protk 1.2.6.pre5 → 1.3.0.pre1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +84 -45
- data/bin/add_retention_times.rb +9 -5
- data/bin/augustus_to_proteindb.rb +7 -11
- data/bin/interprophet.rb +28 -46
- data/bin/make_decoy.rb +16 -48
- data/bin/mascot_search.rb +57 -71
- data/bin/mascot_to_pepxml.rb +13 -26
- data/bin/msgfplus_search.rb +70 -107
- data/bin/omssa_search.rb +52 -109
- data/bin/peptide_prophet.rb +44 -119
- data/bin/pepxml_to_table.rb +24 -27
- data/bin/protein_prophet.rb +22 -82
- data/bin/protxml_to_gff.rb +22 -519
- data/bin/protxml_to_table.rb +2 -16
- data/bin/sixframe.rb +10 -32
- data/bin/tandem_search.rb +30 -403
- data/bin/tandem_to_pepxml.rb +43 -0
- data/bin/unimod_to_loc.rb +1 -1
- data/ext/{protk/decoymaker → decoymaker}/decoymaker.c +74 -21
- data/ext/decoymaker/extconf.rb +3 -0
- data/lib/protk/constants.rb +16 -2
- data/lib/protk/data/default_config.yml +2 -1
- data/lib/protk/data/tandem_gpm_defaults.xml +175 -0
- data/lib/protk/data/tandem_isb_kscore_defaults.xml +123 -0
- data/lib/protk/data/tandem_isb_native_defaults.xml +123 -0
- data/lib/protk/data/tandem_params.xml +17 -54
- data/lib/protk/fastadb.rb +2 -2
- data/lib/protk/prophet_tool.rb +1 -1
- data/lib/protk/protxml_to_gff_tool.rb +474 -0
- data/lib/protk/search_tool.rb +58 -103
- data/lib/protk/setup_rakefile.rake +9 -5
- data/lib/protk/tandem_search_tool.rb +256 -0
- data/lib/protk/tool.rb +85 -104
- data/lib/protk.rb +1 -6
- metadata +24 -103
- data/bin/annotate_ids.rb +0 -59
- data/bin/asapratio.rb +0 -27
- data/bin/blastxml_to_table.rb +0 -119
- data/bin/correct_omssa_retention_times.rb +0 -27
- data/bin/feature_finder.rb +0 -95
- data/bin/file_convert.rb +0 -164
- data/bin/generate_omssa_loc.rb +0 -42
- data/bin/gffmerge.rb +0 -208
- data/bin/libra.rb +0 -70
- data/bin/toppas_pipeline.rb +0 -84
- data/bin/uniprot_annotation.rb +0 -141
- data/bin/xls_to_table.rb +0 -52
- data/bin/xpress.rb +0 -27
- data/ext/protk/decoymaker/extconf.rb +0 -3
- data/ext/protk/simplealign/extconf.rb +0 -3
- data/lib/protk/biotools_excel_converter.rb +0 -60
- data/lib/protk/eupathdb_gene_information_table.rb +0 -158
- data/lib/protk/gapped_aligner.rb +0 -264
- data/lib/protk/protein_annotator.rb +0 -646
- data/lib/protk/spreadsheet_extensions.rb +0 -79
- data/lib/protk/xtandem_defaults.rb +0 -11
@@ -1,646 +0,0 @@
|
|
1
|
-
require 'rubygems'
|
2
|
-
require 'spreadsheet'
|
3
|
-
require 'protk/swissprot_database'
|
4
|
-
require 'protk/bio_sptr_extensions'
|
5
|
-
require 'protk/protxml'
|
6
|
-
require 'protk/spreadsheet_extensions'
|
7
|
-
require 'protk/biotools_excel_converter'
|
8
|
-
require 'protk/plasmodb'
|
9
|
-
require 'protk/constants'
|
10
|
-
|
11
|
-
|
12
|
-
class ProteinAnnotator < Object
|
13
|
-
|
14
|
-
|
15
|
-
def initialize()
|
16
|
-
@genv = Constants.new()
|
17
|
-
end
|
18
|
-
|
19
|
-
def env
|
20
|
-
return @genv
|
21
|
-
end
|
22
|
-
|
23
|
-
def outputBookFromExcelInput(inputFile,numrows=0)
|
24
|
-
|
25
|
-
# Open the original excel workbook for reading
|
26
|
-
inputBook = Spreadsheet.open "#{inputFile}"
|
27
|
-
|
28
|
-
return inputBook.copyBook(numrows)
|
29
|
-
|
30
|
-
end
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
# Combines results from prot and pep xml files
|
35
|
-
#
|
36
|
-
def outputBookFromProtXMLAndPepXML(inputFileProt,inputFilePep,numrows=0)
|
37
|
-
protxml=ProtXML.new(inputFileProt)
|
38
|
-
|
39
|
-
# By default here we don't report anything with a probability less than 0.6
|
40
|
-
# This should be a user parameter someday
|
41
|
-
#
|
42
|
-
rows=protxml.as_rows(0.6)
|
43
|
-
|
44
|
-
# Figure out how many rows to convert if not specified
|
45
|
-
#
|
46
|
-
if ( numrows==0 || numrows >= rows.length)
|
47
|
-
numrows=rows.length
|
48
|
-
else
|
49
|
-
rows=rows[0...numrows]
|
50
|
-
end
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
# Create a new workbook from scratch for writing
|
55
|
-
outputBook = Spreadsheet::Workbook.new
|
56
|
-
outputSheet = outputBook.create_worksheet
|
57
|
-
|
58
|
-
rows.reverse!
