annotate mismatch_frequencies.py @ 28:bb3d962e8cb1 draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
author mvdbeek
date Sat, 22 Dec 2018 04:14:53 -0500
parents 6590be3f8e3f
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
1 import re
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
2 import string
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
3 import pysam
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
4 import matplotlib
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
5 import pandas as pd
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
6 from collections import defaultdict
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
7 from collections import OrderedDict
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
8 import argparse
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
9 import itertools
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
10
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
11 matplotlib.use('pdf')
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
12 import matplotlib.pyplot as plt # noqa: E402
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
13
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
14
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
15 class MismatchFrequencies:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
16 '''Iterate over a SAM/BAM alignment file, collecting reads with mismatches. One
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
17 class instance per alignment file. The result_dict attribute will contain a
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
18 nested dictionary with name, readlength and mismatch count.'''
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
19 def __init__(self, result_dict={}, alignment_file=None, name="name", minimal_readlength=21,
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
20 maximal_readlength=21,
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
21 number_of_allowed_mismatches=1,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
22 ignore_5p_nucleotides=0,
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
23 ignore_3p_nucleotides=0,
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
24 possible_mismatches=[
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
25 'AC', 'AG', 'AT',
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
26 'CA', 'CG', 'CT',
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
27 'GA', 'GC', 'GT',
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
28 'TA', 'TC', 'TG'
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
29 ]):
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
30
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
31 self.result_dict = result_dict
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
32 self.name = name
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
33 self.minimal_readlength = minimal_readlength
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
34 self.maximal_readlength = maximal_readlength
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
35 self.number_of_allowed_mismatches = number_of_allowed_mismatches
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
36 self.ignore_5p_nucleotides = ignore_5p_nucleotides
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
37 self.ignore_3p_nucleotides = ignore_3p_nucleotides
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
38 self.possible_mismatches = possible_mismatches
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
39
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
40 if alignment_file:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
41 self.pysam_alignment = pysam.Samfile(alignment_file)
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
42 self.references = self.pysam_alignment.references # names of fasta reference sequences
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
43 result_dict[name] = self.get_mismatches(
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
44 self.pysam_alignment,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
45 minimal_readlength,
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
46 maximal_readlength,
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
47 possible_mismatches
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
48 )
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
49
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
50 def get_mismatches(self, pysam_alignment, minimal_readlength,
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
51 maximal_readlength, possible_mismatches):
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
52 rec_dd = lambda: defaultdict(rec_dd)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
53 len_dict = rec_dd()
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
54 for alignedread in pysam_alignment:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
55 if self.read_is_valid(alignedread, minimal_readlength, maximal_readlength):
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
56 chromosome = pysam_alignment.getrname(alignedread.rname)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
57 try:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
58 len_dict[int(alignedread.rlen)][chromosome]['total valid reads'] += 1
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
59 except TypeError:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
60 len_dict[int(alignedread.rlen)][chromosome]['total valid reads'] = 1
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
61 MD = alignedread.opt('MD')
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
62 if self.read_has_mismatch(alignedread, self.number_of_allowed_mismatches):
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
63 (ref_base, mismatch_base) = self.read_to_reference_mismatch(MD, alignedread.seq, alignedread.is_reverse)
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
64 if not ref_base:
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
65 continue
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
66 else:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
67 for i, base in enumerate(ref_base):
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
68 if not ref_base[i]+mismatch_base[i] in possible_mismatches:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
69 continue
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
70 try:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
71 len_dict[int(alignedread.rlen)][chromosome][ref_base[i]+mismatch_base[i]] += 1
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
72 except TypeError:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
73 len_dict[int(alignedread.rlen)][chromosome][ref_base[i]+mismatch_base[i]] = 1
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
74 return len_dict
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
75
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
76 def read_is_valid(self, read, min_readlength, max_readlength):
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
77 '''Filter out reads that are unmatched, too short or
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
78 too long or that contian insertions'''
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
79 if read.is_unmapped:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
80 return False
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
81 if read.rlen < min_readlength:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
82 return False
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
83 if read.rlen > max_readlength:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
84 return False
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
85 else:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
86 return True
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
87
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
88 def read_has_mismatch(self, read, number_of_allowed_mismatches=1):
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
89 '''keep only reads with one mismatch. Could be simplified'''
