Merge pull request #43 from jolespin/devel

Fixed error with unnecessary argument in compile_eukaryotic_classifications.py script

src/classify-eukaryotic.py

@@ -140,6 +140,7 @@ def get_hmmsearch_cmd( input_filepaths, output_filepaths, output_directory, dire
         "-t {}".format(os.path.join(directories["intermediate"], "identifier_mapping.metaeuk.tsv")),
         "--drop_duplicates",
         "--index_column 4",
+        "--index_name id_gene",
         ">",
         os.path.join(directories["intermediate"], "identifier_mapping.metaeuk.score_filtered.tsv"),
     ]
@@ -673,7 +674,7 @@ def main(args=None):
     if opts.veba_database is None:
         assert "VEBA_DATABASE" in os.environ, "Please set the following environment variable 'export VEBA_DATABASE=/path/to/veba_database' or provide path to --veba_database"
         opts.veba_database = os.environ["VEBA_DATABASE"]
-    opts.eukaryotic_database = os.path.join(opts.veba_database, "Classify", "Microeukaryotic")
+    opts.eukaryotic_database = os.path.join(opts.veba_database, "Classify", "MicroEuk")
     opts.hmms = os.path.join(opts.veba_database, "MarkerSets", "eukaryota_odb10.hmm.gz")
     opts.scores_cutoff = os.path.join(opts.veba_database, "MarkerSets", "eukaryota_odb10.scores_cutoff.tsv.gz")
 

src/scripts/compile_eukaryotic_classifications.py

@@ -32,7 +32,7 @@ def main(args=None):
     parser.add_argument("--header", type=int, default=1, help="Include header in output {0=No, 1=Yes) [Default: 1]")
     parser.add_argument("--debug", action="store_true")
     parser.add_argument("--remove_genes_with_missing_values", action="store_true")
-    parser.add_argument("--use_original_metaeuk_gene_identifiers", action="store_true")
+    # parser.add_argument("--use_original_metaeuk_gene_identifiers", action="store_true")
 
     # Options
     opts = parser.parse_args()
@@ -164,9 +164,9 @@ def main(args=None):
     if opts.remove_genes_with_missing_values:
         df_gene_classifications = df_gene_classifications.dropna(how="any", axis=0)
 
-    if not opts.use_original_metaeuk_gene_identifiers:
-        metaeuk_to_gene = df_metaeuk["gene_id"].to_dict()
-        df_gene_classifications.index = df_gene_classifications.index.map(lambda x: metaeuk_to_gene[x])
+    # if not opts.use_original_metaeuk_gene_identifiers: #!
+        # gene_to_header = df_metaeuk["MetaEuk_header"]
+    #     df_gene_classifications.index = df_gene_classifications.index.map(lambda x: gene_to_header[x])
 
     df_gene_classifications.to_csv(opts.output, sep="\t", header=bool(opts.header))
 

src/scripts/subset_table.py

@@ -6,7 +6,7 @@
 
 # from tqdm import tqdm
 __program__ = os.path.split(sys.argv[0])[-1]
-__version__ = "2023.3.14"
+__version__ = "2023.12.28"
 
 #
 def main(args=None):
@@ -28,6 +28,8 @@ def main(args=None):
     parser.add_argument("-a","--axis", type=int, default=0, help = "index:axis=0, columns:axis=1")
     # parser.add_argument("--column", type=int, help = "Column to look for index")
     parser.add_argument("--index_column", type=int, default=0, help = "Index column [Default: 0]")
+    parser.add_argument("--index_name", type=str,  help = "Add index name")
+
     parser.add_argument("-d", "--drop_duplicates", action="store_true", help = "Drop duplicates")
 
     parser.add_argument("--sep", type=str, default="\t", help = "Separator [Default: <tab>]")
@@ -83,6 +85,8 @@ def main(args=None):
             df = df.drop(index, axis=1)
 
     # Write table
+    if opts.index_name:
+        df.index.name = opts.index_name
     df.to_csv(opts.output_table, sep=opts.sep, header=not opts.no_header)
 
 if __name__ == "__main__":