diff --git a/DESCRIPTION b/DESCRIPTION index 3396a01c..558e0511 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,6 +1,6 @@ Package: AMR -Version: 1.4.0.9012 -Date: 2020-11-05 +Version: 1.4.0.9013 +Date: 2020-11-09 Title: Antimicrobial Resistance Analysis Authors@R: c( person(role = c("aut", "cre"), diff --git a/NEWS.md b/NEWS.md index b533a07b..e8f2d755 100755 --- a/NEWS.md +++ b/NEWS.md @@ -1,8 +1,13 @@ -# AMR 1.4.0.9012 -## Last updated: 5 November 2020 +# AMR 1.4.0.9013 +## Last updated: 9 November 2020 ### New -* Functions `is_gram_negative()` and `is_gram_positive()` as wrappers around `mo_gramstain()`. They always return `TRUE` or `FALSE`, thus always return `FALSE` for species outside the taxonomic kingdom of Bacteria. +* Functions `is_gram_negative()` and `is_gram_positive()` as wrappers around `mo_gramstain()`. They always return `TRUE` or `FALSE` (except when the input is `NA` or the MO code is `UNKNOWN`), thus always return `FALSE` for species outside the taxonomic kingdom of Bacteria. If you have the `dplyr` package installed, they can even determine the column with microorganisms themselves inside `dplyr` functions: + ```r + example_isolates %>% + filter(is_gram_positive()) + #> NOTE: Using column `mo` as input for 'x' + ``` * Functions `%not_like%` and `%not_like_case%` as wrappers around `%like%` and `%like_case%`. The RStudio addin to insert the text " %like% " as provided in this package now iterates over all like variants. So if you have defined the keyboard shortcut Ctrl/Cmd + L to this addin, it will first insert ` %like% ` and by pressing it again it will be replaced with ` %not_like% `, etc. ### Changed diff --git a/R/ab_class_selectors.R b/R/ab_class_selectors.R index 7d58173c..54be0406 100644 --- a/R/ab_class_selectors.R +++ b/R/ab_class_selectors.R @@ -54,7 +54,7 @@ #' #' # get bug/drug combinations for only macrolides in Gram-positives: #' example_isolates %>% -#' filter(mo %>% is_gram_positive()) %>% +#' filter(is_gram_positive()) %>% #' select(mo, macrolides()) %>% #' bug_drug_combinations() %>% #' format() diff --git a/R/eucast_rules.R b/R/eucast_rules.R index 464910b3..f0a9b0dd 100755 --- a/R/eucast_rules.R +++ b/R/eucast_rules.R @@ -773,7 +773,7 @@ eucast_rules <- function(x, like_is_one_of <- trimws(eucast_rules_df[i, "like.is.one_of", drop = TRUE]) mo_value <- trimws(eucast_rules_df[i, "this_value", drop = TRUE]) - # be sure to comprise all coagulase-negative/-positive Staphylococci when they are mentioned + # be sure to comprise all coagulase-negative/-positive staphylococci when they are mentioned if (mo_value %like% "coagulase" && any(x$genus == "Staphylococcus", na.rm = TRUE)) { if (mo_value %like% "negative") { eucast_rules_df[i, "this_value"] <- paste0("^(", paste0(all_staph[which(all_staph$CNS_CPS %like% "negative"), diff --git a/R/mo.R b/R/mo.R index 3dccdf3c..08fb4a32 100755 --- a/R/mo.R +++ b/R/mo.R @@ -28,7 +28,7 @@ #' Use this function to determine a valid microorganism ID ([`mo`]). Determination is done using intelligent rules and the complete taxonomic kingdoms Bacteria, Chromista, Protozoa, Archaea and most microbial species from the kingdom Fungi (see Source). The input can be almost anything: a full name (like `"Staphylococcus aureus"`), an abbreviated name (like `"S. aureus"`), an abbreviation known in the field (like `"MRSA"`), or just a genus. Please see *Examples*. #' @inheritSection lifecycle Stable lifecycle #' @param x a character vector or a [data.frame] with one or two columns -#' @param Becker a logical to indicate whether *Staphylococci* should be categorised into coagulase-negative *Staphylococci* ("CoNS") and coagulase-positive *Staphylococci* ("CoPS") instead of their own species, according to Karsten Becker *et al.* (1,2,3). +#' @param Becker a logical to indicate whether staphylococci should be categorised into coagulase-negative staphylococci ("CoNS") and coagulase-positive staphylococci ("CoPS") instead of their own species, according to Karsten Becker *et al.* (1,2,3). #' #' This excludes *Staphylococcus aureus* at default, use `Becker = "all"` to also categorise *S. aureus* as "CoPS". #' @param Lancefield a logical to indicate whether beta-haemolytic *Streptococci* should be categorised into Lancefield groups instead of their own species, according to Rebecca C. Lancefield (4). These *Streptococci* will be categorised in their first group, e.g. *Streptococcus dysgalactiae* will be group C, although officially it was also categorised into groups G and L. diff --git a/R/mo_property.R b/R/mo_property.R index c5132733..7011fe06 100755 --- a/R/mo_property.R +++ b/R/mo_property.R @@ -41,7 +41,7 @@ #' #' Since the top-level of the taxonomy is sometimes referred to as 'kingdom' and sometimes as 'domain', the functions [mo_kingdom()] and [mo_domain()] return the exact same results. #' -#' The Gram stain - [mo_gramstain()] - will be determined based on the taxonomic kingdom and phylum. According to Cavalier-Smith (2002, [PMID 11837318](https://pubmed.ncbi.nlm.nih.gov/11837318)), who defined subkingdoms Negibacteria and Posibacteria, only these phyla are Posibacteria: Actinobacteria, Chloroflexi, Firmicutes and Tenericutes. These bacteria are considered Gram-positive - all other bacteria are considered Gram-negative. Species outside the kingdom of Bacteria will return a value `NA`. Functions [is_gram_negative()] and [is_gram_positive()] always return `TRUE` or `FALSE`, even for species outside the kingdom of Bacteria. +#' The Gram stain - [mo_gramstain()] - will be determined based on the taxonomic kingdom and phylum. According to Cavalier-Smith (2002, [PMID 11837318](https://pubmed.ncbi.nlm.nih.gov/11837318)), who defined subkingdoms Negibacteria and Posibacteria, only these