P281424/AMR
1
0 Fork 0
mirror of https://github.com/msberends/AMR.git synced 2026-10-01 04:13:33 +02:00
Code Releases Activity

incorporate Bartlett et al (2022)

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends committed 2022-12-19 15:32:41 +01:00
1 parent 23fe427cbc
commit b1b7534c78
24 files changed
+36375 -36304
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

data-raw/_pre_commit_hook.R
+15 -23
View File
@@ -168,29 +168,21 @@ MO_STREP_ABCG <- AMR_env$MO_lookup$mo[which(AMR_env$MO_lookup$genus == "Streptoc
))]
MO_FULLNAME_LOWER <- create_MO_fullname_lower()
MO_PREVALENT_GENERA <- c(
"Absidia", "Acanthamoeba", "Acholeplasma", "Acremonium", "Actinotignum", "Aedes", "Alistipes", "Alloprevotella",
"Alternaria", "Amoeba", "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", "Christensenella", "Chryseobacterium", "Chrysonilia", "Cladophialophora", "Cladosporium",
"Conidiobolus", "Contracaecum", "Cordylobia", "Cryptococcus", "Curvularia", "Deinococcus", "Demodex",
"Dermatobia", "Dientamoeba", "Diphyllobothrium", "Dirofilaria", "Dysgonomonas", "Echinostoma", "Elizabethkingia",
"Empedobacter", "Entamoeba", "Enterobius", "Exophiala", "Exserohilum", "Fasciola", "Flavobacterium", "Fonsecaea",
"Fusarium", "Fusobacterium", "Giardia", "Haloarcula", "Halobacterium", "Halococcus", "Hendersonula",
"Heterophyes", "Histomonas", "Histoplasma", "Hymenolepis", "Hypomyces", "Hysterothylacium", "Leishmania", "Lelliottia",
"Leptosphaeria", "Leptotrichia", "Lucilia", "Lumbricus", "Malassezia", "Malbranchea", "Metagonimus", "Meyerozyma",
"Microsporidium", "Microsporum", "Mortierella", "Mucor", "Mycocentrospora", "Mycoplasma", "Myroides", "Necator",
"Nectria", "Ochroconis", "Odoribacter", "Oesophagostomum", "Oidiodendron", "Opisthorchis",
"Ornithobacterium", "Parabacteroides", "Pediculus", "Pedobacter", "Phlebotomus", "Phocaeicola",
"Phocanema", "Phoma", "Pichia", "Piedraia", "Pithomyces", "Pityrosporum", "Pneumocystis", "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", "Trypanosoma", "Trombicula", "Tunga", "Ureaplasma", "Victivallis", "Wautersiella",
"Weeksella", "Wuchereria"
"Absidia", "Acanthamoeba", "Acremonium", "Aedes", "Alternaria", "Amoeba", "Ancylostoma", "Angiostrongylus",
"Anisakis", "Anopheles", "Apophysomyces", "Aspergillus", "Aureobasidium", "Basidiobolus", "Beauveria",
"Blastocystis", "Blastomyces", "Candida", "Capillaria", "Chaetomium", "Chrysonilia", "Cladophialophora",
"Cladosporium", "Conidiobolus", "Contracaecum", "Cordylobia", "Cryptococcus", "Curvularia", "Demodex",
"Dermatobia", "Dientamoeba", "Diphyllobothrium", "Dirofilaria", "Echinostoma", "Entamoeba", "Enterobius",
"Exophiala", "Exserohilum", "Fasciola", "Fonsecaea", "Fusarium", "Giardia", "Haloarcula", "Halobacterium",
"Halococcus", "Hendersonula", "Heterophyes", "Histomonas", "Histoplasma", "Hymenolepis", "Hypomyces",
"Hysterothylacium", "Leishmania", "Malassezia", "Malbranchea", "Metagonimus", "Meyerozyma", "Microsporidium",
"Microsporum", "Mortierella", "Mucor", "Mycocentrospora", "Necator", "Nectria", "Ochroconis", "Oesophagostomum",
"Oidiodendron", "Opisthorchis", "Pediculus", "Phlebotomus", "Phoma", "Pichia", "Piedraia", "Pithomyces",
"Pityrosporum", "Pneumocystis", "Pseudallescheria", "Pseudoterranova", "Pulex", "Rhizomucor", "Rhizopus",
"Rhodotorula", "Saccharomyces", "Sarcoptes", "Scolecobasidium", "Scopulariopsis", "Scytalidium", "Spirometra",
"Sporobolomyces", "Stachybotrys", "Strongyloides", "Syngamus", "Taenia", "Toxocara", "Trichinella", "Trichobilharzia",
"Trichoderma", "Trichomonas", "Trichophyton", "Trichosporon", "Trichostrongylus", "Trichuris", "Tritirachium",
"Trombicula", "Trypanosoma", "Tunga", "Wuchereria"
)
# antibiotic groups
data-raw/eucast_rules.tsv
+6 -6
View File
@@ -69,9 +69,9 @@ genus_species is Moraxella catarrhalis ERY S AZM, CLR, RXT S Moraxella catarrhal
genus_species is Moraxella catarrhalis ERY I AZM, CLR, RXT I Moraxella catarrhalis Breakpoints 10
genus_species is Moraxella catarrhalis ERY R AZM, CLR, RXT R Moraxella catarrhalis Breakpoints 10
genus_species is Moraxella catarrhalis TCY S DOX, MNO S Moraxella catarrhalis Breakpoints 10
genus one_of Actinomyces, Bifidobacterium, Clostridium, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN S AMP, AMX, PIP, TZP, TIC S Anaerobic Gram-positives Breakpoints 10
genus one_of Actinomyces, Bifidobacterium, Clostridium, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN I AMP, AMX, PIP, TZP, TIC I Anaerobic Gram-positives Breakpoints 10
genus one_of Actinomyces, Bifidobacterium, Clostridium, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN R AMP, AMX, PIP, TZP, TIC R Anaerobic Gram-positives Breakpoints 10
genus one_of Actinomyces, Bifidobacterium, Clostridium, Clostridioides, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN S AMP, AMX, PIP, TZP, TIC S Anaerobic Gram-positives Breakpoints 10
genus one_of Actinomyces, Bifidobacterium, Clostridium, Clostridioides, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN I AMP, AMX, PIP, TZP, TIC I Anaerobic Gram-positives Breakpoints 10
genus one_of Actinomyces, Bifidobacterium, Clostridium, Clostridioides, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN R AMP, AMX, PIP, TZP, TIC R Anaerobic Gram-positives Breakpoints 10
genus one_of Bacteroides, Bilophila , Fusobacterium, Mobiluncus, Porphyromonas, Prevotella PEN S AMP, AMX, PIP, TZP, TIC S Anaerobic Gram-negatives Breakpoints 10
genus one_of Bacteroides, Bilophila , Fusobacterium, Mobiluncus, Porphyromonas, Prevotella PEN I AMP, AMX, PIP, TZP, TIC I Anaerobic Gram-negatives Breakpoints 10
genus one_of Bacteroides, Bilophila , Fusobacterium, Mobiluncus, Porphyromonas, Prevotella PEN R AMP, AMX, PIP, TZP, TIC R Anaerobic Gram-negatives Breakpoints 10
@@ -175,9 +175,9 @@ genus_species is Moraxella catarrhalis ERY S AZM, CLR, RXT S Moraxella catarrhal
genus_species is Moraxella catarrhalis ERY I AZM, CLR, RXT I Moraxella catarrhalis Breakpoints 11
genus_species is Moraxella catarrhalis ERY R AZM, CLR, RXT R Moraxella catarrhalis Breakpoints 11
genus_species is Moraxella catarrhalis TCY S DOX, MNO S Moraxella catarrhalis Breakpoints 11
