_chart] >> [chart] >> [struct_class]
[annotation_pie_chart]
[chart]
(data.frame) A data.frame of annotation data. The default is data.frame().
data.frame()
(data.frame, NULL) A data.frame of annotation data. The default is data.frame().
A annotation_database object inherits the following struct classes: annotation_database() ⭢ annotation_source() ⭢ struct_class()
A annotation_database object inherits the following struct classes: [annotation_database] >> [annotation_source] >> [struct_class]
Other annotation databases: +AnnotationDb_database, +GO_database, annotation_source, +rdata_database, +rds_cache, rds_database
Other annotation sources: annotation_table, @@ -122,7 +126,12 @@
M = annotation_database( + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
A annotation_histogram object inherits the following struct classes: annotation_histogram() ⭢ chart() ⭢ struct_class()
annotation_histogram
annotation_histogram()
A annotation_histogram object inherits the following struct classes: [annotation_histogram] >> [chart] >> [struct_class]
[annotation_histogram]
A annotation_histogram2d object inherits the following struct classes: annotation_histogram2d() ⭢ annotation_histogram() ⭢ chart() ⭢ struct_class()
annotation_histogram2d
annotation_histogram2d()
A annotation_histogram2d object inherits the following struct classes: [annotation_histogram2d] >> [annotation_histogram] >> [chart] >> [struct_class]
[annotation_histogram2d]
Other annotation databases: +AnnotationDb_database, +GO_database, annotation_database, +rdata_database, +rds_cache, rds_database
annotation_table( - data = data.frame(id = character(0)), - tag = "", - id_column = "id", - ... -)
annotation_table(data = data.frame(), tag = "", id_column = NULL, ...)
(data.frame) A data.frame of annotation data. The default is data.frame(id = character(0)).
data.frame(id = character(0))
(character) The column name of the annotation data.frame containing row identifers. If NULL This will be generated automatically. The default is NULL.
NULL
A annotation_table object inherits the following struct classes: annotation_table() ⭢ annotation_source() ⭢ struct_class()
annotation_table()
A annotation_table object inherits the following struct classes: [annotation_table] >> [annotation_source] >> [struct_class]
[annotation_table]
Other annotation tables: -MetFrag_source, cd_source, ls_source
MetFrag_source
cd_source
ls_source
Other annotation sources: @@ -135,7 +129,13 @@
M = annotation_table( + id_column = "id", + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
A annotation_venn_chart object inherits the following struct classes: annotation_venn_chart() ⭢ chart() ⭢ struct_class()
annotation_venn_chart
annotation_venn_chart()
A annotation_venn_chart object inherits the following struct classes: [annotation_venn_chart] >> [chart] >> [struct_class]
[annotation_venn_chart]
Akyol T (2019). RVenn: Set Operations for Many Sets. R package version 1.1.0, https://CRAN.R-project.org/package=RVenn.
Gao C (2023). ggVennDiagram: A 'ggplot2' Implement of Venn Diagram. R -package version 1.4.9, +
Gao C, Dusa A (2024). ggVennDiagram: A 'ggplot2' Implement of Venn +Diagram. R package version 1.5.2, https://CRAN.R-project.org/package=ggVennDiagram.
A calc_ppm_diff object inherits the following struct classes: calc_ppm_diff() ⭢ model() ⭢ struct_class()
calc_ppm_diff
calc_ppm_diff()
A calc_ppm_diff object inherits the following struct classes: [calc_ppm_diff] >> [model] >> [struct_class]
[calc_ppm_diff]
A calc_rt_diff object inherits the following struct classes: calc_rt_diff() ⭢ model() ⭢ struct_class()
calc_rt_diff
calc_rt_diff()
A calc_rt_diff object inherits the following struct classes: [calc_rt_diff] >> [model] >> [struct_class]
[calc_rt_diff]
cd_source(source, sheets = c(1, 1), tag = "CD", ...)
cd_source( + source, + sheets = c(1, 1), + tag = "CD", + mz_column = "mz", + rt_column = "rt", + id_column = "id", + ... +)
(character) The column name of the annotation data.frame containing m/z values. The default is "mz".
"mz"
(character) The column name of the annotation data.frame containing retention time values. The default is "rt".
"rt"
(character) The column name of the annotation data.frame containing row identifers. If NULL This will be generated automatically. The default is "id".
