This file is indexed.

/var/lib/mobyle/programs/hmmsim.xml is in mobyle-programs 5.1.2-2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
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
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
<?xml version='1.0' encoding='UTF-8'?>
<!-- XML Authors: Corinne Maufrais                                               -->
<!-- 'Biological Software and Databases' Group, Institut Pasteur, Paris.         -->
<!-- Distributed under LGPLv2 License. Please refer to the COPYING.LIB document. -->
<program>
  <head>
    <name>hmmsim</name>
    <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="Entities/hmmer_package.xml"/>
    <doc>
      <title>HMMSIM</title>
      <description>
        <text lang="en">
          Collect profile HMM score distributions on random sequences
        </text>
      </description>
    </doc>
    <category>hmm:simulation</category>
    <command>hmmsim</command>
  </head>
  <parameters>
    <parameter ismandatory="1" issimple="1">
      <name>hmmfile</name>
      <prompt lang="en">HMM file</prompt>
      <type>
        <datatype>
          <class>HmmProfile</class>
          <superclass>AbstractText</superclass>
        </datatype>
      </type>
      <format>
        <code proglang="perl">" $value"</code>
        <code proglang="python">" "+str(value)</code>
      </format>
      <argpos>30</argpos>
    </parameter>
    <paragraph>
      <name>generalOptions</name>
      <prompt lang="en">General options</prompt>
      <argpos>1</argpos>
      <parameters>
        <parameter>
          <name>aln</name>
          <prompt lang="en">Obtain alignment length statistics (-a)</prompt>
          <type>
            <datatype>
              <class>Boolean</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">$altSco eq '--vit'</code>
            <code proglang="python">altSco == '--vit'</code>
          </precond>
          <vdef>
            <value>0</value>
          </vdef>
          <format>
            <code proglang="perl">($value) ? " -a" : ""</code>
            <code proglang="python">( "" , " -a" )[ value ]</code>
          </format>
          <comment>
            <text lang="en">Collect expected Viterbi alignment length statistics from each simulated sequence.
            This only works with Viterbi scores (the default; see --vit). Two additional fields are
            printed in the output table for each model: the mean length of Viterbi alignments,
            and the standard deviation.</text>
          </comment>
        </parameter>
        <parameter>
          <name>verbose</name>
          <prompt lang="en">Verbose: print scores (-v)</prompt>
          <type>
            <datatype>
              <class>Boolean</class>
            </datatype>
          </type>
          <vdef>
            <value>0</value>
          </vdef>
          <format>
            <code proglang="perl">($value) ? " -v" : ""</code>
            <code proglang="python">( "" , " -v" )[ value ]</code>
          </format>
        </parameter>
        <parameter>
          <name>Length</name>
          <prompt lang="en">Length of random target sequences (-L)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>100</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef ) ? " -L $value" : ""</code>
            <code proglang="python">( "" , " -L " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <ctrl>
            <message>
              <text lang="en">value &gt; 0</text>
            </message>
            <code proglang="perl">$value &gt; 0</code>
            <code proglang="python">value &gt; 0</code>
          </ctrl>
        </parameter>
        <parameter>
          <name>number</name>
          <prompt lang="en">Number of random target sequences (-N)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>1000</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " -N $value" : ""</code>
            <code proglang="python">( "" , " -N " + str(value) )[ value is not None and value !=vdef]</code>
          </format>
          <ctrl>
            <message>
              <text lang="en">value &gt; 0</text>
            </message>
            <code proglang="perl">$value &gt; 0</code>
            <code proglang="python">value &gt; 0</code>
          </ctrl>
        </parameter>
      </parameters>
    </paragraph>
    <paragraph>
      <name>AdvancedOptions</name>
      <prompt lang="en">Advanced options</prompt>
      <argpos>1</argpos>
      <parameters>
        <parameter>
          <name>altAln</name>
          <prompt lang="en">Alternative alignment styles</prompt>
          <type>
            <datatype>
              <class>Choice</class>
            </datatype>
          </type>
          <vdef>
            <value>--fs</value>
          </vdef>
          <vlist>
            <velem>
              <value>--fs</value>
              <label>multihit local alignment (fs)</label>
            </velem>
            <velem>
              <value>--sw</value>
              <label>unihit local alignment (sw)</label>
