fileNames = ['/Users/biggus/Documents/James/Data/ReClustering/PrelimData_Grant_Feb09/Clus2_kmerSearch.6-8mers.FDR_lessThan0.01.txt',]
coRegSeqs = '/Users/biggus/Documents/James/Data/ReClustering/kmedsPear33Clus50x_2/Clus2_247genes.genes.txt'
allPromoters = promoterSeqPaths.Aa_2000bpUp_hardMasked
MDfileType = 'list'
dfltFactor = 0.75
coRegSeqs = map(lambda l: l.strip(), open(coRegSeqs, 'rU').readlines())
motifs = []
for f in fileNames:
motifs.append([f.split('/')[-1],loadMotifsFromOutFile(f, MDfileType)])
probSet = ProbeSet(allPromoters)
# get and print motif and pVal(s)
out = '#outFile\tMotif\tHyperGeoPval (%s)\tfrac (%s)\tBestHG (pval)\tfrac (bestHG_ScoreThresh)\tBestHG (scoreThresh)\tbinoPval (%s)\tbinoPval (bestHG_scoreThresh)' \
% (dfltFactor,dfltFactor,dfltFactor)
print out
out = out+'\n'
for m in motifs:
for i in m[1]:
bestE = probSet.best_p_value(m[1],coRegSeqs)
temp ='%s\t%s\t%.3e\t%.3f\t%.3e\t%.3f\t%.3f\t%.3e\t%.3e' % (m[0],
m[1],
probSet.Enrichment(m[1],coRegSeqs,factor=dfltFactor),
from gusPyCode.MDAP_proj.MDAP_defs import loadMotifsFromOutFile
from TAMO import MotifTools
mdOutFiles = ['/Users/biggus/Documents/James/Data/ReClustering/PrelimData_Grant_Feb09/RandSplitFastas/AceResults/Clus2_247gene_0.8_Apr16_14-46-33.ace.1.txt',
'/Users/biggus/Documents/James/Data/ReClustering/PrelimData_Grant_Feb09/RandSplitFastas/AceResults/Clus2_247gene_0.8_Apr16_14-46-33.ace.2.txt',
'/Users/biggus/Documents/James/Data/ReClustering/PrelimData_Grant_Feb09/RandSplitFastas/AceResults/Clus2_247gene_0.8_Apr16_14-46-33.ace.3.txt']
for mdFile in mdOutFiles:
motifs = loadMotifsFromOutFile(mdFile,'list') # ['Meme', 'AlignAce', 'MDscan', 'Weeder','list']
MotifTools.save_motifs(motifs,mdFile+'.tmo')
print 'Done.'