"id"
A cd_source object inherits the following struct classes: cd_source() ⭢ lcms_table() ⭢ annotation_table() ⭢ annotation_source() ⭢ struct_class()
cd_source()
lcms_table()
A cd_source object inherits the following struct classes: [cd_source] >> [lcms_table] >> [annotation_table] >> [annotation_source] >> [struct_class]
[cd_source]
[lcms_table]
mspurity_source
Other annotation tables: -MetFrag_source, annotation_table, ls_source
# test if column present -AT = annotation_source(data.frame(id = character(0))) +AT <- annotation_source(data.frame(id = character(0))) #> Error in validObject(obj): invalid class “entity” object: ANY: class of value must match "type" -check_for_columns(AT,'id') # TRUE +check_for_columns(AT, "id") # TRUE #> Error in h(simpleError(msg, call)): error in evaluating the argument 'obj' in selecting a method for function 'check_for_columns': object 'AT' not found -check_for_columns(AT,'cake') # FALSE +check_for_columns(AT, "cake") # FALSE #> Error in h(simpleError(msg, call)): error in evaluating the argument 'obj' in selecting a method for function 'check_for_columns': object 'AT' not found # return a message if missing -check_for_columns(AT,'cake',msg = TRUE) +check_for_columns(AT, "cake", msg = TRUE) #> Error in h(simpleError(msg, call)): error in evaluating the argument 'obj' in selecting a method for function 'check_for_columns': object 'AT' not found
A classyfire_lookup object inherits the following struct classes: classyfire_lookup() ⭢ rest_api() ⭢ model() ⭢ struct_class()
classyfire_lookup
classyfire_lookup()
rest_api()
A classyfire_lookup object inherits the following struct classes: [classyfire_lookup] >> [rest_api] >> [model] >> [struct_class]
[classyfire_lookup]
[rest_api]
R/combine_columns_class.R
combine_columns.Rd
Several columns are merged into a single column. If multiple columns contain overlapping values then priority can be given columns earlier in the list.
A wrapper for paste() and interaction(). Combines the values in multiple columns row-wise.
paste()
interaction()
combine_columns( column_names, - output_name, - source_name, - source_tags = column_names, + separator = "_", + prefix = NULL, + suffix = NULL, + output_column = "combined", clean = TRUE, ... )
(character) The name(s) of column(s) to be combined.
(character) The column name(s) in the annotation_source to combine.
(character) The name of the new column.
(character) A string placed in between the two being joined. The default is "_".
"_"
(character) The column name used to indicate the where the merged values originated.
(character, NULL) A string placed at the start of the combined strings. The default is NULL.
(character) The tags used to identify the source of each item in the new column. A tag should be provided for each column_name. By default the column name is used.
(character, NULL) A string placed at the end of the combined strings. The default is NULL.
(character) The name of a column to store the combined values in. The default is "combined".
"combined"
A combine_columns object with the following output slots:
combine_columns
A combine_columns object inherits the following struct classes: combine_columns() ⭢ model() ⭢ struct_class()
combine_columns()
A combine_columns object inherits the following struct classes: [combine_columns] >> [model] >> [struct_class]
[combine_columns]
M = combine_columns( column_names = "V1", - output_name = "", + separator = "_", + output_column = "combined", clean = FALSE, - source_name = "source_name", - source_tags = "x") + prefix = NULL, + suffix = NULL)
A combine_records object inherits the following struct classes: combine_records() ⭢ model() ⭢ struct_class()
combine_records()
A combine_records object inherits the following struct classes: [combine_records] >> [model] >> [struct_class]
[combine_records]
Lloyd GR, Jankevics A, Weber RJM (2020). "struct: an R/Bioconductor-based framework for standardized metabolomics data @@ -146,7 +146,7 @@
# Select matching records -M = combine_records( - group_by = 'example', - default_fcn = .select_match( - match_col = 'match_column', - match = 'find_me', - separator = ', ', - na_string = 'NA') - ) +M <- combine_records( + group_by = "example", + default_fcn = .select_match( + match_col = "match_column", + match = "find_me", + separator = ", ", + na_string = "NA" + ) +) #> Error in .select_match(match_col = "match_column", match = "find_me", separator = ", ", na_string = "NA"): unused argument (match = "find_me") # Collapse unique values -M = combine_records( - group_by = 'example', - default_fcn = .unique( - digits = 6, - separator = ', ', - na_string = 'NA') - ) +M <- combine_records( + group_by = "example", + default_fcn = .unique( + digits = 6, + separator = ", ", + na_string = "NA" + ) +) # Prioritise by source -M = combine_records( - group_by = 'InChiKey', - default_fcn = .prioritise( - match_col = 'source', - priority = c('CD','LS'), - separator = ' || ') +M <- combine_records( + group_by = "InChiKey", + default_fcn = .prioritise( + match_col = "source", + priority = c("CD", "LS"), + separator = " || " ) +) # Do nothing to all columns -M = combine_records( - group_by = 'InChiKey', - default_fcn = .nothing() - ) +M <- combine_records( + group_by = "InChiKey", + default_fcn = .nothing() +) # Add a column with the number of records with a matching inchikey -M = combine_records( - group_by = 'InChiKey', - fcns = list( - count = .count() - )) +M <- combine_records( + group_by = "InChiKey", + fcns = list( + count = .count() + ) +) # Select annotation with highest (best) grade -M = combine_records( - group_by = 'InChiKey', - default_fcn = .select_grade( - grade_col = 'grade', - keep_NA = FALSE, - upper_case = TRUE - )) +M <- combine_records( + group_by = "InChiKey", + default_fcn = .select_grade( + grade_col = "grade", + keep_NA = FALSE, + upper_case = TRUE + ) +)
(character, NULL) A named vector of columns names to be created by merging columns from individual sources. e.g. c('hello'='world') will rename the 'hello' column to 'world' if found in any of the tables. The default is NULL.
c('hello'='world')
(character, NULL) A list of column names to keep in the combined table (padded with NA) if detected in one of the input tables. Special case ".all" will keep all columns from all tables. The default is NULL.