            </velem>
            <velem>
              <value>--ls</value>
              <label>multihit glocal alignment (ls)</label>
            </velem>
          </vlist>
          <!--<velem>  'Failed to parse command line: Abbreviated option "-s" is ambiguous'
            <value>-s</value>
            <label>unihit glocal alignment (s)</label>
           </velem>
           -->
          <format>
            <code proglang="perl">(defined $value and $value ne $vdef) ? " $value" : ""</code>
            <code proglang="python">( "" , " " + str(value) )[ value is not None and value != vdef ]</code>
          </format>
          <comment>
            <text lang="en">H3 only uses multihit local alignment ( --fs mode), and this is where we believe the statistical fits. Unihit
            local alignment scores (Smith/Waterman; --sw mode) also obey our statistical conjectures. Glocal alignment
            statistics (either multihit or unihit) are still not adequately understood nor adequately fitted.</text>
            <text lang="en">fs: Collect multihit local alignment scores. This is the default. 'fs comes from HMMER2'
            s historical terminology for multihit local alignment as 'fragment search mode'.</text>
            <text lang="en">sw: Collect unihit local alignment scores. The H3 J state is disabled. 'sw' comes from
            HMMER2's historical terminology for unihit local alignment as 'Smith/Waterman search mode'.</text>
            <text lang="en">ls Collect multihit glocal alignment scores. In glocal (global/local) alignment, the entire
            model must align, to a subsequence of the target. The H3 local entry/exit transition
            probabilities are disabled. 'ls' comes from HMMER2's historical terminology
            for multihit local alignment as 'local search mode'.</text>
            <text lang="en">s: Collect unihit glocal alignment scores. Both the H3 J state and local entry/exit transition
            probabilities are disabled. 's' comes from HMMER2's historical terminology
            for unihit glocal alignment.</text>
          </comment>
        </parameter>
        <parameter>
          <name>altSco</name>
          <prompt lang="en">Option controlling scoring algorithm</prompt>
          <type>
            <datatype>
              <class>Choice</class>
            </datatype>
          </type>
          <vdef>
            <value>--vit</value>
          </vdef>
          <vlist>
            <velem>
              <value>--vit</value>
              <label>Score sequences with the Viterbi algorithm (vit)</label>
            </velem>
            <velem>
              <value>--fwd</value>
              <label>Score sequences with the Forward algorithm (fwd)</label>
            </velem>
            <velem>
              <value>--hyd</value>
              <label>Score sequences with the Hybrid algorithm (hyd)</label>
            </velem>
            <velem>
              <value>--msv</value>
              <label>Score sequences with the MSV algorithm (msv)</label>
            </velem>
            <velem>
              <value>--fast</value>
              <label>Use the optimized versions of the above (fast)</label>
            </velem>
          </vlist>
          <format>
            <code proglang="perl">(defined $value and $value ne $vdef) ? "  $value" : ""</code>
            <code proglang="python">( "" , " " + str(value) )[ value is not None and value != vdef ]</code>
          </format>
          <comment>
            <text lang="en">vit: Collect Viterbi maximum likelihood alignment scores. This is the default.</text>
            <text lang="en">fwd: Collect Forward log-odds likelihood scores, summed over alignment ensemble.</text>
            <text lang="en">hyb: Collect 'Hybrid' scores, as described in papers by Yu and Hwa (for instance, Bioinformatics
            18:864, 2002). These involve calculating a Forward matrix and taking the
            maximum cell value. The number itself is statistically somewhat unmotivated, but
            the distribution is expected be a well-behaved extreme value distribution (Gumbel).</text>
            <text lang="en">msv: Collect MSV (multiple ungapped segment Viterbi) scores, using H3's main acceleration
            heuristic.</text>
            <text lang="en">fast: For any of the above options, use H3's optimized production implementation (using
            SIMD vectorization). The default is to use the 'generic' implementation (slow and
            non-vectorized). The optimized implementations sacrifice a small amount of numerical
            precision. This can introduce confounding noise into statistical simulations
            and fits, so when one gets super-concerned about exact details, it's better to be
            able to factor that source of noise out.</text>
          </comment>
        </parameter>
      </parameters>
    </paragraph>
    <paragraph>
      <name>controlMasse</name>
      <prompt lang="en">Controlling range of fitted tail masses</prompt>
      <argpos>1</argpos>
      <parameters>
        <parameter>
          <name>tmin</name>
          <prompt lang="en">Set lower bound tail mass for fwd,island (--tmin)</prompt>
          <type>
            <datatype>
              <class>Float</class>
            </datatype>
          </type>
          <vdef>
            <value>0.02</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --tmin $value" : ""</code>
            <code proglang="python">( "" , " --tmin " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Set the lower bound on the tail mass distribution. (The default is 0.02 for the default
            single tail mass.)</text>
          </comment>
        </parameter>
        <parameter>
          <name>tmax</name>
          <prompt lang="en">Set upper bound tail mass for fwd,island (--tmax)</prompt>
          <type>
            <datatype>
              <class>Float</class>
            </datatype>
          </type>
          <vdef>
            <value>0.02</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --tmax $value" : ""</code>
            <code proglang="python">( "" , " --tmax " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Set the upper bound on the tail mass distribution. (The default is 0.02 for the default
            single tail mass.)</text>
          </comment>
        </parameter>
        <parameter>
          <name>tpoints</name>
          <prompt lang="en">Set number of tail probs to try (--tpoints)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>1</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --tpoints $value" : ""</code>
            <code proglang="python">( "" , " --tpoints " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Set the number of tail masses to sample, starting from --tmin and ending at --tmax.
            The default is 1, for the default 0.02 single tail mass.</text>
          </comment>
        </parameter>
        <parameter>
          <name>tlinear</name>
          <prompt lang="en">Use linear not log spacing of tail probs (--tlinear)</prompt>
          <type>
            <datatype>
              <class>Boolean</class>
            </datatype>
          </type>
          <vdef>
            <value>0</value>
          </vdef>
          <format>
            <code proglang="perl">($value) ? " --tlinear" : ""</code>
            <code proglang="python">( "" , " --tlinear" )[ value ]</code>
          </format>
          <comment>
            <text lang="en">Sample a range of tail masses with uniform linear spacing. The default is to use
            uniform logarithmic spacing.</text>
          </comment>
        </parameter>
      </parameters>
    </paragraph>
    <paragraph>
      <name>ECalibration</name>
      <prompt lang="en">Options controlling h3 parameter estimation methods</prompt>
      <argpos>1</argpos>
      <comment>
        <text lang="en">H3 uses three short random sequence simulations to estimating the location parameters 
        for the expected score distributions for MSV scores, Viterbi scores, and Forward scores. These options 
        allow these simulations to be modified.</text>
      </comment>
      <parameters>
        <parameter>
          <name>EmL</name>
          <prompt lang="en">Lengt of sequences for MSV Gumbel mu fit (EmL)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>200</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value!=$vdef) ? " --EmL $value" : ""</code>
            <code proglang="python">( "" , " --EmL " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Sets the sequence length in simulation that estimates the location parameter mu
         for MSV E-values. Default is 200. Enter a value &gt; 0. </text>
          </comment>
          <ctrl>
            <message>
              <text lang="en">Enter a value &gt; 0 </text>
            </message>
            <code proglang="perl">$value &gt; 0 </code>
            <code proglang="python">value &gt; 0 </code>
          </ctrl>
        </parameter>
        <parameter>
          <name>EmN</name>
          <prompt lang="en">Number of sequences for MSV Gumbel mu fit (EmN)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>200</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value!=$vdef) ? " --EmN $value" : ""</code>
            <code proglang="python">( "" , " --EmN " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Sets the number of sequences in simulation that estimates the location parameter
              mu for MSV E-values. Default is 200. Enter a value &gt; 0.</text>
          </comment>
          <ctrl>
            <message>
              <text lang="en">Enter a value &gt; 0 </text>
            </message>
            <code proglang="perl">$value &gt; 0 </code>
            <code proglang="python">value &gt; 0 </code>
          </ctrl>
        </parameter>
        <parameter>
          <name>EvL</name>
          <prompt lang="en">Lengt of sequences for Viterbi Gumbel mu fit (EvL)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>200</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value!=$vdef) ? " --EvL $value" : ""</code>
