Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Testing Please ignore - copy biodatacat #1805

175 changes: 115 additions & 60 deletions gen3.theanvil.io/etlMapping.yaml
Original file line number Diff line number Diff line change
@@ -1,64 +1,119 @@
mappings:
- name: etl_anvil
doc_type: case
type: aggregator
root: case
- name: gen3.theanvil.io_subject
doc_type: subject
type: aggregator
root: subject
props:
- name: submitter_id
- name: project_id
- name: sex
- name: age_value
- name: ancestry
- name: disease_description
- name: phenotype_present
- name: phenotype_absent
- name: disease_id
- name: solve_state
- name: congenital_status
- name: age_of_onset
aggregated_props:
- name: sample_provider
path: samples
src: sample_provider
fn: set
- name: tissue_affected_status
path: samples
src: tissue_affected_status
fn: set
- name: tissue_type
path: samples
src: tissue_type
fn: set
- name: sample_type
path: samples
src: sample_type
fn: set
- name: original_material_type
path: samples
src: original_material_type
fn: set
- name: exome_capture_platform
path: samples.sequencings
src: exome_capture_platform
fn: set
- name: library_prep_kit_method
path: samples.sequencings
src: library_prep_kit_method
fn: set
- name: capture_region_bed_file
path: samples.sequencings
src: capture_region_bed_file
fn: set
- name: reference_genome_build
path: samples.sequencings
src: reference_genome_build
fn: set
- name: sequencing_assay
path: samples.sequencings
src: sequencing_assay
fn: set
- name: alignment_method
path: samples.sequencings
src: alignment_method
fn: set
- name: data_processing_pipeline
path: samples.sequencings
src: data_processing_pipeline
fn: set
- name: _samples_count
path: samples
fn: count
- name: _sequencings_count
path: samples.sequencings
fn: count
joining_props:
- index: file
join_on: subject_id
props:
- name: submitter_id
- name: data_format
src: data_format
fn: set
- name: data_type
src: data_type
fn: set
parent_props:
- path: projects[project_code:code]
- path: projects[project_name:name]
- path: projects[project_dbgap_phs:dbgap_phs]
- path: projects[project_dbgap_consent_text:dbgap_consent_text]
- path: projects[project_short_name:short_name]
- path: projects[project_dbgap_accession_number:dbgap_accession_number]
- name: gen3.theanvil.io_file
doc_type: file
type: collector
root: None
category: data_file
props:
- name: project_id
- name: submitter_id
- name: object_id
- name: md5sum
- name: file_name
- name: file_size
- name: data_format
- name: data_type
- name: state
- name: data_category
- name: analyte_type
- name: sequencing_assay
injecting_props:
subject:
props:
- name: subject_id
src: id
fn: set
- name: subject_submitter_id
src: submitter_id
fn: set
- name: project_id
flatten_props:
- path: demographics
props:
- name: sex
- name: race
- name: ethnicity
- name: age
- path: death_records
props:
- name: hardy_scale
aggregated_props:
- name: _samples_count
path: samples
fn: count
- name: ischemic_time
path: samples
src: ischemic_time
fn: set
- name: _aliquots_count
path: samples.aliquots
fn: count
- name: _read_groups_count
path: samples.aliquots.read_groups
fn: count
- name: _submitted_aligned_reads_count
path: samples.aliquots.read_groups.submitted_aligned_reads_files
fn: count
joining_props:
- index: file
join_on: case_id
props:
- name: data_format
src: data_format
fn: set
- name: data_type
src: data_type
fn: set
- name: file_anvil
doc_type: file
type: collector
root: None
category: data_file
props:
- name: object_id
- name: md5sum
- name: file_name
- name: file_size
- name: data_format
- name: data_type
- name: state
injecting_props:
case:
props:
- name: case_id
src: id
- name: project_id
58 changes: 29 additions & 29 deletions gen3.theanvil.io/manifest.json
Original file line number Diff line number Diff line change