phyla are Posibacteria: Actinobacteria, Chloroflexi, Firmicutes and Tenericutes. These bacteria are considered Gram-positive - all other bacteria are considered Gram-negative. Species outside the kingdom of Bacteria will return a value `NA`. Functions [is_gram_negative()] and [is_gram_positive()] always return `TRUE` or `FALSE` (except when the input is `NA` or the MO code is `UNKNOWN`), thus always return `FALSE` for species outside the taxonomic kingdom of Bacteria. #' #' All output will be [translate]d where possible. #' @@ -122,7 +122,7 @@ #' mo_shortname("S. pyo", Lancefield = TRUE) # "GAS" (='Group A Streptococci') #' #' -#' # language support for German, Dutch, Spanish, Portuguese, Italian and French +#' # language support -------------------------------------------------------- #' mo_gramstain("E. coli", language = "de") # "Gramnegativ" #' mo_gramstain("E. coli", language = "nl") # "Gram-negatief" #' mo_gramstain("E. coli", language = "es") # "Gram negativo" @@ -139,7 +139,11 @@ #' Lancefield = TRUE, #' language = "nl") # "Streptococcus groep A" #' +#' # gram stains can be used as a filter +#' example_isolates %>% +#' filter(is_gram_positive()) #' +#' # other -------------------------------------------------------------------- #' # get a list with the complete taxonomy (from kingdom to subspecies) #' mo_taxonomy("E. coli") #' # get a list with the taxonomy, the authors, Gram-stain and URL to the online database @@ -177,10 +181,10 @@ mo_shortname <- function(x, language = get_locale(), ...) { # exceptions for where no species is known shortnames[shortnames %like% ".[.] spp[.]"] <- genera[shortnames %like% ".[.] spp[.]"] - # exceptions for Staphylococci + # exceptions for staphylococci shortnames[shortnames == "S. coagulase-negative"] <- "CoNS" shortnames[shortnames == "S. coagulase-positive"] <- "CoPS" - # exceptions for Streptococci: Streptococcus Group A -> GAS + # exceptions for streptococci: Group A Streptococcus -> GAS shortnames[shortnames %like% "S. group [ABCDFGHK]"] <- paste0("G", gsub("S. group ([ABCDFGHK])", "\\1", shortnames[shortnames %like% "S. group [ABCDFGHK]"]), "S") # unknown species etc. shortnames[shortnames %like% "unknown"] <- paste0("(", trimws(gsub("[^a-zA-Z -]", "", shortnames[shortnames %like% "unknown"])), ")") @@ -311,6 +315,23 @@ mo_gramstain <- function(x, language = get_locale(), ...) { #' @rdname mo_property #' @export is_gram_negative <- function(x, language = get_locale(), ...) { + if (missing(x)) { + peek_mask_dplyr <- import_fn("peek_mask", "dplyr", error_on_fail = FALSE) + if (!is.null(peek_mask_dplyr)) { + try({ + df <- as.data.frame(peek_mask_dplyr()$across_cols(), stringsAsFactors = FALSE) + mo <- suppressMessages(search_type_in_df(df, "mo")) + if (!is.null(mo)) { + message_("Using column `", font_bold(mo), "` as input for 'x'") + x <- df[, mo, drop = TRUE] + } else { + stop_("Argument 'x' is missing") + } + }, silent = TRUE) + } else { + stop_("Argument 'x' is missing") + } + } meet_criteria(x, allow_NA = TRUE) meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE) @@ -318,12 +339,31 @@ is_gram_negative <- function(x, language = get_locale(), ...) { metadata <- get_mo_failures_uncertainties_renamed() grams <- mo_gramstain(x.mo, language = NULL) load_mo_failures_uncertainties_renamed(metadata) - grams == "Gram-negative" & !is.na(grams) + out <- grams == "Gram-negative" & !is.na(grams) + out[x.mo %in% c(NA, "UNKNOWN")] <- NA + out } #' @rdname mo_property #' @export is_gram_positive <- function(x, language = get_locale(), ...) { + if (missing(x)) { + peek_mask_dplyr <- import_fn("peek_mask", "dplyr", error_on_fail = FALSE) + if (!is.null(peek_mask_dplyr)) { + try({ + df <- as.data.frame(peek_mask_dplyr()$across_cols(), stringsAsFactors = FALSE) + mo <- suppressMessages(search_type_in_df(df, "mo")) + if (!is.null(mo)) { + message_("Using column `", font_bold(mo), "` as input for 'x'") + x <- df[, mo, drop = TRUE] + } else { + stop_("Argument 'x' is missing") + } + }, silent = TRUE) + } else { + stop_("Argument 'x' is missing") + } + } meet_criteria(x, allow_NA = TRUE) meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE) @@ -331,7 +371,9 @@ is_gram_positive <- function(x, language = get_locale(), ...) { metadata <- get_mo_failures_uncertainties_renamed() grams <- mo_gramstain(x.mo, language = NULL) load_mo_failures_uncertainties_renamed(metadata) - grams == "Gram-positive" & !is.na(grams) + out <- grams == "Gram-positive" & !is.na(grams) + out[x.mo %in% c(NA, "UNKNOWN")] <- NA + out } #' @rdname mo_property diff --git a/docs/404.html b/docs/404.html index e52ba3cd..e697ec40 100644 --- a/docs/404.html +++ b/docs/404.html @@ -81,7 +81,7 @@ AMR (for R) - 1.4.0.9012 + 1.4.0.9013 diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html index 7997ba76..88ded881 100644 --- a/docs/LICENSE-text.html +++ b/docs/LICENSE-text.html @@ -81,7 +81,7 @@ AMR (for R) - 1.4.0.9012 + 1.4.0.9013 diff --git a/docs/articles/index.html b/docs/articles/index.html index 176ce3e4..36ecae2e 100644 --- a/docs/articles/index.html +++ b/docs/articles/index.html @@ -81,7 +81,7 @@ AMR (for R) - 1.4.0.9012 + 1.4.0.9013 diff --git a/docs/authors.html b/docs/authors.html index e40b20ca..b01618be 100644 --- a/docs/authors.html +++ b/docs/authors.html @@ -81,7 +81,7 @@ AMR (for R) - 1.4.0.9012 + 1.4.0.9013 diff --git a/docs/index.html b/docs/index.html index 32495e37..fb58e2cc 100644 --- a/docs/index.html +++ b/docs/index.html @@ -43,7 +43,7 @@ AMR (for R) - 1.4.0.9012 + 1.4.0.9013 diff --git a/docs/news/index.html b/docs/news/index.html index 0f1ddc17..ad9a4558 100644 --- a/docs/news/index.html +++ b/docs/news/index.html @@ -81,7 +81,7 @@ AMR (for R) - 1.4.0.9012 + 1.4.0.9013 @@ -236,20 +236,26 @@ Source: NEWS.md -
-

