Update authors and readme.md

alexhambley · alexhambley · commit 8db4f9caf33d · 2024-08-21T14:57:16.000+01:00
- Addresses #40, #39, #38, #36 - Added newer diagram to readme. - Removed references to ghcr, this will be added back later - Added proper authors and orcids - Replaced Dockerfile encodingFormat with text/plain - Added created_files.json to RO Crate and added to data_entity["isBasedOn"].
diff --git a/README.md b/README.md
@@ -1,37 +1,42 @@
-# WorkflowHub Knowledge Graph 
+# WorkflowHub Knowledge Graph
 
-## Getting started
+A tool to generate a knowledge graph from a source of RO Crates. By default, this tool sources and generates an RDF graph of crates from [WorkflowHub](https://workflowhub.eu/). 
 
-### Obtaining workflowhub-graph
+## Getting Started
 
-workflowhub-graph is available packaged as a Docker container. You can pull the latest version of the container by running:
+This tool is run as a Snakemake workflow. We recommend building a Docker container to run the workflow:
 
-```bash
-docker pull ghcr.io/uomresearchit/workflowhub-graph:latest
+```bash 
+docker build -t knowledgegraph .
 ```
 
-This provides the a wrapper for the executable `workflowhub-graph` which can be used to run the various tools provided by the package.
+Then, you can run the workflow using the following command:
 
-### Running workflowhub-graph
+```bash
+docker run --rm -v $(pwd):/app -w /app knowledgegraph --cores 4 -s /app/Snakefile
+```
 
-There are several tools provided by the `workflowhub-graph` package. These are:
-- 'help': Display help information.
-- 'source-crates': Download ROCrates from the WorkflowHub API.
-- 'absolutize': Make all paths in an ROCrate absolute.
-- 'upload': Upload an ROCrate to Zenodo.
-- 'merge': Merge multiple ROCrates into an RDF graph.
+This command runs a Docker container using the `knowledgegraph` image. It mounts the working directory to `/app` 
+inside the container, sets `/app` as the working directory, and then runs the workflow. Once the workflow completes, 
+the container is automatically removed.
 
-To run any of these tools, you can use the following command:
+## Structure
 
-```bash
-docker run ghcr.io/uomresearchit/workflowhub-graph:latest <tool> <args>
+```mermaid
+flowchart TD
+    A[Source RO Crates] --> B[Check Outputs];
+    B[Check Outputs] --> C[Report Downloaded RO Crates];
+    B[Check Outputs]-->D[Merge RO Crates];
+    D[Merge RO Crates]-->E[Create Merged Workflow Run RO Crate]
 ```
 
-For example, to download ROCrates from the WorkflowHub API, you can run:
+- **`source_ro_crates`**: This rule sources RO crates from the WorkflowHub API (`source_crates.py`) and then checks 
+the output (`check_outputs.py`). This generates a list of expected file paths based on the workflow IDs and versions to 
+facilitate the workflow.
 
-```bash
-docker run ghcr.io/uomresearchit/workflowhub-graph:latest source-crates
-```
+- **`report_created_files`**: Optional. This rule reports the downloaded RO crates to the user.
+- **`merge_files`**: This rule merges the downloaded RO crates into a single RDF graph (`merge_ro_crates.py`).
+- **`create_ro_crate`**: This rule creates a merged workflow run RO crate from the merged RDF graph (`create_ro_crate.py`).
 
 ## Contributing
 
@@ -46,10 +51,6 @@ docker run ghcr.io/uomresearchit/workflowhub-graph:latest source-crates
 - **Development Branch**: The `develop` branch is currently our main integration branch. Features and fixes should target `develop` through PRs.
 - **Feature Branches**: These feature branches should be short-lived and focused. Once done, please create a pull request to merge it into `develop`.
 
-## Overview
-
-![arch_diagram.png](./docs/images/arch_diagram.png)
-
 ## License
 
 [BSD 2-Clause License](https://opensource.org/license/bsd-2-clause)
diff --git a/workflowhub_graph/create_ro_crate.py b/workflowhub_graph/create_ro_crate.py
@@ -12,7 +12,6 @@ def create_ro_crate(input_file: str, workflow_file: str, output_dir: str) -> Non
     :param input_file: The input file provided by the Snakemake workflow (e.g., merged data file).
     :param workflow_file: Reference to the Snakemake workflow.
     :param output_dir: The output directory to store the RO-Crate metadata file.
-    :return:
     """
     crate = ROCrate()
 
