Refactor internal data structure and major variable names (#338)

* rename contig to more general sequence
* rename seq 'sequence' attribute to 'nt'
* rename genome data structure to data
* reorganize data strucutre
* fix io
* refactor seq var name in list comprehensions
* remove io.py
* refactor var names in list comprehensions

README.md

@@ -382,7 +382,7 @@ positional arguments:
 Input / Output:
   --db DB, -d DB        Database path (default = <bakta_path>/db). Can also be provided as BAKTA_DB environment variable.
   --min-contig-length MIN_CONTIG_LENGTH, -m MIN_CONTIG_LENGTH
-                        Minimum contig size (default = 1; 200 in compliant mode)
+                        Minimum contig/sequence size (default = 1; 200 in compliant mode)
   --prefix PREFIX, -p PREFIX
                         Prefix for output files
   --output OUTPUT, -o OUTPUT
@@ -409,7 +409,7 @@ Annotation:
                         Locus tag increment: 1/5/10 (default = 1)
 
   --keep-contig-headers
-                        Keep original contig headers
+                        Keep original contig/sequence headers
   --compliant           Force Genbank/ENA/DDJB compliance
   --replicons REPLICONS, -r REPLICONS
                         Replicon information table (tsv/csv)

bakta/__init__.py

@@ -1,2 +1,2 @@
-__version__ = '1.9.4'
+__version__ = '1.10.0-beta'
 __db_schema_version__ = 5

bakta/config.py

@@ -30,7 +30,7 @@
 db_info = None
 tmp_path = None
 genome_path = None
-min_contig_length = None
+min_sequence_length = None
 prefix = None
 output_path = None
 force = None
@@ -46,7 +46,7 @@
 complete = None
 prodigal_tf = None
 translation_table = None
-keep_contig_headers = None
+keep_sequence_headers = None
 locus = None
 locus_tag = None
 locus_tag_increment = None
@@ -92,7 +92,7 @@ def setup(args):
         verbose = True
 
     # input / output path configurations
-    global db_path, db_info, tmp_path, genome_path, min_contig_length, prefix, output_path, force
+    global db_path, db_info, tmp_path, genome_path, min_sequence_length, prefix, output_path, force
     db_path = check_db_path(args)
     tmp_path = check_tmp_path(args)
 
@@ -108,11 +108,11 @@ def setup(args):
     log.info('genome-path=%s', genome_path)
 
     # input / output configurations
-    min_contig_length = args.min_contig_length
-    if(min_contig_length <= 0):
-        log.error("wrong argument for 'min-contig-length' parameter! min_contig_length=%s", min_contig_length)
-        sys.exit(f"ERROR: wrong argument ({min_contig_length}) for 'min- contig-length' parameter! Value must be larger than 0")
-    log.info('min_contig_length=%s', min_contig_length)
+    min_sequence_length = args.min_contig_length
+    if(min_sequence_length <= 0):
+        log.error("wrong argument for 'min-contig-length' parameter! min_contig_length=%s", min_sequence_length)
+        sys.exit(f"ERROR: wrong argument ({min_sequence_length}) for 'min- contig-length' parameter! Value must be larger than 0")
+    log.info('min_contig_length=%s', min_sequence_length)
     log.info('prefix=%s', prefix)  # set in main.py before global logger config
     log.info('output-path=%s', output_path)
     force = args.force
@@ -163,7 +163,7 @@ def setup(args):
         taxon = None
 
     # annotation configurations
-    global complete, prodigal_tf, translation_table, keep_contig_headers, locus, locus_tag, locus_tag_increment, gram, replicons, compliant, user_proteins, user_hmms, meta, regions
+    global complete, prodigal_tf, translation_table, keep_sequence_headers, locus, locus_tag, locus_tag_increment, gram, replicons, compliant, user_proteins, user_hmms, meta, regions
     complete = args.complete
     log.info('complete=%s', complete)
     prodigal_tf = args.prodigal_tf
@@ -186,8 +186,8 @@ def setup(args):
     compliant = args.compliant
     log.info('compliant=%s', compliant)
     if(compliant):
-        min_contig_length = 200
-        log.info('compliant mode! min_contig_length=%s', min_contig_length)
+        min_sequence_length = 200
+        log.info('compliant mode! min_contig_length=%s', min_sequence_length)
     meta = args.meta
     log.info('meta=%s', meta)
     locus = args.locus
@@ -221,8 +221,8 @@ def setup(args):
     log.info('locus-tag=%s', locus_tag)
     locus_tag_increment = args.locus_tag_increment
     log.info('locus-tag-increment=%s', locus_tag_increment)
-    keep_contig_headers = args.keep_contig_headers
-    log.info('keep_contig_headers=%s', keep_contig_headers)
+    keep_sequence_headers = args.keep_contig_headers
+    log.info('keep_contig_headers=%s', keep_sequence_headers)
     replicons = args.replicons
     if(replicons is not None):
         try:

bakta/constants.py

@@ -191,7 +191,7 @@
 ############################################################################
 REPLICON_CHROMOSOME = 'chromosome'
 REPLICON_PLASMID = 'plasmid'
-REPLICON_CONTIG = 'contig'
+REPLICON_CONTIG = 'sequence'
 REPLICON_LENGTH_THRESHOLD_PLASMID = 112_000  # Nasuia deltocephalinicola -> DOI: 10.1093/gbe/evt118
 REPLICON_LENGTH_THRESHOLD_CHROMOSOME = 2_800_000  # max plasmid length (except 1 outlier-> https://ccb-microbe.cs.uni-saarland.de/plsdb/plasmids/
 TOPOLOGY_CIRCULAR = 'circular'

bakta/expert/amrfinder.py

@@ -80,8 +80,8 @@ def search(cdss: Sequence[dict], cds_fasta_path: Path):
                 cds.setdefault('expert', [])
                 cds['expert'].append(hit)
                 log.debug(
-                    'hit: gene=%s, product=%s, method=%s, target-cov=%0.3f, identity=%0.3f, contig=%s, start=%i, stop=%i, strand=%s',
-                    gene, product, method, model_cov, identity, cds['contig'], cds['start'], cds['stop'], cds['strand']
+                    'hit: gene=%s, product=%s, method=%s, target-cov=%0.3f, identity=%0.3f, seq=%s, start=%i, stop=%i, strand=%s',
+                    gene, product, method, model_cov, identity, cds['sequence'], cds['start'], cds['stop'], cds['strand']
                 )
                 cds_found.add(aa_identifier)
 

bakta/expert/protein_hmms.py

@@ -30,8 +30,8 @@ def search(cdss: Sequence[dict], user_hmms_path):
                 cds = orf_by_aa_digest[aa_identifier]
                 if hmm_query_hit.evalue > bc.MIN_HMM_EVALUE:
                     log.debug(
-                        'discard low evalue: contig=%s, start=%i, stop=%i, strand=%s, id=%s, evalue=%1.1e, bitscore=%f',
-                        cds['contig'], cds['start'], cds['stop'], cds['strand'], hmm_id, hmm_query_hit.evalue, hmm_query_hit.score
+                        'discard low evalue: seq=%s, start=%i, stop=%i, strand=%s, id=%s, evalue=%1.1e, bitscore=%f',
+                        cds['sequence'], cds['start'], cds['stop'], cds['strand'], hmm_id, hmm_query_hit.evalue, hmm_query_hit.score
                     )
                 else:
                     hit_domain_lengths_sum = sum([len(dom.alignment.hmm_sequence) for dom in hmm_query_hit.domains.included])
@@ -64,8 +64,8 @@ def search(cdss: Sequence[dict], user_hmms_path):
                     cds.setdefault('expert', [])
                     cds['expert'].append(hit)
                     log.debug(
-                        'hit: source=UserHMMs, rank=99, contig=%s, start=%i, stop=%i, strand=%s, query-cov=%0.3f, model-cov=%0.3f, hmm-id=%s, gene=%s, product=%s, evalue=%1.1e, bitscore=%f',
-                        cds['contig'], cds['start'], cds['stop'], cds['strand'], hit['aa_cov'], hit['hmm_cov'], hmm_id, hit['gene'], hit['product'], hit['evalue'], hit['score']
+                        'hit: source=UserHMMs, rank=99, seq=%s, start=%i, stop=%i, strand=%s, query-cov=%0.3f, model-cov=%0.3f, hmm-id=%s, gene=%s, product=%s, evalue=%1.1e, bitscore=%f',
+                        cds['sequence'], cds['start'], cds['stop'], cds['strand'], hit['aa_cov'], hit['hmm_cov'], hmm_id, hit['gene'], hit['product'], hit['evalue'], hit['score']
                     )
                     cds_found.add(aa_identifier)
 

bakta/expert/protein_sequences.py

@@ -83,8 +83,8 @@ def search(cdss: Sequence[dict], cds_fasta_path: Path, expert_system: str, db_pa
                 cds.setdefault('expert', [])
                 cds['expert'].append(hit)
                 log.debug(
-                    'hit: source=%s, rank=%i, contig=%s, start=%i, stop=%i, strand=%s, query-cov=%0.3f, subject-cov=%0.3f, identity=%0.3f, score=%0.1f, evalue=%1.1e, gene=%s, product=%s',
-                    source, rank, cds['contig'], cds['start'], cds['stop'], cds['strand'], query_cov, model_cov, identity, bitscore, evalue, gene, product
+                    'hit: source=%s, rank=%i, seq=%s, start=%i, stop=%i, strand=%s, query-cov=%0.3f, subject-cov=%0.3f, identity=%0.3f, score=%0.1f, evalue=%1.1e, gene=%s, product=%s',
+                    source, rank, cds['sequence'], cds['start'], cds['stop'], cds['strand'], query_cov, model_cov, identity, bitscore, evalue, gene, product
                 )
                 cds_found.add(aa_identifier)