Module: MiGA::Cli::Action::Wf

Included in:
ClassifyWf, DerepWf, IndexWf, PreprocWf, QualityWf
Defined in:
lib/miga/cli/action/wf.rb

Overview

Helper module for workflows

Instance Method Summary collapse

Instance Method Details

#call_cli(cmd) ⇒ Object 



243
244
245
246
247
 
# File 'lib/miga/cli/action/wf.rb', line 243

def call_cli(cmd)
  cmd << '-v' if cli[:verbose]
  MiGA::MiGA.DEBUG "Cli::Action::Wf.call_cli #{cmd}"
  MiGA::Cli.new(cmd.map(&:to_s)).launch(true)
end

#cleanup ⇒ Object 



233
234
235
236
237
238
239
240
241
 
# File 'lib/miga/cli/action/wf.rb', line 233

def cleanup
  return if cli[:prepare_and_exit]
  return unless cli[:clean]

  cli.say 'Cleaning up intermediate files'
  %w[data daemon metadata miga.project.json].each do |f|
    FileUtils.rm_rf(File.expand_path(f, cli[:outdir]))
  end
end

#create_project(stage, p_metadata = {}, d_metadata = {}) ⇒ Object 



142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
 
# File 'lib/miga/cli/action/wf.rb', line 142

def create_project(stage, p_metadata = {}, d_metadata = {})
  cli.ensure_par(
    outdir: '-o',
    project_type: '--project-type',
    dataset_type: '--dataset-type'
  )
  paired = cli[:input_type].to_s.include?('_paired')
  cli[:regexp] ||= MiGA::Cli.FILE_REGEXP(paired)

  # Create empty project and populate with datasets
  p = initialize_empty_project(p_metadata)
  download_datasets
  import_datasets(stage)

  # Define datasets metadata
  p.load
  d_metadata[:type] = cli[:dataset_type]
  p.each_dataset { |d| transfer_metadata(d, d_metadata) }
  p
end

#default_opts_for_wf ⇒ Object 



7
8
9
10
11
12
13
14
15
 
# File 'lib/miga/cli/action/wf.rb', line 7

def default_opts_for_wf
  cli.expect_files = true
  cli.defaults = {
    clean: false, project_type: :genomes, dataset_type: :popgenome,
    ncbi_draft: true, ncbi_ref: false,
    min_qual: MiGA::Project.OPTIONS[:min_qual][:default],
    prepare_and_exit: false
  }
end

#download_datasets ⇒ Object 



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
 
# File 'lib/miga/cli/action/wf.rb', line 178

def download_datasets
  # Download datasets from NCBI
  unless cli[:ncbi_taxon].nil?
    what = cli[:ncbi_ref] ? '--reference' :
           cli[:ncbi_draft] ? '--all' : '--complete'
    cmd = ['ncbi_get', '-P', cli[:outdir], '-T', cli[:ncbi_taxon], what]
    cmd += ['--max', cli[:max_download]] if cli[:max_download]
    call_cli(cmd)
  end

  # Download datasets from GTDB
  unless cli[:gtdb_taxon].nil?
    cmd = ['gtdb_get', '-P', cli[:outdir], '-T', cli[:gtdb_taxon]]
    cmd << '--reference' if cli[:gtdb_ref]
    cmd += ['--max', cli[:max_download]] if cli[:max_download]
    call_cli(cmd)
  end

  # Download datasets from SeqCode Registry
  if cli[:seqcode_type]
    cmd = ['seqcode_get', '-P', cli[:outdir]]
    cmd += ['--max', cli[:max_download]] if cli[:max_download]
    call_cli(cmd)
  end
end

#import_datasets(stage) ⇒ Object 



204
205
206
207
208
209
210
211
212
213
214
215
 
# File 'lib/miga/cli/action/wf.rb', line 204

def import_datasets(stage)
  call_cli(
    [
      'add',
      '--ignore-dups',
      '-P', cli[:outdir],
      '-t', cli[:dataset_type],
      '-i', stage,
      '-R', cli[:regexp]
    ] + cli.files
  ) unless cli.files.empty?
end