(logical) Create a column of new identifiers for each annotation by merging the id from each source with the annotation tag. e.g.an annotation with id = "A1" for source tagged "XY" is given a new id "A1_XY" to prevent duplicate IDs from multiple sources. The default is FALSE.
FALSE
(character) The column name that will be created to contain a tag to indicate which source the annotation originated from. The default is "annotation_source".
"annotation_source"
(annotation_source) An annotation_source object to use as the base class for the combined sources. The default is annotation_source(name = "combined", description = paste0("A source created by combining two or ", "more sources")).
annotation_source(name = "combined", description = paste0("A source created by combining two or ", "more sources"))
A combine_sources object inherits the following struct classes: combine_sources() ⭢ model() ⭢ struct_class()
combine_sources
combine_sources()
A combine_sources object inherits the following struct classes: [combine_sources] >> [model] >> [struct_class]
[combine_sources]
A database_lookup object inherits the following struct classes: database_lookup() ⭢ model() ⭢ struct_class()
database_lookup
database_lookup()
A database_lookup object inherits the following struct classes: [database_lookup] >> [model] >> [struct_class]
[database_lookup]
M = BiocFileCache_database( + M <- BiocFileCache_database( path = tempfile(), - resource_name = 'example', - bfc_fun=.cache_as_is) + resource_name = "example", + bfc_fun = .cache_as_is +) #> Error in BiocFileCache_database(path = tempfile(), resource_name = "example", bfc_fun = .cache_as_is): argument "source" is missing, with no default @@ -119,7 +120,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
M <- BiocFileCache_database( path = tempfile(), - resource_name = 'example', - bfc_fun=.cache_as_is) + resource_name = "example", + bfc_fun = .cache_as_is +) #> Error in BiocFileCache_database(path = tempfile(), resource_name = "example", bfc_fun = .cache_as_is): argument "source" is missing, with no default
M = normalise_strings( - search_column ='example', - output_column = 'result', + M <- normalise_strings( + search_column = "example", + output_column = "result", dictionary = .greek_dictionary ) @@ -115,7 +115,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
M <- normalise_strings( + search_column = "example", + output_column = "result", dictionary = .greek_dictionary ) @@ -115,7 +115,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
M = normalise_strings( - search_column ='example', - output_column = 'result', + M <- normalise_strings( + search_column = "example", + output_column = "result", dictionary = .racemic_dictionary ) @@ -115,7 +115,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
M <- normalise_strings( + search_column = "example", + output_column = "result", dictionary = .racemic_dictionary ) @@ -115,7 +115,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
M = normalise_strings( - search_column ='example', - output_column = 'result', + M <- normalise_strings( + search_column = "example", + output_column = "result", dictionary = .amino_acid_dictionary ) #> Error in eval(expr, envir, enclos): object '.amino_acid_dictionary' not found @@ -119,7 +119,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
M <- normalise_strings( + search_column = "example", + output_column = "result", dictionary = .amino_acid_dictionary ) #> Error in eval(expr, envir, enclos): object '.amino_acid_dictionary' not found @@ -119,7 +119,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
M = BiocFileCache_database( + M <- BiocFileCache_database( path = tempfile(), - resource_name = 'example', - bfc_fun=.unzip) + resource_name = "example", + bfc_fun = .unzip +) #> Error in BiocFileCache_database(path = tempfile(), resource_name = "example", bfc_fun = .unzip): argument "source" is missing, with no default @@ -125,7 +126,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
M <- BiocFileCache_database( path = tempfile(), - resource_name = 'example', - bfc_fun=.unzip) + resource_name = "example", + bfc_fun = .unzip +) #> Error in BiocFileCache_database(path = tempfile(), resource_name = "example", bfc_fun = .unzip): argument "source" is missing, with no default
R/eutils_lookup_class.R
eutils_lookup.Rd
Submit a query to one of the NCBI E-utils databases. See https://www.ncbi.nlm.nih.gov/books/NBK25501/ for details.
eutils_lookup(query_column, database, term, result_fields = "idlist", ...)
(character) The column name to use as the reference for searching the database e.g. "HMBD_ID".
(character) The name of the E-utils database to search. See https://www.ncbi.nlm.nih.gov/books/NBK25501/ for details.
(character) A correctly formated search term to use with E-utils. See https://www.ncbi.nlm.nih.gov/books/NBK25501/ for details. When used with the provided url template will automatically include the value from the query_column at the beginning of the term.
query_column
(character) The name of the search result field to return. For E-utils this is often "idlist". The default is "idlist".
"idlist"
A eutils_lookup object with the following output slots:
eutils_lookup
A eutils_lookup object inherits the following struct classes: [eutils_lookup] >> [rest_api] >> [model] >> [struct_class]
[eutils_lookup]
M = eutils_lookup( + database = "gene", + term = "[pdat]", + result_fields = "idlist", + base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils", + url_template = "<base_url>/esearch.fcgi?db=<database>&term=<query_column><term>&retmode=json", + query_column = character(0), + cache = NULL, + status_codes = list(), + delay = 0.5, + suffix = "_rest_api") + +
"FALSE": NA values will be treated as though they did not match to any of the labels.
