comparison tools/ilmn_pacbio/assembly_stats.py @ 0:9071e359b9a3

Uploaded
author xuebing
date Fri, 09 Mar 2012 19:37:19 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:9071e359b9a3
1 #!/usr/bin/env python
2 #
3 #Copyright (c) 2011, Pacific Biosciences of California, Inc.
4 #
5 #All rights reserved.
6 #
7 #Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
8 # * Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
9 # * Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
10 # * Neither the name of Pacific Biosciences nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
11 #
12 #THIS SOFTWARE IS PROVIDED BY PACIFIC BIOSCIENCES AND ITS CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
13 #WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL PACIFIC BIOSCIENCES OR ITS CONTRIBUTORS BE LIABLE FOR ANY
14 #DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
15 #LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
16 #(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
17 #
18 import sys, os
19 from optparse import OptionParser
20 from galaxy import eggs
21 import pkg_resources
22 pkg_resources.require( 'bx-python' )
23 from bx.seq.fasta import FastaReader
24
25 def getStats( fastaFile, genomeLength, minContigLength ):
26 lengths = []
27 stats = { "Num" : 0,
28 "Sum" : 0,
29 "Max" : 0,
30 "Avg" : 0,
31 "N50" : 0,
32 "99%" : 0 }
33 fasta_reader = FastaReader( open( fastaFile, 'rb' ) )
34 while True:
35 seq = fasta_reader.next()
36 if not seq:
37 break
38 if seq.length < minContigLength:
39 continue
40 lengths.append( seq.length )
41 if lengths:
42 stats[ 'Num' ] = len( lengths )
43 stats[ 'Sum' ] = sum( lengths )
44 stats[ 'Max' ] = max( lengths )
45 stats[ 'Avg' ] = int( sum( lengths ) / float( len( lengths ) ) )
46 stats[ 'N50' ] = 0
47 stats[ '99%' ] = 0
48 if genomeLength == 0:
49 genomeLength = sum( lengths )
50 lengths.sort()
51 lengths.reverse()
52 lenSum = 0
53 stats[ "99%" ] = len( lengths )
54 for idx, length in enumerate( lengths ):
55 lenSum += length
56 if ( lenSum > genomeLength / 2 ):
57 stats[ "N50" ] = length
58 break
59 lenSum = 0
60 for idx, length in enumerate( lengths ):
61 lenSum += length
62 if lenSum > genomeLength * 0.99:
63 stats[ "99%" ] = idx + 1
64 break
65 return stats
66
67 def __main__():
68 #Parse Command Line
69 usage = 'Usage: %prog input output --minContigLength'
70 parser = OptionParser( usage=usage )
71 parser.add_option( "--minContigLength", dest="minContigLength", help="Minimum length of contigs to analyze" )
72 parser.add_option( "--genomeLength", dest="genomeLength", help="Length of genome for which to calculate N50s" )
73 parser.set_defaults( minContigLength=0, genomeLength=0 )
74 options, args = parser.parse_args()
75 input_fasta_file = args[ 0 ]
76 output_tabular_file = args[ 1 ]
77 statKeys = "Num Sum Max Avg N50 99%".split( " " )
78 stats = getStats( input_fasta_file, int( options.genomeLength ), int( options.minContigLength ) )
79 fout = open( output_tabular_file, "w" )
80 fout.write( "%s\n" % "\t".join( map( lambda key: str( stats[ key ] ), statKeys ) ) )
81 fout.close()
82
83 if __name__=="__main__": __main__()