diff --git a/DESCRIPTION b/DESCRIPTION index 6d025b4b4..be64ce6fd 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,6 +1,6 @@ Package: AMR -Version: 1.8.1.9012 -Date: 2022-06-03 +Version: 1.8.1.9013 +Date: 2022-06-10 Title: Antimicrobial Resistance Data Analysis Description: Functions to simplify and standardise antimicrobial resistance (AMR) data analysis and to work with microbial and antimicrobial properties by diff --git a/NEWS.md b/NEWS.md index 720556e12..a638fee8f 100755 --- a/NEWS.md +++ b/NEWS.md @@ -1,5 +1,5 @@ -# `AMR` 1.8.1.9012 -## Last updated: 3 June 2022 +# `AMR` 1.8.1.9013 +## Last updated: 10 June 2022 ### New * EUCAST 2022 and CLSI 2022 guidelines have been added for `as.rsi()`. EUCAST 2022 is now the new default guideline for all MIC and disks diffusion interpretations. @@ -11,6 +11,7 @@ * Small fix for using `ab_from_text()` * Fixes for reading in text files using `set_mo_source()`, which now also allows the source file to contain valid taxonomic names instead of only valid microorganism ID of this package * Using any `random_*()` function (such as `random_mic()`) is now possible by directly calling the package without loading it first: `AMR::random_mic(10)` +* Added *Toxoplasma gondii* (`P_TXPL_GOND`) to the `microorganisms` data set, together with its genus, family, and order * Changed value in column `prevalence` of the `microorganisms` data set from 3 to 2 for these genera: *Acholeplasma*, *Alistipes*, *Alloprevotella*, *Bergeyella*, *Borrelia*, *Brachyspira*, *Butyricimonas*, *Cetobacterium*, *Chlamydia*, *Chlamydophila*, *Deinococcus*, *Dysgonomonas*, *Elizabethkingia*, *Empedobacter*, *Haloarcula*, *Halobacterium*, *Halococcus*, *Myroides*, *Odoribacter*, *Ornithobacterium*, *Parabacteroides*, *Pedobacter*, *Phocaeicola*, *Porphyromonas*, *Riemerella*, *Sphingobacterium*, *Streptobacillus*, *Tenacibaculum*, *Terrimonas*, *Victivallis*, *Wautersiella*, *Weeksella* # `AMR` 1.8.1 diff --git a/R/data.R b/R/data.R index 9e91c6a07..f350b7f9b 100755 --- a/R/data.R +++ b/R/data.R @@ -104,6 +104,7 @@ #' - 11 entries of *Streptococcus* (beta-haemolytic: groups A, B, C, D, F, G, H, K and unspecified; other: viridans, milleri) #' - 2 entries of *Staphylococcus* (coagulase-negative (CoNS) and coagulase-positive (CoPS)) #' - 3 entries of *Trichomonas* (*T. vaginalis*, and its family and genus) +#' - 4 entries of *Toxoplasma* (*T. gondii*, and its order, family and genus) #' - 1 entry of *Candida* (*C. krusei*), that is not (yet) in the Catalogue of Life #' - 1 entry of *Blastocystis* (*B. hominis*), although it officially does not exist (Noel *et al.* 2005, PMID 15634993) #' - 1 entry of *Moraxella* (*M. catarrhalis*), which was formally named *Branhamella catarrhalis* (Catlin, 1970) though this change was never accepted within the field of clinical microbiology @@ -111,13 +112,10 @@ #' - 6 families under the Enterobacterales order, according to Adeolu *et al.* (2016, PMID 27620848), that are not (yet) in the Catalogue of Life #' #' ## Direct download -#' This data set is available as 'flat file' for use even without \R - you can find the file here: +#' This data set is available as 'flat file' for use even without \R - you can find the file here: . #' -#' * +#' The file in \R format (with preserved data structure) can be found here: . #' -#' The file in \R format (with preserved data structure) can be found here: -#' -#' * #' @section About the Records from LPSN (see *Source*): #' The List of Prokaryotic names with Standing in Nomenclature (LPSN) provides comprehensive information on the nomenclature of prokaryotes. LPSN is a free to use service founded by Jean P. Euzeby in 1997 and later on maintained by Aidan C. Parte. #' diff --git a/R/mo.R b/R/mo.R index dea905c91..edd60e14e 100755 --- a/R/mo.R +++ b/R/mo.R @@ -2208,3 +2208,282 @@ strip_words <- function(text, n, side = "right") { }) vapply(FUN.VALUE = character(1), out, paste, collapse = " ") } + + +as.mo2 <- function(x, + Becker = FALSE, + Lancefield = FALSE, + allow_uncertain = TRUE, + reference_df = get_mo_source(), + info = interactive(), + property = "mo", + initial_search = TRUE, + dyslexia_mode = FALSE, + debug = FALSE, + ignore_pattern = getOption("AMR_ignore_pattern"), + reference_data_to_use = MO_lookup, + actual_uncertainty = 1, + actual_input = NULL, + language = get_AMR_locale()) { + meet_criteria(x, allow_class = c("mo", "data.frame", "list", "character", "numeric", "integer", "factor"), allow_NA = TRUE) + meet_criteria(Becker, allow_class = c("logical", "character"), has_length = 1) + meet_criteria(Lancefield, allow_class = c("logical", "character"), has_length = 1) + meet_criteria(allow_uncertain, allow_class = c("logical", "numeric", "integer"), has_length = 1) + meet_criteria(reference_df, allow_class = "data.frame", allow_NULL = TRUE) + meet_criteria(property, allow_class = "character", has_length = 1, is_in = colnames(microorganisms)) + meet_criteria(initial_search, allow_class = "logical", has_length = 1) + meet_criteria(dyslexia_mode, allow_class = "logical", has_length = 1) + meet_criteria(debug, allow_class = "logical", has_length = 1) + meet_criteria(ignore_pattern, allow_class = "character", has_length = 1, allow_NULL = TRUE) + meet_criteria(reference_data_to_use, allow_class = "data.frame") + meet_criteria(actual_uncertainty, allow_class = "numeric", has_length = 1) + meet_criteria(actual_input, allow_class = "character", allow_NULL = TRUE) + meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE) + + check_dataset_integrity() + + if (isTRUE(debug) && initial_search == TRUE) { + time_start_tracking() + } + + lookup <- function(needle, + column = property, + haystack = reference_data_to_use, + n = 1, + debug_mode = debug, + initial = initial_search, + uncertainty = actual_uncertainty, + input_actual = actual_input) { + + if (!is.null(input_actual)) { + input <- input_actual + } else { + input <- tryCatch(x_backup[i], error = function(e) "") + } + + # `column` can be NULL for all columns, or a selection + # returns a [character] (vector) - if `column` > length 1 then with columns as names + if (isTRUE(debug_mode)) { + cat(font_silver("Looking up: ", substitute(needle), collapse = ""), + "\n ", time_track()) + } + if (length(column) == 1) { + res_df <- haystack[which(eval(substitute(needle), envir = haystack, enclos = parent.frame())), , drop = FALSE] + if (NROW(res_df) > 1 & uncertainty != -1) { + # sort the findings on matching score + scores <- mo_matching_score(x = input, + n = res_df[, "fullname", drop = TRUE]) + res_df <- res_df[order(scores, decreasing = TRUE), , drop = FALSE] + } + res <- as.character(res_df[, column, drop = TRUE]) + if (length(res) == 0) { + if (isTRUE(debug_mode)) { + cat(font_red(" (no match)\n")) + } + NA_character_ + } else { + if (isTRUE(debug_mode)) { + cat(font_green(paste0(" MATCH (", NROW(res_df), " results)\n"))) + } + if ((length(res) > n | uncertainty > 1) & uncertainty != -1) { + # save the other possible results as well, but not for forced certain results (then uncertainty == -1) + uncertainties <<- rbind(uncertainties, + format_uncertainty_as_df(uncertainty_level = uncertainty, + input = input, + result_mo = res_df[1, "mo", drop = TRUE], + candidates = as.character(res_df[, "fullname", drop = TRUE])), + stringsAsFactors = FALSE) + } + res[seq_len(min(n, length(res)))] + } + } else { + if (is.null(column)) { + column <- names(haystack) + } + res <- haystack[which(eval(substitute(needle), envir = haystack, enclos = parent.frame())), , drop = FALSE] + res <- res[seq_len(min(n, nrow(res))), column, drop = TRUE] + if (NROW(res) == 0) { + if (isTRUE(debug_mode)) { + cat(font_red(" (no rows)\n")) + } + res <- rep(NA_character_, length(column)) + } else { + if (isTRUE(debug_mode)) { + cat(font_green(paste0(" MATCH (", NROW(res), " rows)\n"))) + } + } + res <- as.character(res) + names(res) <- column + res + } + } + + # start off with replaced language-specific non-ASCII characters with ASCII characters + x <- parse_and_convert(x) + # replace mo codes used in older package versions + x <- replace_old_mo_codes(x, property) + # ignore cases that match the ignore pattern + x <- replace_ignore_pattern(x, ignore_pattern) + + # WHONET: xxx = no growth + x[tolower(as.character(paste0(x, ""))) %in% c("", "xxx", "na", "nan")] <- NA_character_ + # Laboratory systems: remove (translated) entries like "no growth", etc. + x[trimws2(x) %like% translate_AMR("no .*growth", language = language)] <- NA_character_ + x[trimws2(x) %like% paste0("^(", translate_AMR("no|not", language = language), ") [a-z]+")] <- "UNKNOWN" + + if (initial_search == TRUE) { + # keep track of time - give some hints to improve speed if it takes a long time + start_time <- Sys.time() + + pkg_env$mo_failures <- NULL + pkg_env$mo_uncertainties <- NULL + pkg_env$mo_renamed <- NULL + } + pkg_env$mo_renamed_last_run <- NULL + + failures <- character(0) + uncertainty_level <- translate_allow_uncertain(allow_uncertain) + uncertainties <- data.frame(uncertainty = integer(0), + input = character(0), + fullname = character(0), + renamed_to = character(0), + mo = character(0), + candidates = character(0), + stringsAsFactors = FALSE) + + x_input <- x + # already strip leading and trailing spaces + x <- trimws(x) + # only check the uniques, which is way faster + x <- unique(x) + # remove empty values (to later fill them in again with NAs) + # ("xxx" is WHONET code for 'no growth') + x <- x[!is.na(x) + & !is.null(x) + & !identical(x, "") + & !identical(x, "xxx")] + + # defined df to check for + if (!is.null(reference_df)) { + check_validity_mo_source(reference_df) + reference_df <- repair_reference_df(reference_df) + } + + # all empty + if (all(identical(trimws(x_input), "") | is.na(x_input) | length(x) == 0)) { + if (property == "mo") { + return(set_clean_class(rep(NA_character_, length(x_input)), + new_class = c("mo", "character"))) + } else { + return(rep(NA_character_, length(x_input))) + } + + } else if (all(x %in% reference_df[, 1][[1]])) { + # all in reference df + colnames(reference_df)[1] <- "x" + suppressWarnings( + x <- MO_lookup[match(reference_df[match(x, reference_df$x), "mo", drop = TRUE], MO_lookup$mo), property, drop = TRUE] + ) + + } else if (all(x %in% reference_data_to_use$mo)) { + x <- MO_lookup[match(x, MO_lookup$mo), property, drop = TRUE] + + } else if (all(tolower(x) %in% reference_data_to_use$fullname_lower)) { + # we need special treatment for very prevalent full names, they are likely! + # e.g. as.mo("Staphylococcus aureus") + x <- MO_lookup[match(tolower(x), MO_lookup$fullname_lower), property, drop = TRUE] + + } else if (all(x %in% reference_data_to_use$fullname)) { + # we need special treatment for very prevalent full names, they are likely! + # e.g. as.mo("Staphylococcus aureus") + x <- MO_lookup[match(x, MO_lookup$fullname), property, drop = TRUE] + + } else if (all(toupper(x) %in% microorganisms.codes$code)) { + # commonly used MO codes + x <- MO_lookup[match(microorganisms.codes[match(toupper(x), + microorganisms.codes$code), + "mo", + drop = TRUE], + MO_lookup$mo), + property, + drop = TRUE] + + } else if (!all(x %in% microorganisms[, property])) { + + strip_whitespace <- function(x, dyslexia_mode) { + # all whitespaces (tab, new lines, etc.) should be one space + # and spaces before and after should be left blank + trimmed <- trimws2(x) + # also, make sure the trailing and leading characters are a-z or 0-9 + # in case of non-regex + if (dyslexia_mode == FALSE) { + trimmed <- gsub("^[^a-zA-Z0-9)(]+", "", trimmed, perl = TRUE) + trimmed <- gsub("[^a-zA-Z0-9)(]+$", "", trimmed, perl = TRUE) + } + trimmed + } + + x_backup_untouched <- x + x <- strip_whitespace(x, dyslexia_mode) + # translate 'unknown' names back to English + if (any(tolower(x) %like_case% "unbekannt|onbekend|desconocid|sconosciut|iconnu|desconhecid", na.rm = TRUE)) { + trns <- subset(TRANSLATIONS, pattern %like% "unknown") + langs <- LANGUAGES_SUPPORTED[LANGUAGES_SUPPORTED != "en"] + for (l in langs) { + for (i in seq_len(nrow(trns))) { + if (!is.na(trns[i, l, drop = TRUE])) { + x <- gsub(pattern = trns[i, l, drop = TRUE], + replacement = trns$pattern[i], + x = x, + ignore.case = TRUE, + perl = TRUE) + } + } + } + } + + # remove spp and species + x <- gsub("(^| )[ .]