|
59
|
-
|
60
|
-
rows.each { |row|
|
61
|
-
outputSheet.insert_row(0,row)
|
62
|
-
}
|
63
|
-
|
64
|
-
outputBook
|
65
|
-
end
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
# Takes a prot.xml file as input and returns an excel workbook with a single column containing the Accessions of proteins in the file
|
71
|
-
# The header of the accessions column will be 'Accessions'
|
72
|
-
# If a protein has 'indistinguishable proteins' each of those is given a separate line
|
73
|
-
#
|
74
|
-
# Throws an error if no proteins could be found in the prot.xml file
|
75
|
-
# In addition to the Accessions column, other information will be extracted from the file including
|
76
|
-
# 1. A list of indistinguishable proteins
|
77
|
-
# 2. The number of peptides on which the ID was based
|
78
|
-
# 3. The protein probability
|
79
|
-
# 4. A ; separated list of peptides on which the ID is based
|
80
|
-
# 5. Percent coverage for the protein
|
81
|
-
#
|
82
|
-
def outputBookFromProtXML(inputFile,numrows=0)
|
83
|
-
protxml=ProtXML.new(inputFile)
|
84
|
-
|
85
|
-
# By default here we don't report anything with a probability less than 0.6
|
86
|
-
# This should be a user parameter someday
|
87
|
-
#
|
88
|
-
rows=protxml.as_rows(0.6)
|
89
|
-
|
90
|
-
# Figure out how many rows to convert if not specified
|
91
|
-
#
|
92
|
-
if ( numrows==0 || numrows>=rows.length)
|
93
|
-
numrows=rows.length
|
94
|
-
else
|
95
|
-
rows=rows[0...numrows]
|
96
|
-
end
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
# Create a new workbook from scratch for writing
|
101
|
-
outputBook = Spreadsheet::Workbook.new
|
102
|
-
outputSheet = outputBook.create_worksheet
|
103
|
-
|
104
|
-
rows.reverse!
|
105
|
-
|
106
|
-
rows.each { |row|
|
107
|
-
outputSheet.insert_row(0,row)
|
108
|
-
}
|
109
|
-
|
110
|
-
outputBook
|
111
|
-
end
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
# Takes a biotools outputted excel file and produces an excel workbook with a single Accessions column of proteins
|
120
|
-
#
|
121
|
-
def outputBookFromBiotoolsExcel(inputFile,numrows=0)
|
122
|
-
converter=BioToolsExcelConverter.new(inputFile)
|
123
|
-
rows=converter.get_rows
|
124
|
-
|
125
|
-
# Create a new workbook from scratch for writing
|
126
|
-
outputBook = Spreadsheet::Workbook.new
|
127
|
-
outputSheet = outputBook.create_worksheet
|
128
|
-
|
129
|
-
rows.reverse!
