update project config

Author: rcannood

_viash.yaml

@@ -2,7 +2,7 @@ viash_version: 0.9.0-RC7
 
 # Step 1: Change the name of the task.
 # example: task_name_of_this_task
-name: task_template
+name: task_dimensionality_reduction
 organization: openproblems-bio
 version: dev
 
@@ -11,68 +11,107 @@ license: MIT
 keywords: [single-cell, openproblems, benchmark]
 # Step 3: Update the `task_template` to the name of the task from step 1.
 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_dimensionality_reduction/issues
+  repository: https://github.com/openproblems-bio/task_dimensionality_reduction
   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.
+label: Dimensionality Reduction for Visualization
+summary: Reduction of high-dimensional datasets to 2D for visualization & interpretation.
 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.
-
-  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.
-
+  Data visualisation is an important part of all stages of single-cell analysis, from
+  initial quality control to interpretation and presentation of final results. For bulk RNA-seq
+  studies, linear dimensionality reduction techniques such as PCA and MDS are commonly used
+  to visualise the variation between samples. While these methods are highly effective they
+  can only be used to show the first few components of variation which cannot fully represent
+  the increased complexity and number of observations in single-cell datasets. For this reason
+  non-linear techniques (most notably t-SNE and UMAP) have become the standard for visualising
+  single-cell studies. These methods attempt to compress a dataset into a two-dimensional space
+  while attempting to capture as much of the variance between observations as possible. Many
+  methods for solving this problem now exist. In general these methods try to preserve distances,
+  while some additionally consider aspects such as density within the embedded space or conservation
+  of continuous trajectories. Despite almost every single-cell study using one of these visualisations
+  there has been debate as to whether they can effectively capture the variation in single-cell
+  datasets [@chari2023speciousart].
+  
+  The dimensionality reduction task attempts to quantify the ability of methods to embed the
+  information present in complex single-cell studies into a two-dimensional space. Thus, this task
+  is specifically designed for dimensionality reduction for visualisation and does not consider other
+  uses of dimensionality reduction in standard single-cell workflows such as improving the
+  signal-to-noise ratio (and in fact several of the methods use PCA as a pre-processing step for this
+  reason). Unlike most tasks, methods for the dimensionality reduction task must accept a matrix
+  containing expression values normalised to 10,000 counts per cell and log transformed (log-10k) and
+  produce a two-dimensional coordinate for each cell. Pre-normalised matrices are required to
+  enforce consistency between the metric evaluation (which generally requires normalised data) and
+  the method runs. When these are not consistent, methods that use the same normalisation as used in
+  the metric tend to score more highly. For some methods we also evaluate the pre-processing
+  recommended by the method.
 # A list of references to relevant literature. Each reference should be a DOI or a bibtex entry
-references:
-  doi:
-    - 10.21203/rs.3.rs-4181617/v1
-  # bibtex:
-  #   - |
-  #     @article{doe_2021_template,
-  #       doi = {10.21203/rs.3.rs-4181617/v1},
-  #       url = {https://doi.org/10.21203/rs.3.rs-4181617/v1},
-  #       author = {Doe, John},
-  #       title = {A template for creating new tasks},
-  #       publisher = {Research Square},
-  #       year = {2021},
-  #     }
+# references:
+#   doi:
+#     - 10.21203/rs.3.rs-4181617/v1
+#   bibtex:
+#     - |
+#       @article{doe_2021_template,
+#         doi = {10.21203/rs.3.rs-4181617/v1},
+#         url = {https://doi.org/10.21203/rs.3.rs-4181617/v1},
+#         author = {Doe, John},
+#         title = {A template for creating new tasks},
+#         publisher = {Research Square},
+#         year = {2021},
+#       }
 
 info:
-  image: The name of the image file to use for the component on the website.
+  image: thumbnail.svg
   # Step 5: Replace the task_template to the name of the task.
   test_resources:
     - type: s3
-      path: s3://openproblems-data/resources_test/task_template/
-      dest: resources_test/task_template
+      path: s3://openproblems-data/resources_test/common/pancreas/
+      dest: resources_test/common/pancreas/
     - type: s3
-      path: s3://openproblems-data/resources_test/common/
-      dest: resources_test/common
+      path: s3://openproblems-data/resources_test/dimensionality_reduction/
+      dest: resources_test/dimensionality_reduction
 
 # 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.).
-    roles: [ "author", "maintainer" ]
-    # Additional information on the author
-    info: 
-      github: johndoe
-      orcid: 0000-0000-0000-0000
-      email: john@doe.me
-      twitter: johndoe
-      linkedin: johndoe
+  - name: Luke Zappia
+    roles: [ maintainer, author ]
+    info:
+      github: lazappi
+  - name: Michal Klein
+    roles: [ author ]
+    info:
+      github: michalk8
+  - name: Scott Gigante
+    roles: [ author ]
+    info:
+      github: scottgigante
+      orcid: "0000-0002-4544-2764"
+  - name: Ben DeMeo
+    roles: [ author ]
+    info:
+      github: bendemeo
+  - name: Robrecht Cannoodt
+    roles: [ author ]
+    info:
+      github: rcannood
+      orcid: 0000-0003-3641-729X
+  - name: Kai Waldrant
+    roles: [ contributor ]
+    info:
+      github: KaiWaldrant
+      orcid: 0009-0003-8555-1361
+  - name: Sai Nirmayi Yasa
+    roles: [ contributor ]
+    info:
+      github: sainirmayi
+      orcid: 0009-0003-6319-9803
+  - name: Juan A. Cordero Varela
+    roles: [ contributor ]
+    info:
+      github: jacorvar
+      orcid: 0000-0002-7373-5433
 
 # Step 7: Remove all of the comments of the steps you completed
 # Step 8: High five yourself!

scripts/download_resources.sh

@@ -5,5 +5,5 @@ set -e
 echo ">> Downloading resources"
 
 # the sync_resources script uses the test_resources S3 URI's in the _viash.yaml to download the resources.
-common/sync_resources/sync_resources \
+common/scripts/sync_resources \
   --delete