cplaisier

# Load counts
d0 = read.csv('gexp_counts.csv',header=T,row.names=1)
d0 = d0[which(apply(d0,1,sum)!=0),]
library(DESeq2)
conds = data.frame(subset=factor(c(rep('Cntl_CD44Low',4), rep('Cntl_Ag85B_Plus_PD1_Plus',4), rep('Cntl_ESAT6_Plus_PD1_Plus',4), rep('Stim_Ag85B_Plus_PD1_Plus',4), rep('Stim_ESAT6_Plus_PD1_Plus',4))))
rownames(conds) = colnames(d0)

# Make a map of Entrez IDs to UCSC transcript IDs
d1 = read.csv('entrez2ucsc.csv',header=F)
entrez2ucsc = list()

cplaisier

[General]
num_iterations = 2000
num_clusters = 133
normalize_ratios = False
num_cores = 6
checkpoint_interval = 100
stats_frequency = 50
result_frequency = 50

[SetEnrichment]

cplaisier

from itertools import imap
import operator
import logicFuncs as lf

def mean_squared_error(r1, p1):
    #assert len(r1) == len(p1)
    return sum([(float(p1[i])-float(r1[i]))**2 for i in range(len(r1))])/float(len(r1))

def hammingDist(str1, str2):
    assert len(str1) == len(str2)

cplaisier

# Loading JSON file
# https://www.safaribooksonline.com/library/view/python-cookbook-3rd/9781449357337/ch06s02.html
# Example:
# import json
#
# # Reading data back
# with open('data.json', 'r') as f:
#      data = json.load(f)

import json

cplaisier

motifName2entrezId = {}
entrezId2motifName = {}
# humanTFs_All.csv with columns separated by commas - Motif Name,Gene Symbol,Entrez ID
with open('id_conversion/humanTFs_All.csv','r') as inFile:
    header = inFile.readline().strip().split(',') # Capture header, get rid of white space ".strip()", and split by commas ".split(',')"
    while 1:
        inLine = inFile.readline()
        #Breaks out of the while loop when we hit the end of the file
        if not inLine:
            break

cplaisier

# -*- coding: utf-8 -*-
"""
Created on Mon Mar 12 18:16:24 2018

@author: Fuzzy
"""

import json
with open('tfbsDb_plus_and_minus_5000_entrez.json', 'r') as f:
    data = json.load(f)

cplaisier

# -*- coding: utf-8 -*-
"""
Created on Mon Mar 12 18:16:24 2018

@author: Fuzzy
"""

import json
with open('tfbsDb_plus_and_minus_5000_entrez.json', 'r') as f:
    data = json.load(f)

cplaisier

import GEOparse
import pandas as pd
import matplotlib.pyplot as plt
import numpy
from matplotlib.backends.backend_pdf import PdfPages

#gseNums = ['GSE14860']
#gseNums = ['GSE49278', 'GSE19750', 'GSE10846']
gseNums = ['GSE19417', 'GSE49278', 'GSE19750', 'GSE10846', 'GSE39582', 'GSE35158', 'GSE19422', 'GSE19987', 'GSE32894', 'GSE35158', 'GSE27155', 'GSE33630', 'GSE56303', 'GSE29695', 'GSE10141', 'GSE9843', 'GSE25097', 'GSE32225', 'GSE26566', 'GSE65858', 'GSE39366', 'GSE22138', 'GSE46517', 'GSE71729', 'GSE8607', 'GSE4573', 'GSE29354', 'GSE71118', 'GSE19949', 'GSE15641', 'GSE26253', 'GSE15460', 'GSE21034', 'GSE9891', 'GSE32062', 'GSE72094', 'GSE26939', 'GSE29174', 'GSE31448', 'GSE45725', 'GSE40435', 'GSE14860']

cplaisier

# -*- coding: utf-8 -*-
"""
Created on Sat Mar 24 12:19:38 2018

@author: Fuzzy
"""

import json
with open('tfbsDb_plus_and_minus_5000_entrez.json', 'r') as f:
    data = json.load(f)

cplaisier

# Load libraries
library(GEOquery)
library(genefilter)

# Set working directory
setwd('C:/Users/cplaisie/Dropbox (ASU)/ASU/Students/Omar')

# Load up data
gset <- getGEO(filename="data/GSE26253_series_matrix.txt.gz", GSEMatrix=TRUE, AnnotGPL=T)
pData(gset)