Merge pull request #1 from openproblems-bio/initial_setup

Initial setup

Author: seohyonkim

CHANGELOG.md

@@ -1,33 +1,18 @@
-# task_template x.y.z
+# task_spatial_trajectory_inference 1.0.0
 
 ## BREAKING CHANGES
 
 <!-- * Restructured `src` directory (PR #3). -->
 
 ## NEW FUNCTIONALITY
 
-* Added `control_methods/true_labels` component (PR #5).
-
-* Added `methods/logistic_regression` component (PR #5).
-
-* Added `metrics/accuracy` component (PR #5).
 
 ## MAJOR CHANGES
 
-* Updated `api` files (PR #5).
-
-* Updated configs, components and CI to the latest Viash version (PR #8).
-
-* Updated to Viash 0.9.4 (PR #12).
-
-* Use dependencies in `openproblems-bio/openproblems` (PR #12).
+* Updated `api` files and set the data processor (PR #1).
 
 ## MINOR CHANGES
 
-* Updated `README.md` (PR #5).
-
-* `run_benchmark`: write the commit the workflow ran from and the launch time into
-  `task_info.yaml`, instead of publishing `_viash.yaml` verbatim (PR #18).
 
 ## BUGFIXES
 

_viash.yaml

@@ -1,34 +1,28 @@
 viash_version: 0.9.4
 
-# Step 1: Change the name of the task.
-# example: task_name_of_this_task
-name: task_template
+name: task_spatial_trajectory_inference
 organization: openproblems-bio
 version: dev
 
 license: MIT
-# Step 2: Add keywords to describe the task.
-keywords: [single-cell, openproblems, benchmark]
-# Step 3: Update the `task_template` to the name of the task from step 1.
+keywords: [single-cell, openproblems, benchmark, spatial, trajectory inference]
 links:
-  issue_tracker: https://github.com/openproblems-bio/task_template/issues
-  repository: https://github.com/openproblems-bio/task_template
+  issue_tracker: https://github.com/openproblems-bio/task_spatial_trajectory_inference/issues
+  repository: https://github.com/openproblems-bio/task_spatial_trajectory_inference
   docker_registry: ghcr.io
 
 
-# Step 4: Update the label, summary and description.
-# A unique, human-readable, short label. Used for creating summary tables and visualisations.
-label: Template
-summary: A one sentence summary of purpose and methodology. Used for creating an overview tables.
-description: |
-  Provide a clear and concise description of your task, detailing the specific problem it aims
-  to solve. Outline the input data types, the expected output, and any assumptions or constraints.
-  Be sure to explain any terminology or concepts that are essential for understanding the task.
+label: Spatial Trajectory Inference
+summary: Predicting the spatial trajectory of cells in a tissue based on spatial transcriptomics data.
+description: 
 
-  Explain the motivation behind your proposed task. Describe the biological or computational 
-  problem you aim to address and why it's important. Discuss the current state of research in
-  this area and any gaps or challenges that your task could help address. This section 
-  should convince readers of the significance and relevance of your task.
+  Spatial transcriptomics preserves each cell's physical position alongside its expression profile, enabling pseudotime prediction using 2D spatial context.
+  Different methods make different assumptions about resolution, input format, and output, and are further complicated by spatial batch effects not present in dissociated single-cell data.
+  While dynbenchmark resolved this comparison problem for non-spatial trajectory inference methods, no equivalent standardized benchmark exists for spatial pseudotime prediction, and existing method papers are validated only against each other or qualitative marker trends rather than tissues with independently known trajectories.
+
+  This task benchmarks pseudotime prediction methods on 2D tissue datasets with well-characterized ground-truth spatial axes.
+  Input data consists of AnnData objects containing 2D spatial transcriptomics data with spatial coordinates.
+  The output is a set of quantitative metric scores comparing each method's predicted pseudotime against ground truth, capturing both trajectory accuracy and preservation of relevant biological information.
 
 # A list of references to relevant literature. Each reference should be a DOI or a bibtex entry
 references:
@@ -47,32 +41,51 @@ references:
 
 info:
   image: The name of the image file to use for the component on the website.
-  # Step 5: Replace the task_template to the name of the task.
   test_resources:
     - type: s3
       path: s3://openproblems-data/resources_test/common/
       dest: resources_test/common
     - type: s3
-      path: s3://openproblems-data/resources_test/task_template/
-      dest: resources_test/task_template
+      path: s3://openproblems-data/resources_test/task_spatial_trajectory_inference/
+      dest: resources_test/task_spatial_trajectory_inference
 
-# Step 6: Update the authors of the task.
 authors: 
-  # Full name of the author, usually in the name of FirstName MiddleName LastName.
-  - name: John Doe
-    # Role of the author. Possible values:
-    # 
-    # * `"author"`: Authors who have made substantial contributions to the component.
-    # * `"maintainer"`: The maintainer of the component.
-    # * `"contributor"`: Authors who have made smaller contributions (such as code patches etc.).
+  - name: Chit Tong Lio
+    roles: [ "author", "maintainer" ]
+    info: 
+      github: yollct
+      orcid: 0000-0003-2297-831X
+      email: chit-tong.lio@tum.de
+  - name: Seo Hyon Kim
+    roles: [ "author", "maintainer" ]
+    info: 
+      github: seohyonkim
+      orcid: 0009-0007-3062-4681
+      email: seohyon.l.kim@gmail.com
+  - name: Wenjia Zhong
+    roles: [ "author", "maintainer" ]
+    info: 
+      github: Wenjia218
+      orcid: 0009-0009-1594-8009
+      email: wenjia.zhong@tum.de
+  - name: Luisa Katharina Bender
+    roles: [ "author", "maintainer" ]
+    info: 
+      github: luisabender
+      orcid: 0009-0001-8753-7307
+      email: luisa.bender@tum.de
+  - name: Florian Röckl
+    roles: [ "author", "maintainer" ]
+    info: 
+      github: floro5
+      orcid: 0009-0009-6050-890X
+      email: florian.roeckl@tum.de
+  - name: Jonathan Unger
     roles: [ "author", "maintainer" ]
-    # Additional information on the author
     info: 
-      github: johndoe
-      orcid: 0000-0000-0000-0000
-      email: john@doe.me
-      twitter: johndoe
-      linkedin: johndoe
+      github: Jonique02
+      orcid: 0009-0009-5022-2975
+      email: jonathan.unger@tum.de
 
 # Step 7: Remove all of the comments of the steps you completed
 

src/api/comp_control_method.yaml

@@ -3,7 +3,7 @@ info:
   type: control_method
   type_info:
     label: Control Method
-    summary: Quality control methods for verifying the pipeline.
+    summary: Quality control methods for verifying the pipeline of the spatial TI task.
     description: |
       This folder contains control components for the task. 
       These components have the same interface as the regular methods
@@ -12,12 +12,8 @@ info:
       the task, and also as a quality control for the metrics defined
       in the task.
 arguments:
-  - name: --input_train
-    __merge__: file_train.yaml
-    required: true
-    direction: input
-  - name: --input_test
-    __merge__: file_test.yaml
+  - name: --dataset
+    __merge__: file_dataset.yaml
     required: true
     direction: input
   - name: "--input_solution"
@@ -33,5 +29,5 @@ test_resources:
     path: /common/component_tests/run_and_check_output.py
   - type: python_script
     path: /common/component_tests/check_config.py
-  - path: /resources_test/task_template/cxg_mouse_pancreas_atlas
-    dest: resources_test/task_template/cxg_mouse_pancreas_atlas
+  - path: /resources_test/common/cxg_mouse_pancreas_atlas
+    dest: resources_test/common/cxg_mouse_pancreas_atlas

src/api/comp_data_processor.yaml

@@ -3,20 +3,16 @@ info:
   type: data_processor
   type_info:
     label: Data processor
-    summary: A data processor.
-    description: |
+    summary: A data processor for the spatial TI task.
+    description: | # better description TODO
       A component for processing a Common Dataset into a task-specific dataset.
 arguments:
   - name: "--input"
     __merge__: file_common_dataset.yaml
     direction: input
     required: true
-  - name: "--output_train"
-    __merge__: file_train.yaml
-    direction: output
-    required: true
-  - name: "--output_test"
-    __merge__: file_test.yaml
+  - name: "--output_dataset"
+    __merge__: file_dataset.yaml
     direction: output
     required: true
   - name: "--output_solution"

src/api/comp_method.yaml

@@ -5,16 +5,12 @@ info:
     label: Method
     summary: A method.
     description: |
-      A method to predict the task effects.
+      A method for the spatial TI task.
 arguments:
-  - name: --input_train
-    __merge__: file_train.yaml
+  - name: --input
+    __merge__: file_dataset.yaml
     required: true
     direction: input
-  - name: "--input_test"
-    __merge__: file_test.yaml
-    direction: input
-    required: true
   - name: --output
     __merge__: file_prediction.yaml
     required: true
@@ -24,5 +20,5 @@ test_resources:
     path: /common/component_tests/run_and_check_output.py
   - type: python_script
     path: /common/component_tests/check_config.py
-  - path: /resources_test/task_template/cxg_mouse_pancreas_atlas
-    dest: resources_test/task_template/cxg_mouse_pancreas_atlas
+  - path: /resources_test/common/cxg_mouse_pancreas_atlas
+    dest: resources_test/common/cxg_mouse_pancreas_atlas

src/api/comp_metric.yaml

@@ -3,9 +3,9 @@ info:
   type: metric
   type_info:
     label: Metric
-    summary: A task template metric.
+    summary: A metric for spatial TI task.
     description: |
-      A metric for evaluating method predictions.
+      A metric for evaluating spatial TI method predictions.
 arguments:
   - name: "--input_solution"
     __merge__: file_solution.yaml
@@ -24,5 +24,5 @@ test_resources:
     path: /common/component_tests/run_and_check_output.py
   - type: python_script
     path: /common/component_tests/check_config.py
-  - path: /resources_test/task_template/cxg_mouse_pancreas_atlas
-    dest: resources_test/task_template/cxg_mouse_pancreas_atlas
+  - path: /resources_test/common/cxg_mouse_pancreas_atlas
+    dest: resources_test/common/cxg_mouse_pancreas_atlas

src/api/file_train.yaml src/api/file_dataset.yamlsrc/api/file_train.yaml renamed to src/api/file_dataset.yaml

@@ -1,24 +1,23 @@
-#TODO: Change to the required and/or optional fields of the anndata
 type: file
-example: "resources_test/task_template/cxg_mouse_pancreas_atlas/train.h5ad"
-label: "Training data"
-summary: "The training data in h5ad format"
+example: "resources_test/task_spatial_trajectory_inference/cxg_mouse_pancreas_atlas/dataset.h5ad"
+label: "Input data"
+summary: "The input data for the spatial TI methods"
 info:
   format:
     type: h5ad
-    layers: 
+    layers:
       - type: integer
         name: counts
         description: Raw counts
         required: true
       - type: double
         name: normalized
-        description: Normalized counts
+        description: Normalized expression values
         required: true
     obs:
       - type: string
-        name: label
-        description: Ground truth cell type labels
+        name: cell_type
+        description: Cell type information
         required: true
       - type: string
         name: batch
@@ -34,6 +33,10 @@ info:
         description: A ranking of the features by hvg.
         required: true
     obsm:
+      - type: double
+        name: X_spatial
+        description: Spatial coordinates of each cell/spot.
+        required: true
       - type: double
         name: X_pca
         description: The resulting PCA embedding.
@@ -46,4 +49,4 @@ info:
       - type: string
         name: normalization_id
         description: "Which normalization was used"
-        required: true
+        required: true

src/api/file_solution.yaml

@@ -1,42 +1,32 @@
-#TODO: Change to the required and/or optional fields of the anndata
 type: file
-example: "resources_test/task_template/cxg_mouse_pancreas_atlas/solution.h5ad"
+example: "resources_test/task_spatial_trajectory_inference/cxg_mouse_pancreas_atlas/solution.h5ad"
 label: "Solution"
-summary: "The solution for the test data"
+summary: "The solution (ground truth) for the test data"
 info:
   format:
     type: h5ad
-    layers: 
+    layers:
       - type: integer
         name: counts
         description: Raw counts
         required: true
-      - type: double
-        name: normalized
-        description: Normalized counts
-        required: true
     obs:
       - type: string
-        name: label
-        description: Ground truth cell type labels
+        name: cell_type
+        description: Cell type information
         required: true
       - type: string
         name: batch
         description: Batch information
         required: true
-    var:
-      - type: boolean
-        name: hvg
-        description: Whether or not the feature is considered to be a 'highly variable gene'
-        required: true
       - type: double
-        name: hvg_score
-        description: A ranking of the features by hvg.
+        name: pseudotime_true
+        description: Ground truth pseudotime for each cell/spot.
         required: true
     obsm:
       - type: double
-        name: X_pca
-        description: The resulting PCA embedding.
+        name: X_spatial
+        description: Spatial coordinates of each cell/spot.
         required: true
     uns:
       - type: string
@@ -71,3 +61,7 @@ info:
         name: normalization_id
         description: "Which normalization was used"
         required: true
+      - type: dataframe
+        name: marker_genes
+        description: "Marker genes per biological state, with expected ordering along the trajectory (columns: gene_name, biological_state, expected_order). Used by marker-based metrics when provided."
+        required: false