#initialize_empty_project(metadata) ⇒ Object 



163
164
165
166
167
168
169
170
171
172
173
174
175
176
 
# File 'lib/miga/cli/action/wf.rb', line 163

def initialize_empty_project(metadata)
  call_cli(
    ['new', '-P', cli[:outdir], '-t', cli[:project_type]]
  ) unless MiGA::Project.exist? cli[:outdir]

  # Define project metadata
  p = cli.load_project(:outdir, '-o')
  metadata[:type] = cli[:project_type]
  transfer_metadata(p, metadata)
  %i[haai_p aai_p ani_p ess_coll min_qual].each do |i|
    p.set_option(i, cli[i])
  end
  p
end

#opts_for_wf(opt, files_desc, params = {}) ⇒ Object 



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
 
# File 'lib/miga/cli/action/wf.rb', line 17

def opts_for_wf(opt, files_desc, params = {})
  {
    multi: false, cleanup: true, project_type: false, ncbi: true, qual: true
  }.each { |k, v| params[k] = v if params[k].nil? }
  opt.on(
    '-o', '--out_dir PATH',
    '(Mandatory) Directory to be created with all output data'
  ) { |v| cli[:outdir] = v }
  opt.on(
    '-P', '--project PATH',
    '::HIDE::' # Applying the principle of least surprise, alias of -o
  ) { |v| cli[:outdir] = v }
  opt.separator ''
  opt.separator "    FILES...: #{files_desc}"
  opt.separator ''
  opt.separator 'Workflow Control Options'
  opt.on(
    '-C', '--collection STRING',
    'Collection of essential genes to use as reference',
    'One of: dupont_2012 (default), lee_2019'
  ) { |v| cli[:ess_coll] = v }
  if params[:ncbi]
    opt.on(
      '-T', '--ncbi-taxon STRING',
      'Download all the genomes in NCBI classified as this taxon'
    ) { |v| cli[:ncbi_taxon] = v }
    opt.on(
      '--no-draft', '::HIDE::' # Deprecated
    ) { |v| cli[:ncbi_draft] = v }
    opt.on(
      '--ncbi-complete',
      'Only download complete genomes, not drafts (requires -T)'
    ) { |v| cli[:ncbi_draft] = !v }
    opt.on(
      '--ncbi-ref',
      'Only download RefSeq reference genomes (requires -T)'
    ) { |v| cli[:ncbi_ref] = v }
    opt.on(
      '-G', '--gtdb-taxon STRING',
      'Download all the genomes in GTDB classified as this taxon'
    ) { |v| cli[:gtdb_taxon] = v }
    opt.on(
      '--gtdb-ref',
      'Only download reference anchor genomes in GTDB (requires -G)'
    ) { |v| cli[:gtdb_ref] = v }
    opt.on(
      '-S', '--seqcode-type',
      'Download all type genomes from the SeqCode Registry'
    ) { |v| cli[:seqcode_type] = v }
    opt.on(
      '--max-download INT', Integer,
      'Maximum number of genomes to download (by default: unlimited)',
      'It applies independently to -T, -G and --S'
    ) { |v| cli[:max_download] = v }
  end
  if params[:qual]
    opt.on(
      '--min-qual FLOAT',
      'Minimum genome quality to include in analysis',
      "By default: #{cli[:min_qual]}"
    ) { |v| cli[:min_qual] = v == 'no' ? v : v.to_f }
  end
  if params[:cleanup]
    opt.on(
      '-c', '--clean',
      'Clean all intermediate files after generating the reports'
    ) { |v| cli[:clean] = v }
  end
  opt.on(
    '-R', '--name-regexp REGEXP', Regexp,
    'Regular expression indicating how to extract the name from the path',
    "By default: '#{MiGA::Cli.FILE_REGEXP}'"
  ) { |v| cli[:regexp] = v }
  opt_object_type(opt, :dataset, params[:multi])
  opt_object_type(opt, :project, params[:multi]) if params[:project_type]
  opt.on(
    '--daemon PATH',
    'Use custom daemon configuration in JSON format',
    'By default: ~/.miga_daemon.json'
  ) { |v| cli[:daemon_json] = v }
  opt.on(
    '-j', '--jobs INT', Integer,
    'Number of parallel jobs to execute',
    'By default controlled by the daemon configuration (maxjobs)'
  ) { |v| cli[:jobs] = v }
  opt.on(
    '-t', '--threads INT', Integer,
    'Number of CPUs to use per job',
    'By default controlled by the daemon configuration (ppn)'
  ) { |v| cli[:threads] = v }
  opt.on(
    '--threads-project INT', Integer,
    'Number of CPUs to use per project-wide job',
    'By default controlled by the daemon configuration (ppn_project or ppn)'
  ) { |v| cli[:threads_project] = v }
  opt.on(
    '--prepare-and-exit',
    'Create project and import datasets, but do not run any analyses'
  ) { |v| cli[:prepare_and_exit] = v }
end

