biopython-bio

Biopython Bio

Bioinformatics operations using Biopython.

When to Use

• Reading/writing sequence files (FASTA, GenBank)
• Running BLAST searches (local or remote NCBI)
• Sequence alignment and manipulation
• Parsing PDB protein structures
• Phylogenetic tree construction
• Querying NCBI Entrez databases

When NOT to Use

• Clinical genomics or variant calling (use GATK, bcftools)
• RNA-seq differential expression (use DESeq2, edgeR)
• Genome assembly (use SPAdes, Canu)
• Molecular dynamics simulations (use GROMACS, OpenMM)

Sequence Reading and Writing

from Bio import SeqIO
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord

for record in SeqIO.parse('sequences.fasta', 'fasta'):
    print(f"{record.id}: {len(record.seq)} bp")

# Write FASTA
records = [SeqRecord(Seq('ATGCGATCGATCG'), id='seq1', description='example')]
SeqIO.write(records, 'output.fasta', 'fasta')

Sequence Manipulation

from Bio.Seq import Seq
from Bio.SeqUtils import gc_fraction, molecular_weight

dna = Seq('ATGCGATCGATCGATCG')
rev_comp = dna.reverse_complement()
protein = dna.translate()
gc = gc_fraction(dna)
mw = molecular_weight(dna, seq_type='DNA')

BLAST Searches

from Bio.Blast import NCBIWWW, NCBIXML

result_handle = NCBIWWW.qblast('blastn', 'nt', 'ATGCGATCGATCGATCG')
for record in NCBIXML.parse(result_handle):
    for aln in record.alignments:
        for hsp in aln.hsps:
            if hsp.expect < 1e-10:
                print(f"{aln.title[:60]}, E={hsp.expect}")

Pairwise Alignment

from Bio import Align

aligner = Align.PairwiseAligner()
aligner.mode = 'global'
aligner.match_score = 2
aligner.mismatch_score = -1
best = aligner.align('ATCGATCGATCG', 'ATCAATCAATCG')[0]
print(best, f"Score: {best.score}")

PDB Structure Parsing

from Bio.PDB import PDBParser, PDBList

structure = PDBParser(QUIET=True).get_structure('prot', 'structure.pdb')
for chain in structure[0]:
    for res in chain:
        if res.id[0] == ' ' and 'CA' in res:
            print(f"{res.resname} {res.id[1]}: {res['CA'].coord}")