read data from cloud object store with biopython

read_from_s3.py

"""
Reads a fastq file directly from the 1000genomes AWS public dataset
into a Bio.SeqRecord set

Requires an AWS Account
"""

from smart_open import open
from Bio import SeqIO

# file handle-like reference to ~60MB object in S3
fh = open('s3://1000genomes/phase3/data/NA12878/sequence_read/SRR622461.filt.fastq.gz')

for record in SeqIO.parse(fh, 'fastq'):
    print(record.id)

read_from_s3_s3fs.py

"""
Reads a fastq file directly from the 1000genomes AWS public dataset
into a Bio.SeqRecord set

Does not require an AWS Account
"""
import io
from gzip import GzipFile

import s3fs
from Bio import SeqIO

fs = s3fs.S3FileSystem(anon=True)

with fs.open('1000genomes/phase3/data/NA12878/sequence_read/SRR622461.filt.fastq.gz','rb') as f:
     for record in SeqIO.parse(io.TextIOWrapper(GzipFile(fileobj=f)), 'fastq'):
         print(record.id)

Looks like smart_open does use boto3, but does not provide anonymous access to S3. That feature seems unique to s3fs.