details: http://www.bx.psu.edu/hg/galaxy/rev/90d04fcbcdf4 changeset: 1709:90d04fcbcdf4 user: guru date: Thu Jan 15 13:10:04 2009 -0500 description: More changes to mutability tool. 2 file(s) affected in this change: tools/regVariation/microsats_mutability.py tools/regVariation/microsats_mutability.xml diffs (99 lines): diff -r 78c2f403cb43 -r 90d04fcbcdf4 tools/regVariation/microsats_mutability.py --- a/tools/regVariation/microsats_mutability.py Thu Jan 15 10:49:01 2009 -0500 +++ b/tools/regVariation/microsats_mutability.py Thu Jan 15 13:10:04 2009 -0500 @@ -128,11 +128,13 @@ uniq_s_elems_2 = get_binned_lists(uniq_s_elems_2,s_bin_size) for pitem1 in uniq_elems_1: - repeats1 = [] - repeats2 = [] + #repeats1 = [] + #repeats2 = [] thresholds = [] if s_group_cols[0] != -1: #Sub-group by feature is not None for sitem1 in uniq_s_elems_1: + repeats1 = [] + repeats2 = [] if type(sitem1) == type(''): sitem1 = sitem1.strip() for bline in blk_lines: @@ -223,11 +225,13 @@ count1[str(pitem1)]=sum(repeats2) for pitem2 in uniq_elems_2: - repeats1 = [] - repeats2 = [] + #repeats1 = [] + #repeats2 = [] thresholds = [] if s_group_cols[0] != -1: #Sub-group by feature is not None for sitem2 in uniq_s_elems_2: + repeats1 = [] + repeats2 = [] if type(sitem2)==type(''): sitem2 = sitem2.strip() for bline in blk_lines: @@ -349,11 +353,10 @@ count = count1[key] mut = "%.2e" %(mut/num_generations) if region == 'align': - print >>fout, str(blk) + '\t'+seq1 + '\t' + start1+ '\t'+end1+ '\t'+seq2 + '\t'+start2+ '\t'+end2+ '\t'+key.strip()+ '\t'+str(mut) + '\t'+ str(count) + print >>fout, str(blk) + '\t'+seq1 + '\t' + seq2 + '\t' +key.strip()+ '\t'+str(mut) + '\t'+ str(count) elif region == 'win': fout.write("%s\t%s\t%s\t%s\n" %(blk,key.strip(),mut,count)) fout.flush() - #print >>fout, blk + '\t'+key.strip()+ '\t'+str(mut)+ '\t'+ str(count) #catch any remaining repeats, for instance if the orthologous position contained different repeat units for remaining_key in mut2.keys(): @@ -361,7 +364,7 @@ mut = "%.2e" %(mut/num_generations) count = count2[remaining_key] if region == 'align': - print >>fout, str(blk) + '\t'+seq1 + '\t' + start1+ '\t'+end1+ '\t'+seq2 + '\t'+start2+ '\t'+end2+ '\t'+remaining_key.strip()+ '\t'+str(mut)+ '\t'+ str(count) + print >>fout, str(blk) + '\t'+seq1 + '\t'+seq2 + '\t'+remaining_key.strip()+ '\t'+str(mut)+ '\t'+ str(count) elif region == 'win': fout.write("%s\t%s\t%s\t%s\n" %(blk,remaining_key.strip(),mut,count)) fout.flush() @@ -420,17 +423,9 @@ fix_strand = True) msatTree = quicksect.IntervalTree() for item in msats: - #print >>sys.stderr, item if type( item ) is GenomicInterval: msatTree.insert( item, msats.linenum, item.fields ) - """ - result = [] - msatTree.traverse(lambda node: result.append( node )) - for n in result: - print >>sys.stderr,n.other - print >>sys.stderr,msatTree.chroms - #sys.exit() - """ + for iline in fint: try: iline = iline.rstrip('\r\n') @@ -460,7 +455,7 @@ print "Skipped %d intervals as invalid." %(skipped) elif region == 'align': if s_group_cols[0] != -1: - print >>fout, "#Window\tSpecies_1\tWindow_Start\tWindow_End\tSpecies_2\tGroupby_Feature\tSubGroupby_Feature\tMutability\tCount" + print >>fout, "#Window\tSpecies_1\tSpecies_2\tGroupby_Feature\tSubGroupby_Feature\tMutability\tCount" else: print >>fout, "#Window\tSpecies_1\tWindow_Start\tWindow_End\tSpecies_2\tGroupby_Feature\tMutability\tCount" prev_bnum = -1 diff -r 78c2f403cb43 -r 90d04fcbcdf4 tools/regVariation/microsats_mutability.xml --- a/tools/regVariation/microsats_mutability.xml Thu Jan 15 10:49:01 2009 -0500 +++ b/tools/regVariation/microsats_mutability.xml Thu Jan 15 13:10:04 2009 -0500 @@ -106,6 +106,10 @@ This tool computes microsatellite mutability for the orthologous microsatellites fetched from 'Extract Orthologous Microsatellites from pair-wise alignments' tool. +Mutability is computed according to the method described in the following paper: + +*Webster et al., Microsatellite evolution inferred from human-chimpanzee genomic sequence alignments, Proc Natl Acad Sci 2002 June 25; 99(13): 8748-8753* + ----- .. class:: warningmark