mikerobeson

#!/usr/bin/env python
# Takes input in the form of:
#	OTU6	d:Viridiplantae,k:Streptophyta,p:asterids,c:Gentianales,o:Rubiaceae;
#	OTU7	d:Viridiplantae,k:Streptophyta;
# and outputs to:
#	OTU6	d__Viridiplantae;k__Streptophyta;p__asterids;c__Gentianales;o__Rubiaceae;f__;g__;s__
#	OTU7	d__Viridiplantae;k__Streptophyta;p__;c__;o__;f__;g__;s__


# WARNING! This script will fail if there are extraneous other ':' in the taxonomy labels.

mikerobeson

#! /usr/bin/env python
# Created by: Michael S. Robeson II
from cogent import LoadSeqs
import string

def read_sequence_file(file_path):
    """Reads in an ALIGNED fasta formated sequence file
        -file_path : path to the file to be read in
    """
    seq_data = LoadSeqs(file_path, alignment=True)

mikerobeson

#!/usr/bin/env python

from cogent.parse.fasta import MinimalFastaParser


def check_for_iupac(seq):
	"""Flag seqs with IUPAC amibuity codes
	like RYSWKMBDHVN
	"""
	iupac = 'RYSWKMBDHVN'

mikerobeson

#!/usr/bin/env python
# Mike Robeson (GitHub: @mikerobeson)
# Needs PyCogent installed.


from cogent.parse.fastq import MinimalFastqParser
from cogent.parse.fasta import MinimalFastaParser
from os.path import abspath, join, splitext, dirname, basename
from os import system, mkdir
from optparse import OptionParser, OptionGroup

mikerobeson

#!/usr/bin/env python
# Mike Robeson
# quickly hacked / draft code to build a compatable fasta file for use in usearch v8.1
# See: http://www.drive5.com/usearch/manual/utax_user_train.html

from optparse import OptionParser, OptionGroup
from cogent.parse.ncbi_taxonomy import NcbiTaxonomyFromFiles
from cogent.parse.fasta import MinimalFastaParser
import unicodedata

mikerobeson

#! /usr/bin/env python
# This script will extract a region of an aligment

from skbio.io import read as read_fasta
import argparse



def extract_region(seq_str, startp, endp):
	return seq_str[int(startp):int(endp)]

mikerobeson

#!/ur/bin/env python
# By: Mike Robeson & Se-ran Jun Nov 20, 2018
# I ran this code within the `qiime2-2018.11` environment.
# Simple concept code to prepare a Greengenes-like taxonomy for SILVA (v132). 
from skbio.tree import TreeNode
import re

allowed_ranks_list = [('domain','d__'), ('kingdom','k__'), ('phylum','p__'),
					  ('class','c__'), ('order','o__'), ('family','f__'),
					  ('genus','g__')]

mikerobeson

#!/usr/bin/env python
# Mike Robeson (GitHub: @mikerobeson)
# A quick hacked together script to allow the use of multiple cpus to run ITSx 
# (http://microbiology.se/software/itsx/) much faster. Code based on:
# https://medium.com/@thechriskiehl/parallelism-in-one-line-40e9b2b36148
# Needs PyCogent & ITSx installed.


from cogent.parse.fastq import MinimalFastqParser
from cogent.parse.fasta import MinimalFastaParser

mikerobeson

#!/usr/bin/env python

# There are times when the R1/R2 reads or merged reads fastq files become out of sync 
# with its respective index reads file (quality filtering, failed merges, etc...). This
# will cause the `split_libraries_fastq.py` script in QIIME to fail.
# This script will iterate through the index reads file and remove any indexes that do not
# have any corresponding read in the main reads file; making appropriate input for 
# `split_libraries_fastq.py`.
# I pulled this chunk of code out the `join_paired_ends.py` script I wrote for QIIME v1.8
# and later. Specifically, the code activated by the `-b` flag of `join_paired_ends.py`.