Hotfix/documentation

big_scape/cli/cli_common_options.py

@@ -49,8 +49,9 @@ def common_all(fn):
             "--verbose",
             is_flag=True,
             help=(
-                "output all kinds of logs, "
-                "including debugging log info, and write to logfile."
+                "Prints more detailed information of each step in the analysis,"
+                "output all kinds of logs, including debugging log info, and writes to logfile."
+                "Toggle to activate."
             ),
         ),
         click.option(
@@ -64,7 +65,8 @@ def common_all(fn):
             "--label",
             default=None,
             type=str,
-            help="A run label to be added to the output results folder name. "
+            help="A run label to be added to the output results folder name, as well as "
+            "dropdown menu in the visualization page. "
             "By default, BiG-SCAPE runs will have a name such as YYYY-MM-DD_HH-MM-SS_[label]",
         ),
         click.option(
@@ -98,15 +100,15 @@ def common_all(fn):
             is_flag=True,
             default=False,
             help="Do not dump the sqlite database to disk. This will speed up your run,"
-            " but in case of a crashed run no info will be stored and you’ll have to"
+            " but in case of a crashed run no info will be stored and you'll have to"
             " re-start the run from scratch",
         ),
         click.option(
             "--no-interactive",
             type=bool,
             is_flag=True,
             default=False,
-            help="Do not generate an interactive visualization. This greatly speeds up runs, and "
+            help="Do not generate an interactive visualization. This speeds up runs, and "
             "for runs with a large amount of BGCs, the interactive visualization can fail to load.",
         ),
         click.option(
@@ -171,7 +173,7 @@ def common_cluster_query(fn):
             "--mibig_version",
             type=str,
             required=False,
-            help="MIBiG release number (e.g. 3.1). If not provided, MIBiG will not be "
+            help="MIBiG release number (from 3.1 onwards). If not provided, MIBiG will not be "
             "included in the analysis. If required, BiG-SCAPE will download the "
             "MIBiG database to ./big_scape/MIBiG/mibig_antismash_<version>_gbk. "
             "(Advanced) Any custom MIBiG collection can be used as long as the expected "
@@ -192,8 +194,8 @@ def common_cluster_query(fn):
             default="cluster,region",
             callback=validate_filter_gbk,
             help=(
-                "A comma separated list of strings. "
-                "Only gbk files with this string(s) will be used for the analysis "
+                "A comma separated list of strings. Only gbk files that have "
+                "the string(s) in their filename will be used for the analysis "
                 "(default: 'cluster,region'). Use an asterisk to accept every "
                 "file (overrides '--exclude_gbk_str')."
             ),
@@ -278,7 +280,7 @@ def common_cluster_query(fn):
                 "Does not use antiSMASH BGC classes to run analyses on "
                 "class-based bins, instead it uses BiG-SCAPE v1 predefined groups: "
                 "PKS1, PKSOther, NRPS, NRPS-PKS-hybrid, RiPP, Saccharide, Terpene, Others. "
-                "Will also use BiG-SCAPEv1 legacy_weights for distance calculations. "
+                "Will also use BiG-SCAPE v1 legacy_weights for distance calculations. "
                 "This feature is available for backwards compatibility with "
                 "antiSMASH versions up to v7. For higher antiSMASH versions, use "
                 "at your own risk, as BGC classes may have changed. All antiSMASH "
@@ -301,7 +303,8 @@ def common_cluster_query(fn):
                 "of the shortest upstream/downstream arms in a compared pair. "
                 "'auto': use glocal when at least one of the BGCs in each pair "
                 "has the 'contig_edge' annotation from antiSMASH v4+, otherwise "
-                "use global mode on that pair (default: glocal)."
+                "use global mode on that pair. For an in depth description, see the wiki."
+                " (default: glocal)."
             ),
         ),
         click.option(
@@ -310,7 +313,8 @@ def common_cluster_query(fn):
             default="legacy",
             callback=validate_extend_strategy,
             help="Strategy to extend BGCs. 'legacy' will use the original BiG-SCAPE extension strategy, "
-            "while 'greedy' will use a new greedy extension strategy. (default: legacy).",
+            "while 'greedy' will use a new greedy extension strategy. For an in depth description,"
+            " see the wiki. (default: legacy).",
         ),
         # networking parameters
         click.option(

big_scape/cli/cluster_cli.py

@@ -39,7 +39,7 @@
 @click.option(
     "--include_singletons",
     is_flag=True,
-    help=("Include singletons in the network. (default: False)"),
+    help=("Include singletons in the network."),
 )
 @click.pass_context
 def cluster(ctx, *args, **kwargs):

