ep5 ProfileMostProbableKmer.py

def Pr(Text, Profile):
    """
    Calculate the probability of a given k-mer Text based on a profile matrix.

    Args:
        Text (str): A k-mer (substring of DNA sequence).
        Profile (dict): A profile matrix where keys are nucleotides and values 
                        are lists of probabilities for each position.

    Returns:
        float: Probability of Text being generated by Profile.
    """
    p = 1  # Initialize probability
    for i in range(len(Text)):
        p *= Profile[Text[i]][i]  # Multiply probabilities for each nucleotide
    return p


def ProfileMostProbableKmer(Text, k, Profile):
    """
    Find the most probable k-mer in Text based on a given profile matrix.

    Args:
        Text (str): DNA sequence.
        k (int): Length of the k-mer.
        Profile (dict): A profile matrix where keys are nucleotides and values 
                        are lists of probabilities for each position.

    Returns:
        str: The most probable k-mer in Text based on Profile.
    """
    max_probability = -1  # Initialize max probability as a very low value
    most_probable_kmer = ''  # Initialize the most probable k-mer

    # Slide through the Text to consider all possible k-mers
    for i in range(len(Text) - k + 1):
        kmer = Text[i:i + k]  # Extract k-mer
        probability = Pr(kmer, Profile)  # Calculate its probability

        # Update the most probable k-mer if a higher probability is found
        if probability > max_probability:
            max_probability = probability
            most_probable_kmer = kmer

    return most_probable_kmer


# Example Input
Text = "ACGTACGTGACG"
k = 3
Profile = {
    'A': [0.2, 0.4, 0.3],
    'C': [0.4, 0.3, 0.1],
    'G': [0.3, 0.1, 0.5],
    'T': [0.1, 0.2, 0.1]
}

# Find and display the most probable k-mer
result = ProfileMostProbableKmer(Text, k, Profile)
print("Most Probable k-mer:", result)