Add much more information about GTDB genomes

erikrikarddaniel · Jul 14, 2020 · 68e8d7d · 68e8d7d
1 parent 089a593
commit 68e8d7d
Show file tree

Hide file tree

Showing 8 changed files with 92 additions and 87 deletions.
diff --git a/conda/meta.yaml b/conda/meta.yaml
@@ -1,4 +1,4 @@
-{% set version = "1.9.7" %}
+{% set version = "1.9.8" %}
 
 package:
   name: pfitmap-db

diff --git a/src/R-test/pf-classify.gtdb.04.expect b/src/R-test/pf-classify.gtdb.04.expect
diff --git a/src/R-test/pf-classify.gtdb.05.expect b/src/R-test/pf-classify.gtdb.05.expect
diff --git a/src/R-test/pf-classify.gtdb.06.expect b/src/R-test/pf-classify.gtdb.06.expect
diff --git a/src/R/pf-classify.r b/src/R/pf-classify.r
@@ -13,7 +13,7 @@ suppressPackageStartupMessages(library(tidyr))
 suppressPackageStartupMessages(library(stringr))
 suppressPackageStartupMessages(library(feather))
 
-SCRIPT_VERSION = "1.9.7"
+SCRIPT_VERSION = "1.9.8"
 ROWS_PER_SEQUENCE_TSV = 1e7
 
 options(warn = 1)
@@ -144,7 +144,12 @@ if ( gtdb ) {
       trank  = 'species',
       ncbi_taxon_id = ncbi_species_taxid
     ) %>%
-    select(accno0, accno1, tdomain:tspecies, trank, ncbi_taxon_id) %>%
+    select(
+      accno0, accno1, tdomain:tspecies, trank, ncbi_taxon_id, checkm_completeness, checkm_contamination, checkm_strain_heterogeneity,
+      contig_count, genome_size, gtdb_genome_representative, gtdb_representative, l50_contigs, l50_scaffolds, longest_contig,
+      longest_scaffold, mean_contig_length, mean_scaffold_length, n50_contigs, n50_scaffolds, ncbi_bioproject, ncbi_biosample,
+      ncbi_genbank_assembly_accession, protein_count, scaffold_count
+    ) %>%
     as.data.table()
 } else {
   logmsg(sprintf("Reading NCBI taxonomy from %s", opt$options$taxflat))

diff --git a/src/R/pf-db2feather.r b/src/R/pf-db2feather.r
@@ -13,7 +13,7 @@ suppressPackageStartupMessages(library(optparse))
 suppressPackageStartupMessages(library(purrr))
 suppressPackageStartupMessages(library(stringr))
 
-SCRIPT_VERSION = "1.9.7"
+SCRIPT_VERSION = "1.9.8"
 
 # Options for testing: opt <- list(options = list(gtdb = TRUE, verbose = TRUE, prefix='testing'), args = 'pf-classify.02.sqlite3')
 # Get arguments

diff --git a/src/R/pf-fasta-unique-taxon-protein.r b/src/R/pf-fasta-unique-taxon-protein.r
@@ -16,7 +16,7 @@ suppressPackageStartupMessages(library(readr))
 suppressPackageStartupMessages(library(dplyr))
 suppressPackageStartupMessages(library(tidyr))
 
-SCRIPT_VERSION = "1.9.7"
+SCRIPT_VERSION = "1.9.8"
 
 # Testing arguments: opt <- list('options' = list('featherprefix' = 'pf-fasta-unique-taxon-protein.01', 'prank' = 'psubclass', 'trank' = 'tspecies'), args = c('pf-fasta-unique-taxon-protein.01.faa'))
 # Get arguments

diff --git a/src/R/pf-fetchseqs.r b/src/R/pf-fetchseqs.r
@@ -14,7 +14,7 @@
 suppressPackageStartupMessages(library(optparse))
 
 # Arguments for testing: opt <- list(options = list(sqlitedb = 'pf-fetchseqs.07.original.sqlite3', fetch = TRUE, verbose = TRUE, sourcedbs = 'refseq,pdb', faalevel='pfamily', faadir='.'))
-SCRIPT_VERSION = "1.9.7"
+SCRIPT_VERSION = "1.9.8"
 
 # Get arguments
 option_list = list(