from Bio import SeqIO

for record in SeqIO.parse('sequences.fasta', 'fasta'):
    print(record.id, len(record.seq))

record = SeqIO.read('single.fasta', 'fasta')

records = SeqIO.to_dict(SeqIO.parse('sequences.fasta', 'fasta'))
seq = records['sequence_id'].seq

records = SeqIO.index('large.fasta', 'fasta')
seq = records['sequence_id'].seq
records.close()

# Create index (first time - parses file)
records = SeqIO.index_db('index.sqlite', 'large.fasta', 'fasta')
seq = records['sequence_id'].seq
records.close()

# Reuse existing index (instant load)
records = SeqIO.index_db('index.sqlite')

# Index multiple files together
records = SeqIO.index_db('combined.sqlite', ['file1.fasta', 'file2.fasta'], 'fasta')

from Bio.SeqIO.FastaIO import SimpleFastaParser

with open('large.fasta') as handle:
    for title, sequence in SimpleFastaParser(handle):
        if len(sequence) > 1000:
            print(title.split()[0])  # First word is usually ID

from Bio.SeqIO.QualityIO import FastqGeneralIterator

with open('reads.fastq') as handle:
    for title, sequence, quality in FastqGeneralIterator(handle):
        avg_qual = sum(ord(c) - 33 for c in quality) / len(quality)

# Read Sanger sequencing trace with quality
record = SeqIO.read('sample.ab1', 'abi')
print(f'Sequence: {record.seq}')
qualities = record.letter_annotations['phred_quality']

# Auto-trim low quality ends
record_trimmed = SeqIO.read('sample.ab1', 'abi-trim')

for record in SeqIO.parse('reads.sff', 'sff'):
    print(record.id, len(record.seq))

# With trimming applied
for record in SeqIO.parse('reads.sff', 'sff-trim'):
    print(record.id, len(record.seq))

# Get sequences from SEQRES records
for record in SeqIO.parse('structure.pdb', 'pdb-seqres'):
    print(f'Chain {record.id}: {record.seq}')

# Get sequences from ATOM coordinates
for record in SeqIO.parse('structure.pdb', 'pdb-atom'):
    print(f'Chain {record.id}: {record.seq}')

record.id          # Sequence identifier (string)
record.name        # Sequence name (string)
record.description # Full description line (string)
record.seq         # Sequence data (Seq object)
record.features    # List of SeqFeature objects (GenBank/EMBL)
record.annotations # Dictionary of annotations
record.letter_annotations  # Per-letter annotations (quality scores)
record.dbxrefs     # Database cross-references

records = list(SeqIO.parse('sequences.fasta', 'fasta'))

count = sum(1 for _ in SeqIO.parse('sequences.fasta', 'fasta'))

from Bio.SeqIO.FastaIO import SimpleFastaParser
with open('sequences.fasta') as f:
    count = sum(1 for _ in SimpleFastaParser(f))

ids = [record.id for record in SeqIO.parse('sequences.fasta', 'fasta')]

for record in SeqIO.parse('sequence.gb', 'genbank'):
    for feature in record.features:
        if feature.type == 'CDS':
            print(feature.qualifiers.get('product', ['Unknown'])[0])
            cds_seq = feature.extract(record.seq)  # Get feature sequence

for record in SeqIO.parse('reads.fastq', 'fastq'):
    qualities = record.letter_annotations['phred_quality']
    avg_quality = sum(qualities) / len(qualities)

with open('sequences.fasta', 'r') as handle:
    for record in SeqIO.parse(handle, 'fasta'):
        print(record.id)

def get_accession(identifier):
    return identifier.split('.')[0]  # Remove version

records = SeqIO.index('sequences.fasta', 'fasta', key_function=get_accession)

Need to read sequences?
├── Single record in file?
│   └── Use SeqIO.read()
├── Multiple records?
│   ├── Need all in memory at once?
│   │   └── Use list(SeqIO.parse()) or SeqIO.to_dict()
│   ├── Process one at a time (memory efficient)?
│   │   └── Use SeqIO.parse() iterator
│   ├── Large file, need random access by ID?
│   │   ├── Single session? → Use SeqIO.index()
│   │   └── Persistent/multi-file? → Use SeqIO.index_db()
│   └── Maximum throughput needed?
│       └── Use SimpleFastaParser or FastqGeneralIterator
├── Sanger sequencing trace?
│   └── Use 'abi' or 'abi-trim' format
├── 454/Ion Torrent data?
│   └── Use 'sff' or 'sff-trim' format
└── Protein from structure?
    └── Use 'pdb-seqres' or 'pdb-atom' format