runchuan-bu/bioclaw/blast-search

# Create query file
cat > /tmp/query.fa << 'EOF'
>query_sequence
ATGCGATCGATCGATCG...
EOF
 
# Create subject file (if user provides reference)
cat > /tmp/subject.fa << 'EOF'
>reference
ATGCGATCGATCGATCG...
EOF
 
# Run BLAST
blastn -query /tmp/query.fa -subject /tmp/subject.fa -outfmt 6 -evalue 1e-5

from Bio.Blast import NCBIWWW, NCBIXML
from Bio import SeqIO
# Read sequence
sequence = "ATGCGATCGATCGATCG..."
# Run remote BLAST
result_handle = NCBIWWW.qblast("blastn", "nt", sequence)
blast_records = NCBIXML.parse(result_handle)
for record in blast_records:
    for alignment in record.alignments[:10]:
        print(f"Title: {alignment.title}")
        for hsp in alignment.hsps:
            print(f"  Score: {hsp.score}, E-value: {hsp.expect}")
            print(f"  Identity: {hsp.identities}/{hsp.align_length} ({hsp.identities/hsp.align_length*100:.1f}%)")

*BLAST Results (top 10 hits)*
 
• Hit 1: Homo sapiens TP53 gene (98.5% identity, E=1e-45)
• Hit 2: Mus musculus Trp53 gene (89.2% identity, E=1e-38)
...