Mercurial > repos > jjohnson > column_join
changeset 0:6bb6c0a30c67 draft default tip
Uploaded
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/column_join.py Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,279 @@ +#!/usr/bin/env python + +""" +This tool takes a tab-delimited text file as input and creates filters on columns based on certain properties. The tool will skip over invalid lines within the file, informing the user about the number of lines skipped. + +usage: %prog -o output -1 input1 -2 input2 -c column1[,column2[,column3[,...]]] -g hinge1[,hinge2[,hinge3[,...]]] -f <fill_options_file> [other_input1 [other_input2 [other_input3 ...]]] + -o, output=0: the output pileup + -1, input1=1: the pileup file to start with + -2, input2=2: the second pileup file to join + -g, hinge=h: the columns to be used for matching + -c, columns=c: the columns that should appear in the output + -f, fill_options_file=f: the file specifying the fill value to use + other_inputs: the other input files to join +""" + +import optparse, os, re, struct, sys, tempfile +from galaxy.util.bunch import Bunch +from galaxy.util import stringify_dictionary_keys +import json + +def stop_err( msg ): + sys.stderr.write( msg ) + sys.exit() + +def split_nums( text ): + """ + Splits a string into pieces of numbers and non-numbers, like 'abc23B3' --> [ 'abc', 23, 'B', 3 ] + """ + split_t = [] + c = '' + n = '' + for ch in text: + try: + v = int( ch ) + n += ch + if c: + split_t.append( ''.join( c ) ) + c = '' + except ValueError: + c += ch + if n: + split_t.append( int( ''.join( n ) ) ) + n = '' + if c: + split_t.append( ''.join( c ) ) + if n: + split_t.append( int( ''.join( n ) ) ) + return split_t + +def hinge_compare( hinge1, hinge2 ): + """ + Compares items like 'chr10' and 'chrM' or 'scaffold2' and scaffold10' so that + first part handled as text but last part as number + """ + split_hinge1 = hinge1.split( '\t' ) + split_hinge2 = hinge2.split( '\t' ) + # quick check if either hinge is empty + if not ''.join( split_hinge2 ): + if ''.join( split_hinge1 ): + return 1 + elif not ''.join( split_hinge1 ): + return 0 + else: + if not ''.join( split_hinge1 ): + return -1 + # go through all parts of the hinges and compare + for i, sh1 in enumerate( split_hinge1 ): + # if these hinge segments are the same, just move on to the next ones + if sh1 == split_hinge2[ i ]: + continue + # check all parts of each hinge + h1 = split_nums( sh1 ) + h2 = split_nums( split_hinge2[ i ] ) + for j, h in enumerate( h1 ): + # if second hinge has no more parts, first is considered larger + if j > 0 and len( h2 ) <= j: + return 1 + # if these two parts are the same, move on to next + if h == h2[ j ]: + continue + # do actual comparison, depending on whether letter or number + if type( h ) == int: + if type( h2[ j ] ) == int: + if h > h2[ j ]: + return 1 + elif h < h2[ j ]: + return -1 + # numbers are less than letters + elif type( h2[ j ] ) == str: + return -1 + elif type( h ) == str: + if type( h2[ j ] ) == str: + if h > h2[ j ]: + return 1 + elif h < h2[ j ]: + return -1 + # numbers are less than letters + elif type( h2[ j ] ) == int: + return 1 + # if all else has failed, just do basic string comparison + if hinge1 > hinge2: + return 1 + elif hinge1 == hinge2: + return 0 + elif hinge1 < hinge2: + return -1 + +def hinge_sort( infile, outfile, hinge ): + """Given input file name, sorts logically (text vs. numeric) into provided output file name.""" + hinge_locs = {} + bad_lines = [] + fin = open( infile, 'rb' ) + line = fin.readline() + while line.strip(): + try: + hinge_parts = line.split( '\t' )[ :hinge ] + try: + hinge_locs[ '\t'.join( hinge_parts ) ].append( fin.tell() - len( line ) ) + except KeyError: + hinge_locs[ '\t'.join( hinge_parts ) ] = [ fin.tell() - len( line ) ] + except ValueError: + bad_line.append( line ) + line = fin.readline() + fin.close() + fin = open( infile, 'rb' ) + fout = open( outfile, 'wb' ) + hinge_locs_sorted = hinge_locs.keys() + hinge_locs_sorted.sort( hinge_compare ) + for hinge_loc in hinge_locs_sorted: + locs = hinge_locs[ hinge_loc ] + for loc in locs: + fin.seek( loc ) + fout.write( fin.readline() ) + fout.close() + fin.close() + +def __main__(): + parser = optparse.OptionParser() + parser.add_option( '-o', '--output', dest='output', help='The name of the output file' ) + parser.add_option( '-1', '--input1', dest='input1', help='The name of the first input file' ) + parser.add_option( '-2', '--input2', dest='input2', help='The name of the second input file' ) + parser.add_option( '-g', '--hinge', dest='hinge', help='The "hinge" to use (the value to compare)' ) + parser.add_option( '-c', '--columns', dest='columns', help='The columns to include in the output file' ) + parser.add_option( '-f', '--fill_options_file', dest='fill_options_file', default=None, help='The file specifying the fill value to use' ) + (options, args) = parser.parse_args() + hinge = int( options.hinge ) + cols = [ int( c ) for c in str( options.columns ).split( ',' ) if int( c ) > hinge ] + inputs = [ options.input1, options.input2 ] + if options.fill_options_file == 'None': + inputs.extend( args ) + elif len( args ) > 0: + inputs.extend( args ) + fill_options = None + if options.fill_options_file != 'None' and options.fill_options_file