The default is FALSE.
A filter_labels object inherits the following struct classes: filter_labels() ⭢ model() ⭢ struct_class()
filter_labels()
A filter_labels object inherits the following struct classes: [filter_labels] >> [model] >> [struct_class]
[filter_labels]
A filter_na object inherits the following struct classes: filter_na() ⭢ model() ⭢ struct_class()
filter_na
filter_na()
A filter_na object inherits the following struct classes: [filter_na] >> [model] >> [struct_class]
[filter_na]
Removes annotations where the names column is greater than an upper limit or less than a lower limit.
A filter_range object inherits the following struct classes: filter_range() ⭢ model() ⭢ struct_class()
filter_range
filter_range()
A filter_range object inherits the following struct classes: [filter_range] >> [model] >> [struct_class]
[filter_range]
A filter_venn object inherits the following struct classes: filter_venn() ⭢ model() ⭢ struct_class()
filter_venn
filter_venn()
A filter_venn object inherits the following struct classes: [filter_venn] >> [model] >> [struct_class]
[filter_venn]
R/github_file_class.R
github_file.Rd
Uses the GitHub REST API to retrieve a file from a specifiedGitHub repository.
github_file( + username, + repository_name, + file_path, + bfc_path = NULL, + resource_name = paste(username, repository_name, file_path, sep = "_"), + ... +)
(character) The GitHub username to retireve the file from.
(character) The name of a repository for the specified GitHub usernamethat contains the file to download.
(character) The path to the file to download within the specified GitHub repository.
(character, NULL) BiocFileCache is used to cache the database locally and prevent unnecessary downloads. If a path is provided then BiocFileCache will use this location. If NULL it will use the default location (see BiocFileCache::BiocFileCache() for details). The default is NULL.
BiocFileCache::BiocFileCache()
(character) The name given to this resource in the cache. (see BiocFileCache::BiocFileCache() for details). The default is paste(username, repository_name, file_path, sep = "_").
paste(username, repository_name, file_path, sep = "_")
A +github_file + object. This object has no output slots.
+github_file +
httr
A github_file object inherits the following struct classes: [github_file] >> [BiocFileCache_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
github_file
[github_file]
Shepherd L, Morgan M (2023). BiocFileCache: Manage Files Across +Sessions. doi:10.18129/B9.bioc.BiocFileCache +https://doi.org/10.18129/B9.bioc.BiocFileCache, R package version +2.11.1, https://bioconductor.org/packages/BiocFileCache.
Wickham H (2023). httr: Tools for Working with URLs and HTTP. R +package version 1.4.7, https://CRAN.R-project.org/package=httr.
M = github_file( + username = character(0), + repository_name = character(0), + file_path = character(0), + bfc_path = NULL, + resource_name = "bfc", + bfc_fun = function(){}, + import_fun = function(){}, + offline = FALSE, + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
A hmdb_lookup object inherits the following struct classes: hmdb_lookup() ⭢ rest_api() ⭢ model() ⭢ struct_class()
hmdb_lookup
hmdb_lookup()
A hmdb_lookup object inherits the following struct classes: [hmdb_lookup] >> [rest_api] >> [model] >> [struct_class]
[hmdb_lookup]
Temple Lang D (2023). XML: Tools for Parsing and Generating XML Within -R and S-Plus. R package version 3.99-0.16, +
Temple Lang D (2024). XML: Tools for Parsing and Generating XML Within +R and S-Plus. R package version 3.99-0.16.1, https://CRAN.R-project.org/package=XML.
A id_counts object inherits the following struct classes: id_counts() ⭢ model() ⭢ struct_class()
id_counts
id_counts()
A id_counts object inherits the following struct classes: [id_counts] >> [model] >> [struct_class]
[id_counts]
A import_source object inherits the following struct classes: import_source() ⭢ model() ⭢ struct_class()
import_source
import_source()
A import_source object inherits the following struct classes: [import_source] >> [model] >> [struct_class]
[import_source]
M = import_source() + +
GO_database()
rds_database()
github_file()
is_writable()
prioritise_columns()
concatenate_columns()
select_columns()
split_column()
split_records()
AnnotationDb_select()
Various supporting functions are used by MetMashR
Supporting functions are used by MetMashR
check_for_columns()
required_cols()
-M = annotation_database() +M <- annotation_database() is.writable(M) #> Error in is.writable(M): could not find function "is.writable" @@ -115,7 +115,7 @@ Examples - Site built with pkgdown 2.0.7. + Site built with pkgdown 2.0.7.9000.
A kegg_lookup object inherits the following struct classes: kegg_lookup() ⭢ model() ⭢ struct_class()
kegg_lookup
kegg_lookup()
A kegg_lookup object inherits the following struct classes: [kegg_lookup] >> [model] >> [struct_class]
[kegg_lookup]
Tenenbaum D, Maintainer B (2023). KEGGREST: Client-side REST access to the Kyoto Encyclopedia of Genes and Genomes (KEGG). doi:10.18129/B9.bioc.KEGGREST -https://doi.org/10.18129/B9.bioc.KEGGREST, R package version 1.42.0, +https://doi.org/10.18129/B9.bioc.KEGGREST, R package version 1.43.0, https://bioconductor.org/packages/KEGGREST.
