add pathways.txt.gz

we also introduce the inner Snakefile

Author: tristan-f-r

cache/directory.py

@@ -358,6 +358,11 @@ def download(self, output: str | PathLike):
             name="PathwayCommons Universal BioPAX file",
             cached="https://drive.google.com/uc?id=1R7uE2ky7fGlZThIWCOblu7iqbpC-aRr0",
             pinned="https://download.baderlab.org/PathwayCommons/PC2/v14/pc-biopax.owl.gz"
+        ),
+        "pathways.txt.gz": CacheItem(
+            name="PathwayCommons Pathway Identifiers",
+            cached="https://drive.google.com/uc?id=1SMwuuohuZuNFnTev4zRNJrBnBsLlCHcK",
+            pinned="https://download.baderlab.org/PathwayCommons/PC2/v14/pathways.txt.gz",
         )
     }
 }

datasets/synthetic-data/.gitignore

@@ -1,3 +1,3 @@
-intermediate
-processed
-raw
+/intermediate
+/processed
+/raw

datasets/synthetic-data/README.md

@@ -1,13 +1,11 @@
 # Synthetic Data
 
-## Download STRING Human Interactome
-1. Download the STRING *Homo sapiens* `9606.protein.links.full.v12.0.txt.gz` database file from [STRING](https://string-db.org/cgi/download?sessionId=bL9sRTdIaUEt&species_text=Homo+sapiens&settings_expanded=0&min_download_score=0&filter_redundant_pairs=0&delimiter_type=txt).
-2. Move the downloaded file into the `raw/human-interactome/` folder.
-3. From the `raw/synthetic-data/` directory, extract the file using:
+## PANTHER Pathway Fetching
 
-   ```sh
-   gunzip human-interactome/9606.protein.links.full.v12.0.txt.gz
-   ```
+This dataset has a kind of 'sub'-dataset, which is a separate Snakemake rule
+used for generating the pathway files and their associated metadata to be used inside this one.
+
+Located under `./panther_pathways`, it provides TODO.
 
 ## Download New PANTHER Pathways
 1. Visit [Pathway Commons](https://www.pathwaycommons.org/).

datasets/synthetic-data/Snakefile

@@ -38,7 +38,6 @@ produce_fetch_rules({
     "raw/human-interactome/table_S3_surfaceome.xlsx": ["Surfaceome", "table_S3_surfaceome.xlsx"],
     "raw/human-interactome/Homo_sapiens_TF.tsv": ["TranscriptionFactors", "Homo_sapiens_TF.tsv"],
     "raw/human-interactome/HUMAN_9606_idmapping_selected.tsv": FetchConfig(["UniProt", "9606", "HUMAN_9606_idmapping_selected.tab.gz"], uncompress=True),
-    "raw/pc-biopax.owl": FetchConfig(["PathwayCommons", "pc-biopax.owl.gz"], uncompress=True)
 })
 
 rule interactome:

datasets/synthetic-data/panther_pathways/.gitignore

@@ -0,0 +1 @@
+/raw

datasets/synthetic-data/panther_pathways/Snakefile

@@ -0,0 +1,11 @@
+include: "../../../cache/Snakefile"
+
+rule all:
+    input:
+        # TODO: pass to script
+        "raw/pathways.txt"   
+
+produce_fetch_rules({
+    "raw/pc-biopax.owl": FetchConfig(["PathwayCommons", "pc-biopax.owl.gz"], uncompress=True),
+    "raw/pathways.txt": FetchConfig(["PathwayCommons", "pathways.txt.gz"], uncompress=True)
+})

datasets/synthetic-data/panther_pathways/panther_identifiers.py

@@ -0,0 +1,5 @@
+def main():
+    pass
+
+if __name__ == "__main__":
+    main()