daler

#!/usr/bin/python
usage = """
Ensures start/stop coords in a BED file are integers
and not in exponential notation (like 9.3e+07)

Usage:

    python fix_coords.py input.bed > fixed.bed
"""
import sys

daler

"""
Clicking the indicated point on the left-hand side causes the indicated point on the top right to
be highlighted.  Adding 0.1 to the x-value of the left-hand side one seems to alleviate this 
problem -- but not adding 0.01.
"""

import numpy as np
import matplotlib.pyplot as plt

x = np.array([-0.58178965, 

daler

"""
PWMSearch

Searches through a fasta sequence for the relevant Position Weight Matrices 
from the Jaspar Database.

"""
from __future__ import division

from optparse import OptionParser

daler

#!/usr/bin/python

# GPLv3 license
# Copyright 2011 Ryan Dale, all rights reserved
# dalerr@niddk.nih.gov

import HTSeq
import argparse
import sys
import time

daler

sudo apt-get install libtool
git clone git://dnaa.git.sourceforge.net/gitroot/dnaa/dnaa dnaa-git
cd dnaa-git
# bfast required. see above gist
cp -r ../bfast-git ./bfast
# samtools require. see above gist.
cp -r ../samtools-svn/ ./samtools

sh autogen.sh && ./configure && make && sudo make install

daler

#!/usr/bin/python

"""
- Submit example data to REVIGO server (http://revigo.irb.hr/)
- Download and run R script for creating the treemap
- Download and run R script for creating the scatterplot

Creates files:
    treemap.R, treemap.Rout, revigo_treemap.pdf
    scatter.R, scatter.Rout, revigo_scatter.pdf

daler

import sys
from gffutils.helpers import DefaultOrderedDict
from collections import defaultdict
from collections import OrderedDict
import random

kind = sys.argv[1]

nlines = 200000
nkeys = 5

daler

import numpy as np
import logging
logging.basicConfig(format='%(message)s', level=logging.DEBUG)


class Merger(object):
    def __init__(self, bin_size=5, diff_thresh=0.3,
                 start_thresh=5., extend_thresh=3.):
        """
        Implements the merging alrogithm described in [1] for a NumPy array.

daler

# From http://www.biostars.org/p/83800/:

# "What I want to do is to plot reads of my histone marks (in bam file)
# around TSS with CpG and TSS without CpG (Essentially a coverage profile)."
#
#
# To install metaseq and dependencies, see:
#
#
#   https://pythonhosted.org/metaseq/install.html

daler

import gffutils
import datetime

# Annotations from:
# ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_19/gencode.v19.annotation.gtf.gz

v19gff = 'gencode.v19.annotation.gtf'
v19db_filename = v19gff + '.db'
gene_transcript = set(('gene', 'transcript'))