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