From d924bc5842d2813aad8359b9cb614c2a87df1ee9 Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Mon, 9 Mar 2015 14:37:04 +0300 Subject: plink: missing values in bim --- wqflask/wqflask/my_pylmm/pyLMM/convertlmm.py | 27 +++++++++++++++++++-------- wqflask/wqflask/my_pylmm/pyLMM/plink.py | 2 ++ 2 files changed, 21 insertions(+), 8 deletions(-) (limited to 'wqflask') diff --git a/wqflask/wqflask/my_pylmm/pyLMM/convertlmm.py b/wqflask/wqflask/my_pylmm/pyLMM/convertlmm.py index 173bae2e..d04f9b94 100644 --- a/wqflask/wqflask/my_pylmm/pyLMM/convertlmm.py +++ b/wqflask/wqflask/my_pylmm/pyLMM/convertlmm.py @@ -136,19 +136,30 @@ if options.pheno: msg(str(count)+" pheno lines written") if options.geno: + msg("Converting geno "+options.geno+'.bed') if not options.plink: raise Exception("Use --plink switch") if not num_inds: raise Exception("Can not figure out the number of individuals, use --pheno or --kinship") - # msg("Converting geno "+options.geno) - - snps = plink.readbim(options.geno+'.bim') - msg("Converting geno "+options.geno+'.bed') - - # def out(i,x): - # print i,x + num_snps = plink.readbim(options.geno+'.bim') + writer = None + if options.prefix: + writer = open(options.prefix+".geno","w") + wrln("# Genotype format version 1.0") + wrln("# Individuals = "+str(num_inds)) + wrln("# Phenotypes = "+str(len(num_snps))) + + def out(i,x): + # print(i,x) + pass - snps = plink.readbed(options.geno+'.bed',num_inds, lambda i,x: print(i,x)) + snps = plink.readbed(options.geno+'.bed',num_inds, out) + # for i in range(num_snps): + # wr("\t"+str(i+1)) + # wr("\n") + # for i in range(count): + # wr("\t".join(phenos[i])) + # wr("\n") msg(str(count)+" geno lines written (with "+str(snps)+" snps)") msg("Converting done") diff --git a/wqflask/wqflask/my_pylmm/pyLMM/plink.py b/wqflask/wqflask/my_pylmm/pyLMM/plink.py index 75d51c3b..4ad2c5f7 100644 --- a/wqflask/wqflask/my_pylmm/pyLMM/plink.py +++ b/wqflask/wqflask/my_pylmm/pyLMM/plink.py @@ -47,6 +47,8 @@ def readbim(fn): list = line.split() if len([True for e in list if e == 'nan']) == 0: res.append( (list[0],list[1],int(list[2]),int(list[3]),int(list[4]),int(list[5])) ) + else: + res.append( (list[0],list[1],list[2],float('nan'),float('nan'),float('nan')) ) return res # .bed (PLINK binary biallelic genotype table) -- cgit v1.2.3