is not None: + try: + fill_options = Bunch( **stringify_dictionary_keys( json.load( open( options.fill_options_file ) ) ) ) + except Exception, e: + print 'Warning: Ignoring fill options due to json error (%s).' % e + if fill_options is None: + fill_options = Bunch() + if 'file1_columns' not in fill_options: + fill_options.file1_columns = None + if fill_options and fill_options.file1_columns: + fill_empty = {} + for col in cols: + fill_empty[ col ] = fill_options.file1_columns[ col - 1 ] + else: + fill_empty = None + assert len( cols ) > 0, 'You need to select at least one column in addition to the hinge' + delimiter = '\t' + # make sure all files are sorted in same way, ascending + tmp_input_files = [] + input_files = inputs[:] + for in_file in input_files: + tmp_file = tempfile.NamedTemporaryFile() + tmp_file_name = tmp_file.name + tmp_file.close() + hinge_sort( in_file, tmp_file_name, hinge ) + tmp_file = open( tmp_file_name, 'rb' ) + tmp_input_files.append( tmp_file ) + # cycle through files, getting smallest line of all files one at a time + # also have to keep track of vertical position of extra columns + fout = file( options.output, 'w' ) + old_current = '' + first_line = True + current_lines = [ f.readline().rstrip( '\r\n' ) for f in tmp_input_files ] + last_lines = ''.join( current_lines ) + last_loc = -1 + while last_lines: + # get the "minimum" hinge, which should come first, and the file location in list + hinges = [ delimiter.join( line.split( delimiter )[ :hinge ] ) for line in current_lines ] + hinge_dict = {} + for i in range( len( hinges ) ): + if not hinge_dict.has_key( hinges[ i ] ): + hinge_dict[ hinges[ i ] ] = i + hinges.sort( hinge_compare ) + hinges = [ h for h in hinges if h ] + current, loc = hinges[0], hinge_dict[ hinges[0] ] + # first output empty columns for vertical alignment (account for "missing" files) + # write output for leading and trailing empty columns + # columns missing from actual file handled further below + current_data = [] + if current != old_current: + # fill trailing empty columns with appropriate fill value + if not first_line: + if last_loc < len( inputs ) - 1: + if not fill_empty: + filler = [ '' for col in range( ( len( inputs ) - last_loc - 1 ) * len( cols ) ) ] + else: + filler = [ fill_empty[ cols[ col % len( cols ) ] ] for col in range( ( len( inputs ) - last_loc - 1 ) * len( cols ) ) ] + fout.write( '%s%s' % ( delimiter, delimiter.join( filler ) ) ) + # insert line break before current line + fout.write( '\n' ) + # fill leading empty columns with appropriate fill value + if loc > 0: + if not fill_empty: + current_data = [ '' for col in range( loc * len( cols ) ) ] + else: + current_data = [ fill_empty[ cols[ col % len( cols ) ] ] for col in range( loc * len( cols ) ) ] + else: + if loc - last_loc > 1: + if not fill_empty: + current_data = [ '' for col in range( ( loc - last_loc - 1 ) * len( cols ) ) ] + else: + current_data = [ fill_empty[ cols[ col % len( cols ) ] ] for col in range( ( loc - last_loc - 1 ) * len( cols ) ) ] + # now output actual data + split_line = current_lines[ loc ].split( delimiter ) + # fill empties within actual line if appropriate + if fill_empty: + new_split_line = split_line[:] + split_line = [] + for i, item in enumerate( new_split_line ): + col = i + 1 + if not item: + try: + split_line.append( fill_empty[ i + 1 ] ) + except KeyError: + split_line.append( item ) + else: + split_line.append( item ) + # add actual data to be output below + if ''.join( split_line ): + for col in cols: + if col > hinge: + # if this column doesn't exist, add the appropriate filler or empty column + try: + new_item = split_line[ col - 1 ] + except IndexError: + if fill_empty: + new_item = fill_empty[ col ] + else: + new_item = '' + current_data.append( new_item ) + # grab next line for selected file + current_lines[ loc ] = tmp_input_files[ loc ].readline().rstrip( '\r\n' ) + # write relevant data to file + if current == old_current and current_data: + fout.write( '%s%s' % ( delimiter, delimiter.join( current_data ) ) ) + elif current_data: + fout.write( '%s%s%s' % ( current, delimiter, delimiter.join( current_data ) ) ) + last_lines = ''.join( current_lines ) + else: + last_lines = None + last_loc = loc + old_current = current + first_line = False + # fill trailing empty columns for final line + if last_loc < len( inputs ) - 1: + if not fill_empty: + filler = [ '' for col in range( ( len( inputs ) - last_loc - 1 ) * len( cols ) ) ] + else: + filler = [ fill_empty[ cols[ col % len( cols ) ] ] for col in range( ( len( inputs ) - last_loc - 1 ) * len( cols ) ) ] + fout.write( '%s%s' % ( delimiter, delimiter.join( filler ) ) ) + fout.write( '\n' ) + fout.close() + for f in tmp_input_files: + os.unlink( f.name ) + +if __name__ == "__main__" : __main__()
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/column_join.xml Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,260 @@ +<tool id="column_join" name="Column Join" version="1.1.0"> + <description></description> + <command interpreter="python"> + column_join.py + --output=$output + --input1=$input1 + --input2=$input2 + --hinge=$hinge + --columns=$columns + #if $fill_empty_columns.fill_empty_columns_switch == "fill_empty": + --fill_options_file=$fill_options_file + #end if + #for $f in $file_chooser: + ${f.input} + #end for + </command> + <inputs> + <param name="input1" type="data" format="tabular" label="Choose the first file for the join" /> + <param name="hinge" type="data_column" data_ref="input1" multiple="false" numerical="false" label="Use this column and columns to left the 'hinge' (matching data for each join)" help="All columns to left of selected column (plus selected column) will be used. Select 2 for pileup" /> + <param name="columns" type="data_column" data_ref="input1" multiple="true" numerical="false" label="Include these column" help="Multi-select list - hold the appropriate key while clicking to select multiple columns" /> + <conditional name="fill_empty_columns"> + <param name="fill_empty_columns_switch" type="select" label="Fill empty columns"> + <option value="no_fill" selected="True">No</option> + <option value="fill_empty">Yes</option> + </param> + <when value="no_fill" /> + <when value="fill_empty"> + <conditional name="do_fill_empty_columns"> + <param name="column_fill_type" type="select" label="Fill Columns by"> + <option value="single_fill_value" selected="True">Single fill value</option> + <option value="fill_value_by_column">Values by column</option> + </param> + <when value="single_fill_value"> + <param type="text" name="fill_value" label="Fill value" value="." /> + </when> + <when value="fill_value_by_column"> + <repeat name="column_fill" title="Fill Column"> + <param name="column_number" label="Column" type="data_column" data_ref="input1" /> + <param type="text" name="fill_value" value="." /> + </repeat> + </when> + </conditional> + </when> + </conditional> + <param name="input2" type="data" format="tabular" label="Choose the second file for the join" /> + <repeat name="file_chooser" title="Additional Input"> + <param name="input" label="Additional input file" type="data" format="tabular" /> + </repeat> + </inputs> + <configfiles> + <configfile name="fill_options_file"><% +import json +%> +#set $__fill_options = {} +#if $fill_empty_columns['fill_empty_columns_switch'] == 'fill_empty': + #if $fill_empty_columns['do_fill_empty_columns']['column_fill_type'] == 'single_fill_value': + #set $__start_fill = $fill_empty_columns['do_fill_empty_columns']['fill_value'].value + #else: + #set $__start_fill = "" + #end if + #set $__fill_options['file1_columns'] = [ __start_fill for i in range( int( $input1.metadata.columns ) ) ] + #if $fill_empty_columns['do_fill_empty_columns']['column_fill_type'] == 'fill_value_by_column': + #for column_fill in $fill_empty_columns['do_fill_empty_columns']['column_fill']: + #set $__fill_options['file1_columns'][ int( column_fill['column_number'].value ) - 1 ] = column_fill['fill_value'].value + #end for + #end if +#end if +${json.dumps( __fill_options )} + </configfile> + </configfiles> + <outputs> + <data name="output" format="tabular" /> + </outputs> + <tests> + <test> + <param name="input1" value="column_join_in1.pileup" ftype="pileup" /> + <param name="hinge" value="2" /> + <param name="columns" value="1,2,3,4,5,7" /> + <param name="fill_empty_columns_switch" value="fill_empty" /> + <param name="column_fill_type" value="single_fill_value" /> + <param name="fill_value" value="?" /> + <param name="input2" value="column_join_in2.pileup" ftype="pileup" /> + <param name="input" value="column_join_in3.pileup" ftype="pileup" /> + <output name="output" file="column_join_out1.pileup" ftype="tabular" /> + </test> + <test> + <param name="input1" value="column_join_in4.pileup" ftype="pileup" /> + <param name="hinge" value="2" /> + <param name="columns" value="1,2,3,4" /> + <param name="fill_empty_columns_switch" value="no_fill" /> + <param name="input2" value="column_join_in5.pileup" ftype="pileup" /> + <param name="input" value="column_join_in6.pileup" ftype="pileup" /> + <output name="output" file="column_join_out2.pileup" ftype="tabular" /> + </test> +<!-- This test is failing for an unclear reason (the column values do not get + passed into the script), but passes in the browser + <test> + <param name="input1" value="column_join_in7.pileup" ftype="tabular" /> + <param name="hinge" value="2" /> + <param name="columns" value="3,4,5" /> + <param name="fill_empty_columns_switch" value="fill_empty" /> + <param name="column_fill_type" value="fill_value_by_column" /> + <param name="column_number" value="5" /> + <param name="fill_value" value="X" /> + <param name="input2" value="column_join_in8.pileup" ftype="tabular" /> + <param name="input" value="column_join_in9.pileup" ftype="tabular" /> + <output name="output" file="column_join_out3.pileup" ftype="tabular" /> + </test> +--> + <test> + <param name="input1" value="column_join_in10.pileup" ftype="pileup" /> + <param name="hinge" value="1" /> + <param name="columns" value="2,7" /> + <param name="fill_empty_columns_switch" value="no_fill" /> + <param name="input2" value="column_join_in11.pileup" ftype="pileup" /> + <param name="input" value="column_join_in12.pileup" ftype="pileup" /> + <output name="output" file="column_join_out4.pileup" ftype="tabular" /> + </test> + <test> + <!-- Test for handling missing column --> + <param name="input1" value="column_join_in13.tabular" ftype="tabular" /> + <param name="hinge" value="1" /> + <param name="columns" value="5" /> + <param name="fill_empty_columns_switch" value="fill_empty" /> + <param name="column_fill_type" value="single_fill_value" /> + <param name="fill_value" value="0" /> + <param name="input2" value="column_join_in14.tabular" ftype="tabular" /> + <param name="input" value="column_join_in15.tabular" ftype="tabular" /> + <output name="output" file="column_join_out5.tabular" ftype="tabular" /> + </test> + </tests> + <help> +**What it does** + +This tool allows you to join several files with the same column structure into one file, removing certain columns if necessary. The user needs to select a 'hinge', which is the number of left-most columns to match on. They also need to select the columns to include in the join, which should include the hinge columns, too. + +Note that the files are expected to have the same number of columns. If for some reason the join column is missing (this only applies to the last column(s)), the tool attempts to handle this situation by inserting an empty item (or the appropriate filler) for that column on that row. This could lead to the situation where a row has a hinge but entirely empty or filled columns, if the hinge exists in at least one file but every file that has it is missing the join column. Also, note that the tool does not distinguish between a file missing the hinge altogether and a file having the hinge but missing the column (in both cases the column would be empty or filled). There is an example of this below. + +----- + +**General Example** + +Given the following files:: + + FILE 1 + chr2 1 T 6 .C..., I$$III + chr2 2 G 6 ..N.., III@II + chr2 3 C 7 ..C..., I$IIIII + chr2 4 G 7 .G...., I#IIIII + chr2 5 G 7 ...N.., IIII#BI + chr2 6 A 7 ..T..., I$IDIII + chr1 1 C 1 ^:. I + chr1 2 G 2 .^:. $I + chr1 3 A 2 .. I% + chr1 4 C 2 .. I$ + chr1 5 T 3 ..^:. I#I + chr1 6 G 3 ..^:, I#I + + FILE 2 + chr1 3 T 1 ^:. I + chr1 4 G 2 .^:. $I + chr1 5 T 2 .. I% + chr1 6 C 3 ..^:. III + chr1 7 G 3 ..^:. I#I + chr1 8 T 4 ...^:, I#II + chr2 77 C 6 .G..., I$$III + chr2 78 G 6 ..N.., III@II + chr2 79 T 7 ..N..., I$IIIII + chr2 80 C 7 .G...., I#IIIII + chr2 81 G 7 ...A.., IIII#BI + chr2 82 A 8 ...G..., I$IDIIII + chr2 83 T 8 .A.....N IIIIIIII + chr2 84 A 9 ......T. I$IIIIIII + + FILE 3 + chr1 1 A 1 . I + chr1 2 T 2 G. I$ + chr1 3 C 2 ., I@ + chr1 4 C 3 ..N III + chr1 42 C 5 ...N^:. III@I + chr1 43 C 5 .N..^:. IIIII + chr1 44 T 5 .A.., IA@II + chr1 45 A 6 .N...^:. IIIII$ + chr1 46 G 6 .GN..^:. I@IIII + chr1 47 A 7 ....^:.., IIIII$I + chr2 73 T 5 .N.., II$II + chr2 74 A 5 ...., IIIII + chr2 75 T 5 ...., IIIII + chr2 76 T 5 ...., IIIII + chr2 77 C 5 ...., IIIBI + chr2 78 T 5 ...., IDIII + +To join on columns 3 and 4 combining on columns 1 and 2, columns 1-4 should be selected for the 'Include these columns' option, and column 2 selected for the 'hinge'. With these settings, the following would be output:: + + chr1 1 C 1 A 1 + chr1 2 G 2 T 2 + chr1 3 A 2 T 1 C 2 + chr1 4 C 2 G 2 C 3 + chr1 5 T 3 T 2 + chr1 6 G 3 C 3 + chr1 7 G 3 + chr1 8 T 4 + chr1 42 C 5 + chr1 43 C 5 + chr1 44 T 5 + chr1 45 A 6 + chr1 46 G 6 + chr1 47 A 7 + chr2 1 T 6 + chr2 2 G 6 + chr2 3 C 7 + chr2 4 G 7 + chr2 5 G 7 + chr2 6 A 7 + chr2 73 T 5 + chr2 74 A 5 + chr2 75 T 5 + chr2 76 T 5 + chr2 77 C 6 C 5 + chr2 78 G 6 T 5 + chr2 79 T 7 + chr2 80 C 7 + chr2 81 G 7 + chr2 82 A 8 + chr2 83 T 8 + chr2 84 A 9 + +**Example with missing columns** + +Given the following input files:: + + FILE 1 + 1 A + 2 B b + 4 C c + 5 D + 6 E e + + FILE 2 + 1 M m + 2 N + 3 O o + 4 P p + 5 Q + 7 R r + +if we join only column 3 using column 1 as the hinge and with a fill value of '0', this is what will be output:: + + 1 0 m + 2 b 0 + 3 0 o + 4 c p + 5 0 0 + 6 e 0 + 7 0 r + +Row 5 appears in both files with the missing column, so it's got nothing but fill values in the output file. + + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in1.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,30 @@ +chrM 1 A G 25 0 25 1 ^:. I +chrM 2 C T 25 0 25 2 .N I$ +chrM 3 T G 27 0 25 2 .. II +chrM 4 G C 36 0 25 3 .^:.^:. II+ +chrM 5 T A 38 0 25 3 ... III +chrM 6 T A 39 0 25 4 .N.. I$II +chrM 7 G C 43 0 25 5 ...^:.^:. IIIII +chrM 8 A C 46 0 25 6 .....^:. IIIIII +chrM 9 T G 53 0 25 8 ..G...^:.^:. IIIII$II +chrM 10 T G 56 0 25 9 ........^:. IIIIIIIII +chrM 11 C G 57 0 25 10 .........^:. IIIIIIIIII +chrM 12 T C 61 0 25 11 ..........^:. IIIIIIIIIII +chrM 13 T G 79 0 25 15 .........^:.^:.^:.^:.^:.^:. IIIIIIIIIIII#II +chrM 14 A C 58 0 25 18 .......G.........^:. BIIIIIII+IIIIIIIII +chrM 15 G A 87 0 25 19 ..N...............^:.^:. DIIIIII$(IIIIIIIIIII +chrM 16 G C 88 0 25 20 .........N.......... IIIIIIIIIIIIIIIIIIII +chrM 17 A C 88 0 25 20 .........G.......... 9IIIIIIIIIIIIIIIIIII +chrM 18 G A 89 0 25 20 ...A................ @IIIIIIIIIIIIIIIIIII +chrM 19 G T 58 0 25 20 ....T.............GG IIIIIIIIIIIIIIIIII'A +chrM 20 T C 55 0 25 20 .........C........C. IIIIIIIIIIIIIII2II#$ +chrM 21 C T 87 0 25 20 ..........G......... IIIIIIIIIIIIIIIIIIII +chrM 22 C A 87 0 25 20 ..........N......... IIIIIIIIIIIIIIAIIIII +chrM 23 A G 87 0 25 20 .....T.............. 9IIIIIIIIII0IIIIIIII +chrM 24 A T 89 0 25 20 .....N..N........... III$IIII"IIIIICII#II +chrM 25 G A 57 0 25 21 ...A................^:. A@.$IIIIIIIFIIIIIIIII +chrM 26 C G 58 0 25 22 ...N....A............. IIHIDII&IIIIII@IIIIII +chrM 27 T A 99 0 25 23 ....................^:.^:.^:. IE8IFIII9IIIIIIIIIIIIII +chrM 28 A C 99 0 25 24 ..G..................... 1FIIIIIIIIIIIIIIIIDEIIII +chrM 29 G C 58 0 25 25 ........C.........NN.... ;IIIIII+HII=III$III""IIII +chrM 30 T T 65 0 25 25 ...C....................^:. ;I?&IAI0IIIIIIIIIIIIIIIII