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
90 NM = read.opt('NM')
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
91 if NM < 1: # filter out reads with no mismatch
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
92 return False
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
93 if NM > number_of_allowed_mismatches: # filter out reads with more than 1 mismtach
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
94 return False
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
95 else:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
96 return True
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
97
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
98 def mismatch_in_allowed_region(self, readseq, mismatch_position):
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
99 '''
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
100 >>> M = MismatchFrequencies()
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
101 >>> readseq = 'AAAAAA'
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
102 >>> mismatch_position = 2
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
103 >>> M.mismatch_in_allowed_region(readseq, mismatch_position)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
104 True
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
105 >>> M = MismatchFrequencies(ignore_3p_nucleotides=2, ignore_5p_nucleotides=2)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
106 >>> readseq = 'AAAAAA'
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
107 >>> mismatch_position = 1
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
108 >>> M.mismatch_in_allowed_region(readseq, mismatch_position)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
109 False
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
110 >>> readseq = 'AAAAAA'
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
111 >>> mismatch_position = 4
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
112 >>> M.mismatch_in_allowed_region(readseq, mismatch_position)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
113 False
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
114 '''
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
115 mismatch_position += 1 # To compensate for starting the count at 0
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
116 five_p = self.ignore_5p_nucleotides
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
117 three_p = self.ignore_3p_nucleotides
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
118 if any([five_p > 0, three_p > 0]):
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
119 if any([mismatch_position <= five_p,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
120 mismatch_position >= (len(readseq) + 1 - three_p)]): # Again compensate for starting the count at 0
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
121 return False
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
122 else:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
123 return True
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
124 else:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
125 return True
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
126
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
127 def read_to_reference_mismatch(self, MD, readseq, is_reverse):
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
128 '''
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
129 This is where the magic happens. The MD tag contains SNP and indel information,
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
130 without looking to the genome sequence. This is a typical MD tag: 3C0G2A6.
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
131 3 bases of the read align to the reference, followed by a mismatch, where the
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
132 reference base is C, followed by 10 bases aligned to the reference.
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
133 suppose a reference 'CTTCGATAATCCTT'
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
134 ||| || ||||||
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
135 and a read 'CTTATATTATCCTT'.
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
136 This situation is represented by the above MD tag.
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
137 Given MD tag and read sequence this function returns the reference base C, G and A,
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
138 and the mismatched base A, T, T.
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
139 >>> M = MismatchFrequencies()
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
140 >>> MD='3C0G2A7'
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
141 >>> seq='CTTATATTATCCTT'
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
142 >>> result=M.read_to_reference_mismatch(MD, seq, is_reverse=False)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
143 >>> result[0]=="CGA"
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
144 True
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
145 >>> result[1]=="ATT"
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
146 True
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
147 >>>
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
148 '''
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
149 search = re.finditer('[ATGC]', MD)
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
150 if '^' in MD:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
151 print 'WARNING insertion detected, mismatch calling skipped for this read!!!'
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
152 return (None, None)
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
153 start_index = 0 # refers to the leading integer of the MD string before an edited base
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
154 current_position = 0 # position of the mismatched nucleotide in the MD tag string
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
155 mismatch_position = 0 # position of edited base in current read
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
156 reference_base = ""
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
157 mismatched_base = ""
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
158 for result in search:
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
159 current_position = result.start()
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
160 mismatch_position = mismatch_position + 1 + int(MD[start_index:current_position]) # converts the leading characters before an edited base into integers
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
161 start_index = result.end()
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
162 reference_base += MD[result.end() - 1]
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
163 mismatched_base += readseq[mismatch_position - 1]
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
164 if is_reverse:
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
165 reference_base = reverseComplement(reference_base)
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
166 mismatched_base = reverseComplement(mismatched_base)
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
167 mismatch_position = len(readseq)-mismatch_position-1
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
168 if mismatched_base == 'N':
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
169 return (None, None)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
170 if self.mismatch_in_allowed_region(readseq, mismatch_position):
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
171 return (reference_base, mismatched_base)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
172 else:
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
173 return (None, None)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
174
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
175
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
176 def reverseComplement(sequence):
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
177 '''do a reverse complement of DNA base.