-AMR 1.4.0.9012 Unreleased +
+

+AMR 1.4.0.9013 Unreleased

-
+

-Last updated: 5 November 2020 +Last updated: 9 November 2020

New

    -
  • Functions is_gram_negative() and is_gram_positive() as wrappers around mo_gramstain(). They always return TRUE or FALSE, thus always return FALSE for species outside the taxonomic kingdom of Bacteria.
    • -
  • Functions %not_like% and %not_like_case% as wrappers around %like% and %like_case%. The RStudio addin to insert the text " %like% " as provided in this package now iterates over all like variants. So if you have defined the keyboard shortcut Ctrl/Cmd + L to this addin, it will first insert %like% and by pressing it again it will be replaced with %not_like%, etc.
    • +
  • +

    Functions is_gram_negative() and is_gram_positive() as wrappers around mo_gramstain(). They always return TRUE or FALSE (except when the input is NA or the MO code is UNKNOWN), thus always return FALSE for species outside the taxonomic kingdom of Bacteria. If you have the dplyr package installed, they can even determine the column with microorganisms themselves inside dplyr functions:

    +
    +example_isolates %>%
+  filter(is_gram_positive())
+#> NOTE: Using column `mo` as input for 'x'
    +
    • +

  • Functions %not_like% and %not_like_case% as wrappers around %like% and %like_case%. The RStudio addin to insert the text " %like% " as provided in this package now iterates over all like variants. So if you have defined the keyboard shortcut Ctrl/Cmd + L to this addin, it will first insert %like% and by pressing it again it will be replaced with %not_like%, etc.

@@ -287,7 +293,7 @@

  • Data set intrinsic_resistant. This data set contains all bug-drug combinations where the ‘bug’ is intrinsic resistant to the ‘drug’ according to the latest EUCAST insights. It contains just two columns: microorganism and antibiotic.

    Curious about which enterococci are actually intrinsic resistant to vancomycin?

    -
    +
     library(AMR)
 library(dplyr)
 intrinsic_resistant %>%
@@ -309,7 +315,7 @@
 
      
 
    • 
 
      Support for using dplyr’s across() to interpret MIC values or disk zone diameters, which also automatically determines the column with microorganism names or codes.
      
