Skip to content

Commit b574294

Browse files
bistlinebistline
authored
Merge pull request #2236 from broadinstitute/jb-alexandria-3.0.0
Updating to latest ingest, convention versions (SCP-5971)
2 parents f841242 + a0d61c5 commit b574294

5 files changed

Lines changed: 826 additions & 54 deletions

File tree

‎config/application.rb‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ class Application < Rails::Application
2929
config.middleware.use Rack::Brotli
3030

3131
# Docker image for file parsing via scp-ingest-pipeline
32-
config.ingest_docker_image = 'gcr.io/broad-singlecellportal-staging/scp-ingest-pipeline:1.41.1'
32+
config.ingest_docker_image = 'gcr.io/broad-singlecellportal-staging/scp-ingest-pipeline:1.41.2'
3333

3434
# Docker image for image pipeline jobs
3535
config.image_pipeline_docker_image = 'gcr.io/broad-singlecellportal-staging/image-pipeline:0.1.0_c2b090043'

‎lib/assets/metadata_schemas/alexandria_convention/alexandria_convention_schema.json‎

Lines changed: 1 addition & 36 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
{
2-
"$id": "https://singlecell.broadinstitute.org/single_cell/api/v1/metadata_schemas/alexandria_convention/2.3.0/json",
2+
"$id": "https://singlecell.broadinstitute.org/single_cell/api/v1/metadata_schemas/alexandria_convention/3.0.0/json",
33
"$schema": "https://json-schema.org/draft-07/schema#",
44
"dependencies": {
55
"cell_type__ontology_label": [
@@ -14,9 +14,6 @@
1414
"culture_duration__unit_label": [
1515
"culture_duration__unit"
1616
],
17-
"development_stage__ontology_label": [
18-
"development_stage"
19-
],
2017
"disease__intracellular_pathogen": [
2118
"disease"
2219
],
@@ -119,16 +116,9 @@
119116
"organism_age__unit_label": [
120117
"organism_age__unit"
121118
],
122-
"race__ontology_label": [
123-
"race"
124-
],
125119
"sequencing_instrument_manufacturer_model__ontology_label": [
126120
"sequencing_instrument_manufacturer_model"
127121
],
128-
"small_molecule_perturbation__concentration": [
129-
"small_molecule_perturbation",
130-
"small_molecule_perturbation__concentration__unit"
131-
],
132122
"small_molecule_perturbation__concentration__unit": [
133123
"small_molecule_perturbation__concentration"
134124
],
@@ -225,9 +215,6 @@
225215
},
226216
"development_stage": {
227217
"description": "A classification of the developmental stage of the organism",
228-
"ontology": "https://www.ebi.ac.uk/ols/api/ontologies/hsapdv,https://www.ebi.ac.uk/ols/api/ontologies/mmusdv",
229-
"ontology_browser_url": "https://www.ebi.ac.uk/ols/ontologies/hsapdv,https://www.ebi.ac.uk/ols/ontologies/mmusdv",
230-
"pattern": "^[-A-Za-z0-9]+[_:][-A-Za-z0-9]+",
231218
"type": "string"
232219
},
233220
"development_stage__ontology_label": {
@@ -374,11 +361,8 @@
374361
"gene_perturbation": {
375362
"description": "A perturbation to a gene done to a cell culture",
376363
"items": {
377-
"ontology_browser_url": "https://www.ebi.ac.uk/ols/ontologies/ogg",
378-
"pattern": "^[-A-Za-z0-9]+[_:][-A-Za-z0-9]+",
379364
"type": "string"
380365
},
381-
