计算序列之间的相似性矩阵

# Let's read the sequences from the uploaded file and calculate the sequence similarity matrix.

# Read the sequences from the uploaded file
file_path = '/mnt/data/similar_seq.txt'
with open(file_path, 'r') as file:
    sequences = file.read().split('>')[1:]  # Split the sequences and ignore the first empty split

# Parse the sequences into a dictionary
seq_dict = {}
for seq in sequences:
    lines = seq.strip().split('\n')
    header = lines[0].split()[0]
    sequence = ''.join(lines[1:])
    seq_dict[header] = sequence

# Extract headers and sequences
headers = list(seq_dict.keys())
sequences = list(seq_dict.values())

# Function to calculate sequence similarity
def calculate_similarity(seq1, seq2):
    matches = sum(a == b for a, b in zip(seq1, seq2))
    return matches / min(len(seq1), len(seq2))  # Normalize by the length of the shorter sequence

# Calculate the similarity matrix
import numpy as np

num_sequences = len(sequences)
similarity_matrix = np.zeros((num_sequences, num_sequences))

for i in range(num_sequences):
    for j in range(num_sequences):
        similarity_matrix[i, j] = calculate_similarity(sequences[i], sequences[j])

similarity_matrix, headers