sminot

#!/usr/bin/python
"""
One Codex CSV Download Script.

Simple 1 dependency (requests) Python 2/3 script for downloading
One Codex analysis results and saving them to CSVs, as well as read-level results
"""
from __future__ import print_function
import os
import requests

sminot

#
# Copyright Reference Genomics, Inc. 2016
# Released under the MIT License
#
# Script for fetching analysis results from the One Codex API (v0)
# See https://docs.onecodex.com for full documentation on the REST API
#
# Script can be run from the command line with:
# `Rscript fetch_ocx_analyses.R $ONE_CODEX_API_KEY $output_filepath`
#

sminot

#!/usr/bin/python
"""Download results from One Codex and combine into a single table (note: requires pandas)."""

import requests
import os
import pandas as pd

# Expects the API key for One Codex to be stored in the ONE_CODEX_API_KEY environment variable
api_key = os.environ['ONE_CODEX_API_KEY']

sminot

#!/usr/local/bin/Rscript

# Copyright Reference Genomics, Inc. 2016
# Released under the MIT License
#
# Script for fetching analysis results from the One Codex API (v0)
# See https://docs.onecodex.com for full documentation on the REST API
#
# Script can be run from the command line with:
# `Rscript fetch_ocx_analyses.R <API_KEY> <FILE> [-d DB] [-b BEGINNING_DATE -e ENDING_DATE]`

sminot

#!/usr/bin/python
"""Split up a FASTQ file based on the first field of the header."""

from collections import defaultdict
import gzip
import sys
import os

fp = sys.argv[1]
if not os.path.exists(fp):

sminot

#!/usr/bin/python
"""Given a set of protein FASTA files, perform pairwise comparison via BLAST, outputting an Excel spreadsheet."""

import os
import sys
import json
import subprocess
import pandas as pd
from collections import defaultdict
from Bio.SeqIO.FastaIO import SimpleFastaParser

sminot

import os
from functools import lru_cache
from collections import defaultdict

# Read in the taxonomy
class NCBITaxonomy():
    def __init__(self, folder):
        self.tax = defaultdict(dict)
        # Read in the file of taxid information
        names_fp = os.path.join(folder, 'names.dmp')

sminot

#!/usr/local/bin/ipython

import pandas as pd
from collections import defaultdict
from random import choice

alph = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j']

# Function to make some test data
def make_dat(nrows=1000, ncols=1000, nvals=1000):

sminot

#!/usr/bin/python
"""Make a taxonomy file compatible with mothur."""

import os
import sys
import pandas as pd

if len(sys.argv) != 4:
    print("Please specify the seq_info.csv, tax_info.csv, and output.tsv files")

sminot

import io
import json
import gzip
import boto3

def read_gzipped_json_file_from_s3(bucket_name, key_name):
    s3 = boto3.client('s3')
    retr = s3.get_object(Bucket=bucket_name, Key=key_name)

    bytestream = io.BytesIO(retr['Body'].read())