cplaisier

goTerms = {}
inFile = open('gene_ontology.obo','r')
while 1:
    line = inFile.readline()
    if not line:
        break
    if line.strip()=='[Term]':
        id1 = inFile.readline().strip().split('id: ')[1]
        name = inFile.readline().strip().split('name: ')[1]
        namespace = inFile.readline().strip().split('namespace: ')[1]

cplaisier

library(topGO)

# Read in GO mappings to gene ids
# <gene>\t<GOID>,<GOID>,...
vng2GO <- readMappings(file='vng2GO.map')

# Load up cluster or gene set identifiers
geneSets <- ## Depends on your analysis, list of vectors of gene ids

################

cplaisier

#################################################################
# @Program: FIRM.py                                             #
# @Version: 1                                                   #
# @Author: Christopher L Plaisier, PhD                          #
# @Sponsored by:                                                #
# Nitin Baliga, ISB                                             #
# Institute for Systems Biology                                 #
# 401 Terry Ave North                                           #
# Seattle, Washington  98109-5234                               #
# (216) 732-2139                                                #

cplaisier

import cPickle, os, re, math
from pssm import pssm
from copy import deepcopy
from multiprocessing import Pool, cpu_count, Manager
from subprocess import *

# Make the files for a TomTom run
def makeQueryFile(nucFreqs, queryPssms, num, strands='+ -'):
    # Header crap
    memeHeader = ''

cplaisier

import glob

# Get a list of the '.clone' files in the 
files = glob.glob('*.clone')

# Read in expression data and put it into a dictionary
matrixDictionary = {}
conditions = []
for file in files:
    condition = file.split('.')[0]

cplaisier

from subprocess import *
from shutil import move
import os

# Read in manifest of samples to process
samples = []
inFile = open('manifest.csv','r')
while 1:
    line = inFile.readline()
    if not line:

cplaisier

#################################################################
# @Program: tomtom.py                                           #
# @Version: 1                                                   #
# @Author: Chris Plaisier                                       #
# @Sponsored by:                                                #
# Nitin Baliga, ISB                                             #
# Institute for Systems Biology                                 #
# 1441 North 34th Street                                        #
# Seattle, Washington  98103-8904                               #
# (216) 732-2139                                                #

cplaisier

# Read in clusters of biclusters
clusters = {}
inFile = open('clustersOfBiclusters_VALL.csv','r')
inFile.readline() # Get rid of header
while 1:
    line = inFile.readline()
    if not line:
        break
    splitUp = line.strip().split(',')
    if not splitUp[1] in clusters:

cplaisier

from subprocess import *

def phyper(q, m, n, k):
    # Get an array of values to run
    rProc = Popen('R --no-save --slave', shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE)
    runMe = []
    for i in range(len(q)):
        runMe.append('phyper('+str(q[i])+','+str(m[i])+','+str(n[i])+','+str(k[i])+',lower.tail=F)')
    runMe = '\n'.join(runMe)+'\n'
    out = rProc.communicate(runMe)

cplaisier

entrezIds = {}
inFile = open('mart_export.txt','r')
inFile.readline() # Get rid of header
while 1:
    line = inFile.readline()
    if not line:
        break
    splitUp = line.strip().split(',')
    if not splitUp[3]=='':
        if not splitUp[3] in entrezIds: