nickloman

--- lib/qiime/pycogent_backports/uclust.py   2011-06-07 21:34:23.000000000 +0100
+++ ../16s/Qiime-1.2.1/build/lib/qiime/pycogent_backports/uclust.py     2011-02-22 21:00:06.000000000 +0000
@@ -107,10 +107,6 @@
         '--optimal':FlagParameter('--',Name='optimal'),

         '--stable_sort':FlagParameter('--',Name='stable_sort'),
-
-        '--gapopen':ValuedParameter('--',Name='gapopen',Delimiter=' '),
-
-        '--gapext':ValuedParameter('--',Name='gapext',Delimiter=' '),

nickloman

# a little script to run BLASTN (BLAST+) and generate an MLST profile from a database defined in 'bugs'
# The alleles and profile files should be located in the directory BLAST_DIRECTORY/<bugname>/
# requires Biopython
# use like: 
#  process('Acinetobacter_baumannii', open('contigs.fa'))

from Bio import SeqIO
from Bio.Blast import NCBIXML
from StringIO import StringIO
import sys

nickloman

rsync -av rsync://ftp.ncbi.nlm.nih.gov/genomes/Bacteria --include "*/" --include "Bacteria/Escherichia*/*.fna" --exclude=* .

# bonus script - concatenate chromosomes and plasmids into single fasta file, make sure the files don't already exist

find . -mindepth 1 -type d | xargs -L 1 -I '{}' find {} -name "*.fna" | while read i ; do cat "$i" >> `dirname "$i"`.fasta ; done

nickloman

from Bio import SeqIO
import sys

rec = SeqIO.parse(open(sys.argv[1]), "fasta").next()
SeqIO.write(rec[0:int(sys.argv[2])], sys.stdout, "fasta")

nickloman

from Bio import SeqIO
import sys
import random

rec = SeqIO.parse(open(sys.argv[1]), "fasta").next()
insert_size = int(sys.argv[2])
rec_length = len(rec)
read_length = int(sys.argv[3])
number_seqs = int(sys.argv[4])
prefix = sys.argv[5]

nickloman

## rarify SNP discovery:

## n isolates from 1 .. total isolates
## x bootstraps (pick randomly without replacement)

## output:
## NumberIsolates   BootStrapNumber  Variants  NoCalls

nickloman

#Usage:
#blastall -p blastn -d db -i query -m 8 | python pullblast.py db.fasta

import sys
from Bio import SeqIO

records = SeqIO.to_dict(SeqIO.parse(open(sys.argv[1]), "fasta"))

for ln in sys.stdin:
        cols = ln.rstrip().split("\t")

nickloman

import sys
from collections import defaultdict
from itertools import izip_longest

def grouper(n, iterable, fillvalue=None):
    args = [iter(iterable)] * n
    return izip_longest(fillvalue=fillvalue, *args)

contigs = defaultdict(dict)

nickloman

require 'formula'

class Hdf5 < Formula
  homepage 'http://www.hdfgroup.org/HDF5'
  url 'http://www.hdfgroup.org/ftp/HDF5/releases/hdf5-1.8.12/src/hdf5-1.8.12.tar.bz2'
  sha1 '8414ca0e6ff7d08e423955960d641ec5f309a55f'
  version '1.8.12'

  # TODO - warn that these options conflict
  option :universal

nickloman

import h5py
from Bio import SeqIO
from StringIO import StringIO
import sys

keys = {'template' : '/Analyses/Basecall_2D_000/BaseCalled_template/Fastq',
        'complement' : '/Analyses/Basecall_2D_000/BaseCalled_complement/Fastq',
        'twodirections' : '/Analyses/Basecall_2D_000/BaseCalled_2D/Fastq'}

for fn in sys.argv[1:]: