Skip to content

Commit

Permalink
update schema file
Browse files Browse the repository at this point in the history
  • Loading branch information
@rcannood
rcannood committed Sep 18, 2024
1 parent fb0eb0c commit 579ac51
Show file tree
Hide file tree
Showing 4 changed files with 66 additions and 101 deletions.
2 changes: 2 additions & 0 deletions .gitignore
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,3 +17,5 @@ singularity_container/
/resources_test
/resources
/.vscode
/.nextflow*
/work
2 changes: 1 addition & 1 deletion common
Submodule common updated 13 files
+83 −0 schemas/api_component_spec.yaml
+31 −0 schemas/api_file_format.yaml
+459 −0 schemas/schema_openproblems_definitions.yaml
+3,135 −0 schemas/schema_viash.yaml
+5 −0 schemas/script.sh
+94 −0 schemas/task_config.yaml
+73 −0 schemas/task_control_method.yaml
+70 −0 schemas/task_method.yaml
+104 −0 schemas/task_metric.yaml
+2 −2 scripts/create_component
+2 −2 scripts/create_task_readme
+2 −2 scripts/sync_resources
+28 −0 scripts/upgrade_config
2 changes: 1 addition & 1 deletion src/api/file_common_singlecell.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ info:
type: h5ad
layers:
- type: integer
name: counts #TODO: Okay to change this one to "raw"?
name: counts
description: Raw counts
required: true
obs:
Expand Down
161 changes: 62 additions & 99 deletions src/api/file_common_spatialdata.yaml
View file
Original file line number Diff line number Diff line change
@@ -1,26 +1,3 @@
#SpatialData object, with associated Zarr store: </paht/to/data.zarr>
#├── Images
#│ ├── '{rep}_he_image': DataTree[cyx] (3, 45087, 11580), (3, 22543, 5790), (3, 11271, 2895), (3, 5635, 1447), (3, 2817, 723)
#│ ├── '{rep}_{flourescence_img}': DataTree[cyx] (2, 17098, 51187), (2, 8549, 25593), (2, 4274, 12796), (2, 2137, 6398), (2, 1068, 3199)
#│ └── '{rep}_{flourescence_img}_3D': DataTree[czyx] (2, 8, 17098, 51187), (2, 8, 8549, 25593), (2, 8, 4274, 12796), (2, 8, 2137, 6398), (2, 8, 1068, 3199)
#├── Labels
#│ ├── '{rep}_{segm1}': DataTree[yxz] (17098, 51187, 3), (8549, 25593, 3), (4274, 12796, 3), (2137, 6398, 3), (1068, 3199, 3)
#│ ├── '{rep}_{segm2}': DataTree[yxz] (17098, 51187, 3), (8549, 25593, 3), (4274, 12796, 3), (2137, 6398, 3), (1068, 3199, 3)
#│ └── '{rep}_expert_segm_{patch}': DataTree[yxz] (17098, 51187, 3), (8549, 25593, 3), (4274, 12796, 3), (2137, 6398, 3), (1068, 3199, 3)
#├── Points
#│ └── '{rep}_transcripts': DataFrame with shape: (<Delayed>, 11) (3D points)
#├── Shapes
#│ ├── '{rep}_{segm1}_boundaries': GeoDataFrame shape: (162254, 1) (2D shapes - 3D supported??)
#│ └── '{rep}_{segm2}_boundaries': GeoDataFrame shape: (162254, 1) (2D shapes)
#└── Tables
# ├── '{rep}_{segm1}': AnnData (162254, 377)
# ├── '{rep}_{segm2}': AnnData (162254, 377)
# ├── '{reference1}': AnnData (n_obs_ref1, ?)
# └── '{reference2}': AnnData (n_obs_ref2, ?)
#with coordinate systems:
# ▸ '{rep}_global', with elements:
# ....

type: file
example: "resources_test/common/2023_10x_mouse_brain_xenium/dataset.zarr"
label: "Common iST Dataset"
Expand All @@ -30,110 +7,97 @@ description: |
info:
format:
type: spatialdata_zarr
variables:
- name: replicate_id
type: string
description: The replicate identifier
required: true
# - name: reference_id
# type: str
# description: Name of the reference dissociated dataset
# required: true
- name: segmentation_id
type: string
description: Custom segmentation identifier
required: false
# - name: patch
# type: string
# description: Expert segmentation image patch identifier
# required: false

images:
- type: datatree
name: "{rep}_image"
- type: object
name: image
description: The raw image data
required: true
coordinates:
- type: integer
name: c
required: true
- type: double
name: "y"
required: true
- type: double
name: x
required: true
- type: datatree
name: "{rep}_image_3D"
- type: object
name: image_3D
description: The raw 3D image data
required: false
coordinates: [] # TODO
- type: datatree
name: "{rep}_he_image"
- type: object
name: he_image
description: H&E image data
required: false
coordinates: [] # TODO
labels:
- type: datatree
dtype: int
name: "{rep}_{segm}"
description: Custom segmentation of the data
- type: object
name: "cell_labels"
description: Cell segmentation labels
required: false
- type: datatree
dtype: int
name: "{rep}_{segm}_3D"
description: Custom segmentation of the 3D data
- type: object
name: "nucleus_labels"
description: Cell segmentation labels
required: false
# - type: datatree
# dtype: int
# name: "{rep}_expert_segm_{patch}"
# name: "{segm}_3D"
# description: Custom segmentation of the 3D data
# required: false
# - type: datatree
# name: "expert_segm_{patch}"
# description: Expert segmentation of a patch of the data
# required: false
# - type: DataTree[zyx]
# dtype: int
# name: "{rep}_expert_segm_{patch}_3D"
# name: "expert_segm_{patch}_3D"
# description: Expert segmentation of a 3D patch of the data
# required: false
points:
- type: dataframe
name: "{rep}_transcripts"
name: transcripts
description: Point cloud data of transcripts
required: true
columns:
- type: float
name: "x"
required: true
description: x-coordinate of the point
- type: float
name: "y"
required: true
description: y-coordinate of the point
- type: float
name: "z"
required: true
description: z-coordinate of the point
- type: categorical
name: feature_name
required: true
description: Name of the feature
- type: integer
name: "cell_id"
required: true
description: Unique identifier of the cell
- type: float
name: qv
required: true
description: Quality value of the point
- type: long
name: transcript_id
required: true
description: Unique identifier of the transcript
- type: boolean
name: overlaps_nucleus
required: true

description: Whether the point overlaps with a nucleus
shapes:
- type: dataframe
name: "{rep}_{segm}_boundaries"
description: Cell polygons referring to "{rep}_{segm}"
name: "cell_boundaries"
description: Cell boundaries
required: false
columns:
- type: object
name: "geometry"
required: true
description: Geometry of the cell boundary
- type: dataframe
name: "nucleus_boundaries"
description: Nucleus boundaries
required: false
columns:
- type: object
name: "geometry"
required: true
description: Geometry of the nucleus boundary
tables:
- type: anndata
name: "metadata"
Expand All @@ -143,62 +107,61 @@ info:
- type: string
name: dataset_id
required: true
description: A unique identifier for the dataset
- type: string
name: dataset_name
required: true
description: A human-readable name for the dataset
- type: string
name: dataset_url
required: true
description: Link to the original source of the dataset
- type: string
name: dataset_reference
required: true
description: Bibtex reference of the paper in which the dataset was published
- type: string
name: dataset_summary
required: true
description: Short description of the dataset
- type: string
name: dataset_description
required: true
description: Long description of the dataset
- type: string
name: dataset_organism
required: true
- type: dictionary
name: variables
required: true
contents:
- type: string
name: replicate_id
required: true
multiple: true
- type: string
name: segmentation_id
required: true
multiple: true
# - type: anndata
# dtype: ???
# name: "{reference}"
# description: Map to define the reference cells to compare to for each rep
# required: true
- type: anndata
name: "{rep}_{segm}_table"
description: Count data referring to "{rep}_{segm}"
required: false
description: The organism of the sample in the dataset
- type: string
name: replicate_id
required: true
description: A unique identifier for the replicate
- type: string
name: segmentation_id
required: true
multiple: true
description: A unique identifier for the segmentation
obs:
- type: string
name: cell_id
required: true
description: A unique identifier for the cell
var:
- type: string
name: gene_ids
required: true
description: Unique identifier for the gene
- type: string
name: feature_types
required: true
description: Type of the feature
obsm:
- type: float
- type: double
name: spatial
required: true
description: Spatial coordinates of the cell
coordinate_systems:
- type: string
name: "{rep}_global"
- type: object
name: global
description: Coordinate system of the replicate
required: true

0 comments on commit 579ac51

Please sign in to comment.