update README

Author: Jtrachsel

README.Rmd

@@ -10,7 +10,7 @@ knitr::opts_chunk$set(echo = TRUE)
 ## Installation
 
 *Requires R >= 4.0* 
-*Requires biostrings, need to install from biocmanager*
+*Requires Biostrings, need to install from BiocManager*
 ```{r, eval=FALSE}
 BiocManager::install('Biostrings')
 remotes::install_github('jtrachsel/pdtools')
@@ -94,7 +94,7 @@ ftp_paths <-
 
 # or within R:
 # set names to the desired path 
-names(ftp_paths) <-paste0('./data/',meta_filt$asm_acc, '.fna')
+names(ftp_paths) <-paste0('./data/',meta_filt$asm_acc, '.fna.gz')
 
 Map(function(u, d) download.file(u, d, mode="wb"), ftp_paths, names(ftp_paths))
 
@@ -136,6 +136,8 @@ get_pangenome_representatives(pan_mat = pan_PA, SEED = 2, desired_coverage = .99
 
 
 ## TODO  
+- Stats on available organisms, num clusters, most recent isolate
+  https://www.ncbi.nlm.nih.gov/pathogens/organisms/
 - update_collection() function?
   - Should take and old metadata file and a new metadata file as inputs.  
   - return a vector of new genomes that were not present in the old list. 

README.md

@@ -3,8 +3,8 @@ pdtools
 
 ## Installation
 
-*Requires R >= 4.1* *Requires biostrings, need to install from
-biocmanager*
+*Requires R >= 4.0* *Requires Biostrings, need to install from
+BiocManager*
 
 ``` r
 BiocManager::install('Biostrings')
@@ -23,11 +23,9 @@ Detection project](https://www.ncbi.nlm.nih.gov/pathogens/)
 #### List available organisms
 
 ``` r
-
 library(pdtools)
 
 list_organisms()
-
 ```
 
 #### Download the most recent metadata for an organism:
@@ -37,7 +35,6 @@ system('mkdir data')
 download_most_recent_complete('Campylobacter', folder_prefix = './data/')
 ```
 
-
 #### Join downloads: metadata and SNP clusters
 
 ``` r
@@ -89,7 +86,7 @@ ftp_paths <-
 
 # or within R:
 # set names to the desired path 
-names(ftp_paths) <-paste0('./data/',meta_filt$asm_acc, '.fna')
+names(ftp_paths) <-paste0('./data/',meta_filt$asm_acc, '.fna.gz')
 
 Map(function(u, d) download.file(u, d, mode="wb"), ftp_paths, names(ftp_paths))
 ```
@@ -125,6 +122,8 @@ get_pangenome_representatives(pan_mat = pan_PA, SEED = 2, desired_coverage = .99
 
 ## TODO
 
+-   Stats on available organisms, num clusters, most recent isolate
+    <https://www.ncbi.nlm.nih.gov/pathogens/organisms/>
 -   update\_collection() function?
     -   Should take and old metadata file and a new metadata file as
         inputs.