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in10.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,26 @@ +0610009D07Rik 2 1.41 1.41 -0.24 12/12 2 1 +1110002N22Rik 2 1.70 1.70 -0.06 10/12 2 1 +1110008L16Rik 3 1.73 1.73 -0.54 12/12 2 1 +1110054O05Rik 1 1.55 1.55 1.14 5/12 1 1 +Actg1 2 4.24 4.24 2.36 4/12 2 1 +Actl6a 2 1.55 1.55 1.00 10/12 1 1 +Actn1 1 3.46 3.46 3.17 1/12 1 1 +Actn4 1 3.46 3.46 3.17 1/12 1 1 +Bnc2 1 2.00 2.00 1.67 3/12 1 1 +Bub3 2 1.89 1.89 1.02 9/12 2 1 +Cad 4 4.90 4.90 3.09 2/12 1 1 +Calm1;Calm3;Calm2 2 2.83 2.83 2.57 3/12 1 1 +E130012A19Rik 2 5.66 5.66 1.50 3/12 2 1 +E2f6 2 3.39 3.39 1.80 5/12 2 1 +Gm12620 1 3.46 3.46 3.17 1/12 1 1 +Gm13092;LOC677017 1 1.15 1.15 0.29 9/12 1 1 +Gm14173;Rpl37a;Gm4149 1 3.00 3.00 1.37 4/12 2 1 +Gm14393;2210418O10Rik;Gm14296;Gm14401;RP23-330D3.5 1 3.46 3.46 3.17 1/12 1 1 +Gm189 1 1.20 1.20 0.16 10/12 2 1 +Sfrs7 1 1.71 1.71 0.18 7/12 2 1 +Sin3a 1 1.71 1.71 -0.12 7/12 2 1 +Ski 1 2.45 2.45 2.13 2/12 1 1 +Skil 1 2.00 2.00 1.03 3/12 1 1 +Tubb2c 1 2.00 2.00 1.67 3/12 1 1 +Tubb2c-ps1 1 12.00 12.00 3.17 1/12 2 1 +Zscan4f 2 1.70 1.70 1.00 10/12 2 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in11.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,36 @@ +0610009D07Rik 3 1.73 1.73 1.15 12/12 2 1 +0610010K14Rik 1 1.41 1.41 0.96 6/12 1 1 +1110002N22Rik 3 2.08 2.08 0.74 10/12 2 1 +1110008L16Rik 1 1.00 1.00 -1.35 12/12 1 1 +Acta1 2 1.54 1.54 0.63 11/12 2 1 +Actb 1 1.33 1.33 0.00 9/12 2 1 +Actg1 1 3.00 3.00 0.87 4/12 2 1 +Actl6a 1 1.10 1.10 -0.33 10/12 1 1 +Actl6b 1 2.45 2.45 2.13 2/12 1 1 +Bnc2 1 2.00 2.00 1.67 3/12 1 1 +Bptf 1 3.46 3.46 3.17 1/12 1 1 +Brip1 1 1.22 1.22 -0.19 8/12 1 1 +Brms1l 1 12.00 12.00 3.17 1/12 2 1 +Btf3;Gm3531 1 2.00 2.00 1.67 3/12 1 1 +Bub3 3 2.00 2.00 2.13 9/12 1 1 +C330007P06Rik 1 2.45 2.45 2.13 2/12 1 1 +Cad 1 2.45 2.45 0.50 2/12 1 1 +Calm1;Calm3;Calm2 1 2.00 2.00 1.03 3/12 1 1 +Cbx1 2 3.39 3.39 2.24 5/12 2 1 +E2f6 1 2.40 2.40 0.53 5/12 2 1 +Eed 1 1.20 1.20 -0.47 10/12 2 1 +Gm10079 2 1.41 1.41 0.16 12/12 1 1 +Gm11230 2 1.48 1.48 1.21 11/12 1 1 +Gm13072;Trmt112 1 3.46 3.46 3.17 1/12 1 1 +Gm13092;LOC677017 1 1.33 1.33 0.29 9/12 2 1 +Gm14231 1 1.31 1.31 0.51 7/12 1 1 +Gm14456;Tpt1 1 2.00 2.00 1.67 3/12 1 1 +Gm15501;Rps8 1 1.55 1.55 1.14 5/12 1 1 +Gm189 1 1.20 1.20 0.16 10/12 2 1 +Sfrs11 3 1.73 1.73 1.15 12/12 2 1 +Sin3a 4 3.43 3.43 1.93 7/12 2 1 +Sirt7 1 2.00 2.00 1.67 3/12 1 1 +Skiv2l2 12 3.46 3.46 -0.72 12/12 2 1 +Tubb2b 4 2.00 2.00 0.49 12/12 2 1 +Zscan4e 1 1.41 1.41 0.63 6/12 1 1 +Zscan4f 2 1.70 1.70 1.00 10/12 2 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in12.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,36 @@ +0610009D07Rik 4 2.00 2.00 2.54 12/12 2 1 +0610010K14Rik 1 1.41 1.41 0.96 6/12 1 1 +1110002N22Rik 2 1.70 1.70 -0.06 10/12 2 1 +1110008L16Rik 6 2.45 2.45 0.68 12/12 2 1 +1110037F02Rik 1 2.45 2.45 2.13 2/12 1 1 +1190005F20Rik 4 2.18 2.18 0.28 11/12 2 1 +Acot8 1 2.00 2.00 0.07 6/12 2 1 +Acta1 2 1.54 1.54 0.63 11/12 2 1 +Actb 2 1.89 1.89 1.35 9/12 2 1 +Actl6b 1 6.00 6.00 2.13 2/12 2 1 +Bend3 1 1.15 1.33 -0.51 9/12 1 1.33 +Bend5 1 3.46 3.46 3.17 1/12 1 1 +Brip1 2 1.73 1.73 0.58 8/12 1 1 +Btf3;Gm3531 1 4.00 4.00 1.67 3/12 2 1 +Bub3 1 1.33 1.33 -0.09 9/12 2 1 +C130039O16Rik 1 2.45 2.45 2.13 2/12 1 1 +C1d 1 1.73 1.73 0.87 4/12 1 1 +Caprin1 2 2.42 2.42 0.51 7/12 2 1 +Cbx3 2 1.54 1.54 0.75 11/12 2 1 +Eed 1 1.10 1.10 -0.47 10/12 1 1 +Efha1 1 3.46 3.46 3.17 1/12 1 1 +Exosc1 3 1.73 1.73 1.29 12/12 2 1 +Exosc10 25 5.00 5.00 1.03 12/12 2 1 +Gm189 2 1.70 1.70 2.12 10/12 2 1 +Gm3200 1 2.45 2.45 2.13 2/12 1 1 +Gm9855;Tdg 2 1.70 1.70 1.37 10/12 2 1 +Sfrs11 4 2.00 2.00 2.54 12/12 2 1 +Sfrs12 2 5.66 5.66 2.57 3/12 2 1 +Sin3a 1 1.31 1.31 -0.12 7/12 1 1 +Sirt7 1 2.00 2.00 1.67 3/12 1 1 +Skiv2l2 34 5.83 5.83 0.68 12/12 2 1 +Tubb2b 3 1.73 1.73 -0.10 12/12 2 1 +Tubb4 1 1.15 1.15 0.29 9/12 1 1 +Zscan4-ps2 1 12.00 12.00 3.17 1/12 2 1 +Zscan4e 2 2.83 2.83 2.12 6/12 2 1 +Zscan4f 2 1.70 1.70 1.00 10/12 2 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in13.tabular Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,6 @@ +alpha beta gamma delta +1 A I a i +2 B II b ii +5 C III c +7 D IV d iii +11 E V e iv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in14.tabular Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,11 @@ +alpha beta gamma delta epsilon +1 AA I2 aa i2 +2 BB II2 bb +3 CC III2 cc ii2 +4 DD IV2 dd iii2 +6 EE V2 ee iv2 +7 FF VI2 ff +8 GG VII2 gg v2 +9 HH VIII2 hh vi2 +10 II IX2 ii vii2 +11 JJ X2 jj viii2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in15.tabular Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,11 @@ +alpha beta gamma +2 BBB II3 bbb i3 +3 CCC III3 ccc ii3 +4 DDD IV2 ddd iii3 +5 EEE V3 eee +6 FFF VI3 fff iv3 +7 GGG VII3 ggg v3 +8 HHH VIII3 hhh +9 III IX3 iii vi3 +10 JJJ X3 jjj vii3 +11 LLL XI3 lll
