simpler snakefiles

config.yaml

@@ -8,8 +8,7 @@ ALVISNLP: '~/code/alvisnlp/.test/alvisnlp/bin/alvisnlp'
 
 
 # NCBI Taxonomy files
-NCBI_NODES_FILE: 'ncbi-taxonomy/nodes.dmp'
-NCBI_NAMES_FILE: 'ncbi-taxonomy/names.dmp'
+NCBI_DIR: 'ncbi-taxonomy_2021-03-26'
 
 
 # Output and working directories

dsmz-match.snakefile

@@ -14,4 +14,4 @@ rule match:
         match='./dsmz-match.py',
         strains=config['OUTDIR'] + '/' + config['DSMZ_STRAINS_DIR']
 
-    shell: '''{input.match} {config[NCBI_NODES_FILE]} {config[NCBI_NAMES_FILE]} {input.strains} {output}'''
+    shell: '''{input.match} {config[NCBI_DIR]}/nodes.dmp {config[NCBI_DIR]}/names.dmp {input.strains} {output}'''

rewrite-taxonomy.snakefile

@@ -8,4 +8,4 @@ rule rewrite:
         config['OUTDIR'] + '/' + config['DSMZ_MATCH_DIR']
 
     shell:
-        '''../bibliome-java-utils/test/install/bin/rewrite-taxonomy -namesFile {config[NCBI_NAMES_FILE]} -namesFile {input}/dsmz-names.dmp  -prefix ncbi: -rejectionFile reject.txt -saturationFile saturate.txt -pattern '{{NAME}}\t{{TAXID}}\t{{CANONICAL}}\t{{TAXID_PATH}}\t{{POS_TAG}}\t{{RANK}}\t{{SPECIES_TAXID}}\t{{SPECIES_NAME}}\n' {config[NCBI_NODES_FILE]} {input}/dsmz-nodes.dmp >{output}'''
+        '''../bibliome-java-utils/test/install/bin/rewrite-taxonomy -namesFile {config[NCBI_DIR]}/names.dmp -namesFile {input}/dsmz-names.dmp  -prefix ncbi: -rejectionFile reject.txt -saturationFile saturate.txt -pattern '{{NAME}}\t{{TAXID}}\t{{CANONICAL}}\t{{TAXID_PATH}}\t{{POS_TAG}}\t{{RANK}}\t{{SPECIES_TAXID}}\t{{SPECIES_NAME}}\n' {config[NCBI_DIR]}/nodes.dmp {input}/dsmz-nodes.dmp >{output}'''