big_scape/cli/query_cli.py

@@ -42,8 +42,8 @@
     required=False,
     help=(
         "Query BGC record number. Used to select the specific record "
-        "from the query BGC gbk. Warning: interleaved or chemical hybrid proto "
-        "cluster/cores are merged, and the relevant number is that of the "
+        "from the query BGC gbk. Warning: if interleaved or chemical hybrid proto "
+        "cluster/cores are merged (see config), the relevant number is that of the "
         "first record of the merged cluster (the one with the lowest number). "
         "e.g. if records 1 and 2 get merged, the relevant number is 1. "
     ),

config.yml

@@ -1,50 +1,52 @@
 # PROFILER
-# Update interval in seconds when profiler functionality is active
+# Update interval in seconds when profiler functionality is active.
 PROFILER_UPDATE_INTERVAL: 0.5
 
 # INPUT
-# list of cand_cluster types where subrecords will be merged
+# list of cand_cluster types where subrecords will be merged.
 MERGED_CAND_CLUSTER_TYPE:
   - chemical_hybrid
   - interleaved
-# Minimum and maximum bgc lengths to be included in the analysis in number of base pairs
+# Minimum and maximum bgc lengths to be included in the analysis in number of base pairs.
 MIN_BGC_LENGTH: 0
 MAX_BGC_LENGTH: 500000
 
 # CDS and DOMAIN
 # Specify at which overlap percentage (as a decimal) two CDS in a gbk
-# are considered to overlap. This preserves longest overlapping CDS
+# are considered to overlap. This preserves longest overlapping CDS.
 CDS_OVERLAP_CUTOFF: 0.1
 # Specify at which overlap percentage (as a decimal) two domains
-# in a CDS are considered to overlap. Domain with the best score is kept
+# in a CDS are considered to overlap. Domain with the best score is kept.
 DOMAIN_OVERLAP_CUTOFF: 0.1
 
 # LCS
-# Minimum length criteria for accepting a Longest Common Subcluster (LCS), measured in
-# fraction of included domains in one of the compared records, when comparing:
-# Regions or Cand_clusters
+# Minimum length percentage for accepting a Longest Common Subcluster (LCS),
+# which must be satisfied in at least one of the compared records, measured in fraction
+# of included domains, when comparing:
+# - Regions or Cand_clusters
 REGION_MIN_LCS_LEN: 0.1
-#Protoclusters or Proto_cores
+# - Protoclusters or Proto_cores
 PROTO_MIN_LCS_LEN: 0
 
 # EXPAND
-# Minimum length citeria for accepting an extended LCS slice, measured in fraction of
-# included domains in one of the compared records, when comparing:
-# Regions or Cand_clusters with no biosynthetic domains in the extended slice
+# Minimum length percentage for accepting an extended LCS slice, which must be
+# satisfied in at least one of the compared records, measured in fraction of
+# included domains, when comparing:
+# - Regions or Cand_clusters with no biosynthetic domains in the extended slice
 REGION_MIN_EXPAND_LEN: 0.3
-# Regions or Cand_clusters with at least one biosynthetic domain in the extended slice
+# - Regions or Cand_clusters with at least one biosynthetic domain in the extended slice
 REGION_MIN_EXPAND_LEN_BIO: 0.2
-# Protoclusters or Proto_cores with at least one biosynthetic domain in the extended slice
+# - Protoclusters or Proto_cores with at least one biosynthetic domain in the extended slice
 PROTO_MIN_EXPAND_LEN: 0.2
-# list of product classes that do not require a minimum length
+# List of product classes that do not require a minimum length.
 NO_MIN_CLASSES:
   - terpene
-# Integer scoring metrics used in the LCS extension algorithm for match, mismatch and gap
+# Integer scoring metrics used in the LCS extension algorithm for match, mismatch and gap.
 EXPAND_MATCH_SCORE: 5
 EXPAND_MISMATCH_SCORE: -3
 EXPAND_GAP_SCORE: -2
 # Maximum distance to accept a matching domain as an actual match during LCS extension
-# as a percentage of total domains present in the compared record
+# as a percentage of total domains present in the compared record.
 EXPAND_MAX_MATCH_PERC: 0.1
 
 # CLUSTER
@@ -53,7 +55,7 @@ EXPAND_MAX_MATCH_PERC: 0.1
 PREFERENCE: 0.0
 
 # TREE
-# The number of common domains used to generate GCF trees in top frequencies of occurrence
+# The number of common domains used to generate GCF trees in top frequencies of occurrence.
 TOP_FREQS: 3
 
 # ANCHOR DOMAINS