"ontology": "https://www.ebi.ac.uk/ols/api/ontologies/ogg",
382366
"type": "array"
383367
},
384368
"gene_perturbation__direction": {
@@ -406,9 +390,6 @@
406390
},
407391
"geographical_region": {
408392
"description": "Location where the sample was collected/donated",
409-
"ontology": "https://www.ebi.ac.uk/ols/api/ontologies/gaz",
410-
"ontology_browser_url": "https://www.ebi.ac.uk/ols/ontologies/gaz",
411-
"pattern": "^[-A-Za-z0-9]+[_:][-A-Za-z0-9]+",
412393
"type": "string"
413394
},
414395
"geographical_region__ontology_label": {
@@ -419,11 +400,8 @@
419400
"dependency_condition": "sample_type in cell line, organoid, cultured primary cells",
420401
"description": "a growth factor added to a cell culture media",
421402
"items": {
422-
"ontology_browser_url": "https://www.ebi.ac.uk/ols/ontologies/pr",
423-
"pattern": "^[-A-Za-z0-9]+[_:][-A-Za-z0-9]+",
424403
"type": "string"
425404
},
426-
"ontology": "https://www.ebi.ac.uk/ols/api/ontologies/pr",
427405
"type": "array"
428406
},
429407
"growth_factor_perturbation__concentration": {
@@ -494,9 +472,6 @@
494472
"mouse_strain": {
495473
"dependency_condition": "species == NCBITaxon_10090",
496474
"description": "Mouse strain of the donor organism (ex. C57BL/6, BALB/c, 129, undetermined)",
497-
"ontology": "https://www.ebi.ac.uk/ols/api/ontologies/ncit",
498-
"ontology_browser_url": "https://www.ebi.ac.uk/ols/ontologies/ncit",
499-
"pattern": "^[-A-Za-z0-9]+[_:][-A-Za-z0-9]+",
500475
"type": "string"
501476
},
502477
"mouse_strain__ontology_label": {
@@ -564,14 +539,10 @@
564539
"type": "string"
565540
},
566541
"race": {
567-
"dependency_condition": "species == NCBITaxon_9606",
568542
"description": "An arbitrary classification of a taxonomic group that is a division of a species",
569543
"items": {
570-
"ontology_browser_url": "https://www.ebi.ac.uk/ols/ontologies/ncit",
571-
"pattern": "^[-A-Za-z0-9]+[_:][-A-Za-z0-9]+",
572544
"type": "string"
573545
},
574-
"ontology": "https://www.ebi.ac.uk/ols/api/ontologies/ncit",
575546
"type": "array"
576547
},
577548
"race__ontology_label": {
@@ -604,11 +575,8 @@
604575
"small_molecule_perturbation": {
605576
"description": "a small molecule added to a cell culture (ex. A drug) growth factor (and if it is recombinant, concentration), gene)",
606577
"items": {
607-
"ontology_browser_url": "https://www.ebi.ac.uk/ols/ontologies/chebi",
608-
"pattern": "^[-A-Za-z0-9]+[_:][-A-Za-z0-9]+",
609578
"type": "string"
610579
},
611-
"ontology": "https://www.ebi.ac.uk/ols/api/ontologies/chebi",
612580
"type": "array"
613581
},
614582
"small_molecule_perturbation__concentration": {
@@ -677,11 +645,8 @@
677645
"vaccination": {
678646
"description": "Any known vaccines administered to the donor organism. NOT a full vaccine history",
679647
"items": {
680-
"ontology_browser_url": "https://www.ebi.ac.uk/ols/ontologies/vo",
681-
"pattern": "^[-A-Za-z0-9]+[_:][-A-Za-z0-9]+",
682648
"type": "string"
683649
},
684-
"ontology": "https://www.ebi.ac.uk/ols/api/ontologies/vo",
685650
"type": "array"
686651
},
687652
"vaccination__adjuvants": {

