Update/outputs

locidex/build.py

@@ -150,9 +150,7 @@ def run(cmd_args=None):
     input_file = cmd_args.input_file
     outdir = cmd_args.outdir
     force = cmd_args.force
-    run_data = dict()
-    run_data['analysis_start_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-    run_data['parameters'] = vars(cmd_args)
+
 
     config = DBConfig(
         db_name=cmd_args.name,
@@ -162,6 +160,12 @@ def run(cmd_args=None):
         db_date=datetime.now().strftime("%Y/%d/%m"),
     )
 
+    run_params = vars(cmd_args)
+    run_params = run_params | config.to_dict()
+    run_data = dict()
+    run_data['analysis_start_time'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    run_data['parameters'] = vars(cmd_args)
+
     if not os.path.isfile(input_file):
         logger.critical(f'Error {input_file} does not exist, please check path and try again')
         raise_file_not_found_e(input_file, logger)

locidex/constants.py

@@ -142,9 +142,6 @@ class ManifestFields:
     db_path: str = "path"
     config_data: str = "config"
 
-SEARCH_RUN_DATA = {
-
-}
 
 
 DB_EXPECTED_FILES = {

locidex/extract.py

@@ -15,7 +15,7 @@
 from locidex.manifest import DBData
 from locidex.classes.db import search_db_conf, db_config
 from locidex.classes.seq_intake import seq_intake, seq_store
-from locidex.constants import SEARCH_RUN_DATA, FILE_TYPES, BlastColumns, BlastCommands, DBConfig, DB_EXPECTED_FILES, EXTRACT_MODES, raise_file_not_found_e
+from locidex.constants import FILE_TYPES, BlastColumns, BlastCommands, DBConfig, DB_EXPECTED_FILES, EXTRACT_MODES, raise_file_not_found_e
 from locidex.version import __version__
 from locidex.classes.aligner import perform_alignment, aligner
 from locidex.utils import check_db_groups, get_format
@@ -106,7 +106,8 @@ def run_extract(config):
     if sample_name == None:
         sample_name = os.path.basename(input_fasta)
 
-    run_data = SEARCH_RUN_DATA
+    config = config | db_data.config_data.to_dict() # update config data to use db data
+    run_data = dict()
     run_data['analysis_start_time'] = datetime.now().strftime("%d/%m/%Y %H:%M:%S")
     run_data['parameters'] = config
 

locidex/format.py

@@ -69,14 +69,17 @@ def __init__(self,input,header,is_protein=False,delim="_",trans_table=11,
         else:
             self.parse_fasta(self.input)
 
-    def process_dir(self):
+    def process_dir(self) -> None:
         files = self.get_dir_files(self.input)
         for f in files[self.__file_input]:
             for e in self.valid_ext:
-                if e in f[1]:
+                if f[1].endswith(e):
                     self.gene_name = f[1].replace(f'{e}','')
                     self.parse_fasta(f[0])
                     break
+            else:
+                logger.critical("File: {} does not have a valid extension. Valid extensions are: {}".format(e, str(self.valid_ext)))
+                raise ValueError("Extension for file: {} is not allowed.".format())
 
     def set_input_type(self):
         if os.path.isfile(self.input):
@@ -133,9 +136,9 @@ def parse_fasta(self, input_file):
         _open = partial(gzip.open, mode='rt') if encoding == 'gzip' else open
         with _open(input_file) as f:
             for record in SeqIO.parse(f, 'fasta'):
-                id = str(record.id)
+                id_in = str(record.id)
                 if self.input_type == self.__file_input:
-                    gene_name = "_".join(id.split(self.delim)[:-1])
+                    gene_name = "_".join(id_in.split(self.delim)[:-1])
                 else:
                     gene_name = self.gene_name
                 dna_seq = str(record.seq).lower().replace('-','')
@@ -153,10 +156,10 @@ def parse_fasta(self, input_file):
                 row = LocidexDBHeader(
                     seq_id=self.seq_idx,
                     locus_name=gene_name,
-                    locus_name_alt=id,
+                    locus_name_alt=id_in,
                     locus_product='',
                     locus_description='',
-                    locus_uid=id.split(self.delim)[-1],
+                    locus_uid=id_in.split(self.delim)[-1],
                     dna_seq=dna_seq,
                     dna_seq_len=dna_len,
                     dna_seq_hash=calc_md5([dna_seq])[0],
@@ -174,7 +177,6 @@ def parse_fasta(self, input_file):
                     dna_min_ident=self.min_ident_perc,
                     min_dna_match_cov=self.min_cov_perc
                 )
-
                 self.data[self.seq_idx] = row
                 self.seq_idx += 1
 

locidex/main.py

@@ -33,7 +33,9 @@ def main(argv=None):
     if args.command is None:
         parser.print_help()
         sys.exit()
+    logger.info("Running {}".format(args.command))
     tasks[args.command][module_idx].run(args)
+    logger.info("Finished: {}".format(args.command))
 
 
 # call main function

locidex/report.py

@@ -10,7 +10,7 @@
 import errno
 from typing import Any
 from locidex.classes.seq_intake import seq_intake
-from locidex.constants import SEARCH_RUN_DATA, START_CODONS, STOP_CODONS, DBConfig
+from locidex.constants import START_CODONS, STOP_CODONS, DBConfig
 from locidex.utils import calc_md5
 from locidex.version import __version__
 
@@ -387,7 +387,7 @@ def run_report(config):
     translation_table = config['translation_table']
 
 
-    run_data = SEARCH_RUN_DATA
+    run_data = dict()
     run_data['analysis_start_time'] = datetime.now().strftime("%d/%m/%Y %H:%M:%S")
     run_data['parameters'] = analysis_parameters
 

locidex/search.py

@@ -15,7 +15,7 @@
 from locidex.classes.db import search_db_conf, db_config
 from locidex.manifest import DBData
 from locidex.classes.seq_intake import seq_intake, seq_store, HitFilters
-from locidex.constants import BlastCommands,  SEARCH_RUN_DATA, FILE_TYPES, BlastColumns, DB_EXPECTED_FILES, OPTION_GROUPS, DBConfig
+from locidex.constants import BlastCommands, FILE_TYPES, BlastColumns, DB_EXPECTED_FILES, OPTION_GROUPS, DBConfig
 from locidex.utils import write_seq_dict, check_db_groups, slots, get_format
 from locidex.version import __version__
 
@@ -136,13 +136,12 @@ def run_search(config):
     if sample_name == None:
         sample_name = query_file.stem
 
-
-    run_data = SEARCH_RUN_DATA
+    db_data = DBData(db_dir=db_dir)
+    config = config | db_data.config_data.to_dict()
+    run_data = dict()
     run_data['analysis_start_time'] = datetime.now().strftime("%d/%m/%Y %H:%M:%S")
     run_data['parameters'] = config
 
-    db_data = DBData(db_dir=db_dir)
-
     if os.path.isdir(outdir) and not force:
         logger.critical(f'Error {outdir} exists, if you would like to overwrite, then specify --force')
         raise FileExistsError(errno.EEXIST, os.strerror(errno.EEXIST), str(outdir))