-
      +
       # until dplyr 1.0.0
 your_data %>% mutate_if(is.mic, as.rsi)
 your_data %>% mutate_if(is.disk, as.rsi)
@@ -326,7 +332,7 @@
 
      • 
 
    • 
 
      Added intelligent data cleaning to as.disk(), so numbers can also be extracted from text and decimal numbers will always be rounded up:
      
-
      +
       as.disk(c("disk zone: 23.4 mm", 23.4))
 #> Class <disk>
 #> [1] 24 24
      
@@ -386,7 +392,7 @@
 
    • Function ab_from_text() to retrieve antimicrobial drug names, doses and forms of administration from clinical texts in e.g. health care records, which also corrects for misspelling since it uses as.ab() internally
      • 
 
    • 
 
      Tidyverse selection helpers for antibiotic classes, that help to select the columns of antibiotics that are of a specific antibiotic class, without the need to define the columns or antibiotic abbreviations. They can be used in any function that allows selection helpers, like dplyr::select() and tidyr::pivot_longer():
      
-
      +
       library(dplyr)
 
 # Columns 'IPM' and 'MEM' are in the example_isolates data set
@@ -574,7 +580,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
    • Fixed important floating point error for some MIC comparisons in EUCAST 2020 guideline
      • 
 
    • 
 
      Interpretation from MIC values (and disk zones) to R/SI can now be used with mutate_at() of the dplyr package:
      
-
      +
       yourdata %>% 
   mutate_at(vars(antibiotic1:antibiotic25), as.rsi, mo = "E. coli")
 
@@ -602,7 +608,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
        
 
      • 
 
        Support for LOINC codes in the antibiotics data set. Use ab_loinc() to retrieve LOINC codes, or use a LOINC code for input in any ab_* function:
        
-
        +
         ab_loinc("ampicillin")
 #> [1] "21066-6" "3355-5"  "33562-0" "33919-2" "43883-8" "43884-6" "87604-5"
 ab_name("21066-6")
@@ -612,7 +618,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
        • 
 
      • 
 
        Support for SNOMED CT codes in the microorganisms data set. Use mo_snomed() to retrieve SNOMED codes, or use a SNOMED code for input in any mo_* function:
        
-
        +
         mo_snomed("S. aureus")
 #> [1] 115329001   3092008 113961008
 mo_name(115329001)
@@ -676,10 +682,10 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
          
 
        • 
 
          If you were dependent on the old Enterobacteriaceae family e.g. by using in your code:
          
-
          +
           if (mo_family(somebugs) == "Enterobacteriaceae") ...
          
 
          then please adjust this to:
          
-
          +
           if (mo_order(somebugs) == "Enterobacterales") ...
          
 
          • 
 
        
@@ -692,7 +698,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
          
 
        • 
 
          Functions susceptibility() and resistance() as aliases of proportion_SI() and proportion_R(), respectively. These functions were added to make it more clear that “I” should be considered susceptible and not resistant.
          
-
          +
           library(dplyr)
 example_isolates %>%
   group_by(bug = mo_name(mo)) %>% 
@@ -720,7 +726,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
        • More intelligent way of coping with some consonants like “l” and “r”
          • 
 
        • 
 
          Added a score (a certainty percentage) to mo_uncertainties(), that is calculated using the Levenshtein distance:
          
-
          +
           as.mo(c("Stafylococcus aureus",
         "staphylokok aureuz"))
 #> Warning: 
@@ -778,13 +784,13 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
            
 
          • 
 
            Determination of first isolates now excludes all ‘unknown’ microorganisms at default, i.e. microbial code "UNKNOWN". They can be included with the new parameter include_unknown:
            
-
            +
             first_isolate(..., include_unknown = TRUE)
            
 
            For WHONET users, this means that all records/isolates with organism code "con" (contamination) will be excluded at default, since as.mo("con") = "UNKNOWN". The function always shows a note with the number of ‘unknown’ microorganisms that were included or excluded.
            
 
            • 
 
          • 
 
            For code consistency, classes ab and mo will now be preserved in any subsetting or assignment. For the sake of data integrity, this means that invalid assignments will now result in NA:
            
-
            +
             # how it works in base R:
 x <- factor("A")
 x[1] <- "B"
@@ -808,7 +814,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
              
 
            • 
 
              Function bug_drug_combinations() to quickly get a data.frame with the results of all bug-drug combinations in a data set. The column containing microorganism codes is guessed automatically and its input is transformed with mo_shortname() at default:
              
-
              +
               x <- bug_drug_combinations(example_isolates)
 #> NOTE: Using column `mo` as input for `col_mo`.
 x[1:4, ]
@@ -830,12 +836,12 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 #> 4 Gram-negative AMX 227  0 405   632
 #> NOTE: Use 'format()' on this result to get a publicable/printable format.
              
 
              You can format this to a printable format, ready for reporting or exporting to e.g. Excel with the base R format() function:
              
-
              +
               format(x, combine_IR = FALSE)
              
 
              • 
 
            • 
 
              Additional way to calculate co-resistance, i.e. when using multiple antimicrobials as input for portion_* functions or count_* functions. This can be used to determine the empiric susceptibility of a combination therapy. A new parameter only_all_tested (which defaults to FALSE) replaces the old also_single_tested and can be used to select one of the two methods to count isolates and calculate portions. The difference can be seen in this example table (which is also on the portion and count help pages), where the %SI is being determined:
              
-
              +
               # --------------------------------------------------------------------
 #                     only_all_tested = FALSE  only_all_tested = TRUE
 #                     -----------------------  -----------------------
@@ -856,7 +862,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
              • 
 
            • 
 
              tibble printing support for classes rsi, mic, disk, ab mo. When using tibbles containing antimicrobial columns, values S will print in green, values I will print in yellow and values R will print in red. Microbial IDs (class mo) will emphasise on the genus and species, not on the kingdom.
              
