Merge pull request #2 from sdsc-ordes/feat/meta

feat: package skeleton

.github/workflows/poetry-pytest.yml

@@ -0,0 +1,39 @@
+name: tests
+
+on: [push]
+
+jobs:
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10"]
+    steps:
+      # https://github.com/actions/checkout
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      # https://github.com/actions/setup-python
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      # https://github.com/snok/install-poetry
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+
+      - name: Install Dependencies
+        run: poetry install
+        if: steps.cache.outputs.cache-hit != 'true'
+
+      - name: Code Quality
+        run: poetry run black . --check
+
+      - name: Test with pytest
+        env:
+          GITHUB_TOKEN: ${{ secrets.ACCESS_GITHUB_TOKEN }}
+          GITLAB_TOKEN: ${{ secrets.GITLAB_ACCESS_TOKEN }}
+        run: make test

.pre-commit-config.yaml

@@ -0,0 +1,11 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+    -   id: check-yaml
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace
+-   repo: https://github.com/psf/black
+    rev: 22.10.0
+    hooks:
+    -   id: black

Makefile

@@ -0,0 +1,23 @@
+.PHONY: install
+install: ## Install with the poetry and add pre-commit hooks
+	@echo "🚀 Installing packages with poetry"
+	@poetry install
+	@poetry run pre-commit install
+
+.PHONY: check
+check: ## Run code quality tools.
+	@echo "🚀 Checking Poetry lock file consistency with 'pyproject.toml': Running poetry lock --check"
+	@poetry lock --check
+	@echo "🚀 Linting code: Running pre-commit"
+	@poetry run pre-commit run -a
+
+.PHONY: test
+test: ## Test the code with pytest
+	@echo "🚀 Testing code: Running pytest"
+	@poetry run pytest
+
+.PHONY: help
+help:
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-20s\033[0m %s\n", $$1, $$2}'
+
+.DEFAULT_GOAL := help

assets/schema.ttl

@@ -0,0 +1,82 @@
+@prefix ex: <http://example.org/> .
+@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
+@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
+@prefix skos: <http://www.w3.org/2004/02/skos/core#> .
+@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
+@prefix bioschemas: <http://bioschemas.org/> .
+@prefix taxon: <http://purl.uniprot.org/taