update mo algorithm

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
-Version: 1.8.2.9065
+Version: 1.8.2.9066
-Date: 2022-12-19
+Date: 2022-12-20
 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

NEWS.md

@@ -1,4 +1,4 @@
-# AMR 1.8.2.9065
+# AMR 1.8.2.9066
 
 *(this beta version will eventually become v2.0! We're happy to reach a new major milestone soon!)*
 

R/mo_matching_score.R

@@ -52,14 +52,16 @@
 #'
 #' The grouping into human pathogenic prevalence (\eqn{p}) is based on recent work from Bartlett *et al.* (2022, \doi{10.1099/mic.0.001269}) who extensively studied medical-scientific literature to categorise all bacterial species into these groups:
 #' 
-#' - **Established**, if a taxonomic species has infected at least three persons in three or more references. These records have `prevalence = 1.0` in the [microorganisms] data set.
+#' - **Established**, if a taxonomic species has infected at least three persons in three or more references. These records have `prevalence = 1.0` in the [microorganisms] data set;
-#' - **Putative**, if a taxonomic species has fewer than three known cases. These records have `prevalence = 2.0` in the [microorganisms] data set.
+#' - **Putative**, if a taxonomic species has fewer than three known cases. These records have `prevalence = 1.25` in the [microorganisms] data set.
 #' 
 #' Furthermore,
 #' 
-#' - Any *other* bacterial genus, species or subspecies of which the genus is present in the two aforementioned groups, has `prevalence = 2.5` in the [microorganisms] data set. 
+#' - Any genus present in the **established** list also has `prevalence = 1.0` in the [microorganisms] data set;
-#' - Any *non-bacterial* genus, species or subspecies of which the genus is present in the following list, also has `prevalence = 2.5` in the [microorganisms] data set: `r vector_or(MO_PREVALENT_GENERA, quotes = "*")`.
+#' - Any other genus present in the **putative** list has `prevalence = 1.25` in the [microorganisms] data set;
-#' - All other records have `prevalence = 3.0` in the [microorganisms] data set.
+#' - Any other species or subspecies of which the genus is present in the two aforementioned groups, has `prevalence = 1.5` in the [microorganisms] data set;
+#' - Any *non-bacterial* genus, species or subspecies of which the genus is present in the following list, has `prevalence = 1.5` in the [microorganisms] data set: `r vector_or(MO_PREVALENT_GENERA, quotes = "*")`;
+#' - All other records have `prevalence = 2.0` in the [microorganisms] data set.
 #'
 #' When calculating the matching score, all characters in \eqn{x} and \eqn{n} are ignored that are other than A-Z, a-z, 0-9, spaces and parentheses.
 #'

R/mo_property.R

@@ -840,7 +840,7 @@ mo_validate <- function(x, property, language, keep_synonyms = keep_synonyms, ..
   } else if (property == "snomed") {
     return(sort(as.character(eval(parse(text = x)))))
   } else {
-    # everything else is character
+    # everything else as character
     return(as.character(x))
   }
 }

data-raw/microorganisms.md5

@@ -1 +1 @@
-9e75112567e7786a6712024730056057
+810cc621f75ee69a51cfe6726ab46398

data-raw/reproduction_of_microorganisms.R

@@ -831,35 +831,50 @@ putative <- pathogens %>%
 established <- established[established %unlike% "unknown"]
 putative <- putative[putative %unlike% "unknown"]
 
-other_bacterial_genera <- c(established, putative) %>% 
+established_genera <- established %>% 
   strsplit(" ", fixed = TRUE) %>% 
   sapply(function(x) x[1]) %>% 
   sort() %>% 
   unique()
 