-
              +
               # (run this on your own console, as this page does not support colour printing)
 library(dplyr)
 example_isolates %>%
@@ -938,7 +944,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                
 
              • 
 
                Function rsi_df() to transform a data.frame to a data set containing only the microbial interpretation (S, I, R), the antibiotic, the percentage of S/I/R and the number of available isolates. This is a convenient combination of the existing functions count_df() and portion_df() to immediately show resistance percentages and number of available isolates:
                
-
                +
                 septic_patients %>%
   select(AMX, CIP) %>%
   rsi_df()
@@ -964,7 +970,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
              • UPEC (Uropathogenic E. coli)
                • 
 
              
 
              All these lead to the microbial ID of E. coli:
              
-
              +
               as.mo("UPEC")
 # B_ESCHR_COL
 mo_name("UPEC")
@@ -1068,7 +1074,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
            • when all values are unique it now shows a message instead of a warning
              • 
 
            • 
 
              support for boxplots:
              
-
              +
               septic_patients %>% 
   freq(age) %>% 
   boxplot()
@@ -1162,7 +1168,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
              • 
 
            • 
 
              New filters for antimicrobial classes. Use these functions to filter isolates on results in one of more antibiotics from a specific class:
              
-
              +
               filter_aminoglycosides()
 filter_carbapenems()
 filter_cephalosporins()
@@ -1175,7 +1181,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 filter_macrolides()
 filter_tetracyclines()
              
 
              The antibiotics data set will be searched, after which the input data will be checked for column names with a value in any abbreviations, codes or official names found in the antibiotics data set. For example:
              
-
              +
               septic_patients %>% filter_glycopeptides(result = "R")
 # Filtering on glycopeptide antibacterials: any of `vanc` or `teic` is R
 septic_patients %>% filter_glycopeptides(result = "R", scope = "all")
@@ -1183,7 +1189,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
              • 
 
            • 
 
              All ab_* functions are deprecated and replaced by atc_* functions:
              
-
              +
               ab_property -> atc_property()
 ab_name -> atc_name()
 ab_official -> atc_official()
@@ -1203,19 +1209,19 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
            • New function age_groups() to split ages into custom or predefined groups (like children or elderly). This allows for easier demographic antimicrobial resistance analysis per age group.
              • 
 
            • 
 
              New function ggplot_rsi_predict() as well as the base R plot() function can now be used for resistance prediction calculated with resistance_predict():
              
-
              +
               x <- resistance_predict(septic_patients, col_ab = "amox")
 plot(x)
 ggplot_rsi_predict(x)
              
 
              • 
 
            • 
 
              Functions filter_first_isolate() and filter_first_weighted_isolate() to shorten and fasten filtering on data sets with antimicrobial results, e.g.:
              
-
              +
               septic_patients %>% filter_first_isolate(...)
 # or
 filter_first_isolate(septic_patients, ...)
              
 
              is equal to:
              
-
              +
               septic_patients %>%
   mutate(only_firsts = first_isolate(septic_patients, ...)) %>%
   filter(only_firsts == TRUE) %>%
@@ -1247,7 +1253,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                
 
              • 
 
                Now handles incorrect spelling, like i instead of y and f instead of ph:
                
-
                +
                 # mo_fullname() uses as.mo() internally
 
 mo_fullname("Sthafilokockus aaureuz")
@@ -1258,7 +1264,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                • 
 
              • 
 
                Uncertainty of the algorithm is now divided into four levels, 0 to 3, where the default allow_uncertain = TRUE is equal to uncertainty level 2. Run ?as.mo for more info about these levels.
                
-
                +
                 # equal:
 as.mo(..., allow_uncertain = TRUE)
 as.mo(..., allow_uncertain = 2)
@@ -1272,7 +1278,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
              • All microbial IDs that found are now saved to a local file ~/.Rhistory_mo. Use the new function clean_mo_history() to delete this file, which resets the algorithms.
                • 
 
              • 
 
                Incoercible results will now be considered ‘unknown’, MO code UNKNOWN. On foreign systems, properties of these will be translated to all languages already previously supported: German, Dutch, French, Italian, Spanish and Portuguese:
                
-
                +
                 mo_genus("qwerty", language = "es")
 # Warning: 
 # one unique value (^= 100.0%) could not be coerced and is considered 'unknown': "qwerty". Use mo_failures() to review it.
@@ -1321,7 +1327,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                  
 
                • 
 
                  Support for tidyverse quasiquotation! Now you can create frequency tables of function outcomes:
                  
-
                  +
                   # Determine genus of microorganisms (mo) in `septic_patients` data set:
 # OLD WAY
 septic_patients %>%
@@ -1404,7 +1410,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                • Fewer than 3 characters as input for as.mo will return NA
                  • 
 
                • 
 
                  Function as.mo (and all mo_* wrappers) now supports genus abbreviations with “species” attached
                  
-
                  +
                   as.mo("E. species")        # B_ESCHR
 mo_fullname("E. spp.")     # "Escherichia species"
 as.mo("S. spp")            # B_STPHY
@@ -1420,14 +1426,14 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                    
 
                  • 
 
                    Support for grouping variables, test with:
                    
-
                    +
                     septic_patients %>% 
   group_by(hospital_id) %>% 
   freq(gender)
                    
 
                    • 
 
                  • 
 
                    Support for (un)selecting columns:
                    
-
                    +
                     septic_patients %>% 
   freq(hospital_id) %>% 
   select(-count, -cum_count) # only get item, percent, cum_percent
                    
@@ -1506,7 +1512,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                    • 
 