*(spp|ssp|ss|sp|subsp|subspecies|biovar|biotype|serovar|species)[ .]*( |$)", "", x, ignore.case = TRUE, perl = TRUE) + x <- strip_whitespace(x, dyslexia_mode) + + x_backup <- x + + # from here on case-insensitive + x <- tolower(x) + + x_backup[x %like_case% "^(fungus|fungi)$"] <- "(unknown fungus)" # will otherwise become the kingdom + x_backup[x_backup_untouched == "Fungi"] <- "Fungi" # is literally the kingdom + + # Fill in fullnames and MO codes directly + known_names <- tolower(x_backup) %in% MO_lookup$fullname_lower + x[known_names] <- MO_lookup[match(tolower(x_backup)[known_names], MO_lookup$fullname_lower), property, drop = TRUE] + known_codes_mo <- toupper(x_backup) %in% MO_lookup$mo + x[known_codes_mo] <- MO_lookup[match(toupper(x_backup)[known_codes_mo], MO_lookup$mo), property, drop = TRUE] + known_codes_lis <- toupper(x_backup) %in% microorganisms.codes$code + x[known_codes_lis] <- MO_lookup[match(microorganisms.codes[match(toupper(x_backup)[known_codes_lis], + microorganisms.codes$code), "mo", drop = TRUE], + MO_lookup$mo), property, drop = TRUE] + already_known <- known_names | known_codes_mo | known_codes_lis + + # now only continue where the right taxonomic output is not already known + if (any(!already_known)) { + x_unknown <- x[!already_known] + x_unknown <- gsub(" ?[(].*[)] ?", "", x_unknown, perl = TRUE) + x_unknown <- gsub("[^a-z ]", " ", x_unknown, perl = TRUE) + x_unknown <- gsub(" +", " ", x_unknown, perl = TRUE) + print(x_unknown) + x_search <- gsub("([a-z])[a-z]*( ([a-z])[a-z]*)?( ([a-z])[a-z]*)?", "^\\1.* \\3.* \\5.*", x_unknown, perl = TRUE) + x_search <- gsub("( [.][*])+$", "", x_search, perl = TRUE) + print(x_search) + for (i in seq_len(length(x_unknown))) { + # search first, second and third part + mos_to_search <- MO_lookup[which(MO_lookup$fullname_lower %like_case% x_search[i]), "fullname", drop = TRUE] + score <- mo_matching_score(x_unknown[i], mos_to_search) + out <- mos_to_search[order(score, decreasing = TRUE)][1:25] # keep first 25 + print(score[order(score, decreasing = TRUE)][1]) + x[!already_known][i] <- MO_lookup$mo[match(out[1], MO_lookup$fullname)] + } + } + } + x +} diff --git a/R/sysdata.rda b/R/sysdata.rda index 7cae28f2e..7c70bf869 100644 Binary files a/R/sysdata.rda and b/R/sysdata.rda differ diff --git a/R/zzz.R b/R/zzz.R index 2d16236ad..21124befd 100755 --- a/R/zzz.R +++ b/R/zzz.R @@ -131,7 +131,12 @@ create_MO_lookup <- function() { MO_lookup[which(is.na(MO_lookup$kingdom_index)), "kingdom_index"] <- 5 # use this paste instead of `fullname` to work with Viridans Group Streptococci, etc. - MO_lookup$fullname_lower <- MO_FULLNAME_LOWER + if (length(MO_FULLNAME_LOWER) == nrow(MO_lookup)) { + MO_lookup$fullname_lower <- MO_FULLNAME_LOWER + } else { + MO_lookup$fullname_lower <- "" + warning("MO table updated - Run: source(\"data-raw/_internals.R\")", call. = FALSE) + } # add a column with only "e coli" like combinations MO_lookup$g_species <- gsub("^([a-z])[a-z]+ ([a-z]+) ?.*", "\\1 \\2", MO_lookup$fullname_lower, perl = TRUE) diff --git a/data-raw/AMR_latest.tar.gz b/data-raw/AMR_latest.tar.gz index 6053d176c..298dca174 100644 Binary files a/data-raw/AMR_latest.tar.gz and b/data-raw/AMR_latest.tar.gz differ diff --git a/data-raw/_internals.R b/data-raw/_internals.R index 6ee1a86c3..2aef36c69 100644 --- a/data-raw/_internals.R +++ b/data-raw/_internals.R @@ -137,6 +137,29 @@ MO_CONS <- create_species_cons_cops("CoNS") MO_COPS <- create_species_cons_cops("CoPS") MO_STREP_ABCG <- as.mo(MO_lookup[which(MO_lookup$genus == "Streptococcus"), "mo", drop = TRUE], Lancefield = TRUE) %in% c("B_STRPT_GRPA", "B_STRPT_GRPB", "B_STRPT_GRPC", "B_STRPT_GRPG") MO_FULLNAME_LOWER <- create_MO_fullname_lower() +MO_PREVALENT_GENERA <- c("Absidia", "Acholeplasma", "Acremonium", "Actinotignum", "Aedes", "Alistipes", "Alloprevotella", + "Alternaria", "Anaerosalibacter", "Ancylostoma", "Angiostrongylus", "Anisakis", "Anopheles", + "Apophysomyces", "Arachnia", "Aspergillus", "Aureobasidium", "Bacteroides", "Basidiobolus", + "Beauveria", "Bergeyella", "Blastocystis", "Blastomyces", "Borrelia", "Brachyspira", "Branhamella", + "Butyricimonas", "Candida", "Capillaria", "Capnocytophaga", "Catabacter", "Cetobacterium", "Chaetomium", + "Chlamydia", "Chlamydophila", "Chryseobacterium", "Chrysonilia", "Cladophialophora", "Cladosporium", + "Conidiobolus", "Contracaecum", "Cordylobia", "Cryptococcus", "Curvularia", "Deinococcus", "Demodex", + "Dermatobia", "Diphyllobothrium", "Dirofilaria", "Dysgonomonas", "Echinostoma", "Elizabethkingia", + "Empedobacter", "Enterobius", "Exophiala", "Exserohilum", "Fasciola", "Flavobacterium", "Fonsecaea", + "Fusarium", "Fusobacterium", "Giardia", "Haloarcula", "Halobacterium", "Halococcus", "Hendersonula", + "Heterophyes", "Histoplasma", "Hymenolepis", "Hypomyces", "Hysterothylacium", "Lelliottia", + "Leptosphaeria", "Leptotrichia", "Lucilia", "Lumbricus", "Malassezia", "Malbranchea", "Metagonimus", + "Microsporum", "Mortierella", "Mucor", "Mycocentrospora", "Mycoplasma", "Myroides", "Necator", + "Nectria", "Ochroconis", "Odoribacter", "Oesophagostomum", "Oidiodendron", "Opisthorchis", + "Ornithobacterium", "Parabacteroides", "Pediculus", "Pedobacter", "Phlebotomus", "Phocaeicola", + "Phocanema", "Phoma", "Piedraia", "Pithomyces", "Pityrosporum", "Porphyromonas", "Prevotella", + "Pseudallescheria", "Pseudoterranova", "Pulex", "Rhizomucor", "Rhizopus", "Rhodotorula", "Riemerella", + "Saccharomyces", "Sarcoptes", "Scolecobasidium", "Scopulariopsis", "Scytalidium", "Sphingobacterium", + "Spirometra", "Spiroplasma", "Sporobolomyces", "Stachybotrys", "Streptobacillus", "Strongyloides", + "Syngamus", "Taenia", "Tannerella", "Tenacibaculum", "Terrimonas", "Toxocara", "Treponema", "Trichinella", + "Trichobilharzia", "Trichoderma", "Trichomonas", "Trichophyton", "Trichosporon", "Trichostrongylus", + "Trichuris", "Tritirachium", "Trombicula", "Tunga", "Ureaplasma", "Victivallis", "Wautersiella", + "Weeksella", "Wuchereria") # antibiotic groups # (these will also be used for eucast_rules() and understanding data-raw/eucast_rules.tsv) @@ -200,6 +223,7 @@ usethis::use_data(EUCAST_RULES_DF, MO_COPS, MO_STREP_ABCG, MO_FULLNAME_LOWER, + MO_PREVALENT_GENERA, AB_LOOKUP, AB_AMINOGLYCOSIDES, AB_AMINOPENICILLINS, @@ -275,7 +299,7 @@ if (changed_md5(mo)) { try(haven::write_sas(dplyr::select(mo, -snomed), "data-raw/microorganisms.sas"), silent = TRUE) try(haven::write_sav(dplyr::select(mo, -snomed), "data-raw/microorganisms.sav"), silent = TRUE) try(haven::write_dta(dplyr::select(mo, -snomed), "data-raw/microorganisms.dta"), silent = TRUE) - try(openxlsx::write.xlsx(mo, "data-raw/microorganisms.xlsx"), silent = TRUE) + try(openxlsx::write.xlsx(dplyr::select(mo, -snomed), "data-raw/microorganisms.xlsx"), silent = TRUE) } if (changed_md5(microorganisms.old)) { diff --git a/data-raw/microorganisms.dta b/data-raw/microorganisms.dta index 995b9e7e4..839d28124 100644 Binary files a/data-raw/microorganisms.dta and b/data-raw/microorganisms.dta differ diff --git a/data-raw/microorganisms.rds b/data-raw/microorganisms.rds index 4d2dc1587..874e610e5 100644 Binary files a/data-raw/microorganisms.rds and b/data-raw/microorganisms.rds differ diff --git a/data-raw/microorganisms.sas b/data-raw/microorganisms.sas index 6ae7b65be..3cf667d53 100644 Binary files a/data-raw/microorganisms.sas and b/data-raw/microorganisms.sas differ diff --git a/data-raw/microorganisms.sav b/data-raw/microorganisms.sav index e04af9745..e5893ca31 100644 Binary files a/data-raw/microorganisms.sav and b/data-raw/microorganisms.sav differ diff --git a/data-raw/microorganisms.txt b/data-raw/microorganisms.txt index 018b6e30e..a32466f99 100644 --- a/data-raw/microorganisms.txt +++ b/data-raw/microorganisms.txt @@ -22446,6 +22446,7 @@ "C_ECHTN_SNTN" "Euchitonia santonica" "Chromista" "Radiozoa" "Polycystina" "Nassellaria" "Plagiacanthidae" "Euchitonia" "santonica" "" "species" "Lipman, 1952" "CoL" 3 "character(0)" "C_ECHTN_TRRD" "Euchitonia triradiata" "Chromista" "Radiozoa" "Polycystina" "Nassellaria" "Plagiacanthidae" "Euchitonia" "triradiata" "" "species" "Lipman, 1960" "CoL" 3 "character(0)" "C_[ORD]_EUCCCDRD" "Eucoccidiorida" "Chromista" "Miozoa" "Conoidasida" "Eucoccidiorida" "(unknown family)" "" "" "" "order" "" "CoL" 2 "717355005" +"[ORD]_EUCCCDRD" "Eucoccidiorida" "(unknown kingdom)" "Apicomplexa" "Conoidasida" "Eucoccidiorida" "" "" "" "" "order" "Leger et al., 1910" "manually added" 2 "NULL" "C_ECCCN" "Eucocconeis" "Chromista" "Ochrophyta" "Bacillariophyceae" "Achnanthales" "Achnanthidiaceae" "Eucocconeis" "" "" "genus" "" "CoL" 3 "character(0)" "C_ECCCN_DPRS" "Eucocconeis depressa" "Chromista" "Ochrophyta" "Bacillariophyceae" "Achnanthales" "Achnanthidiaceae" "Eucocconeis" "depressa" "" "species" "Hust" "CoL" 3 "character(0)" "C_ECCCN_FLXL" "Eucocconeis flexella" "Chromista" "Ochrophyta" "Bacillariophyceae" "Achnanthales" "Achnanthidiaceae" "Eucocconeis" "flexella" "" "species" "Cleve" "CoL" 3 "character(0)" @@ -58199,6 +58200,7 @@ "B_SARCN" "Sarcina" "Bacteria" "Firmicutes" "Clostridia" "Eubacteriales" "Clostridiaceae" "Sarcina" "" "" "genus" "" 516554 "LPSN" 2 "58039002" "B_SARCN_MAXM" "Sarcina maxima" "Bacteria" "Firmicutes" "Clostridia" "Eubacteriales" "Clostridiaceae" "Sarcina" "maxima" "" "species" "Lindner, 1888" 780788 "LPSN" 2 "15560003" "B_SARCN_VNTR" "Sarcina ventriculi" "Bacteria" "Firmicutes" "Clostridia" "Eubacteriales" "Clostridiaceae" "Sarcina" "ventriculi" "" "species" "Goodsir, 1842" 780795 "LPSN" 2 "22267009" +"[FAM]_SRCCYSTD" "Sarcocystidae" "(unknown kingdom)" "Apicomplexa" "Conoidasida" "Eucoccidiorida" "Sarcocystidae" "" "" "" "family" "Poche, 1913" "manually added" 2 "NULL" "P_[PHL]_SRCMSTGP" "Sarcomastigophora" "Protozoa" "Sarcomastigophora" "(unknown class)" "(unknown order)" "(unknown family)" "" "" "" "phylum" "" "CoL" 3 "428002001" "AN_SRCPT" "Sarcoptes" "Animalia" "Arthropoda" "Arachnida" "Astigmata" "Sarcoptidae" "Sarcoptes" "" "" "genus" "" "CoL" 2 "character(0)" "AN_SRCPT_SCAB" "Sarcoptes scabiei" "Animalia" "Arthropoda" "Arachnida" "Astigmata" "Sarcoptidae" "Sarcoptes" "scabiei" "" "species" "Linnaeus, 1758" "CoL" 2 "788310009" @@ -66464,6 +66466,8 @@ "C_TOXND_CHLL" "Toxonidea challengerensis" "Chromista" "Ochrophyta" "Bacillariophyceae" "Naviculales" "Pleurosigmataceae" "Toxonidea" "challengerensis" "" "species" "" "CoL" 3 "character(0)" "C_TOXND_GRGR" "Toxonidea gregoriana" "Chromista" "Ochrophyta" "Bacillariophyceae" "Naviculales" "Pleurosigmataceae" "Toxonidea" "gregoriana" "" "species" "" "CoL" 3 "character(0)" "C_TOXND_INSG" "Toxonidea insignis" "Chromista" "Ochrophyta" "Bacillariophyceae" "Naviculales" "Pleurosigmataceae" "Toxonidea" "insignis" "" "species" "" "CoL" 3 "character(0)" +"P_TXPL" "Toxoplasma" "(unknown kingdom)" "Apicomplexa" "Conoidasida" "Eucoccidiorida" "Sarcocystidae" "Toxoplasma" "" "" "genus" "Nicolle et al., 1909" "manually added" 2 "NULL" +"P_TXPL_GOND" "Toxoplasma gondii" "(unknown kingdom)" "Apicomplexa" "Conoidasida" "Eucoccidiorida" "Sarcocystidae" "Toxoplasma" "gondii" "" "species" "Nicolle et al., 1908" "manually added" 2 "NULL" "P_TXSPR" "Toxospora" "Protozoa" "Microsporidia" "Microsporea" "(unknown order)" "Toxoglugeidae" "Toxospora" "" "" "genus" "" "CoL" 3 "character(0)" "P_TXSPR_VIBR" "Toxospora vibrio" "Protozoa" "Microsporidia" "Microsporea" "(unknown order)" "Toxoglugeidae" "Toxospora" "vibrio" "" "species" "Kudo, 1925" "CoL" 3 "character(0)" "P_TXSPR_VOLG" "Toxospora volgae" "Protozoa" "Microsporidia" "Microsporea" "(unknown order)" "Toxoglugeidae" "Toxospora" "volgae" "" "species" "Voronin, 1993" "CoL" 3 "character(0)" diff --git a/data-raw/microorganisms.xlsx b/data-raw/microorganisms.xlsx index de8f739b1..4a10059d6 100644 Binary files a/data-raw/microorganisms.xlsx and b/data-raw/microorganisms.xlsx differ diff --git a/data-raw/mo.md5 b/data-raw/mo.md5 index 876096835..e25f22820 100644 --- a/data-raw/mo.md5 +++ b/data-raw/mo.md5 @@ -1 +1 @@ -532f52b6cbe1cdb25268122fa0608714 +4709adde8932f9e887fbd892a27ad929 diff --git a/data-raw/reproduction_of_microorganisms.R b/data-raw/reproduction_of_microorganisms.R index f4b92ac25..c2114668e 100644 --- a/data-raw/reproduction_of_microorganisms.R +++ b/data-raw/reproduction_of_microorganisms.R @@ -168,41 +168,6 @@ rm(ref_taxonomy) rm(data_col.bak) rm(data_dsmz.bak) -mo_found_in_NL <- c("Absidia", "Acholeplasma", "Acremonium", "Actinotignum", "Aedes", "Alistipes", - "Alloprevotella", "Alternaria", "Anaerosalibacter", "Ancylostoma", "Angiostrongylus", - "Anisakis", "Anopheles", "Apophysomyces", "Arachnia", "Ascaris", "Aspergillus", - "Aureobacterium", "Aureobasidium", "Bacteroides", "Balantidum", "Basidiobolus", - "Beauveria", "Bergeyella", "Bilophilia", "Blastocystis", "Borrelia", "Brachyspira", - "Branhamella", "Brochontrix", "Brugia", "Butyricimonas", "Calymmatobacterium", - "Candida", "Capillaria", "Capnocytophaga", "Catabacter", "Cdc", "Cetobacterium", - "Chaetomium", "Chilomastix", "Chlamydia", "Chlamydophila", "Chryseobacterium", - "Chryseomonas", "Chrysonilia", "Cladophialophora", "Cladosporium", "Clonorchis", - "Conidiobolus", "Contracaecum", "Cordylobia", "Cryptococcus", "Curvularia", "Deinococcus", - "Demodex", "Dermatobia", "Dicrocoelium", "Dioctophyma", "Diphyllobothrium", "Dipylidium", - "Dirofilaria", "Dracunculus", "Dysgonomonas", "Echinococcus", "Echinostoma", - "Elisabethkingia", "Elizabethkingia", "Empedobacter", "Enterobius", "Enteromonas", - "Euascomycetes", "Exophiala", "Exserohilum", "Fasciola", "Fasciolopsis", "Flavobacterium", - "Fonsecaea", "Fusarium", "Fusobacterium", "Giardia", "Gnathostoma", "Haloarcula", - "Halobacterium", "Halococcus", "Hendersonula", "Heterophyes", "Hymenolepis", "Hypomyces", - "Hysterothylacium", "Kloeckera", "Koserella", "Larva", "Lecythophora", "Leishmania", - "Lelliottia", "Leptomyxida", "Leptosphaeria", "Leptotrichia", "Loa", "Lucilia", "Lumbricus", - "Malassezia", "Malbranchea", "Mansonella", "Mesocestoides", "Metagonimus", "Metarrhizium", - "Molonomonas", "Mortierella", "Mucor", "Multiceps", "Mycocentrospora", "Mycoplasma", - "Myroides", "Nanophetus", "Nattrassia", "Necator", "Nectria", "Novospingobium", "Ochroconis", - "Odoribacter", "Oesophagostomum", "Oidiodendron", "Onchocerca", "Opisthorchis", - "Opistorchis", "Ornithobacterium", "Parabacteroides", "Paragonimus", "Paramyxovirus", - "Pediculus", "Pedobacter", "Phlebotomus", "Phocaeicola", "Phocanema", "Phoma", - "Phthirus", "Piedraia", "Pithomyces", "Pityrosporum", "Porphyromonas", "Prevotella", - "Pseudallescheria", "Pseudoterranova", "Pulex", "Retortamonas", "Rhizomucor", "Rhizopus", - "Rhodotorula", "Riemerella", "Salinococcus", "Sanguibacteroides", "Sarcophagidae", "Sarcoptes", - "Schistosoma", "Scolecobasidium", "Scopulariopsis", "Scytalidium", "Sphingobacterium", - "Spirometra", "Sporobolomyces", "Stachybotrys", "Stenotrophomononas", "Stomatococcus", - "Streptobacillus", "Strongyloides", "Syncephalastraceae", "Syngamus", "Taenia", - "Tenacibaculum", "Ternidens", "Terrimonas", "Torulopsis", "Toxocara", "Toxoplasma", - "Treponema", "Trichinella", "Trichobilharzia", "Trichoderma", "Trichomonas", "Trichophyton", - "Trichosporon", "Trichostrongylus", "Trichuris", "Tritirachium", "Trombicula", "Trypanosoma", - "Tunga", "Ureaplasma", "Victivallis", "Wautersiella", "Weeksella", "Wuchereria") - MOs <- data_total %>% filter( ( @@ -214,7 +179,7 @@ MOs <- data_total %>% & !order %in% c("Eurotiales", "Microascales", "Mucorales", "Saccharomycetales", "Schizosaccharomycetales", "Tremellales", "Onygenales", "Pneumocystales")) ) # or the genus has to be one of the genera we found in our hospitals last decades (Northern Netherlands, 2002-2018) - | genus %in% mo_found_in_NL + | genus %in% MO_PREVALENT_GENERA ) %>% # really no Plantae (e.g. Dracunculus exist both as worm and as plant) filter(kingdom != "Plantae") %>% @@ -407,7 +372,7 @@ MOs <- MOs %>% "Firmicutes", "Actinobacteria", "Sarcomastigophora") - | genus %in% mo_found_in_NL + | genus %in% MO_PREVALENT_GENERA | rank %in% c("kingdom", "phylum", "class", "order", "family")) ~ 2, TRUE ~ 3 diff --git a/data-raw/reproduction_of_microorganisms_update.R b/data-raw/reproduction_of_microorganisms_update.R index 78292955f..46cc353bb 100644 --- a/data-raw/reproduction_of_microorganisms_update.R +++ b/data-raw/reproduction_of_microorganisms_update.R @@ -276,40 +276,7 @@ MOs <- MOs %>% "Firmicutes", "Actinobacteria", "Sarcomastigophora") - | genus %in% c("Absidia", "Acholeplasma", "Acremonium", "Actinotignum", "Aedes", "Alistipes", - "Alloprevotella", "Alternaria", "Anaerosalibacter", "Ancylostoma", "Angiostrongylus", - "Anisakis", "Anopheles", "Apophysomyces", "Arachnia", "Ascaris", "Aspergillus", - "Aureobacterium", "Aureobasidium", "Bacteroides", "Balantidum", "Basidiobolus", - "Beauveria", "Bergeyella", "Bilophilia", "Blastocystis", "Borrelia", "Brachyspira", - "Branhamella", "Brochontrix", "Brugia", "Butyricimonas", "Calymmatobacterium", - "Candida", "Capillaria", "Capnocytophaga", "Catabacter", "Cdc", "Cetobacterium", - "Chaetomium", "Chilomastix", "Chlamydia", "Chlamydophila", "Chryseobacterium", - "Chryseomonas", "Chrysonilia", "Cladophialophora", "Cladosporium", "Clonorchis", - "Conidiobolus", "Contracaecum", "Cordylobia", "Cryptococcus", "Curvularia", "Deinococcus", - "Demodex", "Dermatobia", "Dicrocoelium", "Dioctophyma", "Diphyllobothrium", "Dipylidium", - "Dirofilaria", "Dracunculus", "Dysgonomonas", "Echinococcus", "Echinostoma", - "Elisabethkingia", "Elizabethkingia", "Empedobacter", "Enterobius", "Enteromonas", - "Euascomycetes", "Exophiala", "Exserohilum", "Fasciola", "Fasciolopsis", "Flavobacterium", - "Fonsecaea", "Fusarium", "Fusobacterium", "Giardia", "Gnathostoma", "Haloarcula", - "Halobacterium", "Halococcus", "Hendersonula", "Heterophyes", "Hymenolepis", "Hypomyces", - "Hysterothylacium", "Kloeckera", "Koserella", "Larva", "Lecythophora", "Leishmania", - "Lelliottia", "Leptomyxida", "Leptosphaeria", "Leptotrichia", "Loa", "Lucilia", "Lumbricus", - "Malassezia", "Malbranchea", "Mansonella", "Mesocestoides", "Metagonimus", "Metarrhizium", - "Molonomonas", "Mortierella", "Mucor", "Multiceps", "Mycocentrospora", "Mycoplasma", - "Myroides", "Nanophetus", "Nattrassia", "Necator", "Nectria", "Novospingobium", "Ochroconis", - "Odoribacter", "Oesophagostomum", "Oidiodendron", "Onchocerca", "Opisthorchis", - "Opistorchis", "Ornithobacterium", "Parabacteroides", "Paragonimus", "Paramyxovirus", - "Pediculus", "Pedobacter", "Phlebotomus", "Phocaeicola", "Phocanema", "Phoma", - "Phthirus", "Piedraia", "Pithomyces", "Pityrosporum", "Porphyromonas", "Prevotella", - "Pseudallescheria", "Pseudoterranova", "Pulex", "Retortamonas", "Rhizomucor", "Rhizopus", - "Rhodotorula", "Riemerella", "Salinococcus", "Sanguibacteroides", "Sarcophagidae", "Sarcoptes", - "Schistosoma", "Scolecobasidium", "Scopulariopsis", "Scytalidium", "Sphingobacterium", - "Spirometra", "Sporobolomyces", "Stachybotrys", "Stenotrophomononas", "Stomatococcus", - "Streptobacillus", "Strongyloides", "Syncephalastraceae", "Syngamus", "Taenia", - "Tenacibaculum", "Ternidens", "Terrimonas", "Torulopsis", "Toxocara", "Toxoplasma", - "Treponema", "Trichinella", "Trichobilharzia", "Trichoderma", "Trichomonas", "Trichophyton", - "Trichosporon", "Trichostrongylus", "Trichuris", "Tritirachium", "Trombicula", "Trypanosoma", - "Tunga", "Ureaplasma", "Victivallis", "Wautersiella", "Weeksella", "Wuchereria") + | genus %in% MO_PREVALENT_GENERA | rank %in% c("kingdom", "phylum", "class", "order", "family")) ~ 2, TRUE ~ 3 diff --git a/data-raw/toxoplasma.R b/data-raw/toxoplasma.R new file mode 100644 index 000000000..91b4f3aef --- /dev/null +++ b/data-raw/toxoplasma.R @@ -0,0 +1,68 @@ +microorganisms <- microorganisms |> bind_rows( + # Toxoplasma + data.frame(mo = "P_TXPL_GOND", # species + fullname = "Toxoplasma gondii", + kingdom = "(unknown kingdom)", + phylum = "Apicomplexa", + class = "Conoidasida", + order = "Eucoccidiorida", + family = "Sarcocystidae", + genus = "Toxoplasma", + species = "gondii", + subspecies = "", + rank = "species", + ref = "Nicolle et al., 1908", + species_id = NA_real_, + source = "manually added", + prevalence = 2, + stringsAsFactors = FALSE), + data.frame(mo = "P_TXPL", # genus + fullname = "Toxoplasma", + kingdom = "(unknown kingdom)", + phylum = "Apicomplexa", + class = "Conoidasida", + order = "Eucoccidiorida", + family = "Sarcocystidae", + genus = "Toxoplasma", + species = "", + subspecies = "", + rank = "genus", + ref = "Nicolle et al., 1909", + species_id = NA_real_, + source = "manually added", + prevalence = 2, + stringsAsFactors = FALSE), + data.frame(mo = "[FAM]_SRCCYSTD", # family + fullname = "Sarcocystidae", + kingdom = "(unknown kingdom)", + phylum = "Apicomplexa", + class = "Conoidasida", + order = "Eucoccidiorida", + family = "Sarcocystidae", + genus = "", + species = "", + subspecies = "", + rank = "family", + ref = "Poche, 1913", + species_id = NA_real_, + source = "manually added", + prevalence = 2, + stringsAsFactors = FALSE), + data.frame(mo = "[ORD]_EUCCCDRD", # order + fullname = "Eucoccidiorida", + kingdom = "(unknown kingdom)", + phylum = "Apicomplexa", + class = "Conoidasida", + order = "Eucoccidiorida", + family = "", + genus = "", + species = "", + subspecies = "", + rank = "order", + ref = "Leger et al., 1910", + species_id = NA_real_, + source = "manually added", + prevalence = 2, + stringsAsFactors = FALSE), + ) |> + arrange(fullname) diff --git a/data/microorganisms.rda b/data/microorganisms.rda index ff221d345..86e741bfc 100644 Binary files a/data/microorganisms.rda and b/data/microorganisms.rda differ diff --git a/docs/404.html b/docs/404.html index b52e36f04..abdbb5dda 100644 --- a/docs/404.html +++ b/docs/404.html @@ -43,7 +43,7 @@ AMR (for R) - 1.8.1.9012 + 1.8.1.9013 diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html index ed7363da6..3ada8c727 100644 --- a/docs/LICENSE-text.html +++ b/docs/LICENSE-text.html @@ -17,7 +17,7 @@ AMR (for R) - 1.8.1.9012 + 1.8.1.9013 diff --git a/docs/articles/datasets.html b/docs/articles/datasets.html index dad642969..cf6a09c12 100644 --- a/docs/articles/datasets.html +++ b/docs/articles/datasets.html @@ -44,7 +44,7 @@ AMR (for R) - 1.8.1.9012 + 1.8.1.9013 @@ -190,7 +190,7 @@