            <code proglang="python">( "" , " --EvL " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Sets the sequence length in simulation that estimates the location parameter mu
            for Viterbi E-values. Default is 200. Enter a value &gt; 0</text>
          </comment>
          <ctrl>
            <message>
              <text lang="en">Enter a value &gt; 0 </text>
            </message>
            <code proglang="perl">$value &gt; 0 </code>
            <code proglang="python">value &gt; 0 </code>
          </ctrl>
        </parameter>
        <parameter>
          <name>EvN</name>
          <prompt lang="en">Number of sequences for Viterbi Gumbel mu fit (EvN)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>200</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --EvN $value" : ""</code>
            <code proglang="python">( "" , " --EvN " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Sets the number of sequences in simulation that estimates the location parameter
          mu for Viterbi E-values. Default is 200. Enter a value &gt; 0.</text>
          </comment>
          <ctrl>
            <message>
              <text lang="en">Enter a value &gt; 0 </text>
            </message>
            <code proglang="perl">$value &gt; 0 </code>
            <code proglang="python">value &gt; 0 </code>
          </ctrl>
        </parameter>
        <parameter>
          <name>EfL</name>
          <prompt lang="en">Lengt of sequences for Forward exp tail tau fit (EfL)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>100</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --EfL $value" : ""</code>
            <code proglang="python">( "" , " --EfL " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Sets the sequence length in simulation that estimates the location parameter tau
          for Forward E-values. Default is 100. Enter a value &gt; 0</text>
          </comment>
          <ctrl>
            <message>
              <text lang="en">Enter a value &gt; 0 </text>
            </message>
            <code proglang="perl">$value &gt; 0 </code>
            <code proglang="python">value &gt; 0 </code>
          </ctrl>
        </parameter>
        <parameter>
          <name>EfN</name>
          <prompt lang="en">Number of sequences for Forward exp tail tau fit (EfN)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>200</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --EfN $value" : ""</code>
            <code proglang="python">( "" , " --EfN " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Sets the number of sequences in simulation that estimates the location parameter
            tau for Forward E-values. Default is 200. Enter a value &gt; 0</text>
          </comment>
          <ctrl>
            <message>
              <text lang="en">Enter a value &gt; 0 </text>
            </message>
            <code proglang="perl">$value &gt; 0 </code>
            <code proglang="python">value &gt; 0 </code>
          </ctrl>
        </parameter>
        <parameter>
          <name>Eft</name>
          <prompt lang="en">Tail mass for Forward exponential tail tau fit (Eft)</prompt>
          <type>
            <datatype>
              <class>Float</class>
            </datatype>
          </type>
          <vdef>
            <value>0.04</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --Eft $value" : ""</code>
            <code proglang="python">( "" , " --Eft " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Sets the tail mass fraction to fit in the simulation that estimates the location parameter
            tau for Forward evalues. Default is 0.04. Enter a value &gt; 0 and &lt; 1</text>
          </comment>
          <ctrl>
            <message>
              <text lang="en">Enter a value &gt; 0 and &lt; 1</text>
            </message>
            <code proglang="perl">$value &gt; 0 and $value &lt; 1</code>
            <code proglang="python">value &gt; 0 and value &lt; 1</code>
          </ctrl>
        </parameter>
      </parameters>
    </paragraph>
    <paragraph>
      <name>debugg</name>
      <prompt lang="en">Debugging options</prompt>
      <argpos>1</argpos>
      <parameters>
        <parameter>
          <name>stall</name>
          <prompt lang="en">Arrest after start: for debugging MPI under gdb (--stall)</prompt>
          <type>
            <datatype>
              <class>Boolean</class>
            </datatype>
          </type>
          <vdef>
            <value>0</value>
          </vdef>
          <format>
            <code proglang="perl">($value) ? " --stall" : ""</code>
            <code proglang="python">( "" , " --stall" )[ value ]</code>
          </format>
          <comment>
            <text lang="en">For debugging the MPI master/worker version: pause after start, to enable the
            developer to attach debuggers to the running master and worker(s) processes.
            Send SIGCONT signal to release the pause. (Under gdb: (gdb) signal SIGCONT)
            (Only available if optional MPI support was enabled at compile-time.)</text>
          </comment>
        </parameter>
        <parameter>
          <name>seed</name>
          <prompt lang="en">Set random number seed  (--seed)</prompt>
          <type>
            <datatype>
              <class>Integer</class>
            </datatype>
          </type>
          <vdef>
            <value>0</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --seed $value" : ""</code>
            <code proglang="python">( "" , " --seed " + str(value))[ value is not None and value != vdef ]</code>
          </format>
          <comment>
            <text lang="en">Set the random number seed. The default is 0, which makes the random
            number generator use an arbitrary seed, so that different runs of hmmsim will
            almost certainly generate a different statistical sample. For debugging, it is useful
            to force reproducible results, by fixing a random number seed.</text>
          </comment>
        </parameter>
      </parameters>
    </paragraph>
    <paragraph>
      <name>expert</name>
      <prompt lang="en">Experiments options</prompt>
      <argpos>1</argpos>
      <comment>
        <text lang="en">These options were used in a small variety of different exploratory experiments.</text>
      </comment>
      <parameters>
        <parameter>
          <name>bgflat</name>
          <prompt lang="en">Set uniform background frequencies (--bgflat)</prompt>
          <type>
            <datatype>
              <class>Boolean</class>
            </datatype>
          </type>
          <vdef>
            <value>0</value>
          </vdef>
          <format>
            <code proglang="perl">($value) ? " --bgflat" : ""</code>
            <code proglang="python">( "" , " --bgflat" )[ value ]</code>
          </format>
          <comment>
            <text lang="en">Set the background residue distribution to a uniform distribution, both for purposes
            of the null model used in calculating scores, and for generating the random sequences.
            The default is to use a standard amino acid background frequency distribution.</text>
          </comment>
        </parameter>
        <parameter>
          <name>bgcomp</name>
          <prompt lang="en">Set bg frequencies to model's average composition (--bgcomp)</prompt>
          <type>
            <datatype>
              <class>Boolean</class>
            </datatype>
          </type>
          <vdef>
            <value>0</value>
          </vdef>
          <format>
            <code proglang="perl">($value) ? " --bgcomp" : ""</code>
            <code proglang="python">( "" , " --bgcomp" )[ value ]</code>
          </format>
          <comment>
            <text lang="en">Set the background residue distribution to the mean composition of the profile. This
            was used in exploring some of the effects of biased composition.</text>
          </comment>
        </parameter>
        <parameter>
          <name>lengthmode</name>
          <prompt lang="en">Turn the H3 length model off (--x-no-lengthmode)</prompt>
          <type>
            <datatype>
              <class>Boolean</class>
            </datatype>
          </type>
          <vdef>
            <value>0</value>
          </vdef>
          <format>
            <code proglang="perl">($value) ? " --x-no-lengthmode" : ""</code>
            <code proglang="python">( "" , " --x-no-lengthmode " )[value ]</code>
          </format>
          <comment>
            <text lang="en">Turn the H3 target sequence length model off. Set the self-transitions for N,C,J
            and the null model to 350/351 instead; this emulates HMMER2. Not a good idea
            in general. This was used to demonstrate one of the main H2 vs. H3 differences.</text>
          </comment>
        </parameter>
        <parameter>
          <name>nu</name>
          <prompt lang="en">Set nu parameter (expected HSPs) for GMSV (--nu)</prompt>
          <type>
            <datatype>
              <class>Float</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">$altSco eq '--msv'</code>
            <code proglang="python">altSco == '--msv'</code>
          </precond>
          <vdef>
            <value>2.0</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --nu $value" : ""</code>
            <code proglang="python">( "" , " --nu " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Set the nu parameter for the MSV algorithm -- the expected number of ungapped
          local alignments per target sequence. The default is 2.0, corresponding to a E-&gt;J transition probability of 0.5. This was used to test whether varying nu has
          significant effect on result (it doesn't seem to, within reason). This option only
          works if --msv is selected (it only affects MSV), and it will not work with --fast
          (because the optimized implementations are hardwired to assume nu=2.0).</text>
          </comment>
        </parameter>
        <parameter>
          <name>pthresh</name>
          <prompt lang="en">Set  P-value threshold for --ffile (--pthresh)</prompt>
          <type>
            <datatype>
              <class>Float</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">defined $ffile</code>
            <code proglang="python">ffile is not None</code>
          </precond>
          <vdef>
            <value>0.02</value>
          </vdef>
          <format>
            <code proglang="perl">(defined $value and $value != $vdef) ? " --pthresh $value" : ""</code>
            <code proglang="python">( "" , " --pthresh " + str(value) )[ value is not None and value !=vdef ]</code>
          </format>
          <comment>
            <text lang="en">Set the filter P-value threshold to use in generating filter power files with --ffile. The
            default is 0.02 (which would be appropriate for testing MSV scores, since this is
            the default MSV filter threshold in H3's acceleration pipeline.) Other appropriate
            choices (matching defaults in the acceleration pipeline) would be 0.001 for Viterbi,
            and 1e-5 for Forward.</text>
          </comment>
        </parameter>
      </parameters>
    </paragraph>
    <paragraph>
      <name>output_options</name>
      <prompt lang="en">Output options</prompt>
      <argpos>1</argpos>
      <parameters>
        <parameter>
          <name>save</name>
          <prompt lang="en">Direct summary output to file, not stdout. (-o)</prompt>
          <type>
            <datatype>
              <class>Filename</class>
            </datatype>
          </type>
          <format>
            <code proglang="perl">(defined $value)? " -o $value" : ""</code>
            <code proglang="python">( "" , " -o " + str(value) )[ value is not None ]</code>
          </format>
          <argpos>1</argpos>
        </parameter>
        <parameter isout="1">
          <name>save_out</name>
          <prompt lang="en">Direct summary output to file.</prompt>
          <type>
            <datatype>
              <class>Report</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">defined $save</code>
            <code proglang="python">save is not None</code>
          </precond>
          <filenames>
            <code proglang="perl">"$save"</code>
            <code proglang="python">str( save )</code>
          </filenames>
          <argpos>1</argpos>
        </parameter>
        <parameter>
          <name>afile</name>
          <prompt lang="en">Output alignment lengths to file (--afile)</prompt>
          <type>
            <datatype>
              <class>Filename</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">$aln and $altSco eq '--vit'</code>
            <code proglang="python">aln and altSco == '--vit'</code>
          </precond>
          <format>
            <code proglang="perl">(defined $value)? " --afile $value" : ""</code>
            <code proglang="python">( "" , " --afile " + str(value) )[ value is not None ]</code>
          </format>
          <argpos>1</argpos>
          <comment>
            <text lang="en">When collecting Viterbi alignment statistics (the -a option), for each sampled sequence,
            output two fields per line to a file: the length of the optimal alignment,
            and the Viterbi bit score. Requires that the -a option is also used.</text>
          </comment>
        </parameter>
        <parameter isout="1">
          <name>afile_out</name>
          <prompt lang="en">Output alignment lengths</prompt>
          <type>
            <datatype>
              <class>Report</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">defined $afile</code>
            <code proglang="python">afile is not None</code>
          </precond>
          <filenames>
            <code proglang="perl">"$afile"</code>
            <code proglang="python">str( afile )</code>
          </filenames>
          <argpos>1</argpos>
        </parameter>
        <parameter>
          <name>efile</name>
          <prompt lang="en">Output E vs. E plots to file in xy format (--efile)</prompt>
          <type>
            <datatype>
              <class>Filename</class>
            </datatype>
          </type>
          <format>
            <code proglang="perl">(defined $value)? " --efile $value" : ""</code>
            <code proglang="python">( "" , " --efile " + str(value) )[ value is not None ]</code>
          </format>
          <argpos>1</argpos>
          <comment>
            <text lang="en">Output a rank versus. E-value plot in XMGRACE xy format to file. The x-axis is the
            rank of this sequence, from highest score to lowest; the y-axis is the E-value calculated
            for this sequence. E-values are calculated using H3's default procedures (i.e.