R/annotation_table_class.R
R/lcms_table_class.R
lcms_table.Rd
An annotation_table is an annotation_source() where the imported data.frame contains measured experimental data. An -id_column of values is required to uniquely indentify each record (row) in the table (NB these are NOT molecule identifiers, which may be be present in multiple records).
id_column
An LCMS table extends annotation_table() to represent annotation data for an LCMS experiment. Columns representing m/z and retention time are required for an lcms_table.
lcms_table
lcms_table( - data = data.frame(id = numeric(0), mz = numeric(0), rt = numeric(0)), + data = NULL, tag = "", id_column = "id", mz_column = "mz", @@ -93,7 +90,7 @@ Usage Arguments data -(data.frame) A data.frame of annotation data. The default is data.frame(id = character(0)). +(data.frame, NULL) A data.frame of annotation data. The default is NULL. tag @@ -104,6 +101,14 @@ Arguments. +mz_column +(character) The column name of the annotation data.frame containing m/z values. The default is "mz". + + +rt_column +(character) The column name of the annotation data.frame containing retention time values. The default is "rt". + + ... Additional slots and values passed to struct_class. @@ -113,19 +118,28 @@ ValueA -annotation_table +lcms_table object. This object has no output slots. Inheritance -A annotation_table object inherits the following struct classes: annotation_table() ⭢ annotation_source() ⭢ struct_class() +A lcms_table object inherits the following struct classes: [lcms_table] >> [annotation_table] >> [annotation_source] >> [struct_class] Examples - + M = lcms_table( + mz_column = "mz", + rt_column = "rt", + id_column = "id", + tag = character(0), + data = data.frame(id=NA), + source = "ANY") +#> Error in validObject(.Object): invalid class “lcms_table” object: Column(s) named "mz","id","rt" must be present in the data.frame for this source. + +
(data.frame, NULL) A data.frame of annotation data. The default is NULL.
-annotation_table +lcms_table
A lcms_table object inherits the following struct classes: [lcms_table] >> [annotation_table] >> [annotation_source] >> [struct_class]
M = lcms_table( + mz_column = "mz", + rt_column = "rt", + id_column = "id", + tag = character(0), + data = data.frame(id=NA), + source = "ANY") +#> Error in validObject(.Object): invalid class “lcms_table” object: Column(s) named "mz","id","rt" must be present in the data.frame for this source. + +
A lipidmaps_lookup object inherits the following struct classes: lipidmaps_lookup() ⭢ rest_api() ⭢ model() ⭢ struct_class()
lipidmaps_lookup
lipidmaps_lookup()
A lipidmaps_lookup object inherits the following struct classes: [lipidmaps_lookup] >> [rest_api] >> [model] >> [struct_class]
[lipidmaps_lookup]
ls_source(source, tag = "LS", ...)
ls_source( + source, + tag = "LS", + mz_column = "mz", + rt_column = "rt", + id_column = "id", + ... +)
A ls_source object inherits the following struct classes: ls_source() ⭢ lcms_table() ⭢ annotation_table() ⭢ annotation_source() ⭢ struct_class()
ls_source()
A ls_source object inherits the following struct classes: [ls_source] >> [lcms_table] >> [annotation_table] >> [annotation_source] >> [struct_class]
[ls_source]
Other annotation tables: -MetFrag_source, annotation_table, cd_source
M = ls_source( + mz_column = "mz", + rt_column = "rt", + id_column = "id", + tag = character(0), + data = data.frame(id=NA), + source = "ANY") +#> Error in validObject(.Object): invalid class “ls_source” object: Column(s) named "mz","rt","id" must be present in the data.frame for this source. + +
A mspurity_source object inherits the following struct classes: mspurity_source() ⭢ annotation_source() ⭢ struct_class()
mspurity_source()
A mspurity_source object inherits the following struct classes: [mspurity_source] >> [annotation_source] >> [struct_class]
[mspurity_source]
M = mspurity_source( + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
A mwb_compound_lookup object inherits the following struct classes: mwb_compound_lookup() ⭢ rest_api() ⭢ model() ⭢ struct_class()
mwb_compound_lookup
mwb_compound_lookup()
A mwb_compound_lookup object inherits the following struct classes: [mwb_compound_lookup] >> [rest_api] >> [model] >> [struct_class]
[mwb_compound_lookup]
Lloyd GR, Weber RJM (2023). metabolomicsWorkbenchR: Metabolomics Workbench in R. doi:10.18129/B9.bioc.metabolomicsWorkbenchR https://doi.org/10.18129/B9.bioc.metabolomicsWorkbenchR, R package -version 1.12.0, +version 1.13.0, https://bioconductor.org/packages/metabolomicsWorkbenchR.
A mwb_refmet_database object inherits the following struct classes: mwb_refmet_database() ⭢ annotation_database() ⭢ annotation_source() ⭢ struct_class()
mwb_refmet_database
mwb_refmet_database()
A mwb_refmet_database object inherits the following struct classes: [mwb_refmet_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
[mwb_refmet_database]
Wickham H (2011). "The Split-Apply-Combine Strategy for Data Analysis." @@ -125,7 +125,13 @@
M = mwb_refmet_database( + bfc = character(0), + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
metabolomicsWorkbenchR
This object queries the Metabolomics Workbench API for matches to your query without caching the results. It is therefore intended for limited -use. If you wish to obtain images for a large number of moelucules you should seek -an alternative solution.
A mwb_structure object inherits the following struct classes: mwb_structure() ⭢ chart() ⭢ struct_class()
mwb_structure
mwb_structure()
A mwb_structure object inherits the following struct classes: [mwb_structure] >> [chart] >> [struct_class]
[mwb_structure]
Wilke C (2023). cowplot: Streamlined Plot Theme and Plot Annotations -for 'ggplot2'. R package version 1.1.2, +
Wilke C (2024). cowplot: Streamlined Plot Theme and Plot Annotations +for 'ggplot2'. R package version 1.1.3, https://CRAN.R-project.org/package=cowplot.
(numeric, integer) Ppm window to use for matching. If a single value is provided then the same ppm is used for both variable meta and the annotations. A named vector can also be provided e.g. c("variable_meta"=5,"annotations"=2) to use ", +"different windows for each data table.
A mz_match object inherits the following struct classes: mz_match() ⭢ model() ⭢ struct_class()
mz_match
mz_match()
A mz_match object inherits the following struct classes: [mz_match] >> [model] >> [struct_class]
[mz_match]
(numeric, integer) Ppm window to use for matching. If a single value is provided then the same ppm is used for both variable meta and the annotations. A named vector can also be provided e.g. c("variable_meta"=5,"annotations"=2) to use different ", +"windows for each data table.
(numeric, integer) Rt window to use for matching. If a single value is provided then the same rt is used for both variable meta and the annotations. A named vector can also be provided e.g. c("variable_meta"=5,"annotations"=2) to use different windows for each data table.
(numeric, integer) Rt window to use for matching. If a single value is provided then the same rt is used for both variable meta and the annotations. A named vector can also be provided e.g. c("variable_meta"=5,"annotations"=2) to use different ", +"windows for each data table.
(character) Column name of the variable ids in variable_meta. id_column="rownames" will use the rownames as ids.
(character) Column name of the variable ids in variable_meta. ", +"id_column="rownames" will use the rownames as ids.
A mzrt_match object inherits the following struct classes: mzrt_match() ⭢ model() ⭢ struct_class()
mzrt_match
mzrt_match()
A mzrt_match object inherits the following struct classes: [mzrt_match] >> [model] >> [struct_class]
[mzrt_match]
A normalise_lipids object inherits the following struct classes: normalise_lipids() ⭢ model() ⭢ struct_class()
normalise_lipids
normalise_lipids()
A normalise_lipids object inherits the following struct classes: [normalise_lipids] >> [model] >> [struct_class]
[normalise_lipids]
A normalise_strings object inherits the following struct classes: normalise_strings() ⭢ model() ⭢ struct_class()
normalise_strings
normalise_strings()
A normalise_strings object inherits the following struct classes: [normalise_strings] >> [model] >> [struct_class]
[normalise_strings]
A openbabel_structure object inherits the following struct classes: openbabel_structure() ⭢ chart() ⭢ struct_class()
openbabel_structure
openbabel_structure()
A openbabel_structure object inherits the following struct classes: [openbabel_structure] >> [chart] >> [struct_class]
[openbabel_structure]
Horan K, Girke T (2023). ChemmineOB: R interface to a subset of -OpenBabel functionalities. doi:10.18129/B9.bioc.ChemmineOB -https://doi.org/10.18129/B9.bioc.ChemmineOB, R package version -1.40.0, https://bioconductor.org/packages/ChemmineOB.
Horan K, Girke T (2024). ChemmineOB: R interface to a subset of +OpenBabel functionalities. R package version 1.41.2, +https://github.com/girke-lab/ChemmineOB.
Ooms J (2023). rsvg: Render SVG Images into PDF, PNG, (Encapsulated) PostScript, or Bitmap Arrays. R package version 2.6.0, @@ -211,7 +210,7 @@
A opsin_lookup object inherits the following struct classes: opsin_lookup() ⭢ rest_api() ⭢ model() ⭢ struct_class()
opsin_lookup
opsin_lookup()
A opsin_lookup object inherits the following struct classes: [opsin_lookup] >> [rest_api] >> [model] >> [struct_class]
[opsin_lookup]
R/prioritise_columns_class.R
prioritise_columns.Rd
prioritise_columns( + column_names, + output_name, + source_name, + source_tags = column_names, + clean = TRUE, + ... +)
(logical) Clean old columns. Allowed values are limited to the following:
"TRUE": The named columns are removed after being combined.
"FALSE": The named columns are retained after being combined.
