Mercurial > repos > galaxyp > mzsqlite_psm_align

comparison profmt.py @ 0:f2dc9805107a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mzsqlite_psm_align commit 464e05be1084ed9a65b542c8eabb18147d425666
author galaxyp
date Mon, 16 Apr 2018 18:00:53 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:f2dc9805107a
1 #!/usr/bin/env python
2 """
3 #
4 #------------------------------------------------------------------------------
5 # University of Minnesota
6 # Copyright 2018, Regents of the University of Minnesota
7 #------------------------------------------------------------------------------
8 # Author:
9 #
10 # James E Johnson
11 #
12 #------------------------------------------------------------------------------
13 """
14
15 import sys,re
16 from operator import itemgetter, attrgetter
17 from twobitreader import TwoBitFile
18
19
20 PROBAM_TAGS = ['NH', 'XO', 'XL', 'XP', 'YP', 'XF', 'XI', 'XB', 'XR', 'YB', 'YA', 'XS', 'XQ', 'XC', 'XA', 'XM', 'XN', 'XT', 'XE', 'XG', 'XU']
21
22
23 PROBAM_TYTPES = {
24 'NH' : 'i', #number of genomic locations to which the peptide sequence maps
25 'XO' : 'Z', #uniqueness of the peptide mapping
26 'XL' : 'i', #number of peptides to which the spectrum maps
27 'XP' : 'Z', #peptide sequence
28 'YP' : 'Z', #Protein accession ID from the original search result
29 'XF' : 'Z', #Reading frame of the peptide (0, 1, 2)
30 'XI' : 'f', #Peptide intensity
31 'XB' : 'Z', #massdiff; experimental mass; calculated mass massdiff can be calculated by experimental mass - calculated mass. If any number is unavailable, the value should be left blank (such as 0.01;;).
32 'XR' : 'Z', #reference peptide sequence
33 'YB' : 'Z', #Preceding amino acids (2 AA, B stands for before).
34 'YA' : 'Z', #Following amino acids (2 AA, A stands for after).
35 'XS' : 'f', #PSM score
36 'XQ' : 'f', #PSM FDR (i.e. q-value or 1-PEP).
37 'XC' : 'i', #peptide charge
38 'XA' : 'i', #Whether the peptide is annotated 0:yes; 1:parially unknown; 2:totally unknown;
39 'XM' : 'Z', #Modifications
40 'XN' : 'i', #Number of missed cleavages in the peptide (XP)
41 'XT' : 'i', #Enzyme specificity
42 'XE' : 'i', #Enzyme used in the experiment
43 'XG' : 'A', #Peptide type
44 'XU' : 'Z', #URI
45 }
46
47
48 PROBAM_DEFAULTS = {
49 'NH' : -1, #number of genomic locations to which the peptide sequence maps
50 'XO' : '*', #uniqueness of the peptide mapping
51 'XL' : -1, #number of peptides to which the spectrum maps
52 'XP' : '*', #peptide sequence
53 'YP' : '*', #Protein accession ID from the original search result
54 'XF' : '*', #Reading frame of the peptide (0, 1, 2)
55 'XI' : -1, #Peptide intensity
56 'XB' : '*', #massdiff; experimental mass; calculated mass massdiff can be calculated by experimental mass - calculated mass. If any number is unavailable, the value should be left blank (such as 0.01;;).
57 'XR' : '*', #reference peptide sequence
58 'YB' : '*', #Preceding amino acids (2 AA, B stands for before).
59 'YA' : '*', #Following amino acids (2 AA, A stands for after).
60 'XS' : -1, #PSM score
61 'XQ' : -1, #PSM FDR (i.e. q-value or 1-PEP).