-other_genera <- AMR:::MO_PREVALENT_GENERA %>% 
+putative_genera <- putative %>% 
+  strsplit(" ", fixed = TRUE) %>% 
+  sapply(function(x) x[1]) %>% 
+  sort() %>% 
+  unique()
+
+nonbacterial_genera <- AMR:::MO_PREVALENT_GENERA %>% 
   c(unlist(mo_current(.)),
     unlist(mo_synonyms(., keep_synonyms = FALSE))) %>% 
   strsplit(" ", fixed = TRUE) %>% 
   sapply(function(x) x[1]) %>% 
   sort() %>% 
   unique()
-other_genera <- other_genera[other_genera %unlike% "unknown"]
+nonbacterial_genera <- nonbacterial_genera[nonbacterial_genera %unlike% "unknown"]
 
 # update prevalence based on taxonomy (following the recent and thorough work of Bartlett et al., 2022)
 # see https://doi.org/10.1099/mic.0.001269
 taxonomy <- taxonomy %>% 
   mutate(prevalence = case_when(
-    # 'established' gets a 1 and means 'have infected at least three persons in three or more references'
+    # 'established' means 'have infected at least three persons in three or more references'
-    paste(genus, species) %in% established & rank %in% c("genus", "species", "subspecies") ~ 1.0,
+    paste(genus, species) %in% established & rank %in% c("species", "subspecies") ~ 1.0,
-    # 'putative' gets a 2 and  means 'fewer than three known cases'
+    # other genera in the 'established' group
-    paste(genus, species) %in% putative & rank %in% c("genus", "species", "subspecies") ~ 2.0,
+    genus %in% established_genera & rank == "genus" ~ 1.0,
-    # other species from a genus in either group get a 2.5
+    
-    genus %in% other_bacterial_genera & rank %in% c("genus", "species", "subspecies") ~ 2.5,
+    # 'putative' means 'fewer than three known cases'
+    paste(genus, species) %in% putative & rank %in% c("species", "subspecies") ~ 1.25,
+    # other genera in the 'putative' group
+    genus %in% putative_genera & rank == "genus" ~ 1.25,
+    
+    # species and subspecies in 'established' and 'putative' groups
+    genus %in% c(established_genera, putative_genera) & rank %in% c("species", "subspecies") ~ 1.5,
+    # other species from a genus in either group
+    genus %in% nonbacterial_genera & rank %in% c("genus", "species", "subspecies") ~ 1.5,
     # we keep track of prevalent genera too of non-bacterial species
-    genus %in% AMR:::MO_PREVALENT_GENERA & kingdom != "Bacteria" & rank %in% c("genus", "species", "subspecies") ~ 2.5,
+    genus %in% AMR:::MO_PREVALENT_GENERA & kingdom != "Bacteria" & rank %in% c("genus", "species", "subspecies") ~ 1.5,
-    # all others get a 3
+    
-    TRUE ~ 3.0))
+    # all others
+    TRUE ~ 2.0))
 
 table(taxonomy$prevalence, useNA = "always")
 # (a lot will be removed further below)

data-raw/salmonellae.R

@@ -825,6 +825,7 @@ serovars <- c("Aachen",
               "Leipzig",
               "Leith",
               "Lekke",
+              "Lemmer",
               "Lene",
               "Leoben",
               "Leopoldville",

man/as.mo.Rd

@@ -145,20 +145,22 @@ where:
 
 The grouping into human pathogenic prevalence (\eqn{p}) is based on recent work from Bartlett \emph{et al.} (2022, \doi{10.1099/mic.0.001269}) who extensively studied medical-scientific literature to categorise all bacterial species into these groups:
 \itemize{
-\item \strong{Established}, if a taxonomic species has infected at least three persons in three or more references. These records have \code{prevalence = 1.0} in the \link{microorganisms} data set.
+\item \strong{Established}, if a taxonomic species has infected at least three persons in three or more references. These records have \code{prevalence = 1.0} in the \link{microorganisms} data set;
-\item \strong{Putative}, if a taxonomic species has fewer than three known cases. These records have \code{prevalence = 2.0} in the \link{microorganisms} data set.
+\item \strong{Putative}, if a taxonomic species has fewer than three known cases. These records have \code{prevalence = 1.25} in the \link{microorganisms} data set.
 }
 