genus one_of Actinomyces, Bifidobacterium, Clostridium, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN S AMP, AMX, PIP, TIC S Anaerobic Gram-positives Breakpoints 11
genus one_of Actinomyces, Bifidobacterium, Clostridium, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN I AMP, AMX, PIP, TIC I Anaerobic Gram-positives Breakpoints 11
genus one_of Actinomyces, Bifidobacterium, Clostridium, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN R AMP, AMX, PIP, TIC R Anaerobic Gram-positives Breakpoints 11
genus one_of Actinomyces, Bifidobacterium, Clostridium, Clostridioides, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN S AMP, AMX, PIP, TIC S Anaerobic Gram-positives Breakpoints 11
genus one_of Actinomyces, Bifidobacterium, Clostridium, Clostridioides, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN I AMP, AMX, PIP, TIC I Anaerobic Gram-positives Breakpoints 11
genus one_of Actinomyces, Bifidobacterium, Clostridium, Clostridioides, Cutibacterium, Eggerthella, Eubacterium, Lactobacillus, Propionibacterium PEN R AMP, AMX, PIP, TIC R Anaerobic Gram-positives Breakpoints 11
genus one_of Bacteroides, Bilophila , Fusobacterium, Mobiluncus, Porphyromonas, Prevotella PEN S AMP, AMX, PIP, TIC S Anaerobic Gram-negatives Breakpoints 11
genus one_of Bacteroides, Bilophila , Fusobacterium, Mobiluncus, Porphyromonas, Prevotella PEN I AMP, AMX, PIP, TIC I Anaerobic Gram-negatives Breakpoints 11
genus one_of Bacteroides, Bilophila , Fusobacterium, Mobiluncus, Porphyromonas, Prevotella PEN R AMP, AMX, PIP, TIC R Anaerobic Gram-negatives Breakpoints 11
Can't render this file because it contains an unexpected character in line 5 and column 96.
data-raw/microorganisms.dta
BIN
View File
Binary file not shown.
data-raw/microorganisms.feather
BIN
View File
Binary file not shown.
data-raw/microorganisms.md5
+1 -1
View File
@@ -1 +1 @@
6e6f44705995094be5eddc00e0878308
9e75112567e7786a6712024730056057
data-raw/microorganisms.parquet
BIN
View File
Binary file not shown.
data-raw/microorganisms.rds
BIN
View File
Binary file not shown.
data-raw/microorganisms.sas
BIN
View File
Binary file not shown.
data-raw/microorganisms.sav
BIN
View File
Binary file not shown.
data-raw/microorganisms.txt
+36198 -36198
View File
File diff suppressed because it is too large. Load diff
data-raw/microorganisms.xlsx
BIN
View File
Binary file not shown.
data-raw/reproduction_of_microorganisms.R
+75 -27
View File
@@ -36,20 +36,29 @@
# 2. Go to https://lpsn.dsmz.de/downloads (register first) and download the latest
# CSV file (~12,5 MB) as "taxonomy.csv". Their API unfortunately does
# not include the full taxonomy and is currently (2022) pretty worthless.
# 3. Set this folder_location to the path where these two files are:
# 3. For data about human pathogens, we use Bartlett et al. (2022),
# https://doi.org/10.1099/mic.0.001269. Their latest supplementary material
# can be found here: https://github.com/padpadpadpad/bartlett_et_al_2022_human_pathogens.
#. Download their latest xlsx file in the `data` folder and save it to our
#. `data-raw` folder.
