sminot

#!/usr/bin/python

import os
import sys
import xml
import gzip
import json
import time
from collections import defaultdict
import pandas as pd

sminot

#!/usr/local/bin/python

import os
import io
import json
import gzip
import boto3
import argparse
import pandas as pd

sminot

#!/usr/bin/python
# encoding:utf8
# authors: Erik Garrison, Sébastien Boisvert, Sam Minot
"""This script takes a folder of fastq(.gz) files and interleaves them

Usage:
    interleave-fasta folder
"""

import os

sminot

def read_fasta_from_s3(bucket_name, key_name, sep="\t"):
    s3 = boto3.client('s3')
    retr = s3.get_object(Bucket=bucket_name, Key=key_name)

    for header, seq in SimpleFastaParser(io.StringIO(retr['Body'].read().decode('utf-8'))):
        yield header, seq

sminot

#!/usr/bin/env python3

import os
import sys
import xmltodict
from collections import OrderedDict

assert len(sys.argv) > 1
assert os.path.exists(sys.argv[1])
assert sys.argv[1].endswith(".xml")

sminot

def read_fasta_from_s3(bucket_name, key_name, sep="\t"):
    s3 = boto3.client('s3')
    retr = s3.get_object(Bucket=bucket_name, Key=key_name)
    bytestream = io.BytesIO(retr['Body'].read())
    got_text = gzip.GzipFile(None, 'rb', fileobj=bytestream).read().decode('utf-8')

    for header, seq in SimpleFastaParser(io.StringIO(got_text)):
        yield header, seq

sminot

from Bio import Entrez
import xmltodict

def get_name_from_assembly_id(assembly_name):
    handle = Entrez.esearch("assembly", term=assembly_name)
    search_result = xmltodict.parse("".join(handle.readlines()))
    handle.close()
    try:
        assembly_id = search_result["eSearchResult"]["IdList"]["Id"]
    except:

sminot

#!/bin/bash

set -e

module load PANDAseq/2.11-foss-2016b

find . -name "*_1.fq.gz" | sort -R | while read fwd; do
	rev="${fwd/_1.fq.gz/_2.fq.gz}"
	[[ -s "$rev" ]]

sminot

# KEGG names
@lru_cache(maxsize=None)
def get_kegg_name(ko):
    r = requests.get("http://rest.kegg.jp/list/{}".format(ko))
    return r.text.split("\t")[-1].rstrip("\n")

get_kegg_name("K00975")

sminot

import io
import boto3
import pandas as pd

def read_feather_file_from_s3(s3_url):
    assert s3_url.startswith("s3://")
    bucket_name, key_name = s3_url[5:].split("/", 1)

    s3 = boto3.client('s3')
    retr = s3.get_object(Bucket=bucket_name, Key=key_name)