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in2.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,30 @@ +chrM 1 T G 25 0 25 1 ^:. I +chrM 2 C A 25 0 25 1 . I +chrM 3 C A 25 0 25 2 .. I+ +chrM 4 G A 36 0 25 3 .^:.^:. II+ +chrM 5 A T 36 0 25 3 ... IDI +chrM 6 A G 36 0 25 4 ..T. IIBI +chrM 7 C G 42 0 25 5 ...^:.^:. ID@II +chrM 8 T T 45 0 25 6 .....^:. III$BI +chrM 9 C A 51 0 25 8 ......^:.^:. $#III+III +chrM 10 G G 54 0 25 9 ........^:. III$III#I +chrM 11 T C 57 0 25 10 .........^:. IIIDBIIIII +chrM 12 A T 60 0 25 11 ..........^:. IIIIIIIII$I +chrM 13 A T 78 0 25 18 ..A.........^:.^:.^:.^:.^:.^:. III#$IIIIII+IIDIIB +chrM 14 G A 56 0 25 19 ........T.........^:. BIIIIIII+IIII$IBIII +chrM 15 G A 87 0 25 20 ..................^:.^:. DIIIIIII(IIIIIIIIIII +chr1 1 T T 87 0 25 20 .............T...... IIIIIIIIIIII$DIIIIII +chr1 2 A T 87 0 25 20 ......G............. 9IIIIIIIIIIIIICBIIII +chr1 3 A G 87 0 25 20 ....A............... @IIIIIIIII#IIII#IIII +chr1 4 A T 55 0 25 20 ..................GG IIIII@II$IIIIIIIII'A +chr1 5 C A 54 0 25 20 .......A..........C. IIIIIIIIIDIIIII2II#$ +chr1 6 G T 87 0 25 20 .............A...... IIIIIIIBIIIIII#IIIII +chr1 7 A C 87 0 25 20 ..........C......... IIIII+IIIIIIIIAIIIII +chr1 8 G A 87 0 25 20 ....G.........T..... 9IIIIIIIIII0IIIIIIII +chr1 9 A T 87 0 25 20 ........N........... IIII$III"IIIIICIIIII +chr1 10 G A 57 0 25 21 ...A................^:. A@.$IIIIIIIFIIIIIIIII +chr1 11 C A 57 0 25 22 ....G...A............. IIHIDII&IIIIII#III$II +chr1 12 T A 99 0 25 24 .....................^:.^:.^:. IE8IFIII9IIIIIIIIIIIIIII +chr1 13 A C 99 0 25 25 ...N..................... 1FIIIIIIIIIIIIIIIIDEII$II +chr1 14 G C 55 0 25 25 ....G..............NN.... ;IIIBIII+HII=IIIIII""IIII +chr1 15 T G 68 0 25 28 ...C.......N............^:. ;I?&IAI0IIIIIII@II#$II@II
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in3.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,30 @@ +chr1 1 G G 25 0 25 1 ^:. I +chr1 2 T T 25 0 25 1 . I +chr1 3 T T 27 0 25 1 . I +chr1 4 A A 36 0 25 2 .^:. I+ +chr1 5 A A 36 0 25 3 ... III +chr1 6 T T 36 0 25 4 .N.. II#I +chr1 7 G G 42 0 25 5 ...^:.^:. IIIII +chr1 8 T T 45 0 25 6 .....^:. IIIIII +chr1 9 A A 51 0 25 7 .....^:.^:. IBIIIII +chr1 10 G G 54 0 25 9 ........^:. IIIIIIIII +chr1 11 C C 57 0 25 10 .........^:. IIIIIIII"I +chr1 12 T T 60 0 25 11 ..........^:. IIIIIIDIIII +chr1 13 T T 78 0 25 17 ...........^:.^:.^:.^:.^:.^:. IIII"$IIIIIIIIIII +chr1 14 A A 56 0 25 18 .......G.........^:. BIIIIIII+IIIIIIIII +chr1 15 A A 87 0 25 20 ....N.............^:.^:. DIII$III(IIIIIIIIIII +chr4 1 T T 90 0 25 20 ..........N......... IIIIIIIII$IIIIIIIIII +chr4 2 A A 87 0 25 20 .......C............ 9IIIIIIIII"IIIIIIIII +chr4 3 A A 34 0 25 20 ......G............. @IIIIIIIIIIII#IIIIII +chr4 4 T T 55 0 25 21 ...........N.......GG IIIII@IIIIIIIIIIIII'A +chr4 5 A A 54 0 25 21 ...N...............C. IIII"IIIIIIIIIII2II#$ +chr4 6 T T 87 0 25 21 ................N.... IIIIIIII$IIIIIIIIIIII +chr4 7 A A 80 0 25 21 .....G............... III$IIIIIIIIIIIAIIIII +chr4 8 A A 87 0 25 22 ..N................... 9IIIIIIIIII0IIIII"$III +chr4 9 A A 87 0 25 22 .GG.......N........... IIII$IIIII"IIIIICIIIII +chr4 10 G G 57 0 25 23 .....A................^:. A@.$IIIIIIIIIFIIIIIIIII +chr4 11 C C 57 0 25 25 .......A.....GN.......... IIHIDII&III#IIIIIIIIIIIII +chr4 12 A A 99 0 25 26 .......................^:.^:.^:. IE8IFIII9IIIIIII$IIIIIIIII +chr4 13 A A 99 0 25 27 ........N.................. 1FIIIIII$IIIIIIIIIIIIDEIIII +chr4 14 G G 55 0 25 28 ..N...................NN.... ;III$I#IIII+HII=IIIIII""IIII +chr4 15 G G 68 0 25 30 ...C....N..G.................^:. ;I?&IAI0IIIIIII$#I$@IIIIIIIIII
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in4.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,25 @@ +chr2 1 T 6 .C..., I$$III +chr2 2 G 6 ..N.., III@II +chr2 3 C 7 ..C..., I$IIIII +chr2 4 G 7 .G...., I#IIIII +chr2 5 G 7 ...N.., IIII#BI +chr2 6 A 7 ..T..., I$IDIII +chr2 7 T 8 ...C..., IIIBD$II +chr2 8 A 8 ..A...., IBI#IIII +chr2 9 C 9 .GA..N.., I$IBIII#I +chr2 10 T 9 ........, I$II#IIII +chr2 11 C 10 .>>..T..., IIII@I$I$I +chr2 12 G 10 .N..G...., III$IIIIII +chr2 13 A 11 ....A..T.., IIIIII#I@II +chr1 1 C 1 ^:. I +chr1 2 G 2 .^:. $I +chr1 3 A 2 .. I% +chr1 4 C 2 .. I$ +chr1 5 T 3 ..^:. I#I +chr1 6 G 3 ..^:, I#I +chr1 7 C 4 .N., IIII +chr1 8 A 4 ..., I$II +chr1 9 T 5 ..C., I#IDI +chr1 10 G 5 N..., IBII@ +chr1 11 A 5 .C.., I$II# +chr1 12 C 5 ..N., I$III
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in5.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,25 @@ +chr1 42 T 1 ^:. I +chr1 43 G 2 .^:. $I +chr1 44 T 2 .. I% +chr1 45 C 3 ..^:. III +chr1 46 G 3 ..^:. I#I +chr1 47 T 4 ...^:, I#II +chr1 48 A 4 .N., IIII +chr1 49 C 5 ...., IIIII +chr1 50 A 5 ..G., IIIDI +chr1 51 A 5 A..., IBIII +chr1 52 A 5 ...., IIII# +chr1 53 G 5 ..N., I$III +chr2 77 C 6 .G..., I$$III +chr2 78 G 6 ..N.., III@II +chr2 79 T 7 ..N..., I$IIIII +chr2 80 C 7 .G...., I#IIIII +chr2 81 G 7 ...A.., IIII#BI +chr2 82 A 8 ...G..., I$IDIIII +chr2 83 A 8 ...T..., IIIBD$II +chr2 84 T 8 ..A...., IBI#IIII +chr2 85 G 8 .GA...., IIBIII#I +chr2 86 C 9 ........, I$II#IIII +chr2 87 G 9 ....T..., IIIII$I$I +chr2 88 G 10 .N..G...., III$IIIIII +chr2 89 G 10 ...A..T.., IIIII#I@II