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
178 >>> reverseComplement('ATGC')=='GCAT'
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
179 True
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
180 >>>
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
181 '''
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
182 sequence = sequence.upper()
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
183 complement = string.maketrans('ATCGN', 'TAGCN')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
184 return sequence.upper().translate(complement)[::-1]
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
185
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
186
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
187 def barplot(df, library, axes):
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
188 df.plot(kind='bar', ax=axes, subplots=False,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
189 stacked=False, legend='test',
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
190 title='Mismatch frequencies for {0}'.format(library))
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
191
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
192
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
193 def df_to_tab(df, output):
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
194 df.to_csv(output, sep='\t')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
195
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
196
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
197 def reduce_result(df, possible_mismatches):
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
198 '''takes a pandas dataframe with full mismatch details and
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
199 summarises the results for plotting.'''
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
200 alignments = df['Alignment_file'].unique()
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
201 readlengths = df['Readlength'].unique()
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
202 combinations = itertools.product(*[alignments, readlengths]) # generate all possible combinations of readlength and alignment files
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
203 reduced_dict = {}
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
204 last_column = 3 + len(possible_mismatches)
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
205 for combination in combinations:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
206 library_subset = df[df['Alignment_file'] == combination[0]]
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
207 library_readlength_subset = library_subset[library_subset['Readlength'] == combination[1]]
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
208 sum_of_library_and_readlength = library_readlength_subset.iloc[:, 3:last_column+1].sum()
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
209 if combination[0] not in reduced_dict:
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
210 reduced_dict[combination[0]] = {}
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
211 reduced_dict[combination[0]][combination[1]] = sum_of_library_and_readlength.to_dict()
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
212 return reduced_dict
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
213
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
214
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
215 def plot_result(reduced_dict, args):
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
216 names = reduced_dict.keys()
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
217 nrows = len(names) / 2 + 1
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
218 fig = plt.figure(figsize=(16, 32))
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
219 for i, library in enumerate(names):
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
220 axes = fig.add_subplot(nrows, 2, i+1)
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
221 library_dict = reduced_dict[library]
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
222 df = pd.DataFrame(library_dict)
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
223 df.drop(['total aligned reads'], inplace=True)
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
224 barplot(df, library, axes),
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
225 axes.set_ylabel('Mismatch count / all valid reads * readlength')
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
226 fig.savefig(args.output_pdf, format='pdf')
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
227
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
228
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
229 def format_result_dict(result_dict, chromosomes, possible_mismatches):
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
230 '''Turn nested dictionary into preformatted tab seperated lines'''
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
231 header = "Reference sequence\tAlignment_file\tReadlength\t" + "\t".join(
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
232 possible_mismatches) + "\ttotal aligned reads"
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
233 libraries = result_dict.keys()
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
234 readlengths = result_dict[libraries[0]].keys()
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
235 result = []
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
236 for chromosome in chromosomes:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
237 for library in libraries:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
238 for readlength in readlengths:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
239 line = []
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
240 line.extend([chromosome, library, readlength])
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
241 try:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
242 line.extend([result_dict[library][readlength][chromosome].get(mismatch, 0) for mismatch in possible_mismatches])
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
243 line.extend([result_dict[library][readlength][chromosome].get(u'total valid reads', 0)])
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
244 except KeyError:
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
245 line.extend([0 for mismatch in possible_mismatches])
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
246 line.extend([0])
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
247 result.append(line)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
248 df = pd.DataFrame(result, columns=header.split('\t'))
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
249 last_column = 3 + len(possible_mismatches)
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
250 df['mismatches/per aligned nucleotides'] = df.iloc[:, 3:last_column].sum(1)/(df.iloc[:, last_column] * df['Readlength'])