‎lib/assets/metadata_schemas/alexandria_convention/alexandria_convention_schema.tsv‎

Lines changed: 17 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -19,8 +19,8 @@ cell_type__custom string cell_type__custom
1919
culture_duration number sample_type in cell line, organoid, cultured primary cells culture_duration__unit length of time cells have been in culture
2020
culture_duration__unit string ontology https://www.ebi.ac.uk/ols/api/ontologies/uo https://www.ebi.ac.uk/ols/ontologies/uo UO_0000003 culture_duration culture_duration__unit
2121
culture_duration__unit_label string unit_label culture_duration__unit culture_duration__unit_label
22-
development_stage string ontology https://www.ebi.ac.uk/ols/api/ontologies/hsapdv,https://www.ebi.ac.uk/ols/api/ontologies/mmusdv https://www.ebi.ac.uk/ols/ontologies/hsapdv,https://www.ebi.ac.uk/ols/ontologies/mmusdv A classification of the developmental stage of the organism
23-
development_stage__ontology_label string ontology_label development_stage development_stage__ontology_label
22+
development_stage string A classification of the developmental stage of the organism
23+
development_stage__ontology_label string development_stage__ontology_label
2424
disease__intracellular_pathogen string TRUE ontology https://www.ebi.ac.uk/ols/api/ontologies/mondo https://www.ebi.ac.uk/ols/ontologies/mondo MONDO_0005550 disease If evidence of a pathogen is detected in this cell
2525
disease__intracellular_pathogen__ontology_label string TRUE ontology_label disease__intracellular_pathogen disease__intracellular_pathogen__ontology_label
2626
disease__time_since_onset number TRUE disease disease__time_since_onset__unit Amount of time since disease onset
@@ -38,26 +38,26 @@ enrichment__facs_markers string TRUE enrichment_method The surface marke
3838
enrichment_method string TRUE enum "[""cell size selection"", ""fluorescence-activated cell sorting"", ""magnetic affinity cell sorting"", ""laser capture microdissection"", ""density gradient centrifugation"", ""Ficoll-Hypaque method"", ""enrichment of methylated DNA""]" Method used to enrich cells before running library preparation. This could be flow cytometry, column enrichments, etc.
3939
ethnicity string TRUE ontology https://www.ebi.ac.uk/ols/api/ontologies/hancestro https://www.ebi.ac.uk/ols/ontologies/hancestro HANCESTRO:0004 species == NCBITaxon_9606 The ethnicity or ethnicities of the human donor if known
4040
ethnicity__ontology_label string TRUE ontology_label ethnicity ethnicity__ontology_label
41-
gene_perturbation string TRUE ontology https://www.ebi.ac.uk/ols/api/ontologies/ogg https://www.ebi.ac.uk/ols/ontologies/ogg OGG_0000000002 A perturbation to a gene done to a cell culture
41+
gene_perturbation string TRUE A perturbation to a gene done to a cell culture
4242
gene_perturbation__direction string enum "[""knock in"", ""knock out"",""activation"",""repression""]" gene_perturbation The type of perturbation of the gene defined in gene_perturbation. Knock in and knock out are complete additions/depletions of the gene, activation and repression refer to changes in magnitude of expression.
4343
gene_perturbation__dynamics string gene_perturbation Description of the timing with respect to sequencing and other logistical considerations of the gene perturbation
4444
gene_perturbation__method string TRUE gene_perturbation Process by which the gene was perturbed. Ex. CRISPR knock-out
45-
gene_perturbation__ontology_label string TRUE ontology_label gene_perturbation gene_perturbation__ontology_label
46-
geographical_region string ontology https://www.ebi.ac.uk/ols/api/ontologies/gaz https://www.ebi.ac.uk/ols/ontologies/gaz GAZ_00000013 Location where the sample was collected/donated
47-
geographical_region__ontology_label string ontology_label geographical_region geographical_region__ontology_label
48-
growth_factor_perturbation string TRUE ontology https://www.ebi.ac.uk/ols/api/ontologies/pr https://www.ebi.ac.uk/ols/ontologies/pr PR_000000001 sample_type in cell line, organoid, cultured primary cells a growth factor added to a cell culture media
45+
gene_perturbation__ontology_label string TRUE gene_perturbation gene_perturbation__ontology_label
46+
geographical_region string Location where the sample was collected/donated
47+
geographical_region__ontology_label string geographical_region geographical_region__ontology_label
48+
growth_factor_perturbation string TRUE sample_type in cell line, organoid, cultured primary cells a growth factor added to a cell culture media
4949
growth_factor_perturbation__concentration number TRUE growth_factor_perturbation growth_factor_perturbation__concentration__unit Concentration of of each growth factor in the final tissue culture media. Order should be consistent with growth_factor_perturbation
5050
growth_factor_perturbation__concentration__unit string ontology https://www.ebi.ac.uk/ols/api/ontologies/uo https://www.ebi.ac.uk/ols/ontologies/uo UO_0000003 growth_factor_perturbation__concentration growth_factor_perturbation__concentration__unit
5151
growth_factor_perturbation__concentration__unit_label string unit_label growth_factor_perturbation__concentration__unit growth_factor_perturbation__concentration__unit_label
5252
growth_factor_perturbation__ontology_label string TRUE ontology_label growth_factor_perturbation growth_factor_perturbation__ontology_label
5353
growth_factor_perturbation__solvent string TRUE growth_factor_perturbation Solvent in which the growth factor was added to the cells. Ex. the base media.
5454
growth_factor_perturbation__source string TRUE growth_factor_perturbation Source from which the growth factor was purchased
