summaryrefslogtreecommitdiff
path: root/lib/dataset.rb
blob: 17c30d535c04e39d80bd99e32615bb8306e318ab (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
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
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
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
require 'csv'
require 'tempfile'
require 'digest/md5'

module OpenTox

  # Collection of substances and features
  class Dataset

    field :data_entries, type: Hash, default: {}
    field :md5, type: String

    # Readers

    # Get all compounds
    # @return [Array<OpenTox::Compound>]
    def compounds
      substances.select{|s| s.is_a? Compound}
    end

    # Get all nanoparticles
    # @return [Array<OpenTox::Nanoparticle>]
    def nanoparticles
      substances.select{|s| s.is_a? Nanoparticle}
    end

    # Get all substances
    # @return [Array<OpenTox::Substance>]
    def substances
      @substances ||= data_entries.keys.collect{|id| OpenTox::Substance.find id}.uniq
      @substances
    end

    # Get all features
    # @return [Array<OpenTox::Feature>]
    def features
      @features ||= data_entries.collect{|sid,data| data.keys.collect{|id| OpenTox::Feature.find(id)}}.flatten.uniq
      @features
    end

    # Get all values for a given substance and feature
    # @param [OpenTox::Substance,BSON::ObjectId,String] substance or substance id
    # @param [OpenTox::Feature,BSON::ObjectId,String] feature or feature id
    # @return [TrueClass,FalseClass,Float]
    def values substance,feature
      substance = substance.id if substance.is_a? Substance
      feature = feature.id if feature.is_a? Feature
      if data_entries[substance.to_s] and data_entries[substance.to_s][feature.to_s]
        data_entries[substance.to_s][feature.to_s]
      else
        [nil]
      end
    end

    # Writers

    # Add a value for a given substance and feature
    # @param [OpenTox::Substance,BSON::ObjectId,String] substance or substance id
    # @param [OpenTox::Feature,BSON::ObjectId,String] feature or feature id
    # @param [TrueClass,FalseClass,Float]
    def add(substance,feature,value)
      substance = substance.id if substance.is_a? Substance
      feature = feature.id if feature.is_a? Feature
      data_entries[substance.to_s] ||= {}
      data_entries[substance.to_s][feature.to_s] ||= []
      data_entries[substance.to_s][feature.to_s] << value
      #data_entries[substance.to_s][feature.to_s].uniq! if value.numeric? # assuming that identical values come from the same source
    end

    # Dataset operations

    # Split a dataset into n folds
    # @param [Integer] number of folds
    # @return [Array] Array with folds [training_dataset,test_dataset]
    def folds n
      len = self.substances.size
      indices = (0..len-1).to_a.shuffle
      mid = (len/n)
      chunks = []
      start = 0
      1.upto(n) do |i|
        last = start+mid
        last = last-1 unless len%n >= i
        test_idxs = indices[start..last] || []
        test_substances = test_idxs.collect{|i| substances[i]}
        training_idxs = indices-test_idxs
        training_substances = training_idxs.collect{|i| substances[i]}
        chunk = [training_substances,test_substances].collect do |substances|
          dataset = self.class.create(:name => "#{self.name} (Fold #{i-1})",:source => self.id )
          substances.each do |substance|
            substance.dataset_ids << dataset.id
            substance.dataset_ids.uniq!
            substance.save
            dataset.data_entries[substance.id.to_s] = data_entries[substance.id.to_s] ||= {}
          end
          dataset.save
          dataset
        end
        start = last+1
        chunks << chunk
      end
      chunks
    end

    # Serialisation
    
    # Convert dataset to csv format including compound smiles as first column, other column headers are feature names
    # @return [String]
    # TODO original_id
    def to_csv(inchi=false)
      CSV.generate() do |csv| 
        compound = substances.first.is_a? Compound
        if compound
          csv << [inchi ? "InChI" : "SMILES"] + features.collect{|f| f.name}
        else
          csv << ["Name"] + features.collect{|f| f.name}
        end
        substances.each do |substance|
          if compound
            name = (inchi ? substance.inchi : substance.smiles)
          else
            name = substance.name
          end
          nr_measurements = features.collect{|f| data_entries[substance.id.to_s][f.id.to_s].size if data_entries[substance.id.to_s][f.id.to_s]}.compact.uniq

          if nr_measurements.size > 1
            warn "Unequal number of measurements (#{nr_measurements}) for '#{name}'. Skipping entries."
          else
            (0..nr_measurements.first-1).each do |i|
              row = [name]
              features.each do |f|
                values(substance,f) ? row << values(substance,f)[i] : row << ""
              end
              csv << row
            end
          end
        end
      end
    end

