Fixed description for no repeat structures

extractor/describe.py

@@ -460,12 +460,17 @@ def describe_repeats(reference, sample, units):
         seq_list.append(DNAVar(type='repeat',inserted=repeats[repeat]['unit'],count=repeats[repeat]['count']))
         repeat += 1
 
-    description.append(DNAVar(start=reference_start + 1,end=reference_end,sample_start=sample_start,sample_end=sample_end,type='delins',inserted=seq_list))
-
-    suffix = describe_dna(reference[reference_end:], sample[sample_end:])
-    for variant in suffix:
-        if variant.type != 'none':
-            description.append(variant)
+    if len(variant_list) > 0 or len(repeats) > 0:
+        description.append(DNAVar(start=reference_start + 1,end=reference_end,sample_start=sample_start,sample_end=sample_end,type='delins',inserted=seq_list))
+
+        suffix = describe_dna(reference[reference_end:], sample[sample_end:])
+        for variant in suffix:
+            if variant.type != 'none':
+                variant.start += reference_end
+                variant.end += reference_end
+                description.append(variant)
+    else:
+        description = prefix
 
     return description
 

repeat-extractor.py

@@ -81,7 +81,7 @@ def short_sequence_repeat_extractor(string, min_length=1):
 
 
 min_count = 3
-min_length = 2
+min_length = 3
 
 with open('strlist.txt', 'r') as infile:
     lines = infile.readlines()
@@ -95,39 +95,39 @@ for line in lines:
     else:
         sequences[label] = [string.strip()]
 
-select = 'D8S1179'
-unit_list = ['TCTA', 'TATC']
-reference = sequences[select][0]
-sample = sequences[select][7]
-description = describe_repeats(reference, sample, unit_list)
-print 'l.{}'.format(description)
-
-
-#for sequence in sequences:
-#    best = 0
-#    for string in sequences[sequence]:
-#        repeats = short_sequence_repeat_extractor(string, min_length)
-#        score = 0
-#        for repeat in repeats:
-#            if repeat.count + 1 >= min_count:
-#                score += (repeat.end - repeat.start) * (repeat.end - repeat.start) * (repeat.count + 1)
-#        if score > best:
-#            reference = string
-#            best = score
-
-#    repeats = short_sequence_repeat_extractor(reference, min_length)
-#    units = {}
-#    for repeat in repeats:
-#        if repeat.count + 1 >= min_count:
-#            units[reference[repeat.start:repeat.end]] = repeat.count + 1
-#    unit_list = []
-#    for unit in units:
-#        unit_list.append(unit)
-
-#    print sequence, unit_list
-#    reference = sequences[sequence][0]
-#    for string in sequences[sequence]:
-#        description = describe_repeats(reference, string, unit_list)
-#        print 'l.{}'.format(description)
-#    print
+#select = 'Amel'
+#unit_list = ['TATC']
+#reference = sequences[select][0]
+#sample = sequences[select][0]
+#description = describe_repeats(reference, sample, unit_list)
+#print 'l.{}'.format(description)
+
+
+for sequence in sequences:
+    best = 0
+    for string in sequences[sequence]:
+        repeats = short_sequence_repeat_extractor(string, min_length)
+        score = 0
+        for repeat in repeats:
+            if repeat.count + 1 >= min_count:
+                score += (repeat.end - repeat.start) * (repeat.end - repeat.start) * (repeat.count + 1)
+        if score > best:
+            reference = string
+            best = score
+
+    repeats = short_sequence_repeat_extractor(reference, min_length)
+    units = {}
+    for repeat in repeats:
+        if repeat.count + 1 >= min_count:
+            units[reference[repeat.start:repeat.end]] = repeat.count + 1
+    unit_list = []
+    for unit in units:
+        unit_list.append(unit)
+
+    print sequence, unit_list
+    reference = sequences[sequence][0]
+    for string in sequences[sequence]:
+        description = describe_repeats(reference, string, unit_list)
+        print 'l.{}'.format(description)
+    print