GPF Study Configuration

  • id - ID of the study. This is a required field.

  • name - display name of the study. If the name is not specified, the id will be used as the display name.

  • enabled - whether the study is enabled.

  • description_file - path to the study description file.

  • study_phenotype - study phenotype.

  • has_denovo - whether the study has de novo variants.

  • has_transmitted - whether the study has transmitted variants.

  • has_cnv - whether the study has CNV variants.

  • has_complex - whether the study has complex variants.

  • has_tandem_repeat - whether the study has tandem repeat variants.

  • has_zygosity - whether the study has zygosity information.

  • phenotype_data - phenotype data associated with the study.

  • phenotype_browser - whether the phenotype browser is enabled.

  • phenotype_tool - whether the phenotype tool is enabled.

  • person_set_collections - section to define person set collections associated with the study.

  • genotype_storage - section to define genotype storage configuration for the study.

  • genotype browser - section to define genotype browser configuration for the study.

  • common_report - section to define common report configuration for the study.

  • denovo_gene_sets - section to define de novo gene sets configuration for the study.

  • enrichment - section to define enrichment configuration for the study.

  • gene_browser - section to define gene browser configuration for the study.

  1id: example_study
  2phenotype_browser: false
  3phenotype_tool: false
  4study_type:
  5- WE
  6study_phenotype: autism
  7has_transmitted: false
  8has_denovo: true
  9has_complex: false
 10has_cnv: false
 11
 12person_set_collections:
 13  selected_person_set_collections:
 14  - phenotype
 15  phenotype:
 16    id: phenotype
 17    name: Phenotype
 18    sources:
 19    - from: pedigree
 20      source: status
 21    domain:
 22    - id: autism
 23      name: autism
 24      values:
 25      - affected
 26      color: '#ff2121'
 27    - id: unaffected
 28      name: unaffected
 29      values:
 30      - unaffected
 31      color: '#ffffff'
 32    default:
 33      id: unspecified
 34      name: unspecified
 35      color: '#aaaaaa'
 36
 37genotype_browser:
 38  enabled: true
 39
 40  has_present_in_child: true
 41  has_present_in_parent: true
 42  has_pedigree_selector: true
 43
 44  variant_types:
 45    - sub
 46    - ins
 47    - del
 48    - complex
 49  columns:
 50    genotype:
 51        pedigree:
 52            name: pedigree
 53            source: pedigree
 54        worst_effect:
 55            name: worst effect
 56            source: worst_effect
 57        genes:
 58            name: genes
 59            source: genes
 60        lgd_rank:
 61            name: LGD rank
 62            source: LGD_rank
 63            format: '%%d'
 64        rvis_rank:
 65            name: RVIS rank
 66            source: RVIS_rank
 67            format: '%%d'
 68        pli_rank:
 69            name: pLI rank
 70            source: pLI_rank
 71            format: '%%d'
 72        family_id:
 73            name: family id
 74            source: family
 75        study:
 76            name: study
 77            source: study_name
 78        family_person_ids:
 79            name: family person ids
 80            source: family_person_ids
 81        location:
 82            name: location
 83            source: location
 84        variant:
 85            name: variant
 86            source: variant
 87        chrom:
 88            name: CHROM
 89            source: chrom
 90        position:
 91            name: POS
 92            source: position
 93        reference:
 94            name: REF
 95            source: reference
 96        alternative:
 97            name: ALT
 98            source: alternative
 99        carrier_person_ids:
100            name: carrier person ids
101            source: carrier_person_ids
102        carrier_person_attributes:
103            name: carrier person attributes
104            source: carrier_person_attributes
105        family_person_attributes:
106            name: family person attributes
107            source: family_person_attributes
108        family_phenotypes:
109            name: family phenotypes
110            source: family_phenotypes
111        carrier_phenotypes:
112            name: carrier phenotypes
113            source: carrier_phenotypes
114        inheritance:
115            name: inheritance type
116            source: inheritance_type
117        study_phenotype:
118            name: study phenotype
119            source: study_phenotype
120        best:
121            name: family best state
122            source: best_st
123        family_genotype:
124            name: family genotype
125            source: genotype
126        family_structure:
127            name: family structure
128            source: family_structure
129        geneeffect:
130            name: all effects
131            source: effects
132        effectdetails:
133            name: effect details
134            source: effect_details
135        alt_alleles:
136            name: alt alleles
137            source: af_allele_count
138        par_called:
139            name: parents called
140            source: af_parents_called_count
141        allele_freq:
142            name: allele frequency
143            source: af_allele_freq
144        seen_as_denovo:
145            name: seen_as_denovo
146            source: seen_as_denovo
147        seen_in_affected:
148            name: seen_in_affected
149            source: seen_in_affected
150        seen_in_unaffected:
151            name: seen_in_unaffected
152            source: seen_in_unaffected
153        phylop_phylop100way:
154            name: 100way
155            source: phylop100way
156            format: '%%.3f'
157        phylop_phylop30way:
158            name: 30way
159            source: phylop30way
160            format: '%%.3f'
161        phylop_phylop20way:
162            name: 20way
163            source: phylop20way
164            format: '%%.3f'
165        phastcons_phastcons100way:
166            name: 100way
167            source: phastcons100way
168            format: '%%.3f'
169        phastcons_phastcons30way:
170            name: 30way
171            source: phastcons30way
172            format: '%%.3f'
173        phastcons_phastcons20way:
174            name: 20way
175            source: phastcons20way
176            format: '%%.3f'
177        fitcons_fitcons2_e073:
178            name: Prefrontal Cortex
179            source: fitcons2_e073
180            format: '%%.3f'
181        fitcons_fitcons2_e081:
182            name: ' Male Fetal'
183            source: fitcons2_e081
184            format: '%%.3f'
185        fitcons_fitcons2_e082:
186            name: Female Fetal
187            source: fitcons2_e082
188            format: '%%.3f'
189        freq_ssc:
190            name: SSC
191            source: ssc_freq
192            format: '%%.3f'
193        freq_exome_gnomad:
194            name: exome gnomAD
195            source: exome_gnomad_v2_1_1_af_percent
196            format: '%%.3f'
197        freq_genome_gnomad:
198            name: genome gnomAD
199            source: genome_gnomad_v3_af_percent
200            format: '%%.3f'
201        cadd_raw:
202            name: CADD raw
203            source: cadd_raw
204            format: '%%.3f'
205        cadd_phred:
206            name: CADD phred
207            source: cadd_phred
208            format: '%%.3f'
209        mpc:
210            name: MPC
211            source: mpc
212            format: '%%.3f'
213        linsight:
214            name: Linsight
215            source: linsight
216            format: '%%.3f'
217        genome_gnomad_v2_1_1_ac:
218            name: genome_gnomad_v2_1_1_ac
219            source: genome_gnomad_v2_1_1_ac
220            format: '%%d'
221        genome_gnomad_v2_1_1_an:
222            name: genome_gnomad_v2_1_1_an
223            source: genome_gnomad_v2_1_1_an
224            format: '%%d'
225        genome_gnomad_v2_1_1_controls_ac:
