Apr 25 update

catch_bad_genes.py

@@ -1,14 +1,13 @@
 #!/usr/bin/python
 
 '''
-Catch bad genes given gff3 files
-   1) Stop codon in the middle of proteins
-   2) Check if translation consists of more than 50% X residues
-   3) Check if feature begins or ends in gap
-
- - Input: Multiple gff3s
- - Output: Pickle for filter_gff3s_ver3.py
- Author Byoungnam Min on Feb 20, 2016
+Catch bad genes for given gff3 files
+    1) Stop codon in the middle of proteins
+    2) Check if translation consists of more than 50% X residues
+    3) Check if feature begins or ends in gap
+
+Input: multiple gff3s
+Output: pickle for filter_gff3s_ver3.py
 '''
 
 # Import modeuls

check_dependencies.py

@@ -1,8 +1,15 @@
 #!/usr/bin/python
 
 '''
-Check dependencies
-Author Byoungnam Min on Nov 23, 2016
+Check if dependencies are correctly located and installed
+    1) Hisat2
+    2) Trinity
+    3) Maker
+    4) RepeatModeler
+    5) Braker
+    6) BUSCO
+    7) InterProScan
+    8) GeneMark
 '''
 
 # Import modules

copy_output.py

@@ -2,7 +2,6 @@
 
 '''
 Copy output to fungap_out directory
-Author Byoungnam Min on Feb 2, 2016
 '''
 
 # Import modules
@@ -47,7 +46,9 @@ def copy_output(output_dir):
         )
         sys.exit(2)
     else:
-        fungap_out_gff3 = os.path.join(output_dir, 'fungap_out/fungap_out.gff3')
+        fungap_out_gff3 = os.path.join(
+            output_dir, 'fungap_out/fungap_out.gff3'
+        )
         copyfile(gff3_out, fungap_out_gff3)
 
     prot_out = os.path.join(output_dir, 'gpre_filtered/gpre_filtered_prot.faa')
@@ -57,7 +58,9 @@ def copy_output(output_dir):
         )
         sys.exit(2)
     else:
-        fungap_out_prot = os.path.join(output_dir, 'fungap_out/fungap_out_prot.faa')
+        fungap_out_prot = os.path.join(
+            output_dir, 'fungap_out/fungap_out_prot.faa'
+        )
         copyfile(prot_out, fungap_out_prot)
 
 

create_markdown.py

@@ -2,7 +2,6 @@
 
 '''
 Create Markedown document
-Author Byoungnam Min on Aug 17, 2016
 '''
 
 # Import modules

download_sister_orgs.py

@@ -2,7 +2,9 @@
 
 '''
 Download protein sequences of sister organisms from NCBI
-Author Byoungnam Min on Aug 16, 2016
+
+Input: taxon name (e.g., Neurospora)
+Output: a directory containing protein FASTA files gzipped
 '''
 
 # Import modules
@@ -33,7 +35,8 @@ def main(argv):
         "-t", "--taxon", dest="taxon", nargs=1,
         help=(
             "Taxon that you want to download. You can choose any clade "
-            "registered in NCBI (default: Fungi)."
+            "registered in NCBI (default: Fungi), but genus name is optimal "
+            "(e.g., Neurospora)"
         )
     )
     parser.add_argument(