            the 'pmu, plambda' parameters in the output table). You expect a rough match
            between rank and E-value if E-values are accurately estimated.</text>
          </comment>
        </parameter>
        <parameter isout="1">
          <name>efile_out</name>
          <prompt lang="en">Output E vs. E plots to file in xy format</prompt>
          <type>
            <datatype>
              <class>Report</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">defined $efile</code>
            <code proglang="python">efile is not None</code>
          </precond>
          <filenames>
            <code proglang="perl">"$efile"</code>
            <code proglang="python">str( efile )</code>
          </filenames>
          <argpos>1</argpos>
        </parameter>
        <parameter>
          <name>ffile</name>
          <prompt lang="en">Output filter fraction: sequences passing P thresh (--ffile)</prompt>
          <type>
            <datatype>
              <class>Filename</class>
            </datatype>
          </type>
          <format>
            <code proglang="perl">(defined $value)? " --ffile $value" : ""</code>
            <code proglang="python">( "" , " --ffile " + str(value) )[ value is not None ]</code>
          </format>
          <argpos>1</argpos>
          <comment>
            <text lang="en">Output a 'filter power' file: for each model, a line with three fields: model
            name, number of sequences passing the P-value threshold, and fraction of sequences
            passing the P-value threshold. See --pthresh for setting the P-value
            threshold, which defaults to 0.02 (the default MSV filter threshold in H3). The
            P-values are as determined by H3's default procedures (the 'pmu,plambda' parameters
            in the output table). If all is well, you expect to see filter power equal to
            the predicted P-value setting of the threshold.</text>
          </comment>
        </parameter>
        <parameter isout="1">
          <name>ffile_out</name>
          <prompt lang="en">Output filter fraction: sequences passing P thresh</prompt>
          <type>
            <datatype>
              <class>Report</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">defined $ffile</code>
            <code proglang="python">ffile is not None</code>
          </precond>
          <filenames>
            <code proglang="perl">"$ffile"</code>
            <code proglang="python">str( ffile )</code>
          </filenames>
          <argpos>1</argpos>
        </parameter>
        <parameter>
          <name>pfile</name>
          <prompt lang="en">Output cumulative survival plots (--pfile)</prompt>
          <type>
            <datatype>
              <class>Filename</class>
            </datatype>
          </type>
          <format>
            <code proglang="perl">(defined $value)? " --pfile $value" : ""</code>
            <code proglang="python">( "" , " --pfile " + str(value) )[ value is not None ]</code>
          </format>
          <argpos>1</argpos>
          <comment>
            <text lang="en">Output cumulative survival plots (P(S&gt;x)) to file in XMGRACE xy format.
            There are three plots: (1) the observed score distribution; (2) the maximum likelihood
            fitted distribution; (3) a maximum likelihood fit to the location parameter
            (mu/tau) while assuming lambda=log 2.</text>
          </comment>
        </parameter>
        <parameter isout="1">
          <name>pfile_out</name>
          <prompt lang="en">Output cumulative survival plots</prompt>
          <type>
            <datatype>
              <class>Report</class>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">defined $pfile</code>
            <code proglang="python">pfile is not None</code>
          </precond>
          <filenames>
            <code proglang="perl">"$pfile"</code>
            <code proglang="python">str( pfile )</code>
          </filenames>
          <argpos>1</argpos>
        </parameter>
        <parameter>
          <name>xfile</name>
          <prompt lang="en">Output bitscores as binary double vector to file (--xfile)</prompt>
          <type>
            <datatype>
              <class>Filename</class>
            </datatype>
          </type>
          <format>
            <code proglang="perl">(defined $value)? " --xfile $value" : ""</code>
            <code proglang="python">( "" , " --xfile " + str(value) )[ value is not None ]</code>
          </format>
          <argpos>1</argpos>
          <comment>
            <text lang="en">Output the bit scores as a binary array of double-precision floats (8 bytes per score)
            to file. Programs like Easel's esl-histplot can read such binary files. This is
            useful when generating extremely large sample sizes.</text>
          </comment>
        </parameter>
        <parameter isout="1">
          <name>xfile_out</name>
          <prompt lang="en">Output bitscores as binary double vector to file</prompt>
          <type>
            <datatype>
              <class>BitScores</class>
              <superclass>Binary</superclass>
            </datatype>
          </type>
          <precond>
            <code proglang="perl">defined $xfile</code>
            <code proglang="python">xfile is not None</code>
          </precond>
          <filenames>
            <code proglang="perl">"$xfile"</code>
            <code proglang="python">str( xfile )</code>
          </filenames>
          <argpos>1</argpos>
        </parameter>
      </parameters>
    </paragraph>
  </parameters>
</program>