Amending docs and CLI (for #270)

Mikado/preparation/prepare.py

@@ -582,7 +582,7 @@ def prepare(args, logger):
 
     if not args.json_conf["prepare"]["files"]["keep_redundant"]:
         args.json_conf["prepare"]["files"]["keep_redundant"] = (
-            [getattr(args, "keep_redundant", False)] * len(args.json_conf["prepare"]["files"]["gff"]))
+            [getattr(args, "keep_redundant", True)] * len(args.json_conf["prepare"]["files"]["gff"]))
 
     shelve_names = [path_join(args.json_conf["prepare"]["files"]["output_dir"],
                               "mikado_shelf_{}.db".format(str(_).zfill(5))) for _ in

Mikado/subprograms/configure.py

@@ -376,11 +376,12 @@ def configure_parser():
                        default=False, action="store_true")
     files.add_argument("--gff", help="Input GFF/GTF file(s), separated by comma", type=str,
                        default="")
-    files.add_argument("--list",
-                       help="""Tab-delimited file containing rows with the following format:
-<file>  <label> <strandedness> <score(optional)> <is_reference(optional)> <always_keep(optional)
-strandedness, is_reference and always_keep must be boolean values (True, False)
-score must be a valid floating number.""")
+    files.add_argument("--list", type=argparse.FileType("r"),
+                        help="""Tab-delimited file containing rows with the following format:
+    <file>  <label> <strandedness(def. False)> <score(optional, def. 0)> <is_reference(optional, def. False)> <keep_redundant(optional, def. True)>
+    strandedness, is_reference and keep_redundant must be boolean values (True, False)
+    score must be a valid floating number.
+    """)
     parser.add_argument("--reference", help="Fasta genomic reference.", default=None)
     serialisers = parser.add_argument_group(
         "Options related to the serialisation step")

Mikado/subprograms/prepare.py

@@ -276,8 +276,8 @@ def positive(string):
                         help="Comma-delimited list of strand specific assemblies.")
     parser.add_argument("--list", type=argparse.FileType("r"),
                         help="""Tab-delimited file containing rows with the following format:
-<file>  <label> <strandedness> <score(optional)> <is_reference(optional)> <always_keep(optional)
-strandedness, is_reference and always_keep must be boolean values (True, False)
+<file>  <label> <strandedness, def. False> <score(optional, def. 0)> <is_reference(optional, def. False)> <keep_redundant(optional, def. True)>
+strandedness, is_reference and keep_redundant must be boolean values (True, False)
 score must be a valid floating number.
 """)
     parser.add_argument("-l", "--log", type=argparse.FileType("w"), default=None,
@@ -311,7 +311,8 @@ def positive(string):
                         help="Configuration file.")
     parser.add_argument("-k", "--keep-redundant", default=None,
                         dest="keep_redundant", action="store_true",
-                        help="Boolean flag. If invoked, Mikado prepare will retain redundant models.")
+                        help="Boolean flag. If invoked, Mikado prepare will retain redundant models,\
+ignoring the per-sample instructions.")
     parser.add_argument("--seed", type=int, default=None,
                         help="Random seed number.")
     parser.add_argument("gff", help="Input GFF/GTF file(s).", nargs="*")

Mikado/utilities/__init__.py

@@ -299,7 +299,7 @@ def parse_list_file(json_conf: dict, list_file):
                 score = 0
             json_conf["prepare"]["files"]["source_score"][label] = score
         keep = False
-        for arr, pos, default in [("reference", 4, False), ("keep_redundant", 5, False)]:
+        for arr, pos, default in [("reference", 4, False), ("keep_redundant", 5, True)]:
             try:
                 val = fields[pos]
                 if val.lower() in ("false", "true"):

docs/Usage/Configure.rst

@@ -56,8 +56,10 @@ Usage:
       --no-files            Remove all files-specific options from the printed configuration file.
                                                    Invoking the "--gff" option will disable this flag.
       --gff GFF             Input GFF/GTF file(s), separated by comma
-      --list LIST           Tab-delimited file containing rows with the following format
-                                                    <file>  <label> <strandedness> <score(optional)> <always_keep(optional)>
+      --list LIST           Tab-delimited file containing rows with the following format:
+<file>  <label> <strandedness, def. False> <score(optional, def. 0)> <is_reference(optional, def. False)> <keep_redundant(optional, def. True)>
+strandedness, is_reference and keep_redundant must be boolean values (True, False)
+score must be a valid floating number.
       --reference REFERENCE
                             Fasta genomic reference.
       --strand-specific-assemblies STRAND_SPECIFIC_ASSEMBLIES

docs/Usage/Prepare.rst

@@ -67,8 +67,10 @@ Command line usage:
                             strand.
       -sa STRAND_SPECIFIC_ASSEMBLIES, --strand-specific-assemblies STRAND_SPECIFIC_ASSEMBLIES
                             Comma-delimited list of strand specific assemblies.
-      --list LIST           Tab-delimited file containing rows with the following
-                            format <file> <label> <strandedness>
+      --list LIST           Tab-delimited file containing rows with the following format:
+<file>  <label> <strandedness, def. False> <score(optional, def. 0)> <is_reference(optional, def. False)> <keep_redundant(optional, def. True)>
+strandedness, is_reference and keep_redundant must be boolean values (True, False)
+score must be a valid floating number.
       -l LOG, --log LOG     Log file. Optional.
       --lenient             Flag. If set, transcripts with only non-canonical
                             splices will be output as well.