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in6.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,25 @@ +chr1 42 C 1 ^:. I +chr1 43 C 2 .^:. II +chr1 44 T 2 .. II +chr1 45 A 3 ..^:. III +chr1 46 G 4 ...^:. IIII +chr1 47 A 5 ....^:, IIIII +chr1 48 T 5 ...N, I#III +chr1 49 G 5 ...., IIIII +chr1 50 A 5 .G.., IIIII +chr1 51 G 5 ...., IIIII +chr2 52 T 5 .N.., II$II +chr2 53 A 5 ...., IIIII +chr2 54 T 5 ...., IIIII +chr2 55 T 5 ...., IIIII +chr2 56 C 5 ...., IIIBI +chr2 57 T 5 ...., IDIII +chr2 58 T 6 .N..., IIIIII +chr2 59 A 6 ....., IIII$I +chr3 60 C 6 ...G., I#IIII +chr3 61 T 6 ..N.., IIIIII +chr3 62 C 6 ...A., IIIIII +chr3 63 C 7 .N...., IIIIIII +chr3 64 A 7 ...G.., IIIII$I +chr3 65 T 7 ...AA., IIIII@@ +chr3 66 A 7 ....N., IIIIIII
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in7.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,32 @@ +chr2 1 T 6 .C..., I$$III +chr2 2 G 6 ..N.., III@II +chr2 3 C 7 ..C..., I$IIIII +chr2 4 G 7 .G...., I#IIIII +chr2 5 G 7 ...N.., IIII#BI +chr2 6 A 7 ..T..., I$IDIII +chr2 7 T 8 ...C..., IIIBD$II +chr2 8 A 8 ..A...., IBI#IIII +chr2 9 C 9 .GA..N.., I$IBIII#I +chr2 10 T 9 ........, I$II#IIII +chr2 11 C 10 .>>..T..., IIII@I$I$I +chr2 12 G 10 .N..G...., III$IIIIII +chr2 13 A 11 ....A..T.., IIIIII#I@II +chr2 14 G 11 ..N....... IICIBII@AII +chr2 15 C 11 A.....NG.. IIIIIDIIIII +chr2 16 T 11 ...C.....G I$IIIB@IIIC +chr2 17 C 12 G......TN.. IIAII@IIII$I +chr2 18 A 12 N......G..A IIIBIII$IIII +chr2 19 A 13 .......NN... IIIIIIBIII$$@ +chr2 20 C 13 ..GT.......N IIIIABIIC$III +chr1 1 C 1 ^:. I +chr1 2 G 2 .^:. $I +chr1 3 A 2 .. I% +chr1 4 C 2 .. I$ +chr1 5 T 3 ..^:. I#I +chr1 6 G 3 ..^:, I#I +chr1 7 C 4 .N., IIII +chr1 8 A 4 ..., I$II +chr1 9 T 5 ..C., I#IDI +chr1 10 G 5 N..., IBII@ +chr1 11 A 5 .C.., I$II# +chr1 12 C 5 ..N., I$III
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in8.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,23 @@ +chr1 42 T 1 ^:. I +chr1 43 G 2 .^:. $I +chr1 44 T 2 .. I% +chr1 45 C 3 ..^:. III +chr1 46 G 3 ..^:. I#I +chr1 47 T 4 ...^:, I#II +chr1 48 A 4 .N., IIII +chr1 49 C 5 ...., IIIII +chr1 50 A 5 ..G., IIIDI +chr1 51 A 5 A..., IBIII +chr1 52 A 5 ...., IIII# +chr1 53 G 5 ..N., I$III +chr2 77 C 6 .G..., I$$III +chr2 78 G 6 ..N.., III@II +chr2 79 T 7 ..N..., I$IIIII +chr2 80 C 7 .G...., I#IIIII +chr2 81 G 7 ...A.., IIII#BI +chr2 82 A 8 ...G..., I$IDIIII +chr2 83 A 8 ...T..., IIIBD$II +chr2 84 T 8 ..A...., IBI#IIII +chr2 85 G 8 .GA...., IIBIII#I +chr2 86 C 9 ........, I$II#IIII +chr2 87 G 9 ....T..., IIIII$I$I
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_in9.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,25 @@ +chr1 43 C 2 .^:. II +chr3 65 T 7 ...AA., IIIII@@ +chr1 44 T 2 .. II +chr2 54 T 5 ...., IIIII +chr1 45 A 3 ..^:. III +chr1 47 A 5 ....^:, IIIII +chr1 50 A 5 .G.., IIIII +chr1 51 G 5 ...., IIIII +chr2 52 T 5 .N.., II$II +chr2 53 A 5 ...., IIIII +chr3 60 C 6 ...G., I#IIII +chr3 61 T 6 ..N.., IIIIII +chr1 49 G 5 ...., IIIII +chr2 55 T 5 ...., IIIII +chr2 56 C 5 ...., IIIBI +chr2 58 T 6 .N..., IIIIII +chr2 59 A 6 ....., IIII$I +chr3 62 C 6 ...A., IIIIII +chr1 42 C 1 ^:. I +chr3 63 C 7 .N...., IIIIIII +chr1 48 T 5 ...N, I#III +chr1 46 G 4 ...^:. IIII +chr3 64 A 7 ...G.., IIIII$I +chr3 66 A 7 ....N., IIIIIII +chr2 57 T 5 ...., IDIII
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_out1.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,60 @@ +chr1 1 ? ? ? ? T T 87 25 G G 25 25 +chr1 2 ? ? ? ? A T 87 25 T T 25 25 +chr1 3 ? ? ? ? A G 87 25 T T 27 25 +chr1 4 ? ? ? ? A T 55 25 A A 36 25 +chr1 5 ? ? ? ? C A 54 25 A A 36 25 +chr1 6 ? ? ? ? G T 87 25 T T 36 25 +chr1 7 ? ? ? ? A C 87 25 G G 42 25 +chr1 8 ? ? ? ? G A 87 25 T T 45 25 +chr1 9 ? ? ? ? A T 87 25 A A 51 25 +chr1 10 ? ? ? ? G A 57 25 G G 54 25 +chr1 11 ? ? ? ? C A 57 25 C C 57 25 +chr1 12 ? ? ? ? T A 99 25 T T 60 25 +chr1 13 ? ? ? ? A C 99 25 T T 78 25 +chr1 14 ? ? ? ? G C 55 25 A A 56 25 +chr1 15 ? ? ? ? T G 68 25 A A 87 25 +chr4 1 ? ? ? ? ? ? ? ? T T 90 25 +chr4 2 ? ? ? ? ? ? ? ? A A 87 25 +chr4 3 ? ? ? ? ? ? ? ? A A 34 25 +chr4 4 ? ? ? ? ? ? ? ? T T 55 25 +chr4 5 ? ? ? ? ? ? ? ? A A 54 25 +chr4 6 ? ? ? ? ? ? ? ? T T 87 25 +chr4 7 ? ? ? ? ? ? ? ? A A 80 25 +chr4 8 ? ? ? ? ? ? ? ? A A 87 25 +chr4 9 ? ? ? ? ? ? ? ? A A 87 25 +chr4 10 ? ? ? ? ? ? ? ? G G 57 25 +chr4 11 ? ? ? ? ? ? ? ? C C 57 25 +chr4 12 ? ? ? ? ? ? ? ? A A 99 25 +chr4 13 ? ? ? ? ? ? ? ? A A 99 25 +chr4 14 ? ? ? ? ? ? ? ? G G 55 25 +chr4 15 ? ? ? ? ? ? ? ? G G 68 25 +chrM 1 A G 25 25 T G 25 25 ? ? ? ? +chrM 2 C T 25 25 C A 25 25 ? ? ? ? +chrM 3 T G 27 25 C A 25 25 ? ? ? ? +chrM 4 G C 36 25 G A 36 25 ? ? ? ? +chrM 5 T A 38 25 A T 36 25 ? ? ? ? +chrM 6 T A 39 25 A G 36 25 ? ? ? ? +chrM 7 G C 43 25 C G 42 25 ? ? ? ? +chrM 8 A C 46 25 T T 45 25 ? ? ? ? +chrM 9 T G 53 25 C A 51 25 ? ? ? ? +chrM 10 T G 56 25 G G 54 25 ? ? ? ? +chrM 11 C G 57 25 T C 57 25 ? ? ? ? +chrM 12 T C 61 25 A T 60 25 ? ? ? ? +chrM 13 T G 79 25 A T 78 25 ? ? ? ? +chrM 14 A C 58 25 G A 56 25 ? ? ? ? +chrM 15 G A 87 25 G A 87 25 ? ? ? ? +chrM 16 G C 88 25 ? ? ? ? ? ? ? ? +chrM 17 A C 88 25 ? ? ? ? ? ? ? ? +chrM 18 G A 89 25 ? ? ? ? ? ? ? ? +chrM 19 G T 58 25 ? ? ? ? ? ? ? ? +chrM 20 T C 55 25 ? ? ? ? ? ? ? ? +chrM 21 C T 87 25 ? ? ? ? ? ? ? ? +chrM 22 C A 87 25 ? ? ? ? ? ? ? ? +chrM 23 A G 87 25 ? ? ? ? ? ? ? ? +chrM 24 A T 89 25 ? ? ? ? ? ? ? ? +chrM 25 G A 57 25 ? ? ? ? ? ? ? ? +chrM 26 C G 58 25 ? ? ? ? ? ? ? ? +chrM 27 T A 99 25 ? ? ? ? ? ? ? ? +chrM 28 A C 99 25 ? ? ? ? ? ? ? ? +chrM 29 G C 58 25 ? ? ? ? ? ? ? ? +chrM 30 T T 65 25 ? ? ? ? ? ? ? ?
