nickloman

## rarify SNP discovery:

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

## output:
## NumberIsolates   BootStrapNumber  Variants  NoCalls

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

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

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

# 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

--- 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

--- lib/qiime/assign_taxonomy.py        2011-09-11 20:53:06.000000000 +0100
+++ ../16s/Qiime-1.2.1/build/lib/qiime/assign_taxonomy.py       2011-02-22 21:00:06.000000000 +0000
@@ -89,7 +89,7 @@
         """ Initialize the object
         """
         _params = {
-            'Min percent identity': 90,
+            'Min percent identity': 0.90,
             'Max E value': 1e-30,
             'Application': 'blastn/megablast'

nickloman

# requires biopython
# run like:
#   genbank_to_tbl.py "my organism name" "my strain ID" "ncbi project id" < my_sequence.gbk
#   writes seq.fsa, seq.tbl as output

import sys
from copy import copy
from Bio import SeqIO

def find_gene_entry(features, locus_tag):

nickloman

import os
import sys
import glob

TRUNCATE_LENGTH = int(sys.argv[2])

def system(cmd):
    print >>sys.stderr, cmd
    os.system(cmd)

nickloman

import os
import sys
import glob

def system(cmd):
    print >>sys.stderr, cmd
    os.system(cmd)

# dodir_pyro.py directory