#Python script to parse a FASTQ file and extract basic information such as the sequence identifier, sequence, and quality scores
#pip install biopython
from Bio import SeqIO
def parse_fastq(fastq_file):
# Initialize a list to store parsed sequences
sequences = []
# Read the sequences from the FASTQ file
for record in SeqIO.parse(fastq_file, "fastq"):
sequence_info = {
"id": record.id,
"sequence": str(record.seq),
"quality": record.letter_annotations["phred_quality"]
}
sequences.append(sequence_info)
return sequences
# Example usage
fastq_file = "path/to/your/sequences.fastq"
parsed_sequences = parse_fastq(fastq_file)
# Print out the parsed sequences
for seq in parsed_sequences:
print(f"ID: {seq['id']}")
print(f"Sequence: {seq['sequence']}")
print(f"Quality: {seq['quality']}")
print()