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
251 return df
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
252
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
253
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
254 def setup_MismatchFrequencies(args):
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
255 resultDict = OrderedDict()
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
256 kw_list = [{'result_dict': resultDict,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
257 'alignment_file': alignment_file,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
258 'name': name,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
259 'minimal_readlength': args.min,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
260 'maximal_readlength': args.max,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
261 'number_of_allowed_mismatches': args.n_mm,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
262 'ignore_5p_nucleotides': args.five_p,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
263 'ignore_3p_nucleotides': args.three_p,
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
264 'possible_mismatches': args.possible_mismatches}
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
265 for alignment_file, name in zip(args.input, args.name)]
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
266 return (kw_list, resultDict)
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
267
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
268
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
269 def nested_dict_to_df(dictionary):
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
270 dictionary = {(outerKey, innerKey): values for outerKey, innerDict in dictionary.iteritems() for innerKey, values in innerDict.iteritems()}
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
271 df = pd.DataFrame.from_dict(dictionary).transpose()
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
272 df.index.names = ['Library', 'Readlength']
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
273 return df
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
274
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
275
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
276 def run_MismatchFrequencies(args):
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
277 kw_list, resultDict = setup_MismatchFrequencies(args)
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
278 references = [MismatchFrequencies(**kw_dict).references for kw_dict in kw_list]
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
279 return (resultDict, references[0])
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
280
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
281
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
282 def main():
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
283 result_dict, references = run_MismatchFrequencies(args)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
284 df = format_result_dict(result_dict, references, args.possible_mismatches)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
285 reduced_dict = reduce_result(df, args.possible_mismatches)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
286 plot_result(reduced_dict, args)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
287 reduced_df = nested_dict_to_df(reduced_dict)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
288 df_to_tab(reduced_df, args.output_tab)
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
289 if args.expanded_output_tab:
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
290 df_to_tab(df, args.expanded_output_tab)
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
291 return reduced_dict
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
292
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
293 if __name__ == "__main__":
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
294
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
295 parser = argparse.ArgumentParser(description='Produce mismatch statistics for BAM/SAM alignment files.')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
296 parser.add_argument('--input', nargs='*', help='Input files in SAM/BAM format')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
297 parser.add_argument('--name', nargs='*', help='Name for input file to display in output file. Should have same length as the number of inputs')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
298 parser.add_argument('--output_pdf', help='Output filename for graph')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
299 parser.add_argument('--output_tab', help='Output filename for table')
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
300 parser.add_argument('--expanded_output_tab', default=None, help='Output filename for table')
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
301 parser.add_argument('--possible_mismatches', default=[
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
302 'AC', 'AG', 'AT', 'CA', 'CG', 'CT', 'GA', 'GC', 'GT', 'TA', 'TC', 'TG'
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
303 ], nargs='+', help='specify mismatches that should be counted for the mismatch frequency. The format is Reference base -> observed base, eg AG for A to G mismatches.')
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
304 parser.add_argument('--min', '--minimal_readlength', type=int, help='minimum readlength')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
305 parser.add_argument('--max', '--maximal_readlength', type=int, help='maximum readlength')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
306 parser.add_argument('--n_mm', '--number_allowed_mismatches', type=int, default=1, help='discard reads with more than n mismatches')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
307 parser.add_argument('--five_p', '--ignore_5p_nucleotides', type=int, default=0, help='when calculating nucleotide mismatch frequencies ignore the first N nucleotides of the read')
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
308 parser.add_argument('--three_p', '--ignore_3p_nucleotides', type=int, default=1, help='when calculating nucleotide mismatch frequencies ignore the last N nucleotides of the read')
28
bb3d962e8cb1 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
mvdbeek
parents: 24
diff changeset
309 # args = parser.parse_args(['--input', '3mismatches_ago2ip_s2.bam', '3mismatches_ago2ip_ovary.bam','--possible_mismatches','AC','AG', 'CG', 'TG', 'CT','--name', 'Siomi1', 'Siomi2' , '--five_p', '3','--three_p','3','--output_pdf', 'out.pdf', '--output_tab', 'out.tab', '--expanded_output_tab', 'expanded.tab', '--min', '20', '--max', '22'])
12
848d799e6fe8 Uploaded
mvdbeek
parents:
diff changeset
310 args = parser.parse_args()
24
6590be3f8e3f planemo upload for repository https://bitbucket.org/drosofff/gedtools/
mvdbeek
parents: 22
diff changeset
311 reduced_dict = main()