update to BOLD v5

initial update, should work again

.gitignore

@@ -2,3 +2,4 @@
 *.history
 *.history
 .DS_Store
+PrimerMiner/.DS_Store

PrimerMiner/R/Download_bold.R

@@ -24,20 +24,32 @@ bold.apikey(apikey_bold)
 
 for (k in 1:length(taxon)){
 time <- Sys.time() # get time
-data <- bold.public.search(taxonomy = taxon[k]) # fetch process IDs for specific taxons
+bold.data <- bold.public.search(taxonomy = taxon[k]) # fetch process IDs for specific taxons
 
+data <- bold.fetch(get_by = "processid", identifiers = bold.data$processid)
+
+# save tsv (without any processing)
+if(save_bold_tsv){
+write.table(data, file=paste(folder_path, taxon[k], "_BOLD.tsv"), quote=F, sep='\t', row.names=F)
+}
+
+# filter for only needed marker codes
+data <- data[data$marker_code == marker_bold,]
+
+# remove gabs from sequences
+data$nuc <- gsub("-", "", data$nuc)
+data <- data[nchar(data$nuc)>1,]
 
 
 if(length(data)!=0){
 cat(file=paste(folder_path, taxon[k], "_BOLD.fasta", sep="")) # delet old file
-for (i in 1:length(data)){
-exp <- paste(">", data[i][[1]][1], "_", data[i][[1]][2], "\n", gsub("-", "", data[i][[1]][4]), "\n", sep="")
-cat(exp, file=paste(folder_path, taxon[k], "_BOLD.fasta", sep=""), append=T)
-}
+exp <- paste(">", data$processid, "___", data$order, "_", data$species, "\n", data$nuc, "\n", sep="")
+
+cat(exp, file=paste(folder_path, taxon[k], "_BOLD.fasta", sep=""), append=T, sep="")
 }
 time <- Sys.time() - time
-message(paste("Downloaded ", length(data)," sequences for ", taxon[k], " in ", format(time, digits=2), " from BOLD.", sep=""))
-cat(paste(taxon[k],"\t", length(data), "\t", format(time, digits=2), "\n", sep=""), file= logfile, sep="", append=T)
+message(paste("Downloaded ", nrow(data)," sequences for ", taxon[k], " in ", format(time, digits=2), " from BOLD.", sep=""))
+cat(paste(taxon[k],"\t", nrow(data), "\t", format(time, digits=2), "\n", sep=""), file= logfile, sep="", append=T)
 }
 cat("#Bold_data_end\n\n", file= logfile, sep="", append=T)
 }

PrimerMiner/R/batch_down.R

@@ -49,6 +49,7 @@ if(download_and_cluster){
 # download data!
 
 if (Download){
+message("Starting to downloand data for ", subFolder, ": \"", paste(taxa, collapse="\", \""), "\"")
 if (download_bold){Download_BOLD(taxa, folder= subFolderPath, setwd=subFolder)}
 if (download_GB){Download_GB(taxa, folder= subFolderPath, marker=Marker, maxlength= maxlength_GB, custom_query= custom_query_GB, setwd=subFolder, GB_subset=GB_Subset)}
 if (download_mt){Download_mito(taxa, folder= subFolderPath, minlength= minlength_mt, maxlength= maxlength_mt, custom_query = custom_query_mt, setwd=subFolder, MT_Subset= mt_subset)

README.md

@@ -13,17 +13,19 @@ Please take a look at the PrimerMiner wiki for detailed package documentation an
 
 1) Installation
 You can install PrimerMiner directly from GitHub. You will also need to install [BOLDconnectR](https://github.com/boldsystems-central/BOLDconnectR).
-`install.packages("devtools")`
-`library("devtools")`
-`install_github("boldsystems-central/BOLDconnectR")`
-`install_github("VascoElbrecht/PrimerMiner", subdir="PrimerMiner")`
+```
+install.packages("devtools")
+library("devtools")
+install_github("boldsystems-central/BOLDconnectR")
+install_github("VascoElbrecht/PrimerMiner", subdir="PrimerMiner")
+```
 
 Alternatively, you can download a specific PrimerMiner version manually and install it with:
 `install.packages("path_to_package_file", repos = NULL, type="source", dependencies=T)`
 
 Load the package with `library("PrimerMiner")`. You find all the commands and an executable example in the Sample_Data!
 
-Important: you will need the apikey from you BOLD login to download bold data (currently November 2024 its not checked, any key works, but this might change in the future).
+Important: you will need the apikey from you BOLD login to download bold data. You can find it under user settings in your BOLD login.
 
 2) Batch downloading sequences
 Generate the configuration file by runing `batch_config("config.txt")`in R. Edit this file to review and change the default settings.