Skip to content

Commit c209402

Browse files
authored
Merge pull request #1304 from AlexsLemonade/allyhawkins/merged-formatting-reference
Add merged object information to reference SCE and AnnData files
2 parents 0fe77c9 + 587d087 commit c209402

3 files changed

Lines changed: 462 additions & 18 deletions

File tree

references/anndata-formatting-reference.json

Lines changed: 173 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -13,10 +13,10 @@
1313
"subsets_mito_detected": "int",
1414
"subsets_mito_percent": "float",
1515
"total": "float",
16-
"library_id": "category",
17-
"sample_id": "category",
18-
"assay_ontology_term_id": "category",
19-
"suspension_type": "category",
16+
"library_id": "string",
17+
"sample_id": "string",
18+
"assay_ontology_term_id": "string",
19+
"suspension_type": "string",
2020
"is_primary_data": "bool"
2121
},
2222
"var": {
@@ -110,10 +110,10 @@
110110
"scpca_filter": "string",
111111
"scDblFinder_class": "string",
112112
"scDblFinder_score": "float",
113-
"library_id": "category",
114-
"sample_id": "category",
115-
"assay_ontology_term_id": "category",
116-
"suspension_type": "category",
113+
"library_id": "string",
114+
"sample_id": "string",
115+
"assay_ontology_term_id": "string",
116+
"suspension_type": "string",
117117
"is_primary_data": "bool"
118118
},
119119
"var": {
@@ -258,10 +258,10 @@
258258
"scpca_filter": "string",
259259
"scDblFinder_class": "string",
260260
"scDblFinder_score": "float",
261-
"library_id": "category",
262-
"sample_id": "category",
263-
"assay_ontology_term_id": "category",
264-
"suspension_type": "category",
261+
"library_id": "string",
262+
"sample_id": "string",
263+
"assay_ontology_term_id": "string",
264+
"suspension_type": "string",
265265
"is_primary_data": "bool"
266266
},
267267
"var": {
@@ -459,5 +459,166 @@
459459
"ambient_profile": "float"
460460
}
461461
}
462+
},
463+
"merged": {
464+
"rna": {
465+
"has_raw.X": true,
466+
"layers": [
467+
"spliced"
468+
],
469+
"obs": {
470+
"barcodes": "string",
471+
"sum": "float",
472+
"detected": "int",
473+
"subsets_mito_sum": "float",
474+
"subsets_mito_detected": "int",
475+
"subsets_mito_percent": "float",
476+
"total": "float",
477+
"prob_compromised": "float",
478+
"miQC_pass": "bool",
479+
"scpca_filter": "string",
480+
"scDblFinder_class": "string",
481+
"scDblFinder_score": "float",
482+
"additional_modalities": "string",
483+
"library_id": "string",
484+
"cell_id": "string",
485+
"sample_id": "string",
486+
"scpca_project_id": "string",
487+
"submitter_id": "string",
488+
"participant_id": "string",
489+
"submitter": "string",
490+
"age": "string",
491+
"age_timing": "string",
492+
"sex": "string",
493+
"diagnosis": "string",
494+
"subdiagnosis": "string",
495+
"tissue_location": "string",
496+
"disease_timing": "string",
497+
"organism": "string",
498+
"is_xenograft": "bool",
499+
"is_cell_line": "bool",
500+
"development_stage_ontology_term_id": "string",
501+
"sex_ontology_term_id": "string",
502+
"organism_ontology_term_id": "string",
503+
"self_reported_ethnicity_ontology_term_id": "string",