#opts_for_wf_distances(opt) ⇒ Object 



118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
 
# File 'lib/miga/cli/action/wf.rb', line 118

def opts_for_wf_distances(opt)
  opt.on('--sensitive', 'Alias to: --aai-p blast+ --ani-p blast+') do
    cli[:aai_p] = 'blast+'
    cli[:ani_p] = 'blast+'
  end
  opt.on('--fast', 'Alias to: --aai-p diamond --ani-p fastani (default)') do
    cli[:aai_p] = 'diamond'
    cli[:ani_p] = 'fastani'
  end
  opt.on(
    '--haai-p STRING',
    'hAAI search engine. One of: blast+, fastaai, blat, diamond, fastaai, no',
    'The default is "no" for clade projects and "fastaai" otherwise'
  ) { |v| cli[:haai_p] = v }
  opt.on(
    '--aai-p STRING',
    'AAI search engine. One of: blast+, blat, diamond (default)'
  ) { |v| cli[:aai_p] = v }
  opt.on(
    '--ani-p STRING',
    'ANI search engine. One of: blast+, blat, fastani (default)'
  ) { |v| cli[:ani_p] = v }
end

#run_daemon ⇒ Object 



249
250
251
252
253
254
255
256
257
258
259
260
261
 
# File 'lib/miga/cli/action/wf.rb', line 249

def run_daemon
  return if cli[:prepare_and_exit]

  cmd  = ['daemon', 'run', '-P', cli[:outdir], '--shutdown-when-done']
  cmd += ['--json', cli[:daemon_json]] if cli[:daemon_json]
  cmd += ['--max-jobs', cli[:jobs]] if cli[:jobs]
  cmd += ['--ppn', cli[:threads]] if cli[:threads]
  cmd += ['--ppn-project', cli[:threads_project]] if cli[:threads_project]
  cmd += ['--debug', MiGA::MiGA.debug_trace? ? '2' : '1'] if MiGA::MiGA.debug?
  cwd = Dir.pwd
  call_cli(cmd)
  Dir.chdir(cwd)
end

#summarize(which = %w[cds assembly essential_genes ssu]) ⇒ Object 



217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
 
# File 'lib/miga/cli/action/wf.rb', line 217

def summarize(which = %w[cds assembly essential_genes ssu])
  return if cli[:prepare_and_exit]

  which.each do |r|
    cli.say "Summary: #{r}"
    call_cli(
      [
        'summary',
        '-P', cli[:outdir], '-r', r, '--tab', '--ref', '--active',
        '-o', File.join(cli[:outdir], "#{r}.tsv")
      ]
    )
  end
  call_cli(['browse', '-P', cli[:outdir]])
end

#transfer_metadata(obj, md) ⇒ Object 



263
264
265
266
267
268
269
270
271
 
# File 'lib/miga/cli/action/wf.rb', line 263

def transfer_metadata(obj, md)
  # Clear old metadata
  obj.metadata.each do |k, v|
    obj.metadata[k] = nil if k.to_s =~ /^run_/ || obj.option?(k)
  end
  # Transfer and save
  md.each { |k, v| obj.metadata[k] = v }
  obj.save
end