-
-
Save cplaisier/3f448cdec747b100ed9339351c76e780 to your computer and use it in GitHub Desktop.
input network list, dictionary, hops and output full .sif and sub .sif
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # -*- 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) | |
| #number of hops input | |
| hops = 2 | |
| #starting point for sub network | |
| sPoint = '430' | |
| # Starting ID list | |
| tfStartId = ['430', '1052', '1053', '1385', '84699', '9586', '1871'] | |
| #, '1874', '144455', '79733', '1960', '1997', '2002', '2004', '80712', '2114', '2115', '2120', '51513', '2551', '2623', '2624', '2625', '9421', '3232', '10320', '3659', '3662', '3670', '91464', '3726', '10661', '11278', '128209', '10365', '9314', '1316', '51176', '9935', '23269', '4602', '4774', '4790', '7025', '9480', '5468', '5914', '5916', '3516', '5971', '864', '6257', '4093', '6659', '6660', '6662', '25803', '347853', '30009', '9496', '6929', '6925', '8463', '7022', '29842', '10155', '6935', '132625', '23051', '85416', '7707', '7764', '23528', '201516'] | |
| #tfStartId = [1053] | |
| motif2Id = {} | |
| id2Motif = {} | |
| with open('id_conversion/humanTFs_All.CSV','r') as inFile: | |
| header = inFile.readline().strip().split(',') #get rid of header, strip gets rid of whitespace, split each in element by comma | |
| while 1: | |
| inLine = inFile.readline() | |
| if not inLine: | |
| break | |
| split = inLine.strip().split(',')#create an array with element 0 as key, element 2 as ID | |
| motif2Id[split[0]] = split[2]#store element 0 as key and element 2 as the string | |
| #creating Id to motif, mapping one motif to many Ids, create list inside dictonary | |
| if not split[2] in id2Motif: | |
| id2Motif[split[2]] = [] | |
| id2Motif[split[2]].append(split[0]) | |
| #for translation | |
| name2Entrez = {} | |
| with open('gene2entrezId.CSV','r') as inFile: | |
| while 1: | |
| inLine = inFile.readline() | |
| if not inLine: | |
| break | |
| split = inLine.strip().split(',') | |
| name2Entrez[split[1]] = split[0] | |
| #import in families data | |
| family2Id = {} | |
| id2Family = {} | |
| with open('id_conversion/tfFamilies.CSV','r') as inFile: | |
| header = inFile.readline() | |
| while 1: | |
| inLine = inFile.readline() | |
| if not inLine: | |
| break | |
| split = inLine.split(',') | |
| split[2] = split[2].replace(' ',',').strip().split(',') | |
| family2Id[split[0]] = split[2] | |
| for splitId in split[2]: | |
| id2Family[splitId] = split[0] | |
| # Create a TFreg -> TFtarg dictionary | |
| # TFreg -> TFtarg | |
| # Type I Family Expansion = expand to all possible TFtargs via all motifs from family members | |
| # Type II Family Expansion = If no motif for TFreg then expand to family members | |
| geneNetwork = {} | |
| famExpType = 2 | |
| for TFreg in tfStartId: | |
| motifs = [] | |
| if TFreg in id2Motif: | |
| motifs += id2Motif[TFreg] | |
| if TFreg in id2Family: | |
| if famExpType==1 or (famExpType==2 and len(motifs)==0): | |
| for TFregExp in family2Id[id2Family[TFreg]]: | |
| if (not TFregExp==TFreg) and TFregExp in id2Motif: | |
| motifs += id2Motif[TFregExp] | |
| # Iterate through motifs | |
| for motif in motifs: | |
| if motif in data: | |
| for geneTarg in data[motif]: | |
| if geneTarg in tfStartId: | |
| if not TFreg in geneNetwork: | |
| geneNetwork[TFreg] = [] | |
| if not geneTarg in geneNetwork[TFreg]: | |
| geneNetwork[TFreg].append(geneTarg) | |
| """ | |
| #create Sub (Broke) | |
| incList = {} | |
| incList[0] = [sPoint] | |
| subList = [] | |
| x = 0 | |
| while x < hops: | |
| for inc in geneNetwork: | |
| if inc in incList: | |
| print 'out' | |
| subList.append(inc) | |
| for gene in geneNetwork[inc]: | |
| if not (x+1) in incList: | |
| incList[x+1] = [] | |
| incList[x+1].append(gene) | |
| x = x + 1 | |
| #create .sif file | |
| interact = 'r2t' | |
| writeMe = [] | |
| for key in geneNetwork: | |
| for gene in geneNetwork[key]: | |
| if key in name2Entrez: | |
| key1 = name2Entrez[key] | |
| else: | |
| key1 = key | |
| if gene in name2Entrez: | |
| gene1 = name2Entrez[gene] | |
| else: | |
| gene1 = gene | |
| writeMe.append(key1+'\t'+interact+'\t'+gene1) | |
| with open('gene2GeneNetwork.sif','w') as outFile: | |
| outFile.write('\n'.join(writeMe)) | |
| #write subNetwork .sif file | |
| writeSub = [] | |
| for key in geneNetwork: | |
| for gene in geneNetwork[key]: | |
| if key in name2Entrez: | |
| key1 = name2Entrez[key] | |
| else: | |
| key1 = key | |
| if gene in name2Entrez: | |
| gene1 = name2Entrez[gene] | |
| else: | |
| gene1 = gene | |
| writeMe.append(key1+'\t'+interact+'\t'+gene1) | |
| with open('gene2SubGeneNetwork.sif','w') as outFile: | |
| outFile.write('\n'.join(writeSub)) | |
| """ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment