Merge branch 'ed_develop' into 'master'

DOGMA v3.6

See merge request !2

CHANGELOG

+DOGMA 3.6
+=========
+
+- update to Pfam Database version 34 (default for DOGMA from this version on)
+
+
 DOGMA 3.5
 =========
 
@@ -5,8 +11,6 @@ DOGMA 3.5
 - adjustment of help texts
 
 
-
-
 DOGMA 3.4
 =========
 

README.md

@@ -25,9 +25,6 @@ We provide several precomputed core sets for different clades here:
 https://domainworld.uni-muenster.de/programs/dogma/
 
 
-UProC is not longer supported from DOGMA version 3.0 onwards, however the old coresets and databases can still be found on our website https://domainworld.uni-muenster.de/data/uprocdb/
-
-
 Usage
 -----
 

dogma.py

 #!/usr/bin/env python
 
-# DOGMA version 3.5
+# DOGMA version 3.6
 
 # DOGMA is a python script that can assess proteome or transcriptome quality based on conserved protein domains.
 # To score the domain completeness of a proteome or transcriptome, DOGMA searches its domain annotation for conserved
 # domains. By default, the conserved domains comprise domains that are shared by six eukaryotic model species.
 
-# Copyright (C) 2015-2020 Elias Dohmen
+# Copyright (C) 2015-2021 Elias Dohmen
 # <e.dohmen@wwu.de> based on code by Lukas Kremer.
 
 # DOGMA is free software: you can redistribute it and/or modify it
@@ -48,7 +48,7 @@ conversion_dictionary = None
 
 
 def main():
-    dogma_version = '3.5'
+    dogma_version = '3.6'
 
     try:
         # top level argument parsing
@@ -94,8 +94,8 @@ def main():
         parser_proteome.add_argument("-o", "--outfile", action="store", type=str, default=None,
                                      help="Summary will be saved in a file with the given name (and path), "
                                           "instead of printed in the console.")
-        parser_proteome.add_argument("-m", "--pfam", action="store", type=str, default="33.1",
-                                     help="The version number of the pfam database that should be used (Default is 33.1).")
+        parser_proteome.add_argument("-m", "--pfam", action="store", type=str, default="34",
+                                     help="The version number of the pfam database that should be used (Default is 34).")
         parser_proteome.add_argument("-d", "--database", action="store", type=str, default=None,
                                      help="If the RADIANT database is not located in the RADIANT directory, please specify"
                                           " path and name of the database. (Just necessary for -i option)")
@@ -127,9 +127,9 @@ def main():
         parser_transcriptome.add_argument("-s", "--cda_size", action="store", default=3, type=int,
                                           help="Specifies up to which size subsets of CDAs should be considered "
                                                "(default=3; A-B-C-D --> A-B-C, A-B-D, B-C-D etc.).")
-        parser_transcriptome.add_argument("-m", "--pfam", action="store", type=str, default="33.1",
+        parser_transcriptome.add_argument("-m", "--pfam", action="store", type=str, default="34",
                                           help="The version number of the pfam database that should be used "
-                                               "(Default is 33.1).")
+                                               "(Default is 34).")
         parser_transcriptome.add_argument("-d", "--database", action="store", default=None,
                                           help="If the RADIANT database is not located in the RADIANT directory, please specify"
                                                " path and name of the database. (Just necessary for -i option)")
@@ -269,7 +269,7 @@ class ConversionDictionary(dict):
 
 
 def score_single_transcriptome(annotation_file, outfile=None, max_dom_tup_len=3,
-                               hq_transcriptomes=None, mode='transcriptome', pfam='33.1', initial=None, version='3.5',
+                               hq_transcriptomes=None, mode='transcriptome', pfam='34', initial=None, version='3.6',
                                annotype='pfsc', coverage=0.5):
     """
     combines the functions and classes to score a sample proteome in terms of it's domain completeness.
@@ -347,7 +347,7 @@ def score_single_transcriptome(annotation_file, outfile=None, max_dom_tup_len=3,
 
 
 def score_single_proteome(annotation_file, outfile=None, cutoff=2,
-                          max_dom_tup_len=3, hq_proteomes=None, mode='proteome', pfam='33.1', initial=None, version='3.5',
+                          max_dom_tup_len=3, hq_proteomes=None, mode='proteome', pfam='34', initial=None, version='3.6',
                           annotype='pfsc', coverage=0.5):
     """
     combines the functions and classes to score a sample proteome in terms of it's domain completeness.