A prioritise_columns object with the following output slots:
prioritise_columns
A prioritise_columns object inherits the following struct classes: [prioritise_columns] >> [model] >> [struct_class]
[prioritise_columns]
M = prioritise_columns( + column_names = "V1", + output_name = "", + clean = FALSE, + source_name = "source_name", + source_tags = "x") + +
A pubchem_compound_lookup object inherits the following struct classes: pubchem_compound_lookup() ⭢ rest_api() ⭢ model() ⭢ struct_class()
pubchem_compound_lookup
pubchem_compound_lookup()
A pubchem_compound_lookup object inherits the following struct classes: [pubchem_compound_lookup] >> [rest_api] >> [model] >> [struct_class]
[pubchem_compound_lookup]
A pubchem_property_lookup object inherits the following struct classes: pubchem_property_lookup() ⭢ pubchem_compound_lookup() ⭢ rest_api() ⭢ model() ⭢ struct_class()
pubchem_property_lookup
pubchem_property_lookup()
A pubchem_property_lookup object inherits the following struct classes: [pubchem_property_lookup] >> [pubchem_compound_lookup] >> [rest_api] >> [model] >> [struct_class]
[pubchem_property_lookup]
A pubchem_structure object inherits the following struct classes: pubchem_structure() ⭢ chart() ⭢ struct_class()
pubchem_structure
pubchem_structure()
A pubchem_structure object inherits the following struct classes: [pubchem_structure] >> [chart] >> [struct_class]
[pubchem_structure]
A pubchem_widget object inherits the following struct classes: pubchem_widget() ⭢ chart() ⭢ struct_class()
pubchem_widget
pubchem_widget()
A pubchem_widget object inherits the following struct classes: [pubchem_widget] >> [chart] >> [struct_class]
[pubchem_widget]
R/rdata_database_class.R
rdata_database.Rd
A data.frame stored as an RData file.
rdata_database(source = character(0), variable_name, ...)
(ANY) The source of annotation data. The default is character(0).
character(0)
(character, function) The name of the data.frame in the imported workspace to use as the data.frame for this source. A function can be provided to e.g. extract a data.frame from a list in the imported environment.
A +rdata_database + object. This object has no output slots.
+rdata_database +
A rdata_database object inherits the following struct classes: [rdata_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
[rdata_database]
Other annotation databases: +AnnotationDb_database, +GO_database, +annotation_database, +annotation_source, +rds_cache, +rds_database
M = rdata_database( + tag = character(0), + data = data.frame(id=NA), + source = "ANY") +#> Error in rdata_database(tag = character(0), data = data.frame(id = NA), source = "ANY"): argument "variable_name" is missing, with no default + +
R/rds_cache_class.R
rds_cache.Rd
A data.frame stored as an RDS file. Intended to be used with rest_api objects as mechanism for caching search results. The data.frame for an rds_cache object must have a column named ".search".
rds_cache( + source = character(0), + data = data.frame(.search = character(0)), + ... +)
(data.frame, NULL) A data.frame of annotation data. The default is data.frame(.search = character(0)).
data.frame(.search = character(0))
A +rds_cache + object. This object has no output slots.
+rds_cache +
A rds_cache object inherits the following struct classes: [rds_cache] >> [rds_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
[rds_cache]
[rds_database]
Other annotation databases: +AnnotationDb_database, +GO_database, +annotation_database, +annotation_source, +rdata_database, +rds_database
M = rds_cache( + tag = character(0), + data = data.frame(id=NA), + source = "ANY") +#> Error in validObject(.Object): invalid class “rds_cache” object: Column(s) named ".search" must be present in the data.frame for this source. + +
A rds_database object inherits the following struct classes: rds_database() ⭢ annotation_database() ⭢ annotation_source() ⭢ struct_class()
A rds_database object inherits the following struct classes: [rds_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
Other annotation databases: +AnnotationDb_database, +GO_database, annotation_database, -annotation_source
M = rds_database( + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
M = rds_database(tempfile()) -df = read_database(M) -#> Warning: cannot open compressed file '/tmp/RtmpEYRwVY/file100d2d423e63', probable reason 'No such file or directory' -#> Error in gzfile(file, "rb"): cannot open the connection + M <- rds_database(tempfile()) +df <- read_database(M)
M <- rds_database(tempfile()) +df <- read_database(M)
Import an data from e.g. a raw file and parse it into an annotation_source() -object.
Import an data from e.g. a raw file and parse it into an +annotation_source() object.
# prepare source -CD = cd_source( - source = system.file( - paste0('extdata/MTox/CD/HILIC_POS.xlsx'), - package = 'MetMasheR') - ) +CD <- cd_source( + source = system.file( + paste0("extdata/MTox/CD/HILIC_POS.xlsx"), + package = "MetMashR" + ) +)
R/generics.R
required_cols.Rd
Some annotation_sources, such as LCMS tables (lcms_table), require that +certain columns are present in the data.frame. These are defined by slots in +the source definition. The name of slots containing the required column names +for a source can be retrieved using the required_cols function, which will +collect and return the names of slots containing required column names for +the object and all of its parent objects.
annotation_sources
required_cols
required_cols(obj, ...)