|
130
|
-
|
131
|
-
rows.each { |row|
|
132
|
-
outputSheet.insert_row(0,row)
|
133
|
-
}
|
134
|
-
|
135
|
-
outputBook
|
136
|
-
|
137
|
-
|
138
|
-
end
|
139
|
-
|
140
|
-
# Takes a WarpLC Protein List file as input and returns an excel workbook with a single column containing the Accessions of proteins in the file
|
141
|
-
# The header of the accessions column will be 'Accessions'
|
142
|
-
# Throws an error if no proteins could be found in the WarpLC file .. this could also happen if the file is the wrong format
|
143
|
-
#
|
144
|
-
def outputBookFromWarpLCInput(inputFile,numrows=0)
|
145
|
-
file=File.new(inputFile)
|
146
|
-
xmldoc=REXML::Document.new(file)
|
147
|
-
accessions=REXML::XPath.match(xmldoc,"//ProteinReport/Protein")
|
148
|
-
if ( accessions==nil )
|
149
|
-
throw "No proteins found in the WarpLC Proteinlist file #{inputFile}"
|
150
|
-
end
|
151
|
-
accessions=accessions.collect { |el| el.attributes['Accession']}
|
152
|
-
accessions.insert(0,"Accession")
|
153
|
-
|
154
|
-
# Figure out how many rows to convert if not specified
|
155
|
-
if ( numrows==0 || numrows>accessions.length)
|
156
|
-
numrows=accessions.length+1
|
157
|
-
else
|
158
|
-
accessions=accessions[0...numrows]
|
159
|
-
end
|
160
|
-
|
161
|
-
|
162
|
-
|
163
|
-
# Create a new workbook from scratch for writing
|
164
|
-
outputBook = Spreadsheet::Workbook.new
|
165
|
-
outputSheet = outputBook.create_worksheet
|
166
|
-
|
167
|
-
outputSheet.insert_column(accessions,0)
|
168
|
-
|
169
|
-
outputBook
|
170
|
-
end
|
171
|
-
|
172
|
-
# First looks at the file extension. If it is xls then filetype 'xls' is returned.
|
173
|
-
# Otherwise, we assume the file is XML
|
174
|
-
#
|
175
|
-
def isExcelFile(fileName,input_type)
|
176
|
-
if ( input_type=="excel")
|
177
|
-
return true
|
178
|
-
end
|
179
|
-
|
180
|
-
ext=fileName.split(".").last
|
181
|
-
if(ext=="xls")
|
182
|
-
return true
|
183
|
-
end
|
184
|
-
return false
|
185
|
-
end
|
186
|
-
|
187
|
-
def isProtXMLFile(fileName,input_type)
|
188
|
-
if ( input_type=="protXML")
|
189
|
-
return true
|
190
|
-
end
|
191
|
-
|
192
|
-
|
193
|
-
if ( fileName.match(/\.prot\.xml$/) != nil )
|
194
|
-
return true
|
195
|
-
else
|
196
|
-
return false
|
197
|
-
end
|
198
|
-
end
|
199
|
-
|
200
|
-
def isBioToolsFile(fileName,input_type)
|
201
|
-
BioToolsExcelConverter.isBiotools(fileName)
|
202
|
-
end
|
203
|
-
|
204
|
-
# Given a worksheet with a column called 'Status' change true values to 'Validated' and false values to 'Potential'
|
205
|
-
def renameValuesInColumn(workSheet,colIndex,from,to)
|
206
|
-
workSheet.rows.each { |row|
|
207
|
-
if ( row[colIndex]==from)
|
208
|
-
row[colIndex]=to
|
209
|
-
end
|
210
|
-
}
|
211
|
-
end
|
212
|
-
|
213
|
-
def hasAccession(row)
|
214
|
-
hasit=false
|
215
|
-
row.each do|cell|
|
216
|
-
if (cell.to_s=="Accession")
|
217
|
-
hasit=true
|
218
|
-
end
|
219
|
-
end
|
220
|
-
hasit
|
221
|
-
end
|
222
|
-
|
223
|
-
def row_is_empty(row)
|
224
|
-
isempty=true
|
225
|
-
if (row==nil)
|
226
|
-
return true
|
227
|
-
end
|
228
|
-
|
229
|
-
row.each do |cell|
|
230
|
-