55-
has_electrophysiology boolean boolean
56-
has_morphology boolean boolean
55+
has_electrophysiology boolean boolean
56+
has_morphology boolean boolean
5757
is_living string enum "[""yes"", ""no"", ""unknown""]" Whether organism was alive at time of biomaterial collection
5858
mhc_genotype string MHC genotype for humans and other species
59-
mouse_strain string ontology https://www.ebi.ac.uk/ols/api/ontologies/ncit https://www.ebi.ac.uk/ols/ontologies/ncit "NCIT_C14420 " species == NCBITaxon_10090 Mouse strain of the donor organism (ex. C57BL/6, BALB/c, 129, undetermined)
60-
mouse_strain__ontology_label string ontology_label mouse_strain mouse_strain__ontology_label
59+
mouse_strain string " " species == NCBITaxon_10090 Mouse strain of the donor organism (ex. C57BL/6, BALB/c, 129, undetermined)
60+
mouse_strain__ontology_label string mouse_strain mouse_strain__ontology_label
6161
number_of_reads number Number of reads mapped to that cell
6262
organ_region string TRUE ontology https://api.brain-map.org/api/v2/structure_graph_download/1.json https://atlas.brain-map.org/atlas?atlas=602630314 organ_region
6363
organ_region__ontology_label string TRUE ontology_label organ_region organ_region__ontology_label
@@ -67,13 +67,13 @@ organism_age__unit_label string unit_label organism_age__unit organism_a
6767
paired_ends boolean true if the sequence library has paired end data (false for 10x)
6868
preservation_method string enum "[""Cryopreservation"",""FFPE"",""Fresh"",""Frozen"",""OCT-embedded"",""Snap Frozen""]" Method used for sample preservation
6969
primer string enum "[""poly-dT"",""random""]" Primer used for cDNA synthesis from RNA
70-
race string TRUE ontology https://www.ebi.ac.uk/ols/api/ontologies/ncit https://www.ebi.ac.uk/ols/ontologies/ncit NCIT:C17049 species == NCBITaxon_9606 An arbitrary classification of a taxonomic group that is a division of a species
71-
race__ontology_label string TRUE ontology_label race race__ontology_label
70+
race string TRUE An arbitrary classification of a taxonomic group that is a division of a species
71+
race__ontology_label string TRUE race__ontology_label
7272
read_length string the read structure of the sequencing run
7373
sequencing_instrument_manufacturer_model string ontology https://www.ebi.ac.uk/ols/api/ontologies/efo https://www.ebi.ac.uk/ols/ontologies/efo EFO_0003739 name of sequencing instrument manufacturer
7474
sequencing_instrument_manufacturer_model__ontology_label string ontology_label sequencing_instrument_manufacturer_model sequencing_instrument_manufacturer_model__ontology_label
75-
small_molecule_perturbation string TRUE ontology https://www.ebi.ac.uk/ols/api/ontologies/chebi https://www.ebi.ac.uk/ols/ontologies/chebi CHEBI_24431 a small molecule added to a cell culture (ex. A drug) growth factor (and if it is recombinant, concentration), gene)
76-
small_molecule_perturbation__concentration number TRUE small_molecule_perturbation small_molecule_perturbation__concentration__unit Concentration of each small molecule in the final tissue culture media. Order should be consistent with small_molecule_perturbation
75+
small_molecule_perturbation string TRUE a small molecule added to a cell culture (ex. A drug) growth factor (and if it is recombinant, concentration), gene)
76+
small_molecule_perturbation__concentration number TRUE Concentration of each small molecule in the final tissue culture media. Order should be consistent with small_molecule_perturbation
7777
small_molecule_perturbation__concentration__unit string ontology https://www.ebi.ac.uk/ols/api/ontologies/uo https://www.ebi.ac.uk/ols/ontologies/uo UO_0000003 small_molecule_perturbation__concentration small_molecule_perturbation__concentration__unit
7878
small_molecule_perturbation__concentration__unit_label string unit_label small_molecule_perturbation__concentration__unit small_molecule_perturbation__concentration__unit_label
7979
small_molecule_perturbation__ontology_label string TRUE ontology_label small_molecule_perturbation small_molecule_perturbation__ontology_label
@@ -82,10 +82,10 @@ small_molecule_perturbation__source string TRUE small_molecule_perturbatio
8282
spike_in_concentration string spike_in_kit spike in concentration
8383
spike_in_kit string name of spike in kit
8484
strand string enum "[""first"",""second"",""unstranded""]" library strandedness
85-
vaccination string TRUE ontology https://www.ebi.ac.uk/ols/api/ontologies/vo https://www.ebi.ac.uk/ols/ontologies/vo VO_0000001 Any known vaccines administered to the donor organism. NOT a full vaccine history
85+
vaccination string TRUE Any known vaccines administered to the donor organism. NOT a full vaccine history
8686
vaccination__adjuvants string TRUE vaccination Any adjuvants administered in the vaccine
8787
vaccination__dosage string TRUE vaccination The dosage and units for the vaccine
88-
vaccination__ontology_label string TRUE ontology_label vaccination vaccination__ontology_label
88+
vaccination__ontology_label string TRUE vaccination vaccination__ontology_label
8989
vaccination__route string TRUE enum "[""intradermal"", ""intranasal"", ""intravenous"", ""aerosol"", ""intramuscular"", ""mucosal"", ""oral""]" vaccination Intradermal, Intranasal, Intravenous, Aerosol
9090
vaccination__time_since number TRUE vaccination vaccination__time_since__unit Amount of time since vaccine was administered
9191
vaccination__time_since__unit string ontology https://www.ebi.ac.uk/ols/api/ontologies/uo https://www.ebi.ac.uk/ols/ontologies/uo UO_0000003 vaccination__time_since Time since each vaccine in the vaccination field was administered

0 commit comments

Comments
 (0)