gentrap.json 29 KB
Newer Older
bow's avatar
bow committed
1
2
3
4
5
6
7
8
9
10
11
12
{
    "$schema": "http://json-schema.org/draft-04/schema#",
    "title": "Gentrap Pipeline Summary",
    "description": "Schema for full Gentrap pipeline runs",
    "type": "object",
    "required": [ "samples", "gentrap" ],

    "properties": {

      "meta": {
        "description": "Pipeline run metadata",
        "type": "object",
13
        "required": [ "pipeline_version", "last_commit_hash", "pipeline_name" ],
bow's avatar
bow committed
14
15
16

        "properties": {

17
          "pipeline_version": {
bow's avatar
bow committed
18
19
20
21
22
23
24
25
            "description": "Pipeline release version",
            "type": "string"
          },

          "last_commit_hash": {
            "description": "Commit hash of the source code repository at the time the pipeline was compiled",
            "type": "string",
            "minLength": 7
26
27
          },

28
          "pipeline_name": {
29
30
31
            "description": "Name of the pipeline that created the summary file",
            "type": "string",
            "enum": [ "gentrap" ]
32
33
34
35
36
          },

          "run_name": {
            "description": "User-supplied name of the pipeline run",
            "type": "string"
bow's avatar
bow committed
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
          }
        }
      },

      "samples": {
        "description": "All samples analyzed in the Gentrap run",
        "type": "object",
        "minItems": 1,
        "additionalProperties": { "$ref": "#/definitions/sample" }
      },

      "gentrap": {
        "description": "Pipeline-level Gentrap information",
        "type": "object",
        "required": [ "files", "executables", "settings" ],

        "properties": {

          "files": {
            "description": "File groups tracked by Gentrap",
            "type": "object",

            "properties": {

              "pipeline": {
                "description": "Files tracked by Gentrap",
                "type": "object",
                "required": [ "annotation_refflat" ],
                "additionalProperties": { "$ref": "#/definitions/file" }
              }
            }
          },

          "executables": {
            "description": "Executables used in the Gentrap run",
            "type": "object",
            "additionalProperties": { "$ref": "#/definitions/executable" }
          },

          "settings": {
            "description": "Settings used for the Gentrap run",
            "type": "object",
            "required": [
              "aligner", "call_variants", "remove_ribosomal_reads",
              "expression_measures", "strand_protocol", "reference"
            ],

            "properties": {

              "aligner": { "type": "string" },
              "call_variants": { "type": "boolean" },
              "remove_ribosomal_reads": { "type": "boolean" },

              "expression_measures": {
                "description": "Expression measurements for each sample",
                "type": "array",
                "minItems": 0,
                "items": {
                  "type": "string",
                  "enum": [
                    "FragmentsPerGene", "FragmentsPerExon", "BasesPerGene", "BasesPerExon",
                    "CufflinksStrict", "CufflinksGuided", "CufflinksBlind"
                  ]
                }
              },

              "strand_protocol": {
                "description": "Wet lab protocol that was used to track origin strand of reads",
                "type": "string",
                "enum": [ "NonSpecific", "Dutp" ]
              },

              "reference": {
                "description": "Reference sequence information",
                "type": "object",
                "required": [ "contigs" ],

                "properties": {

                  "contigs": {
                    "description": "All contigs / chromosomes in the reference sequence",
                    "type": "object",
                    "minItems": 1,
                    "additionalProperties": { "$ref": "#/definitions/referenceContig" }
                  }
                }
              }
            }
          }
        }
      }
    },

  "definitions": {

    "sample": {
      "description": "A single Gentrap sample",
      "type": "object",
      "required": [ "libraries", "gentrap" ],

      "properties": {

        "libraries": {
          "description": "All libraries belonging to the sample",
          "type": "object",
          "minItems": 1,
          "additionalProperties": { "$ref": "#/definitions/library" }
        },

        "gentrap": {
          "description": "Sample-level Gentrap information",
          "required": [ "files", "stats" ],

          "properties": {

            "files": {
              "description": "File groups tracked by Gentrap",
              "type": "object",
              "required": [ "pipeline" ],

              "properties": {

                "pipeline": {
                  "description": "Sample-level Gentrap files",
                  "type": "object",
                  "required": [ "alignment" ],
                  "additionalProperties": { "$ref": "#/definitions/file" }
                },

                "rna_metrics": {
bow's avatar
bow committed
167
                  "description": "Sample-level RNA-seq metrics",
bow's avatar
bow committed
168
169
170
171
172
173
174
175
176
                  "type": "object",
                  "required": [ "annotation", "metrics" ],
                  "additionalProperties": { "$ref": "#/definitions/file" }
                }
              },
              "additionalProperties": { "$ref": "#/definitions/fileGroup" }
            },

            "stats": {
bow's avatar
bow committed
177
              "description": "Sample-level Gentrap statistics",
bow's avatar
bow committed
178
179
              "type": "object",

bow's avatar
bow committed
180
181
182
183
              "properties": {

                "rna_metrics": { "$ref": "#/definitions/statsRnaSeqMetrics" }
              }
bow's avatar
bow committed
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
            }
          }
        },

        "bammetrics": {
          "description": "Sample-level mapping metrics",
          "type": "object",
          "required": [ "files", "executables", "stats" ],

          "properties": {

            "files": {
              "description": "File groups tracked by BamMetrics",
              "type": "object",
              "required": [ "pipeline" ],

              "properties": {

                "pipeline": {
                  "description": "Initial input files and final output files in Mapping",
                  "type": "object",
                  "additionalProperties": { "$ref": "#/definitions/file" }
                }
              },
              "additionalProperties": { "$ref": "#/definitions/fileGroup" }
            },

            "executables": {
              "description": "Executables used in BamMetrics",
              "type": "object",
              "additionalProperties": { "$ref": "#/definitions/executable" }
            },

            "stats": {
              "description": "Statistics gathered by BamMetrics",
              "type": "object",
              "required": [ "alignment_metrics", "biopet_flagstat" ],

              "properties": {

                "alignment_metrics": { "$ref": "#/definitions/statsAlignmentSummary" },

                "biopet_flagstat": { "$ref": "#/definitions/statsBiopetFlagstat" },

bow's avatar
bow committed
228
                "insert_size_metrics": { "$ref": "#/definitions/statsInsertSizeMetrics" }
bow's avatar
bow committed
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
              }
            }
          }
        }
      }
    },

    "library": {
      "description": "A single Gentrap library",
      "type": "object",
      "required": [ "flexiprep", "mapping", "bammetrics", "gentrap" ],

      "properties": {

        "flexiprep": {
          "description": "Library-level Flexiprep information",
          "type": "object",
          "required": [ "files", "executables", "settings", "stats" ],

          "properties": {

            "files": {
              "description": "File groups tracked by Flexiprep",
              "type": "object",
              "required": [ "pipeline", "fastqc_R1" ],

              "properties": {

                "pipeline": {
                  "description": "Initial input files and final output files in Flexiprep",
                  "type": "object",
                  "required": [ "input_R1", "output_R1" ],
                  "additionalProperties": { "$ref": "#/definitions/file" }
                },

                "fastqc_R1": {
                  "description": "FastQC files of the R1 read",
                  "type": "object",
                  "additionalProperties": { "$ref": "#/definitions/file" }
                }
              },
              "additionalProperties": { "$ref": "#/definitions/fileGroup" }
            },

            "executables": {
              "description": "Executables used in Flexiprep",
              "type": "object",
              "additionalProperties": { "$ref": "#/definitions/executable" }
            },

            "settings": {
              "description": "Settings used for the Flexiprep run",
              "type": "object",
              "required": [ "skip_trim", "skip_clip", "paired" ],

              "properties": {

                "skip_trim": {
                  "description": "Whether base quality trimming step is skipped or not",
                  "type": "boolean"
                },

                "skip_clip": {
                  "description": "Whether adapter clipping step is skipped or not",
                  "type": "boolean"
                },

                "paired": {
                  "description": "Whether the input sequence is paired or not",
                  "type": "boolean"
                }
              }
            },

            "stats": {
              "description": "Statistics gathered by Flexiprep",
              "type": "object",
              "required": [ "fastqc_R1", "seqstat_R1" ],

              "properties": {

                "seqstat_R1": { "$ref": "#/definitions/statsSeqstat" },
                "seqstat_R2": { "$ref": "#/definitions/statsSeqstat" },
                "seqstat_R1_qc": { "$ref": "#/definitions/statsSeqstat" },
                "seqstat_R1_qc": { "$ref": "#/definitions/statsSeqstat" },
                "fastqc_R1": { "$ref": "#/definitions/statsFastqc" },
                "fastqc_R2": { "$ref": "#/definitions/statsFastqc" },
                "fastqc_R1_qc": { "$ref": "#/definitions/statsFastqc" },
                "fastqc_R2_qc": { "$ref": "#/definitions/statsFastqc" },
                "clipping_R1": { "$ref": "#/definitions/statsCutadapt" },
                "clipping_R2": { "$ref": "#/definitions/statsCutadapt" },

                "fastq_sync": {
                  "description": "Statistics for read syncing, after clipping",
                  "type": "object",

                  "properties": {

                    "num_reads_discarded_R1": { "type": "integer" },
                    "num_reads_discarded_R2": { "type": "integer" },
                    "num_reads_kept": { "type": "integer" }
                  }
                },

                "trimming": {
                  "description": "Statistics for base-quality trimming, based on sickle results",
                  "type": "object",
                  "required": [ "num_reads_discarded_total", "num_reads_kept" ],
                  "additionalProperties": false,

                  "properties": {

                    "num_reads_discarded_total": { "type": "integer" },
                    "num_reads_kept": { "type": "integer" },
                    "num_reads_discarded_R1": { "type": "integer" },
                    "num_reads_discarded_R2": { "type": "integer" },
                    "num_reads_discarded_both": { "type": "integer" },
                    "num_reads_kept_R1": { "type": "integer" },
                    "num_reads_kept_R2": { "type": "integer" }
                  }
                }
              }
            }
          }
        },

        "mapping": {
          "description": "Library-level mapping information",
          "type": "object",
          "required": [ "files", "executables", "settings" ],

          "properties": {

            "files": {
              "description": "File groups tracked by Mapping",
              "type": "object",
              "required": [ "pipeline" ],

              "properties": {

                "pipeline": {
                  "description": "Initial input files and final output files in Mapping",
                  "type": "object",
                  "required": [ "input_R1", "output_bamfile" ],
                  "additionalProperties": { "$ref": "#/definitions/file" }
                }
              },
              "additionalProperties": { "$ref": "#/definitions/fileGroup" }
            },

            "executables": {
              "description": "Executables used in Mapping",
              "type": "object",
              "additionalProperties": { "$ref": "#/definitions/executable" }
            },

            "settings": {
              "description": "Settings used for Mapping",
              "type": "object",
              "required": [ "aligner", "chunking", "number_chunks", "skip_flexiprep", "skip_markduplicates", "skip_metrics" ],

              "properties": {

                "aligner": { "type": "string" },

                "chunking": {
                  "description": "Whether the input FASTQ files are split (chunked), aligned separately, and then merged, or not",
                  "type": "boolean"
                },

                "number_chunks": {
                  "description": "If chungking is enabled, the number of FASTQ chunks",
                  "type": "integer"
                },

                "skip_flexipep": {
                  "description": "Whether the Flexiprep pipeline run is skipped or not",
                  "type": "boolean"
                },

                "skip_markduplicates": {
                  "description": "Whether the Picard MarkDuplicates step is skipped or not",
                  "type": "boolean"
                },

                "skip_metrics": {
                  "description": "Whether the alignment metrics gethering (by the BamMetrics) pipeline is skipped or not",
                  "type": "boolean"
                }
              }
            }
          }
        },

        "bammetrics": {
          "description": "Library-level mapping metrics",
          "type": "object",
          "required": [ "files", "executables", "stats" ],

          "properties": {

            "files": {
              "description": "File groups tracked by BamMetrics",
              "type": "object",
              "required": [ "pipeline" ],

              "properties": {

                "pipeline": {
                  "description": "Initial input files and final output files in Mapping",
                  "type": "object",
                  "additionalProperties": { "$ref": "#/definitions/file" }
                }
              },
              "additionalProperties": { "$ref": "#/definitions/fileGroup" }
            },

            "executables": {
              "description": "Executables used in BamMetrics",
              "type": "object",
              "additionalProperties": { "$ref": "#/definitions/executable" }
            },

            "stats": {
              "description": "Statistics gathered by BamMetrics",
              "type": "object",
              "required": [ "alignment_metrics", "biopet_flagstat" ],

              "properties": {

                "alignment_metrics": { "$ref": "#/definitions/statsAlignmentSummary" },

                "biopet_flagstat": { "$ref": "#/definitions/statsBiopetFlagstat" },

bow's avatar
bow committed
463
                "insert_size_metrics": { "$ref": "#/definitions/statsInsertSizeMetrics" }
bow's avatar
bow committed
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
              }
            }
          }
        },

