Sat, May 4, 2024, 4:35 PM -07:00

1 files changed, 58 insertions, 0 deletions

diff --git a/wk6/pset/dna/dna.py b/wk6/pset/dna/dna.py
new file mode 100644
index 0000000..401e674
--- /dev/null
+++ b/wk6/pset/dna/dna.py
@@ -0,0 +1,58 @@
+import csv
+import sys
+
+
+def main():
+
+    # TODO: Check for command-line usage
+
+    # TODO: Read database file into a variable
+    
+    # TODO: Read DNA sequence file into a variable
+
+    # TODO: Find longest match of each STR in DNA sequence
+
+    # TODO: Check database for matching profiles
+
+    return
+
+
+def longest_match(sequence, subsequence):
+    """Returns length of longest run of subsequence in sequence."""
+
+    # Initialize variables
+    longest_run = 0
+    subsequence_length = len(subsequence)
+    sequence_length = len(sequence)
+
+    # Check each character in sequence for most consecutive runs of subsequence
+    for i in range(sequence_length):
+
+        # Initialize count of consecutive runs
+        count = 0
+
+        # Check for a subsequence match in a "substring" (a subset of characters) within sequence
+        # If a match, move substring to next potential match in sequence
+        # Continue moving substring and checking for matches until out of consecutive matches
+        while True:
+
+            # Adjust substring start and end
+            start = i + count * subsequence_length
+            end = start + subsequence_length
+
+            # If there is a match in the substring
+            if sequence[start:end] == subsequence:
+                count += 1
+            
+            # If there is no match in the substring
+            else:
+                break
+        
+        # Update most consecutive matches found
+        longest_run = max(longest_run, count)
+
+    # After checking for runs at each character in seqeuence, return longest run found
+    return longest_run
+
+
+main()