Expand Up @@ -7,31 +7,33 @@
"autodeploy": "yes"
},
"versions": {
"arborist": "quay.io/cdis/arborist:2020.05",
"arborist": "quay.io/cdis/arborist:2020.07",
"aws-es-proxy": "abutaha/aws-es-proxy:0.8",
"fence": "quay.io/cdis/fence:2020.05",
"fence": "quay.io/cdis/fence:2020.07",
"fluentd": "fluent/fluentd-kubernetes-daemonset:v1.2-debian-cloudwatch",
"guppy": "quay.io/cdis/guppy:2020.05",
"hatchery": "quay.io/cdis/hatchery:2020.05",
"ambassador": "quay.io/datawire/ambassador:0.60.3",
"indexd": "quay.io/cdis/indexd:2020.05",
"manifestservice": "quay.io/cdis/manifestservice:2020.05",
"peregrine": "quay.io/cdis/peregrine:2020.05",
"pidgin": "quay.io/cdis/pidgin:2020.05",
"portal": "quay.io/cdis/data-portal:2020.05",
"revproxy": "quay.io/cdis/nginx:2020.05",
"sheepdog": "quay.io/cdis/sheepdog:2020.05",
"sower": "quay.io/cdis/sower:2020.05",
"spark": "quay.io/cdis/gen3-spark:2020.05",
"tube": "quay.io/cdis/tube:2020.05",
"ssjdispatcher": "quay.io/cdis/ssjdispatcher:2020.05",
"wts": "quay.io/cdis/workspace-token-service:2020.05"
"guppy": "quay.io/cdis/guppy:2020.07",
"hatchery": "quay.io/cdis/hatchery:2020.07",
"ambassador": "quay.io/datawire/ambassador:1.4.2",
"indexd": "quay.io/cdis/indexd:2020.07",
"manifestservice": "quay.io/cdis/manifestservice:2020.07",
"peregrine": "quay.io/cdis/peregrine:2020.07",
"pidgin": "quay.io/cdis/pidgin:2020.07",
"portal": "quay.io/cdis/data-portal:2020.07",
"revproxy": "quay.io/cdis/nginx:2020.07",
"sheepdog": "quay.io/cdis/sheepdog:2020.07",
"sower": "quay.io/cdis/sower:2020.07",
"spark": "quay.io/cdis/gen3-spark:2020.07",
"tube": "quay.io/cdis/tube:2020.07",
"ssjdispatcher": "quay.io/cdis/ssjdispatcher:2020.07",
"wts": "quay.io/cdis/workspace-token-service:2020.07",
"dashboard": "quay.io/cdis/gen3-statics:2020.07",
"metadata": "quay.io/cdis/metadata-service:2020.07"
},
"global": {
"environment": "anvilprod",
"hostname": "gen3.theanvil.io",
"revproxy_arn": "arn:aws:acm:us-east-1:474789003679:certificate/9fd731e3-3366-4bd0-a3ef-0453dc07289a",
"dictionary_url": "https://s3.amazonaws.com/dictionary-artifacts/anvil/1.1.6/schema.json",
"dictionary_url": "https://s3.amazonaws.com/dictionary-artifacts/anvil/2.1.10/schema.json",
"portal_app": "gitops",
"kube_bucket": "kube-anvilprod-gen3",
"logs_bucket": "logs-anvilprod-gen3",
Expand All @@ -49,7 +51,7 @@
"action": "export",
"container": {
"name": "job-task",
"image": "quay.io/cdis/pelican-export:2020.05",
"image": "quay.io/cdis/pelican-export:2020.07",
"pull_policy": "Always",
"env": [
{
Expand All @@ -72,7 +74,7 @@
},
{
"name": "ROOT_NODE",
"value": "case"
"value": "subject"
}
],
"volumeMounts": [
Expand Down Expand Up @@ -114,7 +116,7 @@
},
"ssjdispatcher": {
"job_images": {
"indexing": "quay.io/cdis/indexs3client:2020.05"
"indexing": "quay.io/cdis/indexs3client:2020.07"
}
},
"arborist": {
Expand All @@ -123,18 +125,16 @@
"guppy": {
"indices": [
{
"index": "etl_anvil",
"type": "case"
"index": "gen3.theanvil.io_subject",
"type": "subject"
},
{
"index": "file_anvil",
"index": "gen3.theanvil.io_file",
"type": "file"
}
],
"auth_filter_field": "auth_resource_path"
},
"peregrine": {
"sidecar": "True"
"auth_filter_field": "auth_resource_path",
"config_index": "gen3.theanvil.io_array-config"
},
"canary": {
"default": 0
Expand Down Expand Up @@ -195,4 +195,4 @@
"targetCpu": 40
}
}
}
}
4 changes: 2 additions & 2 deletions gen3.theanvil.io/manifests/hatchery/hatchery.json
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"sidecar": {
"cpu-limit": "1.0",
"memory-limit": "512Mi",
"image": "quay.io/cdis/gen3fuse-sidecar:2020.05",
"image": "quay.io/cdis/gen3fuse-sidecar:2020.07",
"env": {
"NAMESPACE": "default",
"HOSTNAME": "gen3.theanvil.io"
Expand Down Expand Up @@ -172,4 +172,4 @@
"fs-gid": 100
}
]
}
}
Loading