Data sets for download / own use

-

03 June 2022

+

10 June 2022

Source: vignettes/datasets.Rmd @@ -224,15 +224,15 @@ column names:
mo, fullname, kingdom, phylumsnomed.

This data set is in R available as microorganisms, after you load the AMR package.

-

It was last updated on 3 June 2022 11:18:29 UTC. Find more info about -the structure of this data set here.

+

It was last updated on 10 June 2022 11:09:45 UTC. Find more info +about the structure of this data set here.

Direct download links:

  • Download as R file (1.3 MB)
  • Download as Excel -file (5.1 MB)
    +file (4.8 MB)
  • Download as plain text file (13.1 MB)
    diff --git a/docs/authors.html b/docs/authors.html index 442888b0b..223ed8fdd 100644 --- a/docs/authors.html +++ b/docs/authors.html @@ -17,7 +17,7 @@ AMR (for R) - 1.8.1.9012 + 1.8.1.9013
diff --git a/docs/index.html b/docs/index.html index 6ef03b772..06e6834b5 100644 --- a/docs/index.html +++ b/docs/index.html @@ -47,7 +47,7 @@ AMR (for R) - 1.8.1.9012 + 1.8.1.9013 diff --git a/docs/news/index.html b/docs/news/index.html index 48eebef86..2b723f9a0 100644 --- a/docs/news/index.html +++ b/docs/news/index.html @@ -17,7 +17,7 @@ AMR (for R) - 1.8.1.9012 + 1.8.1.9013 @@ -157,16 +157,16 @@
-

-AMR 1.8.1.9012

+

+AMR 1.8.1.9013

-

Last updated: 3 June 2022

+

Last updated: 10 June 2022

-

New

+

New

  • EUCAST 2022 and CLSI 2022 guidelines have been added for as.rsi(). EUCAST 2022 is now the new default guideline for all MIC and disks diffusion interpretations.
-

Changed

+

Changed

  • Fix for as.rsi() on certain EUCAST breakpoints for MIC values
  • Removed as.integer() for MIC values, since MIC are not integer values and running table() on MIC values consequently failed for not being able to retrieve the level position (as that’s how normally as.integer() on factors work)
  • @@ -176,6 +176,7 @@
  • Fixes for reading in text files using set_mo_source(), which now also allows the source file to contain valid taxonomic names instead of only valid microorganism ID of this package
  • Using any random_*() function (such as random_mic()) is now possible by directly calling the package without loading it first: AMR::random_mic(10)
    • +
  • Added Toxoplasma gondii (P_TXPL_GOND) to the microorganisms data set, together with its genus, family, and order
  • Changed value in column prevalence of the microorganisms data set from 3 to 2 for these genera: Acholeplasma, Alistipes, Alloprevotella, Bergeyella, Borrelia, Brachyspira, Butyricimonas, Cetobacterium, Chlamydia, Chlamydophila, Deinococcus, Dysgonomonas, Elizabethkingia, Empedobacter, Haloarcula, Halobacterium, Halococcus, Myroides, Odoribacter, Ornithobacterium, Parabacteroides, Pedobacter, Phocaeicola, Porphyromonas, Riemerella, Sphingobacterium, Streptobacillus, Tenacibaculum, Terrimonas, Victivallis, Wautersiella, Weeksella
diff --git a/docs/reference/index.html b/docs/reference/index.html index eed05897e..8123f7f37 100644 --- a/docs/reference/index.html +++ b/docs/reference/index.html @@ -17,7 +17,7 @@ AMR (for R) - 1.8.1.9012 + 1.8.1.9013
@@ -282,7 +282,7 @@

microorganisms

-

Data Set with 70,760 Microorganisms

+

Data Set with 70,764 Microorganisms

microorganisms.codes

diff --git a/docs/reference/microorganisms.html b/docs/reference/microorganisms.html index ad55c3219..adff1b4c4 100644 --- a/docs/reference/microorganisms.html +++ b/docs/reference/microorganisms.html @@ -1,5 +1,5 @@ -Data Set with 70,760 Microorganisms — microorganisms • AMR (for R)Data Set with 70,764 Microorganisms — microorganisms • AMR (for R) @@ -17,7 +17,7 @@ AMR (for R) - 1.8.1.9007 + 1.8.1.9013
@@ -152,7 +152,7 @@
-

Data Set with 70,760 Microorganisms

+

Data Set with 70,764 Microorganisms

Source: R/data.R
@@ -167,7 +167,7 @@

Format

-

A data.frame with 70,760 observations and 16 variables:

  • mo
    ID of microorganism as used by this package

    • +

    A data.frame with 70,764 observations and 16 variables:

    • mo
      ID of microorganism as used by this package

    • fullname
      Full name, like "Escherichia coli"

    • kingdom, phylum, class, order, family, genus, species, subspecies
      Taxonomic rank of the microorganism

    • rank
      Text of the taxonomic rank of the microorganism, like "species" or "genus"

      • @@ -180,17 +180,17 @@

      Source

      Catalogue of Life: 2019 Annual Checklist as currently implemented in this AMR package:

      List of Prokaryotic names with Standing in Nomenclature (5 October 2021) as currently implemented in this AMR package:

      • Parte, A.C., Sarda Carbasse, J., Meier-Kolthoff, J.P., Reimer, L.C. and Goker, M. (2020). List of Prokaryotic names with Standing in Nomenclature (LPSN) moves to the DSMZ. International Journal of Systematic and Evolutionary Microbiology, 70, 5607-5612; doi: 10.1099/ijsem.0.004332