@@ -23,18 +22,54 @@ def create_ro_crate(input_file: str, workflow_file: str, output_dir: str) -> Non
     )
 
     # Add authors:
-    alice = crate.add(
+    auth_1 = crate.add(
         Person(
             crate,
             "https://orcid.org/0000-0000-0000-0000",
-            properties={"name": "Alice Doe", "affiliation": "University of Flatland"},
+            properties={
+                "name": "Alexander Hambley",
+                "affiliation": "University of Manchester",
+            },
+        )
+    )
+    auth_2 = crate.add(
+        Person(
+            crate,
+            "https://orcid.org/0000-0002-0035-6475",
+            properties={
+                "name": "Eli Chadwick",
+                "affiliation": "University of Manchester",
+            },
+        )
+    )
+    auth_3 = crate.add(
+        Person(
+            crate,
+            "https://orcid.org/0000-0002-4565-9760",
+            properties={
+                "name": "Oliver Woolland",
+                "affiliation": "University of Manchester",
+            },
         )
     )
-    bob = crate.add(
+    auth_4 = crate.add(
         Person(
             crate,
-            "https://orcid.org/0000-0000-0000-0001",
-            properties={"name": "Bob Doe", "affiliation": "University of Flatland"},
+            "https://orcid.org/0000-0001-9842-9718",
+            properties={
+                "name": "Stian Soiland-Reyes",
+                "affiliation": "University of Manchester",
+            },
+        )
+    )
+    auth_5 = crate.add(
+        Person(
+            crate,
+            "https://orcid.org/0000-0001-6353-0808",
+            properties={
+                "name": "Volodymyr Savchenko",
+                "affiliation": "University of Geneva",
+            },
         )
     )
 
@@ -52,12 +87,23 @@ def create_ro_crate(input_file: str, workflow_file: str, output_dir: str) -> Non
         properties={
             "@type": "File",
             "name": "Dockerfile",
-            "encodingFormat": "application/yaml",
+            "encodingFormat": "text/plain",
             "description": "The Dockerfile used to build the Docker images for the workflow.",
             "conformsTo": {"@id": "https://docs.docker.com/reference/dockerfile/"},
         },
     )
 
+    created_files = crate.add_file(
+        "./created_files.json",
+        properties={
+            "@type": "File",
+            "name": "created_files.json",
+            "encodingFormat": "application/json",
+            "description": "A JSON file containing the list of files sourced by the workflow.",
+            "conformsTo": {"@id": "https://docs.docker.com/reference/dockerfile/"},
+        },
+    )
+
     crate.add_file("./poetry.lock")
     crate.add_file("./README.md")
 
@@ -68,42 +114,32 @@ def create_ro_crate(input_file: str, workflow_file: str, output_dir: str) -> Non
             "name": "Merged Data File",
             "description": "This file contains merged RDF triples from multiple RO-Crates sourced from WorkflowHub.",
             "encodingFormat": "text/turtle",
-            "author": [alice["@id"], bob["@id"]],
         },
     )
 
+    data_entity["author"] = [auth_1, auth_2, auth_3, auth_4, auth_5]
+    data_entity["isBasedOn"] = created_files
+
     workflow_entity = crate.add_workflow(
         source=workflow_file,
         properties={
             "name": "Snakemake Workflow",
             "description": "This is the Snakemake workflow used to generate the merged RDF triples.",
-            "author": [alice["@id"], bob["@id"]],
-            "output": data_entity["@id"],
         },
         main=True,
         lang="snakemake",
     )
 
+    workflow_entity["author"] = [auth_1, auth_2, auth_3, auth_4]
+    workflow_entity["output"] = data_entity
+
     if "conformsTo" not in crate.root_dataset:
         crate.root_dataset.append_to(
             "conformsTo", {"@id": "https://w3id.org/ro/wfrun/workflow/0.5"}
         )
 
-    crate.add(
-        ContextEntity(
-            crate,
-            identifier=str(uuid.uuid4()),
-            properties={
-                "@type": "CreateAction",
-                "name": "Merge RDF Triples",
-                "description": "Merging RDF triples from sourced crates.",
-                "agent": [alice["@id"], bob["@id"]],
-                "endTime": datetime.now().time().isoformat(),
-                "instrument": workflow_entity["@id"],
-                "result": data_entity["@id"],
-            },
-        )
-    )
+    # Add license:
+    crate.license = "https://opensource.org/license/bsd-2-clause"
 
     # Writing the RO-Crate metadata:
     crate.write(output_dir)