an annotation_source object
a character vector of slot names
# prepare object +M <- lcms_table(id_column = "id", mz_column = "mz", rt_column = "rt") + +#' # get values for required slots +r <- required(M) +#> Error in required(M): could not find function "required" + +# get slot names for required columns +names(r) +#> Error in eval(expr, envir, enclos): object 'r' not found +
A rest_api object inherits the following struct classes: rest_api() ⭢ model() ⭢ struct_class()
A rest_api object inherits the following struct classes: [rest_api] >> [model] >> [struct_class]
A rt_match object inherits the following struct classes: rt_match() ⭢ model() ⭢ struct_class()
rt_match
rt_match()
A rt_match object inherits the following struct classes: [rt_match] >> [model] >> [struct_class]
[rt_match]
R/select_columns_class.R
select_columns.Rd
A wrapper around tidyselect::eval_select. Select columns from an annotation table using tidy grammar. This imitates dplyr::select().
tidyselect::eval_select
dplyr::select()
select_columns(expression = everything(), ...)
(call) A valid rlang::expr for tidy evaluation via eval_select. e.g. +expression = all_of(c("foo","bar")) will select columns +named "foo" and "bar" from the annotation data.frame. +. The default is everything().
expression = all_of(c("foo","bar"))
everything()
A select_columns object with the following output slots:
select_columns
tidyselect
rlang
A select_columns object inherits the following struct classes: [select_columns] >> [model] >> [struct_class]
[select_columns]
Henry L, Wickham H (2024). tidyselect: Select from a Set of Strings. +R package version 1.2.1, +https://CRAN.R-project.org/package=tidyselect.
Henry L, Wickham H (2024). rlang: Functions for Base Types and Core R +and 'Tidyverse' Features. R package version 1.1.3, +https://CRAN.R-project.org/package=rlang.
tidyselect::eval_select()
M = select_columns( + expression = call("example")) + +
R/split_column_class.R
split_column.Rd
A wrapper for strsplit. Divides a column into multiple columns by dividing the contents
strsplit
split_column(column_name, separator = "_", padding = NA, clean = TRUE, ...)
(character) The column name in the annotation_source split.
(character) A substring to split the column by. The default is "_".
(character, logical) Pad missing values. Allowed values are limited to the following:
Strings if after splitting.
The default is NA.
NA
"TRUE": The named columns are removed after being split.
"FALSE": The named columns are retained after being split.
A split_column object with the following output slots:
split_column
A split_column object inherits the following struct classes: [split_column] >> [model] >> [struct_class]
[split_column]
M = split_column( + column_name = "V1", + separator = "_", + clean = FALSE, + padding = "") + +
R/expand_records_class.R
split_records.Rd
Expand single records into multiple records by splitting strings in a named column at the chosen separator. For example, if a for a record the column synonyms = c("glucose,dextrose") then by splitting at the comma results in two records, one for glucose and one for dextrose with identical values (apart from the column being split). The original record is removed.
synonyms = c("glucose,dextrose")
split_records(column_name, separator, clean = TRUE, ...)
(character) The column name of the annotation_source to split intomultiple records.
(character) The substring used to split the values in column_name into multiple records.
(logical) Remove the original column. If FALSE the original column will be retained in the final output with .original appended to the column name. The default is TRUE.
A split_records object with the following output slots:
split_records
tidytext
A split_records object inherits the following struct classes: [split_records] >> [model] >> [struct_class]
[split_records]
Silge J, Robinson D (2016). "tidytext: Text Mining and Analysis Using +Tidy Data Principles in R." JOSS, 1(3). doi:10.21105/joss.00037 +https://doi.org/10.21105/joss.00037, +http://dx.doi.org/10.21105/joss.00037.
M = split_records( + column_name = character(0), + separator = ",", + clean = FALSE) + +
A sqlite_database object inherits the following struct classes: sqlite_database() ⭢ annotation_database() ⭢ annotation_source() ⭢ struct_class()
sqlite_database
sqlite_database()
A sqlite_database object inherits the following struct classes: [sqlite_database] >> [annotation_database] >> [annotation_source] >> [struct_class]
[sqlite_database]
Müller K, Wickham H, James DA, Falcon S (2023). RSQLite: SQLite -Interface for R. R package version 2.3.4, +
Müller K, Wickham H, James DA, Falcon S (2024). RSQLite: SQLite +Interface for R. R package version 2.3.5, https://CRAN.R-project.org/package=RSQLite.
M = sqlite_database( + table = character(0), + tag = character(0), + data = data.frame(id=NA), + source = "ANY") + +
A trim_whitespace object inherits the following struct classes: trim_whitespace() ⭢ model() ⭢ struct_class()
trim_whitespace
trim_whitespace()
A trim_whitespace object inherits the following struct classes: [trim_whitespace] >> [model] >> [struct_class]
[trim_whitespace]
-M = annotation_source() -N = annotation_source() -O = vertical_join(M,N) +M <- annotation_source() +N <- annotation_source() +O <- vertical_join(M, N) #> Error in select(., any_of(keep_cols)): Can't select within an unnamed vector.
M = rds_database(tempfile()) -write_database(M,data.frame()) + M <- rds_database(tempfile()) +write_database(M, data.frame())
M <- rds_database(tempfile()) +write_database(M, data.frame())