504+
"disease_ontology_term_id": "string",
505+
"tissue_ontology_term_id": "string",
506+
"tech_version": "string",
507+
"assay_ontology_term_id": "string",
508+
"suspension_type": "string",
509+
"is_primary_data": "bool"
510+
},
511+
"var": {
512+
"gene_ids": "string",
513+
"gene_symbol": "string",
514+
"mean": "float",
515+
"detected": "float",
516+
"feature_is_filtered": "bool",
517+
"highly_variable": "bool"
518+
},
519+
"obs_conditional": {
520+
"has_submitter": {
521+
"submitter_celltype_annotation": "string"
522+
},
523+
"has_openscpca": {
524+
"openscpca_celltype_annotation": "string",
525+
"openscpca_celltype_ontology": "string"
526+
},
527+
"has_adt": {
528+
"adt_scpca_filter": "string"
529+
},
530+
"has_cellhash": {
531+
"altexps_cellhash_sum": "float",
532+
"altexps_cellhash_detected": "int",
533+
"altexps_cellhash_percent": "float"
534+
},
535+
"has_hashedDrops": {
536+
"hashedDrops_sampleid": "string"
537+
},
538+
"has_HTODemux": {
539+
"HTODemux_sampleid": "string"
540+
},
541+
"has_vireo": {
542+
"vireo_sampleid": "string",
543+
"vireo_donor_id": "string",
544+
"vireo_prob_max": "float",
545+
"vireo_prob_doublet": "float",
546+
"vireo_n_vars": "float",
547+
"vireo_best_singlet": "string",
548+
"vireo_best_doublet": "string",
549+
"vireo_doublet_logLikRatio": "float"
550+
},
551+
"has_normalization": {
552+
"sizeFactor": "float"
553+
},
554+
"has_clusters": {
555+
"cluster": "category"
556+
},
557+
"has_singler": {
558+
"singler_celltype_annotation": "string",
559+
"singler_celltype_ontology": "string"
560+
},
561+
"has_cellassign": {
562+
"cellassign_celltype_annotation": "string",
563+
"cellassign_celltype_ontology": "string",
564+
"cellassign_max_prediction": "float"
565+
},
566+
"has_scimilarity": {
567+
"scimilarity_celltype_annotation": "string",
568+
"scimilarity_celltype_ontology": "string",
569+
"scimilarity_min_distance": "float"
570+
},
571+
"has_consensus": {
572+
"consensus_celltype_annotation": "string",
573+
"consensus_celltype_ontology": "string"
574+
},
575+
"has_infercnv": {
576+
"is_infercnv_reference": "bool",
577+
"infercnv_total_cnv": "int"
578+
},
579+
"is_multiplexed": {
580+
"sample_id": null
581+
}
582+
},
583+
"obsm": [
584+
"X_pca",
585+
"X_umap"
586+
],
587+
"uns": {
588+
"library_id": "string",
589+
"sample_id": "string",
590+
"merged_highly_variable_genes": "string"
591+
}
592+
},
593+
"adt": {
594+
"obs": {
595+
"zero.ambient": "bool",
596+
"discard": "bool",
597+
"library_id": "string",
598+
"cell_id": "string"
599+
},
600+
"var": {
601+
"adt_id": "string",
602+
"mean": "float",
603+
"detected": "float",
604+
"target_type": "string"
605+
},
606+
"obs_conditional": {
607+
"has_negative_control": {
608+
"sum.controls": "int",
609+
"high.control": "bool"
610+
},
611+
"no_negative_control": {
612+
"ambient.scale": "float",
613+
"high.ambient": "bool"
614+
},
615+
"sizeFactor": "float"
616+
},
617+
"uns": {
618+
"library_id": "string",
619+
"sample_id": "string",
620+
"library_metadata": "string"
621+
}
622+
}
462623
}
463624
}