        "gentrap": {
          "description": "Library-level Gentrap information",
          "type": "object",
          "required": [ "files", "stats" ],

          "properties": {

            "files": {
              "description": "File groups tracked by Gentrap",
              "type": "object",
              "required": [ "pipeline", "rna_metrics" ],

              "properties": {

                "pipeline": {
                  "description": "Library-level Gentrap files",
                  "type": "object",
                  "required": [ "alignment" ],
                  "additionalProperties": { "$ref": "#/definitions/file" }
                },

                "rna_metrics": {
                  "description": "Library-level RNA-seq metrics",
                  "type": "object",
                  "required": [ "annotation", "metrics" ],
                  "additionalProperties": { "$ref": "#/definitions/file" }
                }
              },
              "additionalProperties": { "$ref": "#/definitions/fileGroup" }
            },

            "stats": {
              "description": "Library-level Gentrap statistics",
              "type": "object",
              "required": [ "rna_metrics" ],

              "properties": {

                "rna_metrics": { "$ref": "#/definitions/statsRnaSeqMetrics" }
              }
            }
          }
        }
      }
    },

    "referenceContig": {
      "description": "Entry for a single contig in a reference sequence",
      "type": "object",
      "required": [ "md5", "size" ],

      "properties": {

        "md5": {
          "description": "MD5 checksum of the contig",
          "type": "string"
        },

        "size": {
          "description": "Size of the contig in base pairs",
          "type": "integer"
        }
      }
    },

    "fileGroup": {
      "description": "File entries grouped as properties of an object",
      "type": "object",
      "additionalProperties": { "$ref": "#/definitions/file" }
    },

    "file": {
      "description": "A single file entry",
      "type": "object",
      "required": [ "path", "md5" ],
      "additionalProperties": false,

      "properties": {

        "md5":    { "type": "string" },
        "sha1":   { "type": "string" },
        "sha256": { "type": "string" },

        "path":   {
          "description": "Absolute file system path of the file",
          "type": "string"
        }
      }
    },

    "executable": {
      "description": "Entry for storing executable information",
      "type": "object",
      "required": [ "version" ],
      "additionalProperties": false,

      "properties": {

        "version":  {
          "description": "Version of the executable, null if not available",
          "type": ["string", "null"]
        },

        "md5": {
          "description": "MD5 checksum of the executable, null if not available",
          "type": ["string", "null"]
        },

        "jar_md5": {
          "description": "MD5 checksum of the JAR (only for JAR-packaged tools)",
          "type": ["string", "null"]
        },

        "java_md5": {
          "description": "MD5 checksum of the java executable (only for JAR-packaged tools)",
          "type": ["string", "null"]
        }
      }
    },

    "statsSeqstat": {
      "description": "Sequence statistics created by SeqStat (part of the Flexiprep pipeline)",
      "type": "object",
      "required": [ "bases", "reads" ],
      "additionalProperties": false,

      "properties": {

        "bases": {
          "description": "Base pair-level statistics",
          "type": "object",
600
          "required": [ "nucleotides", "num_total", "num_by_qual" ],
bow's avatar
bow committed
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616

          "properties": {

            "nucleotides": {
              "description": "Counts of specific nucleotides across all reads (including ambiguous characters as outlined in http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2865858/",
              "type": "object",
              "additionalProperties": false,

              "patternProperties": {
                "^[ACGTURYMKSWHBVDN]$": { "type": "integer" }
              }
            },

            "num_total": {
              "description": "Total number of bases",
              "type": "integer"
617
618
619
620
621
622
            },

            "num_by_qual": {
              "description": "Array of base counts by quality, from quality 0 to 60",
              "type": "array",
              "items": { "type": "integer" }
bow's avatar
bow committed
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
            }
          }
        },

        "reads": {
          "description": "Read-level statistics",
          "type": "object",
          "required": [ "len_max", "len_min", "num_with_n", "num_total", "qual_encoding" ],

          "properties": {

            "len_max": {
              "description": "Length of longest read",
              "type": "integer"
            },

            "len_min": {
              "description": "Length of shortest read",
              "type": "integer"
            },

            "num_with_n": {
              "description": "Number of reads that contains at least one 'N' or 'n' base",
              "type": "integer"
            },

            "num_total": {
              "description": "Total number of reads",
              "type": "integer"
            },