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_out2.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,65 @@ +chr1 1 C 1 +chr1 2 G 2 +chr1 3 A 2 +chr1 4 C 2 +chr1 5 T 3 +chr1 6 G 3 +chr1 7 C 4 +chr1 8 A 4 +chr1 9 T 5 +chr1 10 G 5 +chr1 11 A 5 +chr1 12 C 5 +chr1 42 T 1 C 1 +chr1 43 G 2 C 2 +chr1 44 T 2 T 2 +chr1 45 C 3 A 3 +chr1 46 G 3 G 4 +chr1 47 T 4 A 5 +chr1 48 A 4 T 5 +chr1 49 C 5 G 5 +chr1 50 A 5 A 5 +chr1 51 A 5 G 5 +chr1 52 A 5 +chr1 53 G 5 +chr2 1 T 6 +chr2 2 G 6 +chr2 3 C 7 +chr2 4 G 7 +chr2 5 G 7 +chr2 6 A 7 +chr2 7 T 8 +chr2 8 A 8 +chr2 9 C 9 +chr2 10 T 9 +chr2 11 C 10 +chr2 12 G 10 +chr2 13 A 11 +chr2 52 T 5 +chr2 53 A 5 +chr2 54 T 5 +chr2 55 T 5 +chr2 56 C 5 +chr2 57 T 5 +chr2 58 T 6 +chr2 59 A 6 +chr2 77 C 6 +chr2 78 G 6 +chr2 79 T 7 +chr2 80 C 7 +chr2 81 G 7 +chr2 82 A 8 +chr2 83 A 8 +chr2 84 T 8 +chr2 85 G 8 +chr2 86 C 9 +chr2 87 G 9 +chr2 88 G 10 +chr2 89 G 10 +chr3 60 C 6 +chr3 61 T 6 +chr3 62 C 6 +chr3 63 C 7 +chr3 64 A 7 +chr3 65 T 7 +chr3 66 A 7
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_out3.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,70 @@ +chr1 1 C 1 ^:. X X +chr1 2 G 2 .^:. X X +chr1 3 A 2 .. X X +chr1 4 C 2 .. X X +chr1 5 T 3 ..^:. X X +chr1 6 G 3 ..^:, X X +chr1 7 C 4 .N., X X +chr1 8 A 4 ..., X X +chr1 9 T 5 ..C., X X +chr1 10 G 5 N..., X X +chr1 11 A 5 .C.., X X +chr1 12 C 5 ..N., X X +chr1 42 X T 1 ^:. C 1 ^:. +chr1 43 X G 2 .^:. C 2 .^:. +chr1 44 X T 2 .. T 2 .. +chr1 45 X C 3 ..^:. A 3 ..^:. +chr1 46 X G 3 ..^:. G 4 ...^:. +chr1 47 X T 4 ...^:, A 5 ....^:, +chr1 48 X A 4 .N., T 5 ...N, +chr1 49 X C 5 ...., G 5 ...., +chr1 50 X A 5 ..G., A 5 .G.., +chr1 51 X A 5 A..., G 5 ...., +chr1 52 X A 5 ...., X +chr1 53 X G 5 ..N., X +chr2 1 T 6 .C..., X X +chr2 2 G 6 ..N.., X X +chr2 3 C 7 ..C..., X X +chr2 4 G 7 .G...., X X +chr2 5 G 7 ...N.., X X +chr2 6 A 7 ..T..., X X +chr2 7 T 8 ...C..., X X +chr2 8 A 8 ..A...., X X +chr2 9 C 9 .GA..N.., X X +chr2 10 T 9 ........, X X +chr2 11 C 10 .>>..T..., X X +chr2 12 G 10 .N..G...., X X +chr2 13 A 11 ....A..T.., X X +chr2 14 G 11 ..N....... X X +chr2 15 C 11 A.....NG.. X X +chr2 16 T 11 ...C.....G X X +chr2 17 C 12 G......TN.. X X +chr2 18 A 12 N......G..A X X +chr2 19 A 13 .......NN... X X +chr2 20 C 13 ..GT.......N X X +chr2 52 X X T 5 .N.., +chr2 53 X X A 5 ...., +chr2 54 X X T 5 ...., +chr2 55 X X T 5 ...., +chr2 56 X X C 5 ...., +chr2 57 X X T 5 ...., +chr2 58 X X T 6 .N..., +chr2 59 X X A 6 ....., +chr2 77 X C 6 .G..., X +chr2 78 X G 6 ..N.., X +chr2 79 X T 7 ..N..., X +chr2 80 X C 7 .G...., X +chr2 81 X G 7 ...A.., X +chr2 82 X A 8 ...G..., X +chr2 83 X A 8 ...T..., X +chr2 84 X T 8 ..A...., X +chr2 85 X G 8 .GA...., X +chr2 86 X C 9 ........, X +chr2 87 X G 9 ....T..., X +chr3 60 X X C 6 ...G., +chr3 61 X X T 6 ..N.., +chr3 62 X X C 6 ...A., +chr3 63 X X C 7 .N...., +chr3 64 X X A 7 ...G.., +chr3 65 X X T 7 ...AA., +chr3 66 X X A 7 ....N.,
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/column_join_out4.pileup Tue Apr 01 09:30:45 2014 -0400 @@ -0,0 +1,65 @@ +0610009D07Rik 2 2 3 2 4 2 +0610010K14Rik 1 1 1 1 +1110002N22Rik 2 2 3 2 2 2 +1110008L16Rik 3 2 1 1 6 2 +1110037F02Rik 1 1 +1110054O05Rik 1 1 +1190005F20Rik 4 2 +Acot8 1 2 +Acta1 2 2 2 2 +Actb 1 2 2 2 +Actg1 2 2 1 2 +Actl6a 2 1 1 1 +Actl6b 1 1 1 2 +Actn1 1 1 +Actn4 1 1 +Bend3 1 1 +Bend5 1 1 +Bnc2 1 1 1 1 +Bptf 1 1 +Brip1 1 1 2 1 +Brms1l 1 2 +Btf3;Gm3531 1 1 1 2 +Bub3 2 2 3 1 1 2 +C1d 1 1 +C130039O16Rik 1 1 +C330007P06Rik 1 1 +Cad 4 1 1 1 +Calm1;Calm3;Calm2 2 1 1 1 +Caprin1 2 2 +Cbx1 2 2 +Cbx3 2 2 +E2f6 2 2 1 2 +E130012A19Rik 2 2 +Eed 1 2 1 1 +Efha1 1 1 +Exosc1 3 2 +Exosc10 25 2 +Gm189 1 2 1 2 2 2 +Gm3200 1 1 +Gm9855;Tdg 2 2 +Gm10079 2 1 +Gm11230 2 1 +Gm12620 1 1 +Gm13072;Trmt112 1 1 +Gm13092;LOC677017 1 1 1 2 +Gm14173;Rpl37a;Gm4149 1 2 +Gm14231 1 1 +Gm14393;2210418O10Rik;Gm14296;Gm14401;RP23-330D3.5 1 1 +Gm14456;Tpt1 1 1 +Gm15501;Rps8 1 1 +Sfrs7 1 2 +Sfrs11 3 2 4 2 +Sfrs12 2 2 +Sin3a 1 2 4 2 1 1 +Sirt7 1 1 1 1 +Ski 1 1 +Skil 1 1 +Skiv2l2 12 2 34 2 +Tubb2b 4 2 3 2 +Tubb2c 1 1 +Tubb2c-ps1 1 2 +Tubb4 1 1 +Zscan4-ps2 1 2 +Zscan4e 1 1 2 2 +Zscan4f 2 2 2 2 2 2