Changes to wrapper to integrate with Bibiserv

bin/traitar_from_archive

@@ -14,6 +14,14 @@ if __name__ == "__main__":
     parser.add_argument("--input_dir", help='directory for the traitar input; will be created if it doesn\'t exist yet', default='traitar_in')
     parser.add_argument("--output_dir", help='directory for the traitar output; will be created if it doesn\'t exist yet', default='traitar_out')
     parser.add_argument("--heatmap_format", choices = ["png", "pdf", "svg", "jpg"], default='pdf', help = "choose file format for the heatmap") 
+
+    parser.add_argument("--gene_gff_type", default=None)
+    parser.add_argument("--primary_models", default=None)
+    parser.add_argument("--secondary_models", default=None)
+    parser.add_argument("--primary_hmm_db", default=None)
+    parser.add_argument("--secondary_hmm_db", default=None)
+    parser.add_argument("--annotation_summary", default=None)
+
     args = parser.parse_args()
     read_archive(args.input_archive, args.archive_type, args.mode, args.sample2cat, args.input_dir)
     call_traitar(args)

traitar/hmmer2filtered_best.py

@@ -49,7 +49,7 @@ def aggregate_domain_hits(filtered_df, out_f):
     #sort by gene identifier and Pfam
     with open(out_f, 'w') as out_fo:
         ps.DataFrame(filtered_df.columns).T.to_csv(out_f, sep = "\t", index = False, header = False, mode = 'a')
-        filtered_df.sort_values(by = ["target name", "query name"], inplace = True)
+        filtered_df.sort_index(by = ["target name", "query name"], inplace = True)
         if filtered_df.shape[0] > 0:
             current_max = filtered_df.iloc[0,] 
         else:

traitar/traitar_from_archive.py

@@ -4,6 +4,8 @@
 import re
 import os
 from .traitar import phenolyze
+from shutil import copyfile
+
 
 def get_sample_names(namelist):
     """parse sample names"""
@@ -47,10 +49,12 @@ def read_archive(input_archive, archive_type, mode, sample2cat, input_dir):
 
     #create sample table
     if sample2cat is not None:
-        sample_cat = pd.read_cvs(sample2cat, index_col = 0, sep = "\t")
+        sample_cat = pd.read_csv(sample2cat, index_col = 0, sep = "\t")
         #replace index with cleaned file names
         sample_cat.index.rename(str, dict([(tf, sfn) for sfn, tf in zip(sample_file_names, namelist)]))
-        sample_table = pd.DataFrame([sample_file_names, sample_cat.loc[sample_file_names,]])
+        sample_table = pd.DataFrame(sample_file_names)
+        categories = pd.Series(sample_cat.loc[sample_file_names, ]['category'].tolist())
+        sample_table['category'] = categories          
         sample_table.columns = ["sample_file_name", "category"]
     else:
         sample_table = pd.DataFrame(sample_file_names)
@@ -68,3 +72,6 @@ def call_traitar(args):
     #compress output
     with tarfile.open(args.out_archive, "w:gz") as tar:
         tar.add(args.output_dir, arcname=os.path.basename(args.output_dir))
+
+    out_image = args.out_archive.replace('.FILE', '2.FILE')
+    copyfile(args.output_dir+"/phenotype_prediction/heatmap_combined.pdf", out_image)