62 'XC' : -1, #peptide charge
63 'XA' : -1, #Whether the peptide is annotated 0:yes; 1:parially unknown; 2:totally unknown;
64 'XM' : '*', #Modifications
65 'XN' : -1, #Number of missed cleavages in the peptide (XP)
66 'XT' : -1, #Enzyme specificity
67 'XE' : -1, #Enzyme used in the experiment
68 'XG' : '*', #Peptide type
69 'XU' : '*', #URI
70 }
71
72 def cmp_alphanumeric(s1,s2):
73 if s1 == s2:
74 return 0
75 a1 = re.findall("\d+|[a-zA-Z]+",s1)
76 a2 = re.findall("\d+|[a-zA-Z]+",s2)
77 for i in range(min(len(a1),len(a2))):
78 if a1[i] == a2[i]:
79 continue
80 if a1[i].isdigit() and a2[i].isdigit():
81 return int(a1[i]) - int(a2[i])
82 return 1 if a1[i] > a2[i] else -1
83 return len(a1) - len(a2)
84
85
86 def sort_chrom_names(names):
87 rnames = sorted(names,cmp=cmp_alphanumeric)
88 if 'chrM' in rnames:
89 rnames.remove('chrM')
90 rnames.insert(0,'chrM')
91 if 'MT' in rnames:
92 rnames.remove('MT')
93 rnames.append('MT')
94 return rnames
95
96
97 def as_int_list(obj):
98 if obj is None:
99 return None
100 if isinstance(obj, list):
101 return [int(x) for x in obj]
102 elif isinstance(obj, str):
103 return [int(x) for x in obj.split(',')]
104 else: # python2 unicode?
105 return [int(x) for x in str(obj).split(',')]
106
107
108 class ProBEDEntry (object):
109 def __init__(self, chrom, chromStart, chromEnd, name, score, strand,
110 blockCount, blockSizes, blockStarts,
111 protacc, peptide, uniqueness, genomeReference,
112 psmScore='.', fdr='.', mods='.', charge='.',
113 expMassToCharge='.', calcMassToCharge='.',
114 psmRank='.', datasetID='.', uri='.'):
115 self.chrom = chrom
116 self.chromStart = int(chromStart)
117 self.chromEnd = int(chromEnd)
118 self.name = name
119 self.score = int(score) if score is not None else 0
120 self.strand = '-' if str(strand).startswith('-') else '+'
121 self.thickStart = self.chromStart
122 self.thickEnd = self.chromEnd
123 self.itemRgb = '0'
124 self.blockCount = int(blockCount)
125 self.blockSizes = as_int_list(blockSizes)
126 self.blockStarts = as_int_list(blockStarts)
127 self.protacc = protacc
128 self.peptide = peptide
129 self.uniqueness = uniqueness
130 self.genomeReference = genomeReference
131 self.psmScore = psmScore
132 self.fdr = fdr
133 self.mods = mods
134 self.charge = charge
135 self.expMassToCharge = expMassToCharge
136 self.calcMassToCharge = calcMassToCharge
137 self.psmRank = psmRank
138 self.datasetID = datasetID
139 self.uri = uri
140
141 def __str__(self):
142 return '%s\t%d\t%d\t%s\t%d\t%s\t%d\t%d\t%s\t%d\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n' % \
143 (self.chrom, self.chromStart, self.chromEnd,
144 self.name, self.score, self.strand,
145 self.thickStart, self.thickEnd, self.itemRgb,
146 self.blockCount,
147 ','.join([str(x) for x in self.blockSizes]),
148 ','.join([str(x) for x in self.blockStarts]),
149 self.protacc, self.peptide, self.uniqueness,
150 self.genomeReference,
151 self.psmScore, self.fdr, self.mods,
152 self.charge, self.expMassToCharge, self.calcMassToCharge,
153 self.psmRank, self.datasetID, self.uri)
154
155
156 class ProBED ( object ):
157 def __init__(self,species=None,assembly=None,comments=[]):
