ONEcode python interface

[AnantMaheshwari]

Uses pybind to create a python interface for ONEcode files, wrapping around existing functionality in the C++ interface (ONElib.hpp).

Notebook provides example usage patterns e.g. see https://github.com/AnantMaheshwari/ONEcode/blob/python_API/pyOnelib.ipynb
for examples of interacting with the API.

For example, the below code block would allow a user to read sequences from a test file (TEST/small.1seq) and write a new ONEfile that is the same sequences reverse complemented (TEST/small_rc.1seq)

def reverse_complement(seq):
    """Simple reverse complement for DNA sequences"""
    complement = {'A': 'T', 'T': 'A', 'G': 'C', 'C': 'G',
                  'a': 't', 't': 'a', 'g': 'c', 'c': 'g'}
    return ''.join(complement.get(base, base) for base in reversed(seq))

# Open input file
infile = ONEcode.ONEfile("./TEST/small.seq", "r", schema, "", 1)

# Create output file for reverse complements
outfile = ONEcode.ONEfile("./TEST/small_rc.1seq", "wb", schema, "seq", 1)
outfile.addProvenance("python_tutorial", "1.0.0", "Reverse complement from Python")

# Process sequences
print("Processing sequences...\n")
while infile.readLine():
    lt = infile.lineType()
    
    if lt == 'S':
        seq = infile.getString()
        rc_seq = reverse_complement(seq)
        outfile.writeLine('S', rc_seq)
        
            print(f"Sequence {seq_count}:")
            print(f"  Original: {seq[:40]}..." if len(seq) > 40 else f"  Original: {seq}")
            print(f"  Rev-comp: {rc_seq[:40]}..." if len(rc_seq) > 40 else f"  Rev-comp: {rc_seq}")
    
    elif lt == 'I':
        seq_id = infile.getString()
        outfile.writeLine('I', seq_id + "_RC")

del outfile

print(f"Output written to: ./TEST/small_rc.1seq")