references/sce-formatting-reference.json

Lines changed: 162 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -319,7 +319,8 @@
319319
"processed": {
320320
"assayNames": [
321321
"counts",
322-
"spliced"
322+
"spliced",
323+
"logcounts"
323324
],
324325
"colData": {
325326
"barcodes": "character",
@@ -575,5 +576,165 @@
575576
}
576577
}
577578
}
579+
},
580+
"merged": {
581+
"assayNames": [
582+
"counts",
583+
"spliced",
584+
"logcounts"
585+
],
586+
"colData": {
587+
"barcodes": "character",
588+
"sum": "numeric",
589+
"detected": "numeric",
590+
"subsets_mito_sum": "numeric",
591+
"subsets_mito_detected": "integer",
592+
"subsets_mito_percent": "numeric",
593+
"total": "numeric",
594+
"prob_compromised": "numeric",
595+
"miQC_pass": "logical",
596+
"scpca_filter": "character",
597+
"scDblFinder_class": "character",
598+
"scDblFinder_score": "numeric",
599+
"additional_modalities": "character",
600+
"library_id": "character",
601+
"cell_id": "character",
602+
"sample_id": "character",
603+
"scpca_project_id": "character",
604+
"submitter_id": "character",
605+
"participant_id": "character",
606+
"submitter": "character",
607+
"age": "character",
608+
"age_timing": "character",
609+
"sex": "character",
610+
"diagnosis": "character",
611+
"subdiagnosis": "character",
612+
"tissue_location": "character",
613+
"disease_timing": "character",
614+
"organism": "character",
615+
"is_xenograft": "logical",
616+
"is_cell_line": "logical",
617+
"development_stage_ontology_term_id": "character",
618+
"sex_ontology_term_id": "character",
619+
"organism_ontology_term_id": "character",
620+
"self_reported_ethnicity_ontology_term_id": "character",
621+
"disease_ontology_term_id": "character",
622+
"tissue_ontology_term_id": "character",
623+
"tech_version": "character",
624+
"assay_ontology_term_id": "character",
625+
"suspension_type": "character"
626+
},
627+
"rowData": {
628+
"gene_ids": "character",
629+
"gene_symbol": "character",
630+
"mean": "numeric",
631+
"detected": "numeric"
632+
},
633+
"colData_conditional": {
634+
"has_submitter": {
635+
"submitter_celltype_annotation": "character"
636+
},
637+
"has_openscpca": {
638+
"openscpca_celltype_annotation": "character",
639+
"openscpca_celltype_ontology": "character"
640+
},
641+
"has_adt": {
642+
"adt_scpca_filter": "character"
643+
},
644+
"has_cellhash": {
645+
"altexps_cellhash_sum": "numeric",
646+
"altexps_cellhash_detected": "integer",
647+
"altexps_cellhash_percent": "numeric"
648+
},
649+
"has_hashedDrops": {
650+
"hashedDrops_sampleid": "character"
651+
},
652+
"has_HTODemux": {
653+
"HTODemux_sampleid": "character"
654+
},
655+
"has_vireo": {
656+
"vireo_sampleid": "character",
657+
"vireo_donor_id": "character",
658+
"vireo_prob_max": "numeric",
659+
"vireo_prob_doublet": "numeric",
660+
"vireo_n_vars": "numeric",
661+
"vireo_best_singlet": "character",
662+
"vireo_best_doublet": "character",
663+
"vireo_doublet_logLikRatio": "numeric"
664+
},
665+
"has_normalization": {
666+
"sizeFactor": "numeric"
667+
},
668+
"has_clusters": {
669+
"cluster": "factor"
670+
},
671+
"has_singler": {
672+
"singler_celltype_annotation": "character",
673+
"singler_celltype_ontology": "character"
674+
},
675+
"has_cellassign": {
676+
"cellassign_celltype_annotation": "character",
677+
"cellassign_celltype_ontology": "character",
678+
"cellassign_max_prediction": "numeric"
679+
},
680+
"has_scimilarity": {
681+
"scimilarity_celltype_annotation": "character",
682+
"scimilarity_celltype_ontology": "character",
683+
"scimilarity_min_distance": "numeric"
684+
},
685+
"has_consensus": {
686+
"consensus_celltype_annotation": "character",
687+
"consensus_celltype_ontology": "character"
688+
},
689+
"has_infercnv": {
690+
"is_infercnv_reference": "logical",
691+
"infercnv_total_cnv": "integer"
692+
}
693+
},
694+
"reducedDimNames": [
695+
"PCA",
696+
"UMAP"
697+
],
698+
"metadata": {
699+
"library_id": "character",
700+
"sample_id": "character",
701+
"library_metadata": "list",
702+
"merged_highly_variable_genes": "character"
703+
},
704+
"altExp": {
705+
"adt": {
706+
"assayNames": [
707+
"counts"
708+
],
709+
"colData": {
710+
"zero.ambient": "logical",
711+
"discard": "logical",
712+
"library_id": "character",
713+
"cell_id": "character"
714+
},
715+
"rowData": {
716+
"adt_id": "character",
717+
"mean": "numeric",
718+
"detected": "numeric",
719+
"target_type": "character"
720+
},
721+
"colData_conditional": {
722+
"has_negative_control": {
723+
"sum.controls": "integer",
724+
"high.control": "logical"
725+
},
726+
"no_negative_control": {
727+
"ambient.scale": "numeric",
728+
"high.ambient": "logical"
729+
},
730+
"sizeFactor": "numeric"
731+
},
732+
"metadata": {
733+
"library_id": "character",
734+
"sample_id": "character",
735+
"library_metadata": "list"
736+
}
737+
}
738+
}
578739
}
579740
}

0 commit comments

Comments
 (0)