158 self.species = species
159 self.assembly = assembly
160 self.comments = comments
161 self.entries = dict()
162
163 def add_entry(self,entry):
164 if not entry.chrom in self.entries:
165 self.entries[entry.chrom] = []
166 self.entries[entry.chrom].append(entry)
167
168 def write(self,fh):
169 rnames = sort_chrom_names(self.entries.keys())
170 for sn in rnames:
171 if sn not in self.entries:
172 continue
173 for pbe in sorted(self.entries[sn], key=attrgetter('chromStart','chromEnd')):
174 fh.write(str(pbe))
175
176
177 class ProBAMEntry (object):
178 def __init__(self, qname='', flag=0, rname='', pos=0, mapq=255, cigar='', rnext='*', pnext='0', tlen='0', seq='*', qual='*', optional=PROBAM_DEFAULTS):
179 self.qname = qname
180 self.flag = flag
181 self.rname = rname
182 self.pos = pos
183 self.mapq = mapq
184 self.cigar = cigar
185 self.rnext = rnext
186 self.pnext = pnext
187 self.tlen = tlen
188 self.seq = seq
189 self.qual = qual
190 self.optional = optional
191 def __str__(self):
192 opt_cols = '\t%s' % '\t'.join(['%s:%s:%s' % (t,PROBAM_TYTPES[t],self.optional[t]) for t in PROBAM_TAGS]) if self.optional else ''
193 return '%s\t%d\t%s\t%d\t%d\t%s\t%s\t%s\t%s\t%s\t%s%s' % (
194 self.qname,self.flag,self.rname,self.pos,self.mapq,self.cigar,
195 str(self.rnext) if self.rnext else '',
196 str(self.pnext) if self.pnext else '',
197 str(self.tlen) if self.tlen else '',
198 self.seq,
199 self.qual, opt_cols)
200 def add_optional(self,tag,value):
201 self.optional[tag] = value
202
203
204 class ProBAM ( object ):
205 def __init__(self,species=None,assembly=None,seqlens={},comments=[]):
206 self.species = species
207 self.assembly = assembly
208 self.seqlens = seqlens
209 self.comments = comments
210 self.entries = dict()
211 self.opt_columns = set()
212 self.rg = []
213
214 def add_entry(self,pb_entry):
215 if not pb_entry.rname in self.entries:
216 self.entries[pb_entry.rname] = []
217 self.entries[pb_entry.rname].append(pb_entry)
218 if pb_entry.optional:
219 self.opt_columns | set(pb_entry.optional.keys())
220
221 def add_entry_from_bed(self,bed_entry,optional=dict()):
222 if bed_entry.pep:
223 optional['XP:Z'] = bed_entry.pep
224 qname=bed_entry.name
225 flag = 0 if bed_entry.strand == '+' else 16
226 rname = bed_entry.chrom
227 pos = bed_entry.chromStart + 1
228 cigar = bed_entry.get_cigar()
229 seq = bed_entry.get_spliced_seq(strand='+') if bed_entry.seq else '*'
230 pb_entry = ProBAMEntry(qname=qname, flag=flag, rname=rname, pos=pos,cigar=cigar,seq=seq,optional=optional)
231 self.add_entry(pb_entry)
232
233 def write(self,fh):
234 fh.write('@HD VN:1.0 SO:coordinate\n')
235 rnames = sort_chrom_names(self.seqlens.keys())
236 for sn in rnames:
237 fh.write('@SQ\tSN:%s\tLN:%d\n' % (sn,self.seqlens[sn]))
238 for rg in self.rg:
239 fh.write('@RG\tID:%s\n' % (rg))
240 fh.write('@PG\tID:SampleSpecificGenerator\n')
241 for comment in self.comments:
242 fh.write('@CO\t%s\n' % comment)
243 for sn in rnames:
244 if sn not in self.entries:
245 continue
246 for pbe in sorted(self.entries[sn], key=attrgetter('pos')):
247 fh.write('%s\n' % str(pbe))