        • -

      • Parte, A.C. (2018). LPSN - List of Prokaryotic names with Standing in Nomenclature (bacterio.net), 20 years on. International Journal of Systematic and Evolutionary Microbiology, 68, 1825-1829; doi: 10.1099/ijsem.0.002786

        • -

      • Parte, A.C. (2014). LPSN - List of Prokaryotic names with Standing in Nomenclature. Nucleic Acids Research, 42, Issue D1, D613-D616; doi: 10.1093/nar/gkt1111

        • -

      • Euzeby, J.P. (1997). List of Bacterial Names with Standing in Nomenclature: a Folder Available on the Internet. International Journal of Systematic Bacteriology, 47, 590-592; doi: 10.1099/00207713-47-2-590

        • +

      List of Prokaryotic names with Standing in Nomenclature (5 October 2021) as currently implemented in this AMR package:

      • Parte, A.C., Sarda Carbasse, J., Meier-Kolthoff, J.P., Reimer, L.C. and Goker, M. (2020). List of Prokaryotic names with Standing in Nomenclature (LPSN) moves to the DSMZ. International Journal of Systematic and Evolutionary Microbiology, 70, 5607-5612; doi:10.1099/ijsem.0.004332

        • +

      • Parte, A.C. (2018). LPSN - List of Prokaryotic names with Standing in Nomenclature (bacterio.net), 20 years on. International Journal of Systematic and Evolutionary Microbiology, 68, 1825-1829; doi:10.1099/ijsem.0.002786

        • +

      • Parte, A.C. (2014). LPSN - List of Prokaryotic names with Standing in Nomenclature. Nucleic Acids Research, 42, Issue D1, D613-D616; doi:10.1093/nar/gkt1111

        • +

      • Euzeby, J.P. (1997). List of Bacterial Names with Standing in Nomenclature: a Folder Available on the Internet. International Journal of Systematic Bacteriology, 47, 590-592; doi:10.1099/00207713-47-2-590

      US Edition of SNOMED CT from 1 September 2020 as currently implemented in this AMR package:

      Details

      Please note that entries are only based on the Catalogue of Life and the LPSN (see below). Since these sources incorporate entries based on (recent) publications in the International Journal of Systematic and Evolutionary Microbiology (IJSEM), it can happen that the year of publication is sometimes later than one might expect.

      -

      For example, Staphylococcus pettenkoferi was described for the first time in Diagnostic Microbiology and Infectious Disease in 2002 (doi: 10.1016/s0732-8893(02)00399-1 -), but it was not before 2007 that a publication in IJSEM followed (doi: 10.1099/ijs.0.64381-0 +

      For example, Staphylococcus pettenkoferi was described for the first time in Diagnostic Microbiology and Infectious Disease in 2002 (doi:10.1016/s0732-8893(02)00399-1 +), but it was not before 2007 that a publication in IJSEM followed (doi:10.1099/ijs.0.64381-0 ). Consequently, the AMR package returns 2007 for mo_year("S. pettenkoferi").

      Manual additions

      @@ -198,6 +198,7 @@

      For convenience, some entries were added manually:

      • 11 entries of Streptococcus (beta-haemolytic: groups A, B, C, D, F, G, H, K and unspecified; other: viridans, milleri)

      • 2 entries of Staphylococcus (coagulase-negative (CoNS) and coagulase-positive (CoPS))

      • 3 entries of Trichomonas (T. vaginalis, and its family and genus)

        • +

      • 4 entries of Toxoplasma (T. gondii, and its order, family and genus)

      • 1 entry of Candida (C. krusei), that is not (yet) in the Catalogue of Life

      • 1 entry of Blastocystis (B. hominis), although it officially does not exist (Noel et al. 2005, PMID 15634993)

      • 1 entry of Moraxella (M. catarrhalis), which was formally named Branhamella catarrhalis (Catlin, 1970) though this change was never accepted within the field of clinical microbiology

        • @@ -209,9 +210,9 @@

        Direct download

        -

        This data set is available as 'flat file' for use even without R - you can find the file here:

        The file in R format (with preserved data structure) can be found here:

      +

      This data set is available as 'flat file' for use even without R - you can find the file here: https://github.com/msberends/AMR/raw/main/data-raw/microorganisms.txt.

      +

      The file in R format (with preserved data structure) can be found here: https://github.com/msberends/AMR/raw/main/data/microorganisms.rda.

      +
diff --git a/docs/survey.html b/docs/survey.html index 53200b505..25800abff 100644 --- a/docs/survey.html +++ b/docs/survey.html @@ -17,7 +17,7 @@ AMR (for R) - 1.8.1.9012 + 1.8.1.9013
diff --git a/man/microorganisms.Rd b/man/microorganisms.Rd index 552da5ee6..2eca7af11 100755 --- a/man/microorganisms.Rd +++ b/man/microorganisms.Rd @@ -3,9 +3,9 @@ \docType{data} \name{microorganisms} \alias{microorganisms} -\title{Data Set with 70,760 Microorganisms} +\title{Data Set with 70,764 Microorganisms} \format{ -A \link{data.frame} with 70,760 observations and 16 variables: +A \link{data.frame} with 70,764 observations and 16 variables: \itemize{ \item \code{mo}\cr ID of microorganism as used by this package \item \code{fullname}\cr Full name, like \code{"Escherichia coli"} @@ -54,6 +54,7 @@ For convenience, some entries were added manually: \item 11 entries of \emph{Streptococcus} (beta-haemolytic: groups A, B, C, D, F, G, H, K and unspecified; other: viridans, milleri) \item 2 entries of \emph{Staphylococcus} (coagulase-negative (CoNS) and coagulase-positive (CoPS)) \item 3 entries of \emph{Trichomonas} (\emph{T. vaginalis}, and its family and genus) +\item 4 entries of \emph{Toxoplasma} (\emph{T. gondii}, and its order, family and genus) \item 1 entry of \emph{Candida} (\emph{C. krusei}), that is not (yet) in the Catalogue of Life \item 1 entry of \emph{Blastocystis} (\emph{B. hominis}), although it officially does not exist (Noel \emph{et al.} 2005, PMID 15634993) \item 1 entry of \emph{Moraxella} (\emph{M. catarrhalis}), which was formally named \emph{Branhamella catarrhalis} (Catlin, 1970) though this change was never accepted within the field of clinical microbiology @@ -64,15 +65,9 @@ For convenience, some entries were added manually: \subsection{Direct download}{ -This data set is available as 'flat file' for use even without \R - you can find the file here: -\itemize{ -\item \url{https://github.com/msberends/AMR/raw/main/data-raw/microorganisms.txt} -} +This data set is available as 'flat file' for use even without \R - you can find the file here: \url{https://github.com/msberends/AMR/raw/main/data-raw/microorganisms.txt}. -The file in \R format (with preserved data structure) can be found here: -\itemize{ -\item \url{https://github.com/msberends/AMR/raw/main/data/microorganisms.rda} -} +The file in \R format (with preserved data structure) can be found here: \url{https://github.com/msberends/AMR/raw/main/data/microorganisms.rda}. } } \section{About the Records from LPSN (see \emph{Source})}{