    # Convert dataset to SDF file
    # @return [String]
    def to_sdf
      substances.each do |substance|
        sdf_lines = substance.sdf.sub(/\$\$\$\$\n/,"").split("\n")
        sdf_lines[0] = substance.smiles
        puts sdf_lines.join("\n")
        features.each do |f|
          puts "> <#{f.name}>"
          puts values(substance,f).uniq.join ","
          puts "\n$$$$"
        end
      end
    end

    # Parsers

    # Create a dataset from PubChem Assay
    # @param [File] 
    # @return [OpenTox::Dataset]
    def self.from_pubchem aid
      csv = RestClientWrapper.get "https://pubchem.ncbi.nlm.nih.gov/rest/pug/assay/aid/#{aid}/CSV"
      table = CSV.read csv
      puts table
=begin
          dataset = self.new(:source => file, :name => name, :md5 => md5)
          dataset.parse_table table, accept_empty_values
        else
      puts csv
i = 0
activities = []
File.readlines(ARGV[0]).each do |line|
  if i > 2
    tokens = line.split ","
    p line if tokens[1].empty?
    activities << [tokens[1],tokens[3]]
  end
  i += 1
end

puts "SMILES,Activity"
activities.each_slice(100) do |slice| # get SMILES in chunks
  sids = slice.collect{|e| e[0]}
  smiles = `curl https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/#{sids.join(",")}/property/CanonicalSMILES/TXT`.split("\n")
  abort("Could not get SMILES for all SIDs from PubChem") unless sids.size == smiles.size
  smiles.each_with_index do |smi,i|
    act = slice[i]
    puts [smi.chomp,act[1]].join(",")
  end
end
=end
    end

    # Create a dataset from SDF file 
    # @param [File] 
    # @return [OpenTox::Dataset]
    def self.from_sdf_file file
      md5 = Digest::MD5.hexdigest(File.read(file)) # use hash to identify identical files
      dataset = self.find_by(:md5 => md5)
      if dataset
        $logger.debug "Skipping import of #{file}, it is already in the database (id: #{dataset.id})."
      else
        $logger.debug "Parsing #{file}."
        table = nil
        read_result = false
        sdf = ""
        dataset = self.new(:source => file, :name => name, :md5 => md5)
        original_id = NominalFeature.find_or_create_by(:name => "original_id")

        feature_name = ""
        compound = nil
        features = {}

        File.readlines(file).each do |line|
          if line.match %r{\$\$\$\$}
            sdf << line
            id = sdf.split("\n").first.chomp
            compound = Compound.from_sdf sdf
            dataset.add compound, original_id, id
            features.each { |f,v| dataset.add compound, f, v }
            sdf = ""
            features = {}
          elsif line.match /^>\s+</
            feature_name = line.match(/^>\s+<(.*)>/)[1]
            read_result = true
          else
            if read_result
              value = line.chomp
              if value.numeric?
                feature = NumericFeature.find_or_create_by(:name => feature_name)
                value = value.to_f
              else
                feature = NominalFeature.find_or_create_by(:name => feature_name)
              end
              features[feature] = value
              #p compound.smiles, feature.name, value
              read_result = false
            else
              sdf << line
            end
          end
        end
      end
      dataset
 
    end
    
    # Create a dataset from CSV file
    # @param [File] 
    # @param [TrueClass,FalseClass] accept or reject empty values
    # @return [OpenTox::Dataset]
    def self.from_csv_file file, accept_empty_values=false
      md5 = Digest::MD5.hexdigest(File.read(file)) # use hash to identify identical files
      dataset = self.find_by(:md5 => md5)
      if dataset
        $logger.debug "Skipping import of #{file}, it is already in the database (id: #{dataset.id})."
      else
        $logger.debug "Parsing #{file}."
        table = nil
        [",","\t",";"].each do |sep| # guess CSV separator
          if File.readlines(file).first.match(/#{sep}/)
            table = CSV.read file, :col_sep => sep, :skip_blanks => true, :encoding => 'windows-1251:utf-8'
            break
          end
        end
        if table
          dataset = self.new(:source => file, :name => name, :md5 => md5)
          dataset.parse_table table, accept_empty_values
        else
          bad_request_error "#{file} is not a valid CSV/TSV file. Could not find "," ";" or TAB as column separator."
        end
      end
      dataset
    end

    # Parse data in tabular format (e.g. from csv)
    #   does a lot of guesswork in order to determine feature types
    # @param [Array<Array>] 
    # @param [TrueClass,FalseClass] accept or reject empty values
    def parse_table table, accept_empty_values

      # features
      feature_names = table.shift.collect{|f| f.strip}
      warnings << "Duplicated features in table header." unless feature_names.size == feature_names.uniq.size

      original_id = nil 
      if feature_names[0] =~ /ID/i # check ID column
        feature_names.shift 
        original_id = NominalFeature.find_or_create_by(:name => "original_id")
      end

      compound_format = feature_names.shift
      bad_request_error "#{compound_format} is not a supported compound format. Accepted formats: SMILES, InChI." unless compound_format =~ /SMILES|InChI/i
      numeric = []
      features = []

      # guess feature types
      feature_names.each_with_index do |f,i|
        metadata = {:name => f}
        values = table.collect{|row| val=row[i+1].to_s.strip; val.blank? ? nil : val }.uniq.compact
        types = values.collect{|v| v.numeric? ? true : false}.uniq
        feature = nil
        if values.size == 0 # empty feature
        elsif  values.size > 5 and types.size == 1 and types.first == true # 5 max classes
          numeric[i] = true
          feature = NumericFeature.find_or_create_by(metadata)
        else
          metadata["accept_values"] = values
          numeric[i] = false
          feature = NominalFeature.find_or_create_by(metadata)
        end
        features << feature if feature
      end
      
      # substances and values

      all_substances = []
      table.each_with_index do |vals,i|
        original_id_value = vals.shift.strip if original_id
        identifier = vals.shift.strip
        warn "No feature values for compound at line #{i+2} of #{source}." if vals.compact.empty? and !accept_empty_values
        begin
          case compound_format
          when /SMILES/i
            substance = OpenTox::Compound.from_smiles(identifier)
          when /InChI/i
            substance = OpenTox::Compound.from_inchi(identifier)
          end
        rescue 
          substance = nil
        end
        if substance.nil? # compound parsers may return nil
          warn "Cannot parse #{compound_format} compound '#{identifier}' at line #{i+2} of #{source}, all entries are ignored."
          next
        end
        all_substances << substance
        substance.dataset_ids << self.id
        substance.dataset_ids.uniq!
        substance.save
          
        unless vals.size == features.size 
          warn "Number of values at position #{i+2} is different than header size (#{vals.size} vs. #{features.size}), all entries are ignored."
          next
        end

        add substance, original_id, original_id_value if original_id

        vals.each_with_index do |v,j|
          if v.blank?
            warn "Empty value for compound '#{identifier}' and feature '#{feature_names[i]}'."
            next
          elsif numeric[j]
            v = v.to_f
          else
            v = v.strip
          end
          add substance, features[j], v
        end
        data_entries[substance.id.to_s] = {} if vals.empty? and accept_empty_values
      end
      all_substances.duplicates.each do |substance|
        positions = []
        all_substances.each_with_index{|c,i| positions << i+1 if !c.blank? and c.inchi and c.inchi == substance.inchi}
        warn "Duplicate compound #{substance.smiles} at rows #{positions.join(', ')}. Entries are accepted, assuming that measurements come from independent experiments." 
      end
      save
    end