            "qual_encoding": {
              "description": "Quality encoding; which can be sanger (ASCII offset 33), solexa, or illumina (both with ASCII offset 64)",
              "type": "string",
              "enum": [ "sanger", "illumina", "solexa" ]
            }
          }
        }
      }
    },

    "statsFastqc": {
      "description": "Sequence statistics created by FastQC (part of the Flexiprep pipeline)",
      "type": "object",
      "required": [ "median_qual_by_position", "content_by_position" ],

      "properties": {

        "median_qual_by_position": {
          "description": "Array of median base quality per position (aggregated from all reads)",
          "type": "array",
          "items": { "type": "number" },
          "minItems": 1
        },

        "content_by_position": {
          "description": "Array of base composition per position (aggregated from all reads)",
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": false,

            "patternProperties": {
              "^[ACGTURYMKSWHBVDN]$": { "type": "number" }
            }
          },
          "minItems": 1
        }
      }
    },

    "statsCutadapt": {
      "description": "Sequence statistics from a Cutadapt run (part of the Flexiprep pipeline)",
      "type": "object",
      "required": [ "adapters", "num_reads_affected", "num_reads_discarded_too_long", "num_reads_discarded_too_short" ],

      "properties": {

        "num_reads_affected": { "type": "integer" },
        "num_reads_discarded_too_long": { "type": "integer" },
        "num_reads_discarded_too_short": { "type": "integer" },

        "adapters": {
          "description": "Adapters found in the library",
          "type": "object",
          "additionalProperties": false,

          "patternProperties": {
            "^.+$": {
              "description": "Adapter sequence and how many times it is clipped by Cutadapt",
              "type": "array",
              "items": { "type": [ "string", "integer" ] },
              "minItems": 2,
              "maxItems": 2
            }
          }
        }
      }
    },

    "statsAlignmentSummary": {
      "description": "Metrics gathered by Picard CollectAlignmentSummaryMetrics",
      "type": "object",
      "additionalProperties": false,

      "properties": {

        "FIRST_OF_PAIR": { "$ref": "#/definitions/statsAlignmentSummaryPair" },
        "SECOND_OF_PAIR": { "$ref": "#/definitions/statsAlignmentSummaryPair" },
        "PAIR": { "$ref": "#/definitions/statsAlignmentSummaryPair" },
        "UNPAIRED": { "$ref": "#/definitions/statsAlignmentSummaryPair" }
      }
    },

    "statsAlignmentSummaryPair": {
      "description": "Alignment statistics gathered by Picard CollectAlignmentSummaryMetrics, per pair",
      "type": "object",
      "required": [ "pct_chimeras", "pf_hq_aligned_reads", "pf_hq_error_rate", "pf_indel_rate", "pf_mismatch_rate",
                    "pf_reads", "total_reads" ],

      "properties": {

        "bad_cycles": { "type": "integer" },
        "mean_read_length": { "type": "number" },
        "pct_adapter": { "type": "number" },
        "pct_chimeras": { "type": "number" },
        "pct_pf_reads": { "type": "number" },
        "pct_pf_reads_aligned": { "type": "number" },
        "pct_reads_aligned_in_pairs": { "type": "number" },
        "pf_aligned_bases": { "type": "integer" },
        "pf_hq_aligned_bases": { "type": "integer" },
        "pf_hq_aligned_q20_bases": { "type": "integer" },
        "pf_hq_aligned_reads": { "type": "integer" },
        "pf_hq_error_rate": { "type": "number" },
        "pf_hq_median_mismatches": { "type": "number" },
        "pf_indel_rate": { "type": "number" },
        "pf_mismatch_rate": { "type": "number" },
        "pf_noise_reads": { "type": "integer" },
        "pf_reads": { "type": "integer" },
        "pf_reads_aligned": { "type": "integer" },
        "reads_aligned_in_pairs": { "type": "integer" },
        "strand_balance": { "type": "number" },
        "total_reads": { "type": "integer" }
      }
    },

    "statsBiopetFlagstat": {
      "description": "Alignment statistics gathered by the BiopetFlagstat tool",
      "type": "object",
      "required": [ "All", "Mapped", "ReadPaired", "ProperPair" ],

      "properties": {

        "All": { "type": "integer" },
        "Duplicates": { "type": "integer" },
        "First inverted, second read inverted": { "type": "integer" },
        "First inverted, second read normal": { "type": "integer" },
        "First normal, second read inverted (paired end orientation)": { "type": "integer" },
        "First normal, second read normal": { "type": "integer" },
        "FirstOfPair": { "type": "integer" },
        "MAPQ>0": { "type": "integer" },
        "MAPQ>10": { "type": "integer" },
        "MAPQ>20": { "type": "integer" },
        "MAPQ>30": { "type": "integer" },
        "MAPQ>40": { "type": "integer" },
        "MAPQ>50": { "type": "integer" },
        "MAPQ>60": { "type": "integer" },
        "Mapped": { "type": "integer" },
        "Mate in same strand": { "type": "integer" },
        "Mate on other chr": { "type": "integer" },
        "MateNegativeStrand": { "type": "integer" },
        "MateUnmapped": { "type": "integer" },
        "NotPrimaryAlignment": { "type": "integer" },
        "ProperPair": { "type": "integer" },
        "ReadFailsVendorQualityCheck": { "type": "integer" },
        "ReadNegativeStrand": { "type": "integer" },
        "ReadPaired": { "type": "integer" },
        "SecondOfPair": { "type": "integer" },
        "SecondaryOrSupplementary": { "type": "integer" },
        "SupplementaryAlignment": { "type": "integer" }
      }
    },

    "statsInsertSizeMetrics": {
      "description": "Alignment statistics gathered by Picard CollectInsertSizeMetrics tool",
      "type": "object",
      "required": [ "max_insert_size", "mean_insert_size", "median_insert_size", "min_insert_size",
                    "pair_orientation", "read_pairs", "standard_deviation" ],

      "properties": {
        "max_insert_size": { "type": "integer" },
        "mean_insert_size": { "type": "number" },
        "median_absolute_deviation": { "type": "number" },
        "median_insert_size": { "type": "number" },
        "min_insert_size": { "type": "integer" },
        "pair_orientation": { "type": "string" },
        "read_pairs": { "type": "integer" },
        "standard_deviation": { "type": "number" },
        "width_of_10_percent": { "type": "integer" },
        "width_of_20_percent": { "type": "integer" },
        "width_of_30_percent": { "type": "integer" },
        "width_of_40_percent": { "type": "integer" },
        "width_of_50_percent": { "type": "integer" },
        "width_of_60_percent": { "type": "integer" },
        "width_of_70_percent": { "type": "integer" },
        "width_of_80_percent": { "type": "integer" },
        "width_of_90_percent": { "type": "integer" },
        "width_of_99_percent": { "type": "integer" }
      }
    },

    "statsRnaSeqMetrics": {
      "description": "RNA-seq statistics gathered by Picard CollectRnaSeqMetrics tool",
      "type": "object",
      "required": [ "coding_bases", "correct_strand_reads", "ignored_reads", "incorrect_strand_reads",
                    "intergenic_bases", "intronic_bases", "median_3prime_bias", "median_5prime_bias",
839
840
                    "median_5prime_to_3prime_bias", "normalized_transcript_cov", "pf_aligned_bases", "pf_bases",
                    "utr_bases" ],
bow's avatar
bow committed
841
842
843
844
845
846
847
848
849
850

      "properties": {
        "coding_bases": { "type": "integer" },
        "correct_strand_reads": { "type": "integer" },
        "ignored_reads": { "type": "integer" },
        "incorrect_strand_reads": { "type": "integer" },
        "intergenic_bases": { "type": "integer" },
        "intronic_bases": { "type": "integer" },
        "median_3prime_bias": { "type": "number" },
        "median_5prime_bias": { "type": "number" },
851
        "median_5prime_to_3prime_bias": { "type": ["number", "string"] },
bow's avatar
bow committed
852
        "median_cv_coverage": { "type": "number" },
853
854
855
856
        "normalized_transcript_cov": {
          "type": "array",
          "items": { "type": "number" }
        },
bow's avatar
bow committed
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
        "pct_coding_bases": { "type": "number" },
        "pct_correct_strand_reads": { "type": "number" },
        "pct_intergenic_bases": { "type": "number" },
        "pct_intronic_bases": { "type": "number" },
        "pct_mrna_bases": { "type": "number" },
        "pct_ribosomal_bases": { "type": "number" },
        "pct_usable_bases": { "type": "number" },
        "pct_utr_bases": { "type": "number" },
        "pf_aligned_bases": { "type": "integer" },
        "pf_bases": { "type": "integer" },
        "ribosomal_bases": { "type": "integer" },
        "utr_bases": { "type": "integer" }
      }
    }
  }
}