if ( cell!=nil && cell.to_s!="")
|
231
|
-
isempty=false
|
232
|
-
end
|
233
|
-
end
|
234
|
-
isempty
|
235
|
-
end
|
236
|
-
|
237
|
-
def convert(inputFile,outputFile,input_type=nil,output_type="xls",numrows=0,accessionColumnName="Accession",entrezIDColumnName="Entrez.ID",hiddenColumns=[])
|
238
|
-
|
239
|
-
@genv.log("Converting #{inputFile} to #{outputFile}",:info)
|
240
|
-
|
241
|
-
Spreadsheet.client_encoding = 'UTF-8'
|
242
|
-
|
243
|
-
|
244
|
-
case true
|
245
|
-
when isExcelFile(inputFile,input_type)
|
246
|
-
@genv.log("Excel file was biotools",:info)
|
247
|
-
if ( isBioToolsFile(inputFile,input_type))
|
248
|
-
outputBook=outputBookFromBiotoolsExcel(inputFile,numrows)
|
249
|
-
else
|
250
|
-
@genv.log("Excel file was non biotools",:info)
|
251
|
-
outputBook=outputBookFromExcelInput(inputFile,numrows)
|
252
|
-
end
|
253
|
-
outputSheet=outputBook.worksheet 0
|
254
|
-
when isProtXMLFile(inputFile,input_type)
|
255
|
-
@genv.log("Got a Prot XML File as Input",:info)
|
256
|
-
outputBook=outputBookFromProtXML(inputFile,numrows)
|
257
|
-
outputSheet=outputBook.worksheet 0
|
258
|
-
else
|
259
|
-
@genv.log("File is not prot.xml or excel .. trying WarpLCResult",:info)
|
260
|
-
outputBook=outputBookFromWarpLCInput(inputFile,numrows)
|
261
|
-
outputSheet=outputBook.worksheet 0
|
262
|
-
end
|
263
|
-
|
264
|
-
# Chop off and save any rows prior to the header and remove any empty rows
|
265
|
-
#
|
266
|
-
rows_for_deletion=[]
|
267
|
-
header_row=nil
|
268
|
-
keep_rows=[]
|
269
|
-
rowi=0
|
270
|
-
outputSheet.each do |row|
|
271
|
-
|
272
|
-
if ( !row_is_empty(row) && header_row==nil && hasAccession(row))
|
273
|
-
header_row=rowi
|
274
|
-
end
|
275
|
-
|
276
|
-
if (row_is_empty(row) || header_row==nil)
|
277
|
-
rows_for_deletion.push(rowi)
|
278
|
-
end
|
279
|
-
|
280
|
-
if (header_row==nil)
|
281
|
-
keep_rows.push(row)
|
282
|
-
end
|
283
|
-
rowi=rowi+1
|
284
|
-
end
|
285
|
-
|
286
|
-
deletion_index=0
|
287
|
-
rows_for_deletion.each do |i|
|
288
|
-
outputSheet.delete_row(i-deletion_index)
|
289
|
-
deletion_index=deletion_index+1
|
290
|
-
end
|
291
|
-
|
292
|
-
header=outputSheet.row 0
|
293
|
-
lastcolIndex=0
|
294
|
-
accessionColumn=nil
|
295
|
-
|
296
|
-
# Grab the accession column
|
297
|
-
for i in 0...header.length
|
298
|
-
if ( header[i]==accessionColumnName)
|
299
|
-
accessionColumn=outputSheet.column i
|
300
|
-
accessionColumnIndex=i
|
301
|
-
end
|
302
|
-
if ( header[i]=="" && lastcolIndex==0)
|
303
|
-
lastcolIndex=i
|
304
|
-
end
|
305
|
-
|
306
|
-
if ( header[i]=="OK")
|
307
|
-
header[i]="Status"
|
308
|
-
renameValuesInColumn(outputSheet,i,"true","Validated")
|
309
|
-
renameValuesInColumn(outputSheet,i,"false","Contaminant")
|
310
|
-
end
|
311
|
-
|
312
|
-
end
|
313
|
-
|
314
|
-
# If we didn't find an empty column then just set lastcolIndex to i
|
315
|
-
if ( lastcolIndex==0)
|
316
|
-
lastcolIndex=i
|
317
|
-
end
|
318
|
-
|
319
|
-
if ( accessionColumn==nil)
|
320
|
-
throw "No Accession column in input excel file. One column must have the header 'Accession'"
|
321
|
-
end
|
322
|
-
|
323
|
-
