Updating repo

.replit

@@ -0,0 +1,9 @@
+modules = ["python-3.12", "bash"]
+run = "~/workspace/assignments/grade_hw.sh"
+
+[nix]
+channel = "stable-24_05"
+packages = ["zip"]
+
+[deployment]
+run = ["sh", "-c", "~/workspace/assignments/grade_hw.sh"]

assignments/01_howdy/howdy.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python3
+"""
+Author : Xavier Griggs
+Date   : 2025-02-02
+Purpose: Print greeting
+"""
+
+import argparse
+
+
+# --------------------------------------------------
+def get_args():
+                    """Get command-line arguments"""
+
+                    parser = argparse.ArgumentParser(
+                        description='Print greeting',
+                        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+
+                    parser.add_argument('-g',
+                                        '--greeting',
+                                        metavar='str',
+                                        type=str,
+                                        default='Howdy',
+                                        help='The greeting (default: Howdy)')
+
+                    parser.add_argument(
+                        '-n',
+                        '--name',
+                        metavar='str',
+                        type=str,
+                        default='Stranger',
+                        help='Whom to greet (default: Stranger)')
+
+                    parser.add_argument(
+                        '-e',
+                        '--excited',
+                        action='store_true',
+                        help='Include an exclamation point (default: False)')
+
+                    return parser.parse_args()
+
+
+# --------------------------------------------------
+def main():
+                    """Generate and print greeting"""
+
+                    args = get_args()
+                    greeting = f"{args.greeting}, {args.name}"
+                    if args.excited:
+                                        greeting += '!'
+                    else:
+                                        greeting += '.'
+
+                    print(greeting)
+
+
+# --------------------------------------------------
+if __name__ == '__main__':
+                    main()

assignments/02_divide/divide.py

@@ -0,0 +1,47 @@
+#!/usr/bin/env python3
+"""
+Author : Xavier Griggs
+Date   : 2025-02-09
+Purpose: divide 2 numbers
+"""
+
+import argparse
+import sys
+
+
+# --------------------------------------------------
+def get_args():
+    """Get command-line arguments"""
+
+    parser = argparse.ArgumentParser(
+        description='Divide two numbers',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+
+    parser.add_argument('ints',
+                        metavar='INT',
+                        type=int,
+                        nargs=2,
+                        help='Numbers to divide')
+
+    return parser.parse_args()
+
+
+# --------------------------------------------------
+def main():
+    """Perform division"""
+
+    args = get_args()
+    num1, num2 = args.ints
+
+    if num2 == 0:
+        print('usage: divide.py [-h] INT INT', file=sys.stderr)
+        print('divide.py: error: Cannot divide by zero, dum-dum!', file=sys.stderr)
+        return 1
+
+    print(f'{num1} / {num2} = {num1 // num2}')
+    return 0
+
+
+# --------------------------------------------------
+if __name__ == '__main__':
+   sys.exit(main())

assignments/03_dna/dna.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+"""
+Author : Xavier Griggs
+Date   : 2025-02-16
+Purpose: sequencing dna
+"""
+import argparse
+
+
+# --------------------------------------------------
+def get_args():
+    """Get command-line arguments"""
+
+    parser = argparse.ArgumentParser(
+        description='Tetranucleotide frequency',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+
+    parser.add_argument('DNA',
+                        metavar='DNA',
+                        help='Input DNA sequence')
+
+    return parser.parse_args()
+
+
+# --------------------------------------------------
+def main():
+    """Count tetranucleotide frequency"""
+
+    args = get_args()
+    dna = args.DNA.upper()
+    counts = {base: dna.count(base) for base in 'ACGT'}
+
+    print(counts['A'], counts['C'], counts['G'], counts['T'])
+
+
+# --------------------------------------------------
+if __name__ == '__main__':
+    main()

assignments/04_revc/revc.py

@@ -0,0 +1,47 @@
+#!/usr/bin/env python3
+"""
+Author :Xavier Griggs
+Date   : 2025-03-14
+Purpose: Add Your Purpose
+"""
+
+import argparse
+import os
+
+
+# --------------------------------------------------
+def get_args():
+    parser = argparse.ArgumentParser(
+        description='Print the reverse complement of DNA',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+
+    parser.add_argument('dna',
+                        metavar='DNA',
+                        type=str,
+                        help='Input sequence or file')
+
+    args = parser.parse_args()
+
+    if os.path.isfile(args.dna):
+        args.dna = open(args.dna).read().rstrip()
+
+    return args
+
+
+# --------------------------------------------------
+def reverse_complement(dna):
+    complement = str.maketrans('ACGTacgt', 'TGCAtgca')
+    return dna.translate(complement)[::-1]
+
+
+# --------------------------------------------------
+def main():
+    args = get_args()
+    dna = args.dna
+
+    print(reverse_complement(dna))
+
+
+# --------------------------------------------------
+if __name__ == '__main__':
+    main()

assignments/04_revc/test.py

@@ -6,8 +6,8 @@
 import re
 
 PRG = './revc.py'
-TEST1 = ('./inputs/input1.txt', './tests/inputs/output1.txt')
-TEST2 = ('./inputs/input2.txt', './tests/inputs/output2.txt')
+TEST1 = ('./inputs/input1.txt', './inputs/output1.txt')
+TEST2 = ('./inputs/input2.txt', './inputs/output2.txt')
 
 
 # --------------------------------------------------

assignments/05_gc/cgc.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+"""
+Author : Xavier Griggs
+Date   : 2025-04-15
+Purpose: Compute GC content of DNA sequences
+"""
+import argparse
+import sys
+
+
+# --------------------------------------------------
+def get_args():
+    "Get command-line arguments"
+
+    parser = argparse.ArgumentParser(
+        description='Compute GC content',
+        formatter_class=argparse.HelpFormatter)
+
+    parser.add_argument('file',
+                        metavar='FILE',
+                        help='Input sequence file',
+                        type=argparse.FileType('rt'),
+                        nargs='?',
+                        default=sys.stdin)
+
+    return parser.parse_args()
+
+
+# --------------------------------------------------
+def read_fasta(file):
+    "Read a FASTA file and return a dict of {ID: sequence}"
+    sequences = {}
+    current_id = None
+    for line in file:
+        line = line.strip()
+        if line.startswith('>'):
+            current_id = line[1:]
+            sequences[current_id] = ''
+        elif current_id:
+            sequences[current_id] += line
+    return sequences
+
+
+# --------------------------------------------------
+def gc_content(seq):
+    "Calculate GC content"
+    gc_count = seq.count('G') + seq.count('C')
+    return gc_count / len(seq) if seq else 0
+
+
+# --------------------------------------------------
+def main():
+    "Compute and print ID with highest GC content"
+
+    args = get_args()
+    sequences = read_fasta(args.file)
+
+    if not sequences:
+        print('No sequences found', file=sys.stderr)
+        sys.exit(1)
+
+    max_id = None
+    max_gc = -1
+
+    for seq_id, seq in sequences.items():
+        gc = gc_content(seq)
+        if gc > max_gc:
+            max_gc = gc
+            max_id = seq_id
+
+    print(f'{max_id} {max_gc * 100:.6f}')
+
+
+# --------------------------------------------------
+if __name__ == '__main__':
+    main()

assignments/06_rna/rna.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python3
+"""
+Author : Xavier Griggs
+Date   : 2025-04-30
+Purpose: Transcribe DNA sequences into RNA and save to output file"""
+
+import argparse
+import os
+import sys
+
+
+# --------------------------------------------------
+def transcribe_dna_to_rna(dna_sequence):
+    """Transcribe a DNA sequence into RNA by replacing T with U"""
+    return dna_sequence.replace('T', 'U')
+
+
+# --------------------------------------------------
+def get_args():
+    """Get command-line arguments"""
+
+    parser = argparse.ArgumentParser(
+        description='Transcribe DNA into RNA',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+
+    # Argument for input DNA file
+    parser.add_argument('files',
+                        metavar='FILE',
+                        nargs='+',
+                        help='One or more input DNA files')
+
+    #default = "out"
+    parser.add_argument('-o',
+                        '--out_dir',
+                        help='Output directory for RNA files (default: out)',
+                        metavar='DIR',
+                        type=str,
+                        default='out')
+
+    return parser.parse_args()
+
+
+# --------------------------------------------------
+def process_files(args):
+    """Process the input files, transcribe DNA to RNA, and write to output dir"""
+
+    # Make sure the output dir exists
+    if not os.path.exists(args.out_dir):
+        os.makedirs(args.out_dir)
+
+    total_sequences = 0
+    for input_file in args.files:
+        # Check if the file exists
+        if not os.path.isfile(input_file):
+            # Only print the usage message (not error message)
+            print(f"Usage: {sys.argv[0]} [-h] [-o DIR] FILE [FILE ...]")
+            print(f"No such file or directory: '{input_file}'")
+            sys.exit(1)  # Exit with a non-zero code if file is missing
+
+        # Read the file and process
+        with open(input_file, 'r') as infile:
+            lines = infile.readlines()
+
+        # Create an output file
+        output_file_path = os.path.join(args.out_dir,
+                                        os.path.basename(input_file))
+
+        with open(output_file_path, 'w') as outfile:
+            for line in lines:
+                dna_sequence = line.strip()
+                if dna_sequence:  # Only transcribe non-empty lines
+                    rna_sequence = transcribe_dna_to_rna(dna_sequence)
+                    outfile.write(rna_sequence + '\n')
+                    total_sequences += 1
+    print(
+        f'Done, wrote {total_sequences} sequence{"s" if total_sequences > 1 else ""} in {len(args.files)} file{"s" if len(args.files) > 1 else ""} to directory "{args.out_dir}".'
+    )
+
+
+# --------------------------------------------------
+def main():
+    args = get_args()
+    process_files(args)
+
+
+# --------------------------------------------------
+if __name__ == '__main__':
+    main()