 Furthermore,
 \itemize{
-\item Any \emph{other} bacterial genus, species or subspecies of which the genus is present in the two aforementioned groups, has \code{prevalence = 2.5} in the \link{microorganisms} data set.
+\item Any genus present in the \strong{established} list also has \code{prevalence = 1.0} in the \link{microorganisms} data set;
-\item Any \emph{non-bacterial} genus, species or subspecies of which the genus is present in the following list, also has \code{prevalence = 2.5} in the \link{microorganisms} data set: \emph{Absidia}, \emph{Acanthamoeba}, \emph{Acremonium}, \emph{Aedes}, \emph{Alternaria}, \emph{Amoeba}, \emph{Ancylostoma}, \emph{Angiostrongylus}, \emph{Anisakis}, \emph{Anopheles}, \emph{Apophysomyces}, \emph{Aspergillus}, \emph{Aureobasidium}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Blastomyces}, \emph{Candida}, \emph{Capillaria}, \emph{Chaetomium}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Contracaecum}, \emph{Cordylobia}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Demodex}, \emph{Dermatobia}, \emph{Dientamoeba}, \emph{Diphyllobothrium}, \emph{Dirofilaria}, \emph{Echinostoma}, \emph{Entamoeba}, \emph{Enterobius}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Fasciola}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Giardia}, \emph{Haloarcula}, \emph{Halobacterium}, \emph{Halococcus}, \emph{Hendersonula}, \emph{Heterophyes}, \emph{Histomonas}, \emph{Histoplasma}, \emph{Hymenolepis}, \emph{Hypomyces}, \emph{Hysterothylacium}, \emph{Leishmania}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Metagonimus}, \emph{Meyerozyma}, \emph{Microsporidium}, \emph{Microsporum}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Necator}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oesophagostomum}, \emph{Oidiodendron}, \emph{Opisthorchis}, \emph{Pediculus}, \emph{Phlebotomus}, \emph{Phoma}, \emph{Pichia}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Pneumocystis}, \emph{Pseudallescheria}, \emph{Pseudoterranova}, \emph{Pulex}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Saccharomyces}, \emph{Sarcoptes}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Spirometra}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Strongyloides}, \emph{Syngamus}, \emph{Taenia}, \emph{Toxocara}, \emph{Trichinella}, \emph{Trichobilharzia}, \emph{Trichoderma}, \emph{Trichomonas}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Trichostrongylus}, \emph{Trichuris}, \emph{Tritirachium}, \emph{Trombicula}, \emph{Trypanosoma}, \emph{Tunga} or \emph{Wuchereria}.
+\item Any other genus present in the \strong{putative} list has \code{prevalence = 1.25} in the \link{microorganisms} data set;
-\item All other records have \code{prevalence = 3.0} in the \link{microorganisms} data set.
+\item Any other species or subspecies of which the genus is present in the two aforementioned groups, has \code{prevalence = 1.5} in the \link{microorganisms} data set;
+\item Any \emph{non-bacterial} genus, species or subspecies of which the genus is present in the following list, has \code{prevalence = 1.5} in the \link{microorganisms} data set: \emph{Absidia}, \emph{Acanthamoeba}, \emph{Acremonium}, \emph{Aedes}, \emph{Alternaria}, \emph{Amoeba}, \emph{Ancylostoma}, \emph{Angiostrongylus}, \emph{Anisakis}, \emph{Anopheles}, \emph{Apophysomyces}, \emph{Aspergillus}, \emph{Aureobasidium}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Blastomyces}, \emph{Candida}, \emph{Capillaria}, \emph{Chaetomium}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Contracaecum}, \emph{Cordylobia}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Demodex}, \emph{Dermatobia}, \emph{Dientamoeba}, \emph{Diphyllobothrium}, \emph{Dirofilaria}, \emph{Echinostoma}, \emph{Entamoeba}, \emph{Enterobius}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Fasciola}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Giardia}, \emph{Haloarcula}, \emph{Halobacterium}, \emph{Halococcus}, \emph{Hendersonula}, \emph{Heterophyes}, \emph{Histomonas}, \emph{Histoplasma}, \emph{Hymenolepis}, \emph{Hypomyces}, \emph{Hysterothylacium}, \emph{Leishmania}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Metagonimus}, \emph{Meyerozyma}, \emph{Microsporidium}, \emph{Microsporum}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Necator}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oesophagostomum}, \emph{Oidiodendron}, \emph{Opisthorchis}, \emph{Pediculus}, \emph{Phlebotomus}, \emph{Phoma}, \emph{Pichia}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Pneumocystis}, \emph{Pseudallescheria}, \emph{Pseudoterranova}, \emph{Pulex}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Saccharomyces}, \emph{Sarcoptes}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Spirometra}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Strongyloides}, \emph{Syngamus}, \emph{Taenia}, \emph{Toxocara}, \emph{Trichinella}, \emph{Trichobilharzia}, \emph{Trichoderma}, \emph{Trichomonas}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Trichostrongylus}, \emph{Trichuris}, \emph{Tritirachium}, \emph{Trombicula}, \emph{Trypanosoma}, \emph{Tunga} or \emph{Wuchereria};
+\item All other records have \code{prevalence = 2.0} in the \link{microorganisms} data set.
 }
 
 When calculating the matching score, all characters in \eqn{x} and \eqn{n} are ignored that are other than A-Z, a-z, 0-9, spaces and parentheses.
 
-All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.095}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
+All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.159}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
 }
 
 \section{Reference Data Publicly Available}{

man/microorganisms.Rd

@@ -3,9 +3,9 @@
 \docType{data}
 \name{microorganisms}
 \alias{microorganisms}
-\title{Data Set with 52,140 Microorganisms}
+\title{Data Set with 52,141 Microorganisms}
 \format{
-A \link[tibble:tibble]{tibble} with 52,140 observations and 22 variables:
+A \link[tibble:tibble]{tibble} with 52,141 observations and 22 variables:
 \itemize{
 \item \code{mo}\cr ID of microorganism as used by this package
 \item \code{fullname}\cr Full name, like \code{"Escherichia coli"}. For the taxonomic ranks genus, species and subspecies, this is the 'pasted' text of genus, species, and subspecies. For all taxonomic ranks higher than genus, this is the name of the taxon.

man/mo_matching_score.Rd

@@ -37,20 +37,22 @@ where:
 
 The grouping into human pathogenic prevalence (\eqn{p}) is based on recent work from Bartlett \emph{et al.} (2022, \doi{10.1099/mic.0.001269}) who extensively studied medical-scientific literature to categorise all bacterial species into these groups:
 \itemize{
-\item \strong{Established}, if a taxonomic species has infected at least three persons in three or more references. These records have \code{prevalence = 1.0} in the \link{microorganisms} data set.
+\item \strong{Established}, if a taxonomic species has infected at least three persons in three or more references. These records have \code{prevalence = 1.0} in the \link{microorganisms} data set;
-\item \strong{Putative}, if a taxonomic species has fewer than three known cases. These records have \code{prevalence = 2.0} in the \link{microorganisms} data set.
+\item \strong{Putative}, if a taxonomic species has fewer than three known cases. These records have \code{prevalence = 1.25} in the \link{microorganisms} data set.
 }
 
 Furthermore,
 \itemize{
-\item Any \emph{other} bacterial genus, species or subspecies of which the genus is present in the two aforementioned groups, has \code{prevalence = 2.5} in the \link{microorganisms} data set.
+\item Any genus present in the \strong{established} list also has \code{prevalence = 1.0} in the \link{microorganisms} data set;
-\item Any \emph{non-bacterial} genus, species or subspecies of which the genus is present in the following list, also has \code{prevalence = 2.5} in the \link{microorganisms} data set: \emph{Absidia}, \emph{Acanthamoeba}, \emph{Acremonium}, \emph{Aedes}, \emph{Alternaria}, \emph{Amoeba}, \emph{Ancylostoma}, \emph{Angiostrongylus}, \emph{Anisakis}, \emph{Anopheles}, \emph{Apophysomyces}, \emph{Aspergillus}, \emph{Aureobasidium}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Blastomyces}, \emph{Candida}, \emph{Capillaria}, \emph{Chaetomium}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Contracaecum}, \emph{Cordylobia}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Demodex}, \emph{Dermatobia}, \emph{Dientamoeba}, \emph{Diphyllobothrium}, \emph{Dirofilaria}, \emph{Echinostoma}, \emph{Entamoeba}, \emph{Enterobius}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Fasciola}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Giardia}, \emph{Haloarcula}, \emph{Halobacterium}, \emph{Halococcus}, \emph{Hendersonula}, \emph{Heterophyes}, \emph{Histomonas}, \emph{Histoplasma}, \emph{Hymenolepis}, \emph{Hypomyces}, \emph{Hysterothylacium}, \emph{Leishmania}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Metagonimus}, \emph{Meyerozyma}, \emph{Microsporidium}, \emph{Microsporum}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Necator}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oesophagostomum}, \emph{Oidiodendron}, \emph{Opisthorchis}, \emph{Pediculus}, \emph{Phlebotomus}, \emph{Phoma}, \emph{Pichia}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Pneumocystis}, \emph{Pseudallescheria}, \emph{Pseudoterranova}, \emph{Pulex}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Saccharomyces}, \emph{Sarcoptes}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Spirometra}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Strongyloides}, \emph{Syngamus}, \emph{Taenia}, \emph{Toxocara}, \emph{Trichinella}, \emph{Trichobilharzia}, \emph{Trichoderma}, \emph{Trichomonas}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Trichostrongylus}, \emph{Trichuris}, \emph{Tritirachium}, \emph{Trombicula}, \emph{Trypanosoma}, \emph{Tunga} or \emph{Wuchereria}.
+\item Any other genus present in the \strong{putative} list has \code{prevalence = 1.25} in the \link{microorganisms} data set;
-\item All other records have \code{prevalence = 3.0} in the \link{microorganisms} data set.
+\item Any other species or subspecies of which the genus is present in the two aforementioned groups, has \code{prevalence = 1.5} in the \link{microorganisms} data set;
+\item Any \emph{non-bacterial} genus, species or subspecies of which the genus is present in the following list, has \code{prevalence = 1.5} in the \link{microorganisms} data set: \emph{Absidia}, \emph{Acanthamoeba}, \emph{Acremonium}, \emph{Aedes}, \emph{Alternaria}, \emph{Amoeba}, \emph{Ancylostoma}, \emph{Angiostrongylus}, \emph{Anisakis}, \emph{Anopheles}, \emph{Apophysomyces}, \emph{Aspergillus}, \emph{Aureobasidium}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Blastomyces}, \emph{Candida}, \emph{Capillaria}, \emph{Chaetomium}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Contracaecum}, \emph{Cordylobia}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Demodex}, \emph{Dermatobia}, \emph{Dientamoeba}, \emph{Diphyllobothrium}, \emph{Dirofilaria}, \emph{Echinostoma}, \emph{Entamoeba}, \emph{Enterobius}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Fasciola}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Giardia}, \emph{Haloarcula}, \emph{Halobacterium}, \emph{Halococcus}, \emph{Hendersonula}, \emph{Heterophyes}, \emph{Histomonas}, \emph{Histoplasma}, \emph{Hymenolepis}, \emph{Hypomyces}, \emph{Hysterothylacium}, \emph{Leishmania}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Metagonimus}, \emph{Meyerozyma}, \emph{Microsporidium}, \emph{Microsporum}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Necator}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oesophagostomum}, \emph{Oidiodendron}, \emph{Opisthorchis}, \emph{Pediculus}, \emph{Phlebotomus}, \emph{Phoma}, \emph{Pichia}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Pneumocystis}, \emph{Pseudallescheria}, \emph{Pseudoterranova}, \emph{Pulex}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Saccharomyces}, \emph{Sarcoptes}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Spirometra}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Strongyloides}, \emph{Syngamus}, \emph{Taenia}, \emph{Toxocara}, \emph{Trichinella}, \emph{Trichobilharzia}, \emph{Trichoderma}, \emph{Trichomonas}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Trichostrongylus}, \emph{Trichuris}, \emph{Tritirachium}, \emph{Trombicula}, \emph{Trypanosoma}, \emph{Tunga} or \emph{Wuchereria};
+\item All other records have \code{prevalence = 2.0} in the \link{microorganisms} data set.
 }
 
 When calculating the matching score, all characters in \eqn{x} and \eqn{n} are ignored that are other than A-Z, a-z, 0-9, spaces and parentheses.
 
-All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.095}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
+All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.159}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
 }
 
 \section{Reference Data Publicly Available}{

man/mo_property.Rd

@@ -328,20 +328,22 @@ where:
 
 The grouping into human pathogenic prevalence (\eqn{p}) is based on recent work from Bartlett \emph{et al.} (2022, \doi{10.1099/mic.0.001269}) who extensively studied medical-scientific literature to categorise all bacterial species into these groups:
 \itemize{
-\item \strong{Established}, if a taxonomic species has infected at least three persons in three or more references. These records have \code{prevalence = 1.0} in the \link{microorganisms} data set.
+\item \strong{Established}, if a taxonomic species has infected at least three persons in three or more references. These records have \code{prevalence = 1.0} in the \link{microorganisms} data set;
-\item \strong{Putative}, if a taxonomic species has fewer than three known cases. These records have \code{prevalence = 2.0} in the \link{microorganisms} data set.
+\item \strong{Putative}, if a taxonomic species has fewer than three known cases. These records have \code{prevalence = 1.25} in the \link{microorganisms} data set.
 }
 
 Furthermore,
 \itemize{
-\item Any \emph{other} bacterial genus, species or subspecies of which the genus is present in the two aforementioned groups, has \code{prevalence = 2.5} in the \link{microorganisms} data set.
+\item Any genus present in the \strong{established} list also has \code{prevalence = 1.0} in the \link{microorganisms} data set;
-\item Any \emph{non-bacterial} genus, species or subspecies of which the genus is present in the following list, also has \code{prevalence = 2.5} in the \link{microorganisms} data set: \emph{Absidia}, \emph{Acanthamoeba}, \emph{Acremonium}, \emph{Aedes}, \emph{Alternaria}, \emph{Amoeba}, \emph{Ancylostoma}, \emph{Angiostrongylus}, \emph{Anisakis}, \emph{Anopheles}, \emph{Apophysomyces}, \emph{Aspergillus}, \emph{Aureobasidium}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Blastomyces}, \emph{Candida}, \emph{Capillaria}, \emph{Chaetomium}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Contracaecum}, \emph{Cordylobia}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Demodex}, \emph{Dermatobia}, \emph{Dientamoeba}, \emph{Diphyllobothrium}, \emph{Dirofilaria}, \emph{Echinostoma}, \emph{Entamoeba}, \emph{Enterobius}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Fasciola}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Giardia}, \emph{Haloarcula}, \emph{Halobacterium}, \emph{Halococcus}, \emph{Hendersonula}, \emph{Heterophyes}, \emph{Histomonas}, \emph{Histoplasma}, \emph{Hymenolepis}, \emph{Hypomyces}, \emph{Hysterothylacium}, \emph{Leishmania}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Metagonimus}, \emph{Meyerozyma}, \emph{Microsporidium}, \emph{Microsporum}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Necator}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oesophagostomum}, \emph{Oidiodendron}, \emph{Opisthorchis}, \emph{Pediculus}, \emph{Phlebotomus}, \emph{Phoma}, \emph{Pichia}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Pneumocystis}, \emph{Pseudallescheria}, \emph{Pseudoterranova}, \emph{Pulex}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Saccharomyces}, \emph{Sarcoptes}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Spirometra}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Strongyloides}, \emph{Syngamus}, \emph{Taenia}, \emph{Toxocara}, \emph{Trichinella}, \emph{Trichobilharzia}, \emph{Trichoderma}, \emph{Trichomonas}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Trichostrongylus}, \emph{Trichuris}, \emph{Tritirachium}, \emph{Trombicula}, \emph{Trypanosoma}, \emph{Tunga} or \emph{Wuchereria}.
+\item Any other genus present in the \strong{putative} list has \code{prevalence = 1.25} in the \link{microorganisms} data set;
-\item All other records have \code{prevalence = 3.0} in the \link{microorganisms} data set.
+\item Any other species or subspecies of which the genus is present in the two aforementioned groups, has \code{prevalence = 1.5} in the \link{microorganisms} data set;
+\item Any \emph{non-bacterial} genus, species or subspecies of which the genus is present in the following list, has \code{prevalence = 1.5} in the \link{microorganisms} data set: \emph{Absidia}, \emph{Acanthamoeba}, \emph{Acremonium}, \emph{Aedes}, \emph{Alternaria}, \emph{Amoeba}, \emph{Ancylostoma}, \emph{Angiostrongylus}, \emph{Anisakis}, \emph{Anopheles}, \emph{Apophysomyces}, \emph{Aspergillus}, \emph{Aureobasidium}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Blastomyces}, \emph{Candida}, \emph{Capillaria}, \emph{Chaetomium}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Contracaecum}, \emph{Cordylobia}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Demodex}, \emph{Dermatobia}, \emph{Dientamoeba}, \emph{Diphyllobothrium}, \emph{Dirofilaria}, \emph{Echinostoma}, \emph{Entamoeba}, \emph{Enterobius}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Fasciola}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Giardia}, \emph{Haloarcula}, \emph{Halobacterium}, \emph{Halococcus}, \emph{Hendersonula}, \emph{Heterophyes}, \emph{Histomonas}, \emph{Histoplasma}, \emph{Hymenolepis}, \emph{Hypomyces}, \emph{Hysterothylacium}, \emph{Leishmania}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Metagonimus}, \emph{Meyerozyma}, \emph{Microsporidium}, \emph{Microsporum}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Necator}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oesophagostomum}, \emph{Oidiodendron}, \emph{Opisthorchis}, \emph{Pediculus}, \emph{Phlebotomus}, \emph{Phoma}, \emph{Pichia}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Pneumocystis}, \emph{Pseudallescheria}, \emph{Pseudoterranova}, \emph{Pulex}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Saccharomyces}, \emph{Sarcoptes}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Spirometra}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Strongyloides}, \emph{Syngamus}, \emph{Taenia}, \emph{Toxocara}, \emph{Trichinella}, \emph{Trichobilharzia}, \emph{Trichoderma}, \emph{Trichomonas}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Trichostrongylus}, \emph{Trichuris}, \emph{Tritirachium}, \emph{Trombicula}, \emph{Trypanosoma}, \emph{Tunga} or \emph{Wuchereria};
+\item All other records have \code{prevalence = 2.0} in the \link{microorganisms} data set.
 }
 
 When calculating the matching score, all characters in \eqn{x} and \eqn{n} are ignored that are other than A-Z, a-z, 0-9, spaces and parentheses.
 
-All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.095}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
+All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.159}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
 }
 
 \section{Source}{