ids = accessionColumn.collect { |id|
|
324
|
-
if ( id!=nil)
|
325
|
-
id
|
326
|
-
else
|
327
|
-
""
|
328
|
-
end
|
329
|
-
}
|
330
|
-
# Remove the 0th value because it is the header
|
331
|
-
ids.delete_at(0)
|
332
|
-
|
333
|
-
#### Now grab some additional column information from uniprot ####
|
334
|
-
|
335
|
-
# Create a Hash with keys corresponding to the keys returned by uniprot.parse and with values corresponding to arrays of column values
|
336
|
-
# We start the columns off with the header name
|
337
|
-
newColumns={'recname'=>["Primary Name"],'cd'=>["CD Antigen Name"],'altnames'=>["Alternate Names"],
|
338
|
-
'location' => ["Subcellular Location"],
|
339
|
-
'function' => ["Known Function"],
|
340
|
-
'similarity' => ["Similarity"],
|
341
|
-
'tissues' => ["Tissue Specificity"],
|
342
|
-
'disease' => ["Disease Association"],
|
343
|
-
'domain' => ["Domain"],
|
344
|
-
'subunit' => ["Sub Unit"],
|
345
|
-
'nextbio' => ["NextBio"],
|
346
|
-
'ipi' => ["IPI"],
|
347
|
-
'intact' => ["Interactions"],
|
348
|
-
'pride' => ['Pride'],
|
349
|
-
'ensembl'=> ['Ensembl'],
|
350
|
-
'num_transmem'=>["Transmembrane Regions"],
|
351
|
-
'signalp'=>['Signal Peptide']
|
352
|
-
}
|
353
|
-
|
354
|
-
newColumnKeys=['recname','cd','altnames','location','function','similarity','tissues','disease','domain','subunit','nextbio','ipi','intact','pride','ensembl','num_transmem','signalp']
|
355
|
-
|
356
|
-
|
357
|
-
# xmlurls=accs.collect {|acc| uniprot.entry_url_for_accession(acc,'xml') }
|
358
|
-
|
359
|
-
@genv.log("Initializing database",:info)
|
360
|
-
|
361
|
-
swissprotdb=SwissprotDatabase.new(@genv)
|
362
|
-
@genv.log("Retrieving data for #{ids.length} entries from Swissprot database ",:info)
|
363
|
-
accs=[]
|
364
|
-
plasmodbids=[]
|
365
|
-
found_plasmodb_ids=false
|
366
|
-
|
367
|
-
$stdout.putc "\n"
|
368
|
-
ids.each { |uniprot_id|
|
369
|
-
|
370
|
-
$stdout.putc "."
|
371
|
-
$stdout.flush
|
372
|
-
|
373
|
-
sptr_entry=swissprotdb.get_entry_for_name(uniprot_id)
|
374
|
-
|
375
|
-
|
376
|
-
if ( sptr_entry==nil)
|
377
|
-
@genv.log("No entry for #{uniprot_id} in uniprot database",:warn)
|
378
|
-
newColumnKeys.each { |key| newColumns[key].push("") }
|
379
|
-
accs.push("")
|
380
|
-
|
381
|
-
# Bit of a hack. If the id is not sp and not decoy we assume it is plasmodb
|
382
|
-
#
|
383
|
-
if ( uniprot_id=~/^decoy_/)
|
384
|
-
else
|
385
|
-
plasmodbids.push(uniprot_id)
|
386
|
-
found_plasmodb_ids=true
|
387
|
-
end
|
388
|
-
|
389
|
-
else
|
390
|
-
accs.push(sptr_entry.accession)
|
391
|
-
plasmodbids.push("")
|
392
|
-
|
393
|
-
newColumnKeys.each { |key|
|
394
|
-
|
395
|
-
val=sptr_entry.send(key)
|
396
|
-
if ( val==nil)
|
397
|
-
str=""
|
398
|
-
elsif ( val.class==Array)
|
399
|
-
str=val.join(";")
|
400
|
-
else
|
401
|
-
str=val.to_s
|
402
|
-
end
|
403
|
-
newColumns[key].push(str)
|
404
|
-
}
|
405
|
-
end
|
406
|
-
}
|
407
|
-
$stdout.putc "\n"
|
408
|
-
|
409
|
-
|
410
|
-
# Trying PlasmoDB for unknown IDs
|
411
|
-
#
|
412
|
-
if ( found_plasmodb_ids )
|
413
|
-
$stdout.putc "Searching PlasmoDB for unknown Id's\n"
|
414
|
-
@genv.log "Searching PlasmoDB for unknown Id's", :info
|
415
|
-
|
416
|
-
plasmodb = PlasmoDB.new(@genv)
|
417
|
-
|
418
|
-
row_index=1 # Starts from 1 because of the header
|
419
|
-
|
420
|
-
plasmodbids.each { |plasmodb_id|
|
421
|
-
|
422
|
-
if ( plasmodb_id!="")
|
423
|
-
p plasmodb_id
|
424
|
-
|
425
|
-
plasmodb_entry = plasmodb.get_entry_for_name(plasmodb_id)
|
426
|
-
|
427
|
-
if ( plasmodb_entry != nil )
|
428
|
-
|
429
|
-
# newColumnKeys=['recname','cd','altnames','location','function','similarity','tissues','disease','domain','subunit','nextbio','ipi','intact','pride','ensembl','num_transmem','signalp']
|
430
|
-
|
431
|
-
newColumns['recname'][row_index]=plasmodb_entry['Product Description']
|
432
|
-
|
433
|
-
if ( plasmodb_entry['Annotated GO Component']!="null" )
|
434
|
-
newColumns['location'][row_index]=plasmodb_entry['Annotated GO Component']
|
435
|
-
else
|
436
|
-
newColumns['location'][row_index]=plasmodb_entry['Predicted GO Component']
|
437
|
-
end
|
438
|
-
|
439
|
-
if ( plasmodb_entry['Annotated GO Function'] !="null" )
|
440
|
-
newColumns['function'][row_index]=plasmodb_entry['Annotated GO Function']
|
441
|
-
else
|
442
|
-
newColumns['function'][row_index]=plasmodb_entry['Predicted GO Function']
|
443
|
-
end
|
444
|
-
|
445
|
-
newColumns['signalp'][row_index]=plasmodb_entry['SignalP Peptide']
|
446
|
-
|
447
|
-
newColumns['num_transmem'][row_index] = plasmodb_entry['# TM Domains']
|
448
|
-
|
449
|
-
end
|
450
|
-
end
|
451
|
-
|
452
|
-
row_index=row_index+1
|
453
|
-
|
454
|
-
|
455
|
-
}
|
456
|
-
|
457
|
-
|
458
|
-
end
|
459
|
-
|
460
|
-
|
461
|
-
@genv.log("Done",:info)
|
462
|
-
|
463
|
-
newColumnKeys.reverse.each { |key|
|
464
|
-
outputSheet.insert_column(newColumns[key],lastcolIndex)
|
465
|
-
}
|
466
|
-
|
467
|
-
# Now hide some columns
|
468
|
-
hide=hiddenColumns
|
469
|
-
for i in 0...outputSheet.row(0).length
|
470
|
-
if ( hide.detect { |h| header[i].include?(h)} !=nil)
|
471
|
-
outputSheet.column(i).hidden=TRUE
|
472
|
-
accessionColumn=outputSheet.column i
|
473
|
-
accessionColumnIndex=i
|
474
|
-
end
|
475
|
-
if ( header[i]=="" && lastcolIndex==0)
|
476
|
-
lastcolIndex=i
|
477
|
-
end
|
478
|
-
end
|
479
|
-
|
480
|
-
|
481
|
-
# Now add hyperlinks to various columns
|
482
|
-
@genv.log("Creating Hyperlinks",:info)
|
483
|
-
|
484
|
-
# Figure out column indexes for all the hyperlinked columns
|
485
|
-
header=outputSheet.row 0
|
486
|
-
|
487
|
-
entrezIDColumn=nil
|
488
|
-
|
489
|
-
|
490
|
-
# Grab the column indexes of existing columns to be hyperlinked
|
491
|
-
for i in 0...header.length
|
492
|
-
if ( header[i]==accessionColumnName )
|
493
|
-
accessionColumnIndex=i
|
494
|
-
end
|
495
|
-
if ( header[i]=="IPI")
|
496
|
-
ipiColumnIndex=i
|
497
|
-
end
|
498
|
-
if ( header[i]=="Interactions")
|
499
|
-
intactColumnIndex=i
|
500
|
-
end
|
501
|
-
if ( header[i]=="Pride")
|
502
|
-
prideColumnIndex=i
|
503
|
-
end
|
504
|
-
if ( header[i]=="Ensembl")
|
505
|
-
ensemblColumnIndex=i
|
506
|
-
end
|
507
|
-
if ( header[i]=="NextBio")
|
508
|
-
nextbioColumnIndex=i
|
509
|
-
end
|
510
|
-
|
511
|
-