    # Delete dataset
    def delete
      compounds.each{|c| c.dataset_ids.delete id.to_s}
      super
    end

  end

  # Dataset for lazar predictions
  class LazarPrediction #< Dataset
    field :creator, type: String
    field :prediction_feature_id, type: BSON::ObjectId
    field :predictions, type: Hash, default: {}

    # Get prediction feature
    # @return [OpenTox::Feature]
    def prediction_feature
      Feature.find prediction_feature_id
    end

    # Get all compounds
    # @return [Array<OpenTox::Compound>]
    def compounds
      substances.select{|s| s.is_a? Compound}
    end

    # Get all substances
    # @return [Array<OpenTox::Substance>]
    def substances
      predictions.keys.collect{|id| Substance.find id}
    end

  end

  class Batch

    include OpenTox
    include Mongoid::Document
    include Mongoid::Timestamps
    store_in collection: "batch"
    field :name,  type: String
    field :source,  type: String
    field :identifiers, type: Array
    field :ids, type: Array
    field :compounds, type: Array
    field :warnings, type: Array, default: []

    def self.from_csv_file file
      source = file
      name = File.basename(file,".*")
      batch = self.find_by(:source => source, :name => name)
      if batch
        $logger.debug "Skipping import of #{file}, it is already in the database (id: #{batch.id})."
      else
        $logger.debug "Parsing #{file}."
        # check delimiter
        line = File.readlines(file).first
        if line.match(/\t/)
          table = CSV.read file, :col_sep => "\t", :skip_blanks => true, :encoding => 'windows-1251:utf-8'
        else
          table = CSV.read file, :skip_blanks => true, :encoding => 'windows-1251:utf-8'
        end
        batch = self.new(:source => source, :name => name, :identifiers => [], :ids => [], :compounds => [])

        # original IDs
        if table[0][0] =~ /ID/i
          @original_ids = table.collect{|row| row.shift}
          @original_ids.shift
        end
        
        # features
        feature_names = table.shift.collect{|f| f.strip}
        warnings << "Duplicated features in table header." unless feature_names.size == feature_names.uniq.size
        compound_format = feature_names.shift.strip
        unless compound_format =~ /SMILES|InChI/i
          File.delete file
          bad_request_error "'#{compound_format}' is not a supported compound format in the header. " \
          "Accepted formats: SMILES, InChI. Please take a look on the help page."
        end
        numeric = []
        features = []
        # guess feature types
        feature_names.each_with_index do |f,i|
          metadata = {:name => f}
          values = table.collect{|row| val=row[i+1].to_s.strip; val.blank? ? nil : val }.uniq.compact
          types = values.collect{|v| v.numeric? ? true : false}.uniq
          feature = nil
          if values.size == 0 # empty feature
          elsif  values.size > 5 and types.size == 1 and types.first == true # 5 max classes
            numeric[i] = true
            feature = NumericFeature.find_or_create_by(metadata)
          else
            metadata["accept_values"] = values
            numeric[i] = false
            feature = NominalFeature.find_or_create_by(metadata)
          end
          features << feature if feature
        end
        
        table.each_with_index do |vals,i|
          identifier = vals.shift.strip.gsub(/^'|'$/,"")
          begin
            case compound_format
            when /SMILES/i
              compound = OpenTox::Compound.from_smiles(identifier)
            when /InChI/i
              compound = OpenTox::Compound.from_inchi(identifier)
            end
          rescue 
            compound = nil
          end
          # collect only for present compounds
          unless compound.nil?
            batch.identifiers << identifier
            batch.compounds << compound.id
            batch.ids << @original_ids[i] if @original_ids
          else
            batch.warnings << "Cannot parse #{compound_format} compound '#{identifier}' at line #{i+2} of #{source}."
          end
        end
        batch.compounds.duplicates.each do |duplicate|
          $logger.debug "Duplicates found in #{name}."
          dup = Compound.find duplicate
          positions = []
          batch.compounds.each_with_index do |co,i|
            c = Compound.find co
            if !c.blank? and c.inchi and c.inchi == dup.inchi
              positions << i+1
            end
          end
          batch.warnings << "Duplicate compound at ID #{positions.join(' and ')}."
        end
        batch.save
      end
      batch
    end

  end

end