rliterman@0: #!/usr/bin/env python3
rliterman@0: 
rliterman@0: from Bio import SeqIO
rliterman@0: import hashlib
rliterman@0: import sys
rliterman@0: import os
rliterman@0: import pandas as pd
rliterman@0: 
rliterman@0: def fasta_info(sample_name,file_path):
rliterman@0:     
rliterman@0:     if not os.path.exists(file_path):
rliterman@0:         sys.exit(f"File {file_path} does not exist.")
rliterman@0:     elif not file_path.lower().endswith(('.fa', '.fasta', '.fna')):
rliterman@0:         sys.exit(f"File {file_path} is not a .fa, .fasta, or .fna file.")
rliterman@0:     
rliterman@0:     records = list(SeqIO.parse(file_path, 'fasta'))
rliterman@0:     contig_count = int(len(records))
rliterman@0:     lengths = sorted([len(record) for record in records], reverse=True)
rliterman@0:     assembly_bases = sum(lengths)
rliterman@0: 
rliterman@0:     with open(file_path, 'rb') as file:
rliterman@0:         sha256 = hashlib.sha256(file.read()).hexdigest()
rliterman@0: 
rliterman@0:     cumulative_length = 0
rliterman@0:     n50 = None
rliterman@0:     n90 = None
rliterman@0:     l50 = None
rliterman@0:     l90 = None
rliterman@0:     
rliterman@0:     for i, length in enumerate(lengths, start=1):
rliterman@0:         cumulative_length += length
rliterman@0:         if cumulative_length >= assembly_bases * 0.5 and n50 is None:
rliterman@0:             n50 = length
rliterman@0:             l50 = i
rliterman@0:         if cumulative_length >= assembly_bases * 0.9 and n90 is None:
rliterman@0:             n90 = length
rliterman@0:             l90 = i
rliterman@0:         if n50 is not None and n90 is not None:
rliterman@0:             break
rliterman@0: 
rliterman@0:     print(f"{sample_name},{file_path},{contig_count},{assembly_bases},{n50},{n90},{l50},{l90},{sha256}")
rliterman@0: 
rliterman@0: fasta_tsv = pd.read_csv(sys.argv[1], sep='\t', header=None, names=['Sample_ID','Fasta_Path'])
rliterman@0: [fasta_info(sample_name, file_path) for sample_name, file_path in fasta_tsv.values]