sminot

import boto3

def aws_s3_ls(bucket, prefix):
    conn = boto3.client('s3')
    
    fps = []
    
    r = conn.list_objects_v2(
        Bucket=bucket, 
        Prefix=prefix

sminot

#!/usr/bin/env python
"""Convert GlimmerHMM GFF3 gene predictions into protein sequences.

This works with the GlimmerHMM GFF3 output format:

##gff-version 3
##sequence-region Contig5.15 1 47390
Contig5.15      GlimmerHMM      mRNA    323     325     .       +       .       ID=Contig5.15.path1.gene1;Name=Contig5.15.path1.gene1
Contig5.15      GlimmerHMM      CDS     323     325     .       +       0       ID=Contig5.15.cds1.1;Parent=Contig5.15.path1.gene1;Name=Contig5.15.path1.gene1;Note=final-exon

sminot

#!/bin/bash

set -e

bucket=$1
prefix=$2

(( ${#bucket} > 0 ))
(( ${#prefix} > 0 ))

sminot

#!/usr/bin/env python3

from Bio.SeqIO.QualityIO import FastqGeneralIterator
from collections import defaultdict
import gzip
from functools import lru_cache
import os
import sys

assert len(sys.argv) == 3, "Please specify input file and output prefix"                                                                                                                            

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)

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

#!/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

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

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

#!/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")