fix for #464

tools/gff3/shinefind.py

@@ -74,7 +74,7 @@ def highlight_sd(cls, sequence, start, end):
         )
 
     @classmethod
-    def to_features(cls, hits, strand, parent_start, parent_end, feature_id=None, sd_min=5, sd_max=15):
+    def to_features(cls, hits, strand, parent_start, parent_end, feature_id=None, sd_min=3, sd_max=17):
         results = []
         for idx, hit in enumerate(hits):
             # gene            complement(124..486)
@@ -113,7 +113,7 @@ def to_features(cls, hits, strand, parent_start, parent_end, feature_id=None, sd
             results.append(tmp)
         return results
 
-    def testFeatureUpstream(self, feature, record, sd_min=5, sd_max=15):
+    def testFeatureUpstream(self, feature, record, sd_min=3, sd_max=17):
         # Strand information necessary to getting correct upstream sequence
         strand = feature.location.strand
 
@@ -135,7 +135,7 @@ def testFeatureUpstream(self, feature, record, sd_min=5, sd_max=15):
         seq = str(tmp.extract(record.seq))
         return self.list_sds(seq), start, end, seq
 
-    def hasSd(self, feature, record, sd_min=5, sd_max=15):
+    def hasSd(self, feature, record, sd_min=3, sd_max=17):
         sds, start, end, seq = self.testFeatureUpstream(
             feature, record, sd_min=sd_min, sd_max=sd_max
         )
@@ -178,8 +178,8 @@ def shinefind(
     gff3,
     gff3_output=None,
     table_output=None,
-    lookahead_min=5,
-    lookahead_max=15,
+    lookahead_min=3,
+    lookahead_max=17,
     top_only=False,
     add=False,
 ):
@@ -396,14 +396,14 @@ def shinefind(
         nargs="?",
         type=int,
         help="Number of bases upstream of CDSs to end search",
-        default=5,
+        default=3,
     )
     parser.add_argument(
         "--lookahead_max",
         nargs="?",
         type=int,
         help="Number of bases upstream of CDSs to begin search",
-        default=15,
+        default=17,
     )
 
     parser.add_argument("--top_only", action="store_true", help="Only report best hits")

tools/gff3/shinefind.xml

@@ -1,4 +1,4 @@
-<tool id="edu.tamu.cpt.genbank.shinefind" name="Shine Find" version="19.1.0.0">
+<tool id="edu.tamu.cpt.genbank.shinefind" name="Shine Find" version="20.9.0.0">
 	<description>Identify shine-dalgarno sequences</description>
 	<macros>
 		<import>macros.xml</import>
@@ -29,8 +29,8 @@ $top_only
 		<expand macro="genome_selector" />
 		<expand macro="gff3_input" />
 
-		<param label="Number of bases upstream of CDSs to end search (--lookahead_min)" name="lookahead_min" type="integer" value="5"/>
-		<param label="Number of bases upstream of CDSs to begin search (--lookahead_max)" name="lookahead_max" type="integer" value="15"/>
+		<param label="Minimum number of bases upstream of CDS for gap (--lookahead_min)" name="lookahead_min" type="integer" value="3"/>
+		<param label="Maximum number of bases upstream of CDS for gap (--lookahead_max)" name="lookahead_max" type="integer" value="17"/>
 		<param checked="true" label="Automatically add RBSs to input GFF3" name="add"
 				type="boolean" truevalue="--add" falsevalue="" />
 		<param checked="true" label="Only report best hits (--top_only)"
@@ -79,6 +79,10 @@ possible Shine-Dalgarno sequences:
 - AGG
 - GGT
 
+**Gap Min/Max Settings**
+ In previous versions of this tool, the min/max was set for the window to find a Shine-Dalgarno sequence, but 
+ currently we specify the minimum and maxium GAP between the end of the SD and the start of the closest CDS. 
+
 By default, only the first (closest to consensus) hit to the list is returned to the GFF3. 
 By selecting ‘No’ for ‘Only report best hits’, **all hits** to the possible SD list will 
 be added to the GFF3 file.