all_tt_count = sp_tools.term_types_all_papers(papersExpLO_dict) #takes a really long time
print "cPikleDump: save that all_tt_count for later"
print clock()
sys.stdout.flush()
sp_tools.cPickleDump(all_tt_count, "Uniprot-Bias/all_tt_countLO.pik")
print "go_terms_with_ec_per_paper: Create a dict that counts up how many times a specific (GO ID, GO Term Text, EvCode) tuple occurs for each paper"
print clock()
sys.stdout.flush()
go_ec_count = sp_tools.go_terms_with_ec_per_paper(papersExpLO_dict, top=top) # this takes a bit of time too
print "ev_codes_all_papers: Calculate the number of times a paper gives a certain experimental evidence code."
print clock()
sys.stdout.flush()
allEvCodes_dict = sp_tools.ev_codes_all_papers(papersExpLO_dict)
print "sort_papers_prots: Sort the dictionary papers_prots according to the number of proteins annotated by a particular paper (PMID)."
print clock()
sys.stdout.flush()
sortedProtsPerPaper_tuple = sp_tools.sort_papers_prots(papers_protsExp_dict)
print "print_paper_per_prots: print out the results of the the top papers per proteins. Final Ouptfile: allExpPaperLeavesOnlyInfoTop50.<date>.tsv"
print clock()
sys.stdout.flush()
sp_tools.print_paper_per_prots_go(papers_annots2_dict, all_tt_count, go_ec_count, allEvCodes_dict,
sortedProtsPerPaper_tuple, finalOutputFile, top=top)
print "all done"
print clock()
top = 50
papers_annots2_dict = sp_tools.top_papers_dict(papersExp_dict,
papers_protsExp_dict,
top=top)
print "really long time... (1)"
all_tt_count = sp_tools.term_types_all_papers(
papersExp_dict) #takes a really long time
print "...done"
go_ec_count = sp_tools.go_terms_with_ec_per_paper(
papersExp_dict, top=top) # this takes a bit of time too
allEvCodes_dict = sp_tools.ev_codes_all_papers(papersExp_dict)
sortedProtsPerPaper_tuple = sp_tools.sort_papers_prots(papers_protsExp_dict)
sp_tools.print_paper_per_prots_go(papers_annots2_dict,
all_tt_count,
go_ec_count,
allEvCodes_dict,
sortedProtsPerPaper_tuple,
"allExpPaperInfoTop50_lo.txt",
top=top)
# Not experimental
"""papersNoExp_handle = open('goa-pickles/goa_not_exp_papers.pik', 'rb')
papersNoExp_dict = cPickle.load(papersNoExp_handle)
papers_protsNoExp_handle = open('goa-pickles/goa_not_exp_papers_prots.pik', 'rb')
papers_protsNoExp_dict = cPickle.load(papers_protsNoExp_handle)
# going for the top fifty papers
top = 50
papers_annots2_dict_no = sp_tools.top_papers_dict(papersNoExp_dict, papers_protsNoExp_dict, top=top)
all_tt_count_no = sp_tools.term_types_all_papers(papersNoExp_dict) #takes a really long time
go_ec_count_no = sp_tools.go_terms_with_ec_per_paper(papersNoExp_dict, top=top) # this takes a bit of time too
#Experimental
papersExp_handle = open('goa_exp_papers_lo.pik', 'rb')
papersExp_dict = cPickle.load(papersExp_handle)
papers_protsExp_handle = open('goa_exp_papers_prots_lo.pik', 'rb')
papers_protsExp_dict = cPickle.load(papers_protsExp_handle)
# going for the top fifty papers
top = 50
papers_annots2_dict = sp_tools.top_papers_dict(papersExp_dict, papers_protsExp_dict, top=top)
print "really long time... (1)"
all_tt_count = sp_tools.term_types_all_papers(papersExp_dict) #takes a really long time
print "...done"
go_ec_count = sp_tools.go_terms_with_ec_per_paper(papersExp_dict, top=top) # this takes a bit of time too
allEvCodes_dict = sp_tools.ev_codes_all_papers(papersExp_dict)
sortedProtsPerPaper_tuple = sp_tools.sort_papers_prots(papers_protsExp_dict)
sp_tools.print_paper_per_prots_go(papers_annots2_dict, all_tt_count, go_ec_count, allEvCodes_dict,
sortedProtsPerPaper_tuple, "allExpPaperInfoTop50_lo.txt", top=top)
# Not experimental
"""papersNoExp_handle = open('goa-pickles/goa_not_exp_papers.pik', 'rb')
papersNoExp_dict = cPickle.load(papersNoExp_handle)
papers_protsNoExp_handle = open('goa-pickles/goa_not_exp_papers_prots.pik', 'rb')
papers_protsNoExp_dict = cPickle.load(papers_protsNoExp_handle)
# going for the top fifty papers
top = 50
papers_annots2_dict_no = sp_tools.top_papers_dict(papersNoExp_dict, papers_protsNoExp_dict, top=top)
all_tt_count_no = sp_tools.term_types_all_papers(papersNoExp_dict) #takes a really long time
go_ec_count_no = sp_tools.go_terms_with_ec_per_paper(papersNoExp_dict, top=top) # this takes a bit of time too
allEvCodes_dict_no = sp_tools.ev_codes_all_papers(papersNoExp_dict)
sortedProtsPerPaper_tuple_no = sp_tools.sort_papers_prots(papers_protsNoExp_dict)
sp_tools.print_paper_per_prots_go(papers_annots2_dict_no, all_tt_count_no, go_ec_count_no, allEvCodes_dict_no,
# count all the species annotations
all_taxonID_dict = sp_tools.count_all_annotations_taxonIDs(papersTaxExp_dict)
#top go codes
top = 500
ec_go_code_count = sp_tools.count_top_go_terms_per_ecode_all_entries(papersExp_dict, "sortedECGO.txt", top)
# going for the top fifty papers
top = 50
papers_annots2_dict = sp_tools.top_papers_dict(papersExp_dict, papers_protsExp_dict, top=top)
all_tt_count = sp_tools.term_types_all_papers(papersExp_dict) #takes a really long time
go_ec_count = sp_tools.go_terms_with_ec_per_paper(papersExp_dict, top=top) # this takes a bit of time too
allEvCodes_dict = sp_tools.ev_codes_all_papers(papersExp_dict)
sortedProtsPerPaper_tuple = sp_tools.sort_papers_prots(papers_protsExp_dict)
sp_tools.print_paper_per_prots_go(papers_annots2_dict, all_tt_count, go_ec_count, allEvCodes_dict,
sortedProtsPerPaper_tuple, "allExpPaperInfoTop50.txt", top=top)
# going for the top fifty papers
top = 50
papers_annots2_dict = sp_tools.top_papers_dict(papersExp_dict, papers_protsExp_dict, top=top)
all_tt_count = sp_tools.term_types_all_papers(papersExp_dict) #takes a really long time
go_ec_count = sp_tools.go_terms_with_ec_per_paper(papersExp_dict, top=top) # this takes a bit of time too
GO_EC_Count_collect_tuple = sp_tools.sort_go_ec_count(go_ec_count)
allEvCodes_dict = sp_tools.ev_codes_all_papers(papersExp_dict)
sortedProtsPerPaper_tuple = sp_tools.sort_papers_prots(papers_protsExp_dict)
sp_tools.print_paper_per_prots_go(papers_annots2_dict, all_tt_count, go_ec_count, allEvCodes_dict,
sortedProtsPerPaper_tuple, "allExpPaperInfoTop50.txt", top=top)