                  
 
                  They also come with support for German, Dutch, French, Italian, Spanish and Portuguese:
                  
-
                  +
                   mo_gramstain("E. coli")
 # [1] "Gram negative"
 mo_gramstain("E. coli", language = "de") # German
@@ -1516,7 +1522,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 mo_fullname("S. group A", language = "pt") # Portuguese
 # [1] "Streptococcus grupo A"
                  
 
                  Furthermore, former taxonomic names will give a note about the current taxonomic name:
                  
-
                  +
                   mo_gramstain("Esc blattae")
 # Note: 'Escherichia blattae' (Burgess et al., 1973) was renamed 'Shimwellia blattae' (Priest and Barker, 2010)
 # [1] "Gram negative"
                  
@@ -1530,7 +1536,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                • Function is.rsi.eligible to check for columns that have valid antimicrobial results, but do not have the rsi class yet. Transform the columns of your raw data with: data %>% mutate_if(is.rsi.eligible, as.rsi)
                  • 
 
                • 
 
                  Functions as.mo and is.mo as replacements for as.bactid and is.bactid (since the microoganisms data set not only contains bacteria). These last two functions are deprecated and will be removed in a future release. The as.mo function determines microbial IDs using intelligent rules:
                  
-
                  +
                   as.mo("E. coli")
 # [1] B_ESCHR_COL
 as.mo("MRSA")
@@ -1538,7 +1544,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 as.mo("S group A")
 # [1] B_STRPTC_GRA
                  
 
                  And with great speed too - on a quite regular Linux server from 2007 it takes us less than 0.02 seconds to transform 25,000 items:
                  
-
                  +
                   thousands_of_E_colis <- rep("E. coli", 25000)
 microbenchmark::microbenchmark(as.mo(thousands_of_E_colis), unit = "s")
 # Unit: seconds
@@ -1571,7 +1577,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                • Added three antimicrobial agents to the antibiotics data set: Terbinafine (D01BA02), Rifaximin (A07AA11) and Isoconazole (D01AC05)
                  • 
 
                • 
 
                  Added 163 trade names to the antibiotics data set, it now contains 298 different trade names in total, e.g.:
                  
-
                  +
                   ab_official("Bactroban")
 # [1] "Mupirocin"
 ab_name(c("Bactroban", "Amoxil", "Zithromax", "Floxapen"))
@@ -1587,7 +1593,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                • Added parameters minimum and as_percent to portion_df
                  • 
 
                • 
 
                  Support for quasiquotation in the functions series count_* and portions_*, and n_rsi. This allows to check for more than 2 vectors or columns.
                  
-
                  +
                   septic_patients %>% select(amox, cipr) %>% count_IR()
 # which is the same as:
 septic_patients %>% count_IR(amox, cipr)
@@ -1606,11 +1612,11 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
 
                • Added longest en shortest character length in the frequency table (freq) header of class character
                  • 
 
                • 
 
                  Support for types (classes) list and matrix for freq
                  
-
                  +
                   my_matrix = with(septic_patients, matrix(c(age, gender), ncol = 2))
 freq(my_matrix)
                  
 
                  For lists, subsetting is possible:
                  
-
                  +
                   my_list = list(age = septic_patients$age, gender = septic_patients$gender)
 my_list %>% freq(age)
 my_list %>% freq(gender)
                  
diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml
index 40ff0ae0..4bc7fd58 100644
--- a/docs/pkgdown.yml
+++ b/docs/pkgdown.yml
@@ -12,7 +12,7 @@ articles:
   datasets: datasets.html
   resistance_predict: resistance_predict.html
   welcome_to_AMR: welcome_to_AMR.html
-last_built: 2020-11-05T00:11Z
+last_built: 2020-11-09T12:06Z
 urls:
   reference: https://msberends.github.io/AMR//reference
   article: https://msberends.github.io/AMR//articles
diff --git a/docs/reference/antibiotic_class_selectors.html b/docs/reference/antibiotic_class_selectors.html
index 9878f8be..d21b93e9 100644
--- a/docs/reference/antibiotic_class_selectors.html
+++ b/docs/reference/antibiotic_class_selectors.html
@@ -82,7 +82,7 @@
       
       
         AMR (for R)
-        1.4.0.9008
+        1.4.0.9013
       
     
                  
 
@@ -315,7 +315,7 @@
     
   # get bug/drug combinations for only macrolides in Gram-positives:
   example_isolates %>% 
-    filter(mo %>% is_gram_positive()) %>% 
+    filter(is_gram_positive()) %>% 
     select(mo, macrolides()) %>% 
     bug_drug_combinations() %>%
     format()
diff --git a/docs/reference/as.mo.html b/docs/reference/as.mo.html
index 64a0351b..65a66c23 100644
--- a/docs/reference/as.mo.html
+++ b/docs/reference/as.mo.html
@@ -82,7 +82,7 @@
       
       
         AMR (for R)
-        1.4.0.9008
+        1.4.0.9013
       
     
                  
 
@@ -270,7 +270,7 @@
     
     
       Becker
-      
                  a logical to indicate whether Staphylococci should be categorised into coagulase-negative Staphylococci ("CoNS") and coagulase-positive Staphylococci ("CoPS") instead of their own species, according to Karsten Becker et al. (1,2,3).
                  
+      
                  a logical to indicate whether staphylococci should be categorised into coagulase-negative staphylococci ("CoNS") and coagulase-positive staphylococci ("CoPS") instead of their own species, according to Karsten Becker et al. (1,2,3).
                  
 
                  This excludes Staphylococcus aureus at default, use Becker = "all" to also categorise S. aureus as "CoPS".
                  
     
     
diff --git a/docs/reference/index.html b/docs/reference/index.html
index 4745e7ac..aa5dedce 100644
--- a/docs/reference/index.html
+++ b/docs/reference/index.html
@@ -81,7 +81,7 @@
       
       
         AMR (for R)
-        1.4.0.9012
+        1.4.0.9013
       
     
                  • 
 
diff --git a/docs/reference/mo_property.html b/docs/reference/mo_property.html
index c7e8aeea..b5bac64e 100644
--- a/docs/reference/mo_property.html
+++ b/docs/reference/mo_property.html
@@ -82,7 +82,7 @@
       
       
         AMR (for R)
-        1.4.0.9008
+        1.4.0.9013
       
     
                  
 
@@ -340,7 +340,7 @@
 
 
                  The short name - mo_shortname() - almost always returns the first character of the genus and the full species, like "E. coli". Exceptions are abbreviations of staphylococci (like "CoNS", Coagulase-Negative Staphylococci) and beta-haemolytic streptococci (like "GBS", Group B Streptococci). Please bear in mind that e.g. E. coli could mean Escherichia coli (kingdom of Bacteria) as well as Entamoeba coli (kingdom of Protozoa). Returning to the full name will be done using as.mo() internally, giving priority to bacteria and human pathogens, i.e. "E. coli" will be considered Escherichia coli. In other words, mo_fullname(mo_shortname("Entamoeba coli")) returns "Escherichia coli".
                  
 
                  Since the top-level of the taxonomy is sometimes referred to as 'kingdom' and sometimes as 'domain', the functions mo_kingdom() and mo_domain() return the exact same results.
                  
-
                  The Gram stain - mo_gramstain() - will be determined based on the taxonomic kingdom and phylum. According to Cavalier-Smith (2002, PMID 11837318), who defined subkingdoms Negibacteria and Posibacteria, only these phyla are Posibacteria: Actinobacteria, Chloroflexi, Firmicutes and Tenericutes. These bacteria are considered Gram-positive - all other bacteria are considered Gram-negative. Species outside the kingdom of Bacteria will return a value NA. Functions is_gram_negative() and is_gram_positive() always return TRUE or FALSE, even for species outside the kingdom of Bacteria.
                  
+
                  The Gram stain - mo_gramstain() - will be determined based on the taxonomic kingdom and phylum. According to Cavalier-Smith (2002, PMID 11837318), who defined subkingdoms Negibacteria and Posibacteria, only these phyla are Posibacteria: Actinobacteria, Chloroflexi, Firmicutes and Tenericutes. These bacteria are considered Gram-positive - all other bacteria are considered Gram-negative. Species outside the kingdom of Bacteria will return a value NA. Functions is_gram_negative() and is_gram_positive() always return TRUE or FALSE (except when the input is NA or the MO code is UNKNOWN), thus always return FALSE for species outside the taxonomic kingdom of Bacteria.
                  
 
                  All output will be translated where possible.
                  
 
                  The function mo_url() will return the direct URL to the online database entry, which also shows the scientific reference of the concerned species.
                  
     
                  Stable lifecycle
                  
@@ -461,7 +461,7 @@ This package contains the complete taxonomic tree of almost all microorganisms (
 mo_shortname("S. pyo", Lancefield = TRUE) # "GAS" (='Group A Streptococci')
 
 
-# language support for German, Dutch, Spanish, Portuguese, Italian and French
+# language support  --------------------------------------------------------
 mo_gramstain("E. coli", language = "de")  # "Gramnegativ"
 mo_gramstain("E. coli", language = "nl")  # "Gram-negatief"
 mo_gramstain("E. coli", language = "es")  # "Gram negativo"
@@ -478,7 +478,11 @@ This package contains the complete taxonomic tree of almost all microorganisms (
             Lancefield = TRUE,
             language = "nl")              # "Streptococcus groep A"
 
+# gram stains can be used as a filter
+example_isolates %>%
+  filter(is_gram_positive())
 
+# other --------------------------------------------------------------------
 # get a list with the complete taxonomy (from kingdom to subspecies)
 mo_taxonomy("E. coli")
 # get a list with the taxonomy, the authors, Gram-stain and URL to the online database
diff --git a/docs/survey.html b/docs/survey.html
index a7216eac..6f52806c 100644
--- a/docs/survey.html
+++ b/docs/survey.html
@@ -81,7 +81,7 @@
       
       
         AMR (for R)
-        1.4.0.9012
+        1.4.0.9013
       
     
                  • 
 
diff --git a/man/antibiotic_class_selectors.Rd b/man/antibiotic_class_selectors.Rd
index ec087d35..8a68cef5 100644
--- a/man/antibiotic_class_selectors.Rd
+++ b/man/antibiotic_class_selectors.Rd
@@ -85,7 +85,7 @@ if (require("dplyr")) {
     
   # get bug/drug combinations for only macrolides in Gram-positives:
   example_isolates \%>\% 
-    filter(mo \%>\% is_gram_positive()) \%>\% 
+    filter(is_gram_positive()) \%>\% 
     select(mo, macrolides()) \%>\% 
     bug_drug_combinations() \%>\%
     format()
diff --git a/man/as.mo.Rd b/man/as.mo.Rd
index edf90246..5682e6ca 100644
--- a/man/as.mo.Rd
+++ b/man/as.mo.Rd
@@ -31,7 +31,7 @@ mo_renamed()
 \arguments{
 \item{x}{a character vector or a \link{data.frame} with one or two columns}
 
-\item{Becker}{a logical to indicate whether \emph{Staphylococci} should be categorised into coagulase-negative \emph{Staphylococci} ("CoNS") and coagulase-positive \emph{Staphylococci} ("CoPS") instead of their own species, according to Karsten Becker \emph{et al.} (1,2,3).
+\item{Becker}{a logical to indicate whether staphylococci should be categorised into coagulase-negative staphylococci ("CoNS") and coagulase-positive staphylococci ("CoPS") instead of their own species, according to Karsten Becker \emph{et al.} (1,2,3).
 
 This excludes \emph{Staphylococcus aureus} at default, use \code{Becker = "all"} to also categorise \emph{S. aureus} as "CoPS".}
 
diff --git a/man/mo_property.Rd b/man/mo_property.Rd
index fac2dfaf..dc4a2bee 100644
--- a/man/mo_property.Rd
+++ b/man/mo_property.Rd
@@ -116,7 +116,7 @@ The short name - \code{\link[=mo_shortname]{mo_shortname()}} - almost always ret
 
 Since the top-level of the taxonomy is sometimes referred to as 'kingdom' and sometimes as 'domain', the functions \code{\link[=mo_kingdom]{mo_kingdom()}} and \code{\link[=mo_domain]{mo_domain()}} return the exact same results.
 
-The Gram stain - \code{\link[=mo_gramstain]{mo_gramstain()}} - will be determined based on the taxonomic kingdom and phylum. According to Cavalier-Smith (2002, \href{https://pubmed.ncbi.nlm.nih.gov/11837318}{PMID 11837318}), who defined subkingdoms Negibacteria and Posibacteria, only these phyla are Posibacteria: Actinobacteria, Chloroflexi, Firmicutes and Tenericutes. These bacteria are considered Gram-positive - all other bacteria are considered Gram-negative. Species outside the kingdom of Bacteria will return a value \code{NA}. Functions \code{\link[=is_gram_negative]{is_gram_negative()}} and \code{\link[=is_gram_positive]{is_gram_positive()}} always return \code{TRUE} or \code{FALSE}, even for species outside the kingdom of Bacteria.
+The Gram stain - \code{\link[=mo_gramstain]{mo_gramstain()}} - will be determined based on the taxonomic kingdom and phylum. According to Cavalier-Smith (2002, \href{https://pubmed.ncbi.nlm.nih.gov/11837318}{PMID 11837318}), who defined subkingdoms Negibacteria and Posibacteria, only these phyla are Posibacteria: Actinobacteria, Chloroflexi, Firmicutes and Tenericutes. These bacteria are considered Gram-positive - all other bacteria are considered Gram-negative. Species outside the kingdom of Bacteria will return a value \code{NA}. Functions \code{\link[=is_gram_negative]{is_gram_negative()}} and \code{\link[=is_gram_positive]{is_gram_positive()}} always return \code{TRUE} or \code{FALSE} (except when the input is \code{NA} or the MO code is \code{UNKNOWN}), thus always return \code{FALSE} for species outside the taxonomic kingdom of Bacteria.
 
 All output will be \link{translate}d where possible.
 
@@ -241,7 +241,7 @@ mo_shortname("S. pyo")                    # "S. pyogenes"
 mo_shortname("S. pyo", Lancefield = TRUE) # "GAS" (='Group A Streptococci')
 
 
-# language support for German, Dutch, Spanish, Portuguese, Italian and French
+# language support  --------------------------------------------------------
 mo_gramstain("E. coli", language = "de")  # "Gramnegativ"
 mo_gramstain("E. coli", language = "nl")  # "Gram-negatief"
 mo_gramstain("E. coli", language = "es")  # "Gram negativo"
@@ -258,7 +258,11 @@ mo_fullname("S. pyogenes",
             Lancefield = TRUE,
             language = "nl")              # "Streptococcus groep A"
 
+# gram stains can be used as a filter
+example_isolates \%>\%
+  filter(is_gram_positive())
 
+# other --------------------------------------------------------------------
 # get a list with the complete taxonomy (from kingdom to subspecies)
 mo_taxonomy("E. coli")
 # get a list with the taxonomy, the authors, Gram-stain and URL to the online database
diff --git a/tests/testthat/test-mo_property.R b/tests/testthat/test-mo_property.R
index 88af6221..af25b6e9 100644
--- a/tests/testthat/test-mo_property.R
+++ b/tests/testthat/test-mo_property.R
@@ -117,4 +117,10 @@ test_that("mo_property works", {
                c(TRUE, FALSE, FALSE))
   expect_equal(is_gram_positive(c("Escherichia coli", "Staphylococcus aureus", "Candida albicans")),
                c(FALSE, TRUE, FALSE))
+  
+  library(dplyr)
+  expect_equal(example_isolates %>% filter(is_gram_negative()) %>% nrow(),
+               730)
+  expect_equal(example_isolates %>% filter(is_gram_positive()) %>% nrow(),
+               1238)
 })