if (header[i]==entrezIDColumnName)
|
512
|
-
entrezIDColumnIndex=i
|
513
|
-
entrezIDColumn=outputSheet.column i
|
514
|
-
entrezIDs=entrezIDColumn.collect { |id| id }
|
515
|
-
end
|
516
|
-
|
517
|
-
end
|
518
|
-
|
519
|
-
|
520
|
-
# Create a format for the hyperlinks
|
521
|
-
hyperlink_format = Spreadsheet::Format.new({:color => :blue,:weight => :bold,:size => 10})
|
522
|
-
|
523
|
-
# Add hyperlink format to the appropriate columns
|
524
|
-
outputSheet.column(accessionColumnIndex).default_format=hyperlink_format
|
525
|
-
outputSheet.column(nextbioColumnIndex).default_format=hyperlink_format
|
526
|
-
outputSheet.column(ipiColumnIndex).default_format=hyperlink_format
|
527
|
-
outputSheet.column(intactColumnIndex).default_format=hyperlink_format
|
528
|
-
outputSheet.column(prideColumnIndex).default_format=hyperlink_format
|
529
|
-
outputSheet.column(ensemblColumnIndex).default_format=hyperlink_format
|
530
|
-
|
531
|
-
if ( entrezIDColumn!=nil)
|
532
|
-
outputSheet.column(entrezIDColumnIndex).default_format=hyperlink_format
|
533
|
-
end
|
534
|
-
|
535
|
-
# Create all the hyperlinks
|
536
|
-
for rowi in 1...outputSheet.rows.length do
|
537
|
-
|
538
|
-
if ( plasmodbids[rowi-1]!="")
|
539
|
-
# Assume plasmodb .. and use plasmodb url
|
540
|
-
outputSheet.row(rowi)[accessionColumnIndex]=Spreadsheet::Link.new(url="http://www.plasmodb.org/plasmo/showRecord.do?name=GeneRecordClasses.GeneRecordClass&project_id=&primary_key=#{ids[rowi-1]}",description=plasmodbids[rowi-1])
|
541
|
-
else
|
542
|
-
# Otherwise assume sp
|
543
|
-
outputSheet.row(rowi)[accessionColumnIndex]=Spreadsheet::Link.new(url="http://www.uniprot.org/uniprot/#{accs[rowi-1]}.html",description=ids[rowi-1])
|
544
|
-
end
|
545
|
-
|
546
|
-
outputSheet.row(rowi)[nextbioColumnIndex]=Spreadsheet::Link.new(url="http://www.nextbio.com/b/home/home.nb?id=#{newColumns['nextbio'][rowi]}&type=feature",description=newColumns['nextbio'][rowi])
|
547
|
-
outputSheet.row(rowi)[ipiColumnIndex]=Spreadsheet::Link.new(url="http://www.ebi.ac.uk/cgi-bin/dbfetch?db=IPI&id=#{newColumns['ipi'][rowi]}",description=newColumns['ipi'][rowi])
|
548
|
-
outputSheet.row(rowi)[intactColumnIndex]=Spreadsheet::Link.new(url="http://www.ebi.ac.uk/intact/pages/interactions/interactions.xhtml?query=#{newColumns['intact'][rowi]}*",description=newColumns['intact'][rowi])
|
549
|
-
outputSheet.row(rowi)[prideColumnIndex]=Spreadsheet::Link.new(url="http://www.ebi.ac.uk/pride/searchSummary.do?queryTypeSelected=identification%20accession%20number&identificationAccessionNumber=#{newColumns['pride'][rowi]}",description=newColumns['pride'][rowi])
|
550
|
-
outputSheet.row(rowi)[ensemblColumnIndex]=Spreadsheet::Link.new(url="http://www.ensembl.org/Homo_sapiens/Transcript/Summary?db=core;t=#{newColumns['ensembl'][rowi]}",description=newColumns['ensembl'][rowi])
|
551
|
-
outputSheet.row(rowi).height=24
|
552
|
-
|
553
|
-
|
554
|
-
if ( entrezIDColumn!=nil && entrezIDs[rowi]!=nil)
|
555
|
-
outputSheet.row(rowi)[entrezIDColumnIndex]=Spreadsheet::Link.new(url="http://www.ncbi.nlm.nih.gov/gene/#{entrezIDs[rowi].to_i.to_s}",description=entrezIDs[rowi].to_i.to_s)
|
556
|
-
end
|
557
|
-
|
558
|
-
end
|
559
|
-
|
560
|
-
# Change the names of any columns to nicer values if you need to
|
561
|
-
#
|
562
|
-
outputSheet.row(0)[accessionColumnIndex]="Uniprot Link"
|
563
|
-
|
564
|
-
if ( entrezIDColumn!=nil)
|
565
|
-
outputSheet.row(0)[entrezIDColumnIndex]="Entrez.ID"
|
566
|
-
end
|
567
|
-
|
568
|
-
|
569
|
-
|
570
|
-
# Having hyperlinked existing columns we now add any additional columns (hyperlinks based on existing data)
|
571
|
-
# Note that all the column indexes will now be invalid which is why this is done near the end
|
572
|
-
#
|
573
|
-
|
574
|
-
# Insert an entrez ID based iHOP literature search link if possible
|
575
|
-
if ( entrezIDColumn!=nil)
|
576
|
-
|
577
|
-
@genv.log("Creating iHOP literature search link",:info)
|
578
|
-
|
579
|
-
ihopURLs=entrezIDs.collect do |entrezid|
|
580
|
-
"http://www.ihop-net.org/UniPub/iHOP/in?dbrefs_1=NCBI_GENE__ID|#{entrezid.to_i.to_s}"
|
581
|
-
end
|
582
|
-
|
583
|
-
columnIndex=ensemblColumnIndex+1
|
584
|
-
|
585
|
-
# Insert this column after the ensembl Link (which is before other literature based stuff)
|
586
|
-
outputSheet.insert_column(ihopURLs,columnIndex)
|
587
|
-
|
588
|
-
# Create the links
|
589
|
-
for rowi in 0...outputSheet.rows.length do
|
590
|
-
outputSheet.row(rowi)[columnIndex]=Spreadsheet::Link.new(url=ihopURLs[rowi],description=entrezIDs[rowi].to_i.to_s)
|
591
|
-
end
|
592
|
-
|
593
|
-
# Format the links
|
594
|
-
outputSheet.column(columnIndex).default_format=hyperlink_format
|
595
|
-
|
596
|
-
# And give the header a proper name
|
597
|
-
outputSheet.row(0)[columnIndex]="iHOP literature search"
|
598
|
-
|
599
|
-
end
|
600
|
-
|
601
|
-
|
602
|
-
@genv.log("Formatting header",:info)
|
603
|
-
|
604
|
-
# Format the Header row
|
605
|
-
headerFormat=Spreadsheet::Format.new({ :weight => :bold,:size => 11 })
|
606
|
-
outputSheet.row(0).default_format=headerFormat
|
607
|
-
|
608
|
-
# Here we put in a little workaround for a problem with the Spreadsheet gem.
|
609
|
-
# If the text "false" is in a column it will substitute nil for the false value and then fail when attempting to convert nil to an integer.
|
610
|
-
# We workaround by changing the word "true" to "positive" and false to "negative"
|
611
|
-
outputSheet.rows.each { |row|
|
612
|
-
|
613
|
-
row.each_index { |ri|
|
614
|
-
|
615
|
-
if ( row[ri].class==NilClass)
|
616
|
-
p "Encountered a nil value in the sheet converting to empty string"
|
617
|
-
row[ri]=""
|
618
|
-
end
|
619
|
-
|
620
|
-
if ( row[ri]==true)
|
621
|
-
row[ri]="positive"
|
622
|
-
elsif (row[ri]==false)
|
623
|
-
row[ri]="negative"
|
624
|
-
end
|
625
|
-
}
|
626
|
-
|
627
|
-
|
628
|
-
|
629
|
-
}
|
630
|
-
|
631
|
-
|
632
|
-
# Put the header rows back
|
633
|
-
#
|
634
|
-
keep_rows.reverse!
|
635
|
-
keep_rows.each do |row|
|
636
|
-
outputSheet.insert_row(0,row)
|
637
|
-
end
|
638
|
-
|
639
|
-
|
640
|
-
|
641
|
-
# Finally write the results
|
642
|
-
@genv.log("Writing New Workbook #{outputFile}",:info)
|
643
|
-
outputBook.write outputFile
|
644
|
-
end
|
645
|
-
|
646
|
-
end
|