226            name: genome_gnomad_v2_1_1_controls_ac
227            source: genome_gnomad_v2_1_1_controls_ac
228            format: '%%d'
229        genome_gnomad_v2_1_1_controls_an:
230            name: genome_gnomad_v2_1_1_controls_an
231            source: genome_gnomad_v2_1_1_controls_an
232            format: '%%d'
233        genome_gnomad_v2_1_1_non_neuro_ac:
234            name: genome_gnomad_v2_1_1_non_neuro_ac
235            source: genome_gnomad_v2_1_1_non_neuro_ac
236            format: '%%d'
237        genome_gnomad_v2_1_1_non_neuro_an:
238            name: genome_gnomad_v2_1_1_non_neuro_an
239            source: genome_gnomad_v2_1_1_non_neuro_an
240            format: '%%d'
241        genome_gnomad_v2_1_1_af_percent:
242            name: genome_gnomad_v2_1_1_af_percent
243            source: genome_gnomad_v2_1_1_af_percent
244            format: '%%.3f'
245        genome_gnomad_v2_1_1_controls_af_percent:
246            name: genome_gnomad_v2_1_1_controls_af_percent
247            source: genome_gnomad_v2_1_1_controls_af_percent
248            format: '%%.3f'
249        genome_gnomad_v2_1_1_non_neuro_af_percent:
250            name: genome_gnomad_v2_1_1_non_neuro_af_percent
251            source: genome_gnomad_v2_1_1_non_neuro_af_percent
252            format: '%%.3f'
253        exome_gnomad_v2_1_1_ac:
254            name: exome_gnomad_v2_1_1_ac
255            source: exome_gnomad_v2_1_1_ac
256            format: '%%d'
257        exome_gnomad_v2_1_1_an:
258            name: exome_gnomad_v2_1_1_an
259            source: exome_gnomad_v2_1_1_an
260        exome_gnomad_v2_1_1_controls_ac:
261            name: exome_gnomad_v2_1_1_controls_ac
262            source: exome_gnomad_v2_1_1_controls_ac
263            format: '%%d'
264        exome_gnomad_v2_1_1_controls_an:
265            name: exome_gnomad_v2_1_1_controls_an
266            source: exome_gnomad_v2_1_1_controls_an
267            format: '%%d'
268        exome_gnomad_v2_1_1_non_neuro_ac:
269            name: exome_gnomad_v2_1_1_non_neuro_ac
270            source: exome_gnomad_v2_1_1_non_neuro_ac
271            format: '%%d'
272        exome_gnomad_v2_1_1_non_neuro_an:
273            name: exome_gnomad_v2_1_1_non_neuro_an
274            source: exome_gnomad_v2_1_1_non_neuro_an
275            format: '%%d'
276        exome_gnomad_v2_1_1_af_percent:
277            name: exome_gnomad_v2_1_1_af_percent
278            source: exome_gnomad_v2_1_1_af_percent
279            format: '%%.3f'
280        exome_gnomad_v2_1_1_controls_af_percent:
281            name: exome_gnomad_v2_1_1_controls_af_percent
282            source: exome_gnomad_v2_1_1_controls_af_percent
283            format: '%%.3f'
284        exome_gnomad_v2_1_1_non_neuro_af_percent:
285            name: exome_gnomad_v2_1_1_non_neuro_af_percent
286            source: exome_gnomad_v2_1_1_non_neuro_af_percent
287            format: '%%.3f'
288        genome_gnomad_v3_ac:
289            name: genome_gnomad_v3_ac
290            source: genome_gnomad_v3_ac
291            format: '%%d'
292        genome_gnomad_v3_an:
293            name: genome_gnomad_v3_an
294            source: genome_gnomad_v3_an
295            format: '%%d'
296        genome_gnomad_v3_af_percent:
297            name: genome_gnomad_v3_af_percent
298            source: genome_gnomad_v3_af_percent
299            format: '%%.3f'
300        phylop100way:
301            name: phyloP100way
302            source: phylop100way
303            format: '%%.3f'
304        phylop30way:
305            name: phyloP30way
306            source: phylop30way
307            format: '%%.3f'
308        phylop20way:
309            name: phyloP20way
310            source: phylop20way
311            format: '%%.3f'
312        phylop7way:
313            name: phyloP7way
314            source: phylop7way
315            format: '%%.3f'
316        phastcons100way:
317            name: phastCons100way
318            source: phastcons100way
319            format: '%%.3f'
320        phastcons30way:
321            name: phastCons30way
