fixes ganon v1.6.0 (#251)

* docs, fix test sets

* genome_updater v0.6.2, small fixes

Author: pirovc

.travis.yml

@@ -31,7 +31,7 @@ before_install:
   - eval "${MATRIX_EVAL}"
   - python3 -m pip install --upgrade pip
   - python3 -m pip install "pandas>=1.1.0"
-  - python3 -m pip install "multitax>=1.2.1"
+  - python3 -m pip install "multitax>=1.3.1"
   - if [ "$BUILD_TYPE" == "Coverage" ]; then 
       python3 -m pip install coverage;
     fi

docs/default_databases.md

@@ -41,8 +41,8 @@ NCBI RefSeq and GenBank repositories are common resources to obtain reference se
 |---|---|---|---|
 | Complete | 1595845 | | <details><summary>cmd</summary>`ganon build --source genbank --organism-group archaea bacteria fungi viral --threads 48 --db-prefix abfv_gb`</details> |
 | One assembly per species | 99505 | 91 - 420 | <details><summary>cmd</summary>`ganon build --source genbank --organism-group archaea bacteria fungi viral --threads 48 --genome-updater "-A 'species:1'" --db-prefix abfv_gb_t1s`</details> |
-| Complete genomes (higher quality) | 92917 | 24 - | <details><summary>cmd</summary>`ganon build --source genbank --organism-group archaea bacteria fungi viral --threads 48 --complete-genomes --db-prefix abfv_gb_cg`</details> |
-| One assembly per species of complete genomes | 34497 | 10 - | <details><summary>cmd</summary>`ganon build --source genbank --organism-group archaea bacteria fungi viral --threads 48 --complete-genomes "-A 'species:1'" --db-prefix abfv_gb_cg_t1s`</details> |
+| Complete genomes (higher quality) | 92917 | 24 - 132 | <details><summary>cmd</summary>`ganon build --source genbank --organism-group archaea bacteria fungi viral --threads 48 --complete-genomes --db-prefix abfv_gb_cg`</details> |
+| One assembly per species of complete genomes | 34497 | 10 - 34 | <details><summary>cmd</summary>`ganon build --source genbank --organism-group archaea bacteria fungi viral --threads 48 --complete-genomes "-A 'species:1'" --db-prefix abfv_gb_cg_t1s`</details> |
 
 \*  Size (GB) is the final size of the database and the approximate amount of RAM necessary to build it (calculated with default parameters). The two values represent databases built with and without the `--hibf` parameter, respectively. The trade-offs between those two modes are explained [here](#hibf).
 

libs/genome_updater

@@ -17,7 +17,7 @@ def read(filename):
     url="https://www.github.com/pirovc/ganon",
     license='MIT',
     author="Vitor C. Piro",
-    description="ganon classifies short DNA sequences against large sets of genomic reference sequences efficiently",
+    description="ganon classifies DNA sequences against large sets of genomic reference sequences efficiently",
     long_description=read("README.md"),
     package_dir={'': 'src'},
     packages=["ganon"],

setup.py

@@ -397,7 +397,7 @@ def validate(self):
                 elif check_file(db_prefix + ".ibf"):
                     ibf = True
                 else:
-                    print_log("File not found: " + prefix + ".ibf/.hibf" )
+                    print_log("File not found: " + db_prefix + ".ibf/.hibf" )
                     return False
 
                 if check_file(db_prefix + ".tax"):

src/ganon/config.py

@@ -0,0 +1,2 @@
+07b534765d6b7d3e4d8bf67f549a5d66  build/releases/latest/ar53_taxonomy.tsv.gz
+70a673d332f60af1cf68e34d09a56816  build/releases/latest/bac120_taxonomy.tsv.gz

tests/ganon/data/build/releases/latest/MD5SUM.txt

@@ -61,14 +61,14 @@ md5sum "${outfld}pub/taxonomy/new_taxdump/new_taxdump.tar.gz" > "${outfld}pub/ta
 rm "${outfld}new_taxdump.tar.gz" "${outfld}taxidlineage.dmp" "${outfld}rankedlineage.dmp" "${outfld}pub/taxonomy/new_taxdump/taxidlineage.dmp" "${outfld}pub/taxonomy/new_taxdump/rankedlineage.dmp"
 
 #gtdb
-gtdb_out="${outfld}releases/release207/207.0/"
+gtdb_out="${outfld}releases/latest/"
 mkdir -p "${gtdb_out}"
-gtdb_tax=( "ar53_taxonomy_r207.tsv.gz" "bac120_taxonomy_r207.tsv.gz" )
+gtdb_tax=( "ar53_taxonomy.tsv.gz" "bac120_taxonomy.tsv.gz" )
 for tax in "${gtdb_tax[@]}"; do
-    wget --quiet --show-progress --output-document "${outfld}${tax}" "https://data.gtdb.ecogenomic.org/releases/release207/207.0/${tax}"
+    wget --quiet --show-progress --output-document "${outfld}${tax}" "https://data.gtdb.ecogenomic.org/releases/latest/${tax}"
     join -1 1 -2 1 <(cut -f 1 "${outfld}accessions_taxids.txt" | sort) <(zcat "${outfld}${tax}" | awk 'BEGIN{FS=OFS="\t"}{print $1,$1,$2}' | sed -r 's/^.{3}//' | sort) -t$'\t' -o "2.2,2.3" | gzip > "${gtdb_out}${tax}"
     rm "${outfld}${tax}"
 done
 
-md5sum ${gtdb_out}*.tsv.gz > "${gtdb_out}MD5SUM"
+md5sum ${gtdb_out}*.tsv.gz > "${gtdb_out}MD5SUM.txt"
 rm ${outfld}accessions_taxids.txt