# 4. Set this folder_location to the path where these two files are:
folder_location <- "~/Downloads/backbone/"
file_gbif <- paste0(folder_location, "Taxon.tsv")
file_lpsn <- paste0(folder_location, "taxonomy.csv")
file_bartlett <- "data-raw/bartlett_et_al_2022_human_pathogens.xlsx"
# 4. Run the rest of this script line by line and check everything :)
if (!file.exists(file_gbif)) stop("GBIF file not found")
if (!file.exists(file_lpsn)) stop("LPSN file not found")
if (!file.exists(file_bartlett)) stop("Bartlett et al. Excel file not found")
library(dplyr)
library(vroom) # to import files
library(rvest) # to scape LPSN website
library(progress) # to show progress bars
library(readxl) # for reading the Bartlett Excel file
devtools::load_all(".") # load AMR package
# Helper functions --------------------------------------------------------
@@ -776,32 +785,6 @@ taxonomy$gbif_parent[taxonomy$rank == "subspecies" & !is.na(taxonomy$gbif)] <- t
all(taxonomy$lpsn_parent %in% taxonomy$lpsn)
all(taxonomy$gbif_parent %in% taxonomy$gbif)
# Add prevalence ----------------------------------------------------------
# update prevalence based on taxonomy (our own JSS paper: Berends MS et al. (2022), DOI 10.18637/jss.v104.i03)
taxonomy <- taxonomy %>%
mutate(prevalence = case_when(
class == "Gammaproteobacteria" |
genus %in% c("Enterococcus", "Staphylococcus", "Streptococcus")
~ 1,
kingdom %in% c("Archaea", "Bacteria", "Chromista", "Fungi") &
(phylum %in% c(
"Sarcomastigophora",
"Firmicutes", # old, now Bacillota
"Bacillota",
"Proteobacteria", # old, now Pseudomonadota
"Pseudomonadota",
"Actinobacteria", # old, now Actinomycetota
"Actinomycetota"
) |
genus %in% AMR:::MO_PREVALENT_GENERA)
~ 2,
TRUE ~ 3
))
table(taxonomy$prevalence, useNA = "always")
# (a lot will be removed further below)
# fix rank
taxonomy <- taxonomy %>%
mutate(rank = case_when(
@@ -817,6 +800,71 @@ taxonomy <- taxonomy %>%
))
# Add prevalence ----------------------------------------------------------
pathogens <- read_excel(file_bartlett, sheet = "Tab 6 Full List")
# get all established, both old and current taxonomic names
established <- pathogens %>%
filter(status == "established") %>%
mutate(fullname = paste(genus, species)) %>%
pull(fullname) %>%
c(unlist(mo_current(.)),
unlist(mo_synonyms(., keep_synonyms = FALSE))) %>%
strsplit(" ", fixed = TRUE) %>%
sapply(function(x) ifelse(length(x) == 1, x, paste(x[1], x[2]))) %>%
sort() %>%
unique()
# get all putative, both old and current taxonomic names
putative <- pathogens %>%
filter(status == "putative") %>%
mutate(fullname = paste(genus, species)) %>%
pull(fullname) %>%
c(unlist(mo_current(.)),
unlist(mo_synonyms(., keep_synonyms = FALSE))) %>%
strsplit(" ", fixed = TRUE) %>%
sapply(function(x) ifelse(length(x) == 1, x, paste(x[1], x[2]))) %>%
sort() %>%
unique()
established <- established[established %unlike% "unknown"]
putative <- putative[putative %unlike% "unknown"]
other_bacterial_genera <- c(established, putative) %>%
strsplit(" ", fixed = TRUE) %>%
sapply(function(x) x[1]) %>%
sort() %>%
unique()
other_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"]
# 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'
paste(genus, species) %in% established & rank %in% c("genus", "species", "subspecies") ~ 1.0,
# 'putative' gets a 2 and means 'fewer than three known cases'
paste(genus, species) %in% putative & rank %in% c("genus", "species", "subspecies") ~ 2.0,
# 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,
# 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,
# all others get a 3
TRUE ~ 3.0))
table(taxonomy$prevalence, useNA = "always")
# (a lot will be removed further below)
# Save intermediate results (2) -------------------------------------------
saveRDS(taxonomy, "data-raw/taxonomy2.rds")