322            source: phastcons30way
323            format: '%%.3f'
324        phastcons20way:
325            name: phastCons20way
326            source: phastcons20way
327            format: '%%.3f'
328        phastcons7way:
329            name: phastCons7way
330            source: phastcons7way
331            format: '%%.3f'
332        fitcons_i6_merged:
333            name: FitCons i6 merged
334            source: fitcons_i6_merged
335            format: '%%.3f'
336        fitcons2_e067:
337            name: FitCons2 Brain Angular Gyrus
338            source: fitcons2_e067
339            format: '%%.3f'
340        fitcons2_e068:
341            name: FitCons2 Brain Anterior Caudate
342            source: fitcons2_e068
343            format: '%%.3f'
344        fitcons2_e069:
345            name: FitCons2 Brain Cingulate Gyrus
346            source: fitcons2_e069
347            format: '%%.3f'
348        fitcons2_e070:
349            name: FitCons2 Brain Germinal Matrix
350            source: fitcons2_e070
351            format: '%%.3f'
352        fitcons2_e071:
353            name: FitCons2 Brain Hippocampus Middle
354            source: fitcons2_e071
355            format: '%%.3f'
356        fitcons2_e072:
357            name: FitCons2 Brain Inferior Temporal Lobe
358            source: fitcons2_e072
359            format: '%%.3f'
360        fitcons2_e073:
361            name: FitCons2 Brain Dorsolateral Prefrontal Cortex
362            source: fitcons2_e073
363            format: '%%.3f'
364        fitcons2_e074:
365            name: FitCons2 Brain Substantia Nigra
366            source: fitcons2_e074
367            format: '%%.3f'
368        fitcons2_e081:
369            name: FitCons2 Fetal Brain Male
370            source: fitcons2_e081
371            format: '%%.3f'
372        fitcons2_e082:
373            name: FitCons2 Fetal Brain Female
374            source: fitcons2_e082
375            format: '%%.3f'
376
377  column_groups:
378    genotype:
379      name: genotype
380      columns:
381      - pedigree
382      - carrier_person_attributes
383      - family_person_attributes
384    effect:
385      name: effect
386      columns:
387      - worst_effect
388      - genes
389    gene_scores:
390      name: vulnerability/intolerance
391      columns:
392      - lgd_rank
393      - rvis_rank
394      - pli_rank
395    family:
396      name: family
397      columns:
398      - family_id
399      - study
400    variant:
401      name: variant
402      columns:
403      - location
404      - variant
405    variant_extra:
406      name: variant
407      columns:
408      - chrom
409      - position
410      - reference
411      - alternative
412    carriers:
413      name: carriers
414      columns:
415      - carrier_person_ids
416      - carrier_person_attributes
417    phenotypes:
418      name: phenotypes
419      columns:
420      - family_phenotypes
421      - carrier_phenotypes
422    mpc_cadd:
423      name: MPC and CADD
424      columns:
425      - mpc
426      - cadd_raw
427      - cadd_phred
428    phylop:
429      name: phyloP
430      columns:
431      - phylop_phylop100way
432      - phylop_phylop30way
433      - phylop_phylop20way
434    phastcons:
435      name: phastCons
436      columns:
437      - phastcons_phastcons100way
438      - phastcons_phastcons30way
439      - phastcons_phastcons20way
440    fitcons:
441      name: FitCons Brain
442      columns:
443      - fitcons_fitcons2_e073
444      - fitcons_fitcons2_e081
445      - fitcons_fitcons2_e082
446    freq:
447      name: Frequency
448      columns:
449      - freq_ssc
450      - freq_exome_gnomad
451      - freq_genome_gnomad
452
453  preview_columns:
454  - family
455  - variant
456  - genotype
457  - effect
458  - gene_scores
459  - phylop
460  - phastcons
461  - mpc_cadd
462  - fitcons
463  - freq
464  download_columns:
465  - family
466  - study_phenotype
467  - variant
468  - variant_extra
469  - family_person_ids
470  - family_structure
471  - best
472  - family_genotype
473  - carriers
474  - inheritance
475  - phenotypes
476  - par_called
477  - allele_freq
478  - effect
479  - geneeffect
480  - effectdetails
481  - gene_scores
482  - phylop100way
483  - phylop30way
484  - phylop20way
485  - phylop7way
486  - phastcons100way
487  - phastcons30way
488  - phastcons20way
489  - phastcons7way
490  - cadd_raw
491  - cadd_phred
492  - mpc
493  - linsight
494  - fitcons_i6_merged
495  - fitcons2_e067
496  - fitcons2_e068
497  - fitcons2_e069
498  - fitcons2_e070
499  - fitcons2_e071
500  - fitcons2_e072
501  - fitcons2_e073
502  - fitcons2_e074
503  - fitcons2_e081
504  - fitcons2_e082
505  - genome_gnomad_v2_1_1_ac
506  - genome_gnomad_v2_1_1_an
507  - genome_gnomad_v2_1_1_controls_ac
508  - genome_gnomad_v2_1_1_controls_an
509  - genome_gnomad_v2_1_1_non_neuro_ac
510  - genome_gnomad_v2_1_1_non_neuro_an
511  - genome_gnomad_v2_1_1_af_percent
512  - genome_gnomad_v2_1_1_controls_af_percent
513  - genome_gnomad_v2_1_1_non_neuro_af_percent
514  - exome_gnomad_v2_1_1_ac
515  - exome_gnomad_v2_1_1_an
516  - exome_gnomad_v2_1_1_controls_ac
517  - exome_gnomad_v2_1_1_controls_an
518  - exome_gnomad_v2_1_1_non_neuro_ac
519  - exome_gnomad_v2_1_1_non_neuro_an
520  - exome_gnomad_v2_1_1_af_percent
521  - exome_gnomad_v2_1_1_controls_af_percent
522  - exome_gnomad_v2_1_1_non_neuro_af_percent
523  - genome_gnomad_v3_ac
524  - genome_gnomad_v3_an
525  - genome_gnomad_v3_af_percent
526
527common_report:
528  enabled: true
529  effect_groups:
530  - LGDs
531  - nonsynonymous
532  - UTRs
533  - CNV
534  effect_types:
535  - Nonsense
536  - Frame-shift
537  - Splice-site
538  - Missense
539  - No-frame-shift
540  - noStart
541  - noEnd
542  - Synonymous
543  - Non coding
544  - Intron
545  - Intergenic
546  - 3'-UTR
547  - 5'-UTR
548
549denovo_gene_sets:
550  enabled: true
551  selected_person_set_collections:
552  - phenotype
553  standard_criterias:
554    effect_types:
555      segments:
556        LGDs: LGDs
557        Missense: missense
558        Synonymous: synonymous
559    sexes:
560      segments:
561        Female: F
562        Male: M
563        Unspecified: U
564  recurrency_criteria:
565    segments:
566      Single:
567          start: 1
568          end: 2
569      Triple:
570          start: 3
571          end: -1
572      Recurrent:
573          start: 2
574          end: -1
575  gene_sets_names:
576  - LGDs
577  - LGDs.Male
578  - LGDs.Female
579  - LGDs.Recurrent
580  - LGDs.Triple
581  - Missense
582  - Missense.Male
583  - Missense.Female
584  - Missense.Recurrent
585  - Missense.Triple
586  - Synonymous
587  - Synonymous.Male
588  - Synonymous.Female
589  - Synonymous.Recurrent
590  - Synonymous.Triple
591
592enrichment:
593  enabled: false
594  selected_person_set_collections:
595  - phenotype
596  selected_background_models:
597  - hg38/enrichment/coding_length_ref_gene_v20170601
598  - enrichment/samocha_background
599  - hg38/enrichment/ur_synonymous_SFARI_SSC_WGS_2
600  - hg38/enrichment/ur_synonymous_SFARI_SSC_WGS_CSHL
601  - hg38/enrichment/ur_synonymous_w1202s766e611_liftover
602  - hg38/enrichment/ur_synonymous_iWES_v1_1
603  - hg38/enrichment/ur_synonymous_iWES_v2
604  - hg38/enrichment/ur_synonymous_iWGS_v1_1
605  - hg38/enrichment/ur_synonymous_AGRE_WG38_859
606  default_background_model: enrichment/samocha_background
607  selected_counting_models:
608  - enrichment_events_counting
609  - enrichment_gene_counting
610  counting:
611    enrichment_events_counting:
612      id: enrichment_events_counting
613      name: Counting events
614      desc: Counting events
615    enrichment_gene_counting:
616      id: enrichment_gene_counting
617      name: Counting affected genes
618      desc: Counting affected genes
619  default_counting_model: enrichment_events_counting
620  effect_types:
621  - LGDs
622  - missense
623  - synonymous
624
625gene_browser:
626  enabled: true
627  frequency_column: genome_gnomad_v3_af_percent
628  frequency_name: genome GnomAD %%
629  effect_column: effect.worst effect type
630  location_column: variant.location
631  domain_min: 0.01
632  domain_max: 100