dna_analysis.py

import collections
from typing import Dict

class InvalidNucleotideError(Exception):
    """"
    Custom error message when an invalid nucleotide is encountered.
    """
    pass

def _validate_dna_sequence(sequence:str)->str:
    """"
    Ensures only A,T,G,C nucleotides are present in the DNA sequence.
    """
    valid_nucleotides= {'A','T','G','C'}
    invalid_characters = set(sequence) - set(valid_nucleotides)
    if invalid_characters:
        raise InvalidNucleotideError(
            f"Invalid nucleotides found: {invalid_characters}"
            f"Only {valid_nucleotides} are allowed in the DNA sequence"
        )
    return sequence

def count_nucleotides(sequence:str)->Dict[str, int]:
    """"
    Returns the count of each nucleotide in the DNA sequence.
    """
    sequence = _validate_dna_sequence(sequence)
    counts={"A":0,"T":0,"G":0,"C":0}
    counts.update(collections.Counter(sequence))
    return counts

def calculate_dna_percentage(sequence:str)-> Dict[str, float]:
    """"
    Calculates the percentage of each nucleotide in the DNA sequence.
    """
    sequence = _validate_dna_sequence(sequence)
    length = len(sequence)
    if length == 0:
        return {"A":0.0,"T":0.0,"G":0.0,"C":0.0}
    counts = count_nucleotides(sequence)
    return {n: round ((c/length)*100, 2)for n,c in counts.items()}

def generate_analysis_report (sequence:str, name:str="Sequence")->str:
    """"
    Generate a comprehensive report of the DNA sequence.
    """
    sequence = _validate_dna_sequence(sequence)
    length = len(sequence)
    count= count_nucleotides(sequence)
    frequency= calculate_dna_percentage(sequence)
    GC= frequency["G"] + frequency["C"]
    AT= frequency["A"] + frequency["T"]

    report = f"\n Nucleotide analysis report for {name}\n"
    report += f"Sequence: {sequence}\n"
    report += f"Length: {length} base pairs\n"
    report+= "{:<10}{:<10}{:<10}\n".format("Nucleotide", "Count", "Frequency(%)")
    report += "-" * 30 + "\n"
    for n in sorted(count):
        report += "{:<10}{:<10}{:<10.2f}\n".format(n, count[n], frequency[n])

    report +=f"\nGC Content: {GC:.2f}%\nAT Content: {AT:.2f}%\n"
    return report

def compare_nucleotide_composition(seq1:str, name1:str, seq2:str, name2:str)->str:
    """"
    Compares the nucleotide composition of two sequences.
    """
    frequency_1 , frequency_2 = calculate_dna_percentage(seq1), calculate_dna_percentage(seq2)
    GC1= frequency_1["G"] + frequency_1["C"]
    GC2= frequency_2["G"] + frequency_2["C"]
    AT1= frequency_1["A"] + frequency_1["T"]
    AT2=  frequency_2["A"] + frequency_2["T"]

    comparison = f"\nComparison of two DNA sequences- {name1} and {name2}\n"
    comparison += "{:<10}{:<15}{:<15}\n".format("Nucleotide", name1, name2)
    comparison += "-" * 40 + "\n"

    for n in sorted(frequency_1):
        comparison += "{:<10}{:<15.2f}{:<15.2f}\n".format(n, frequency_1[n], frequency_2[n])
    comparison += "\n"
    comparison += "{:<10}{:<15.2f}{:<15.2f}\n".format("GC-Content", GC1, GC2)
    comparison += "{:<10}{:<15.2f}{:<15.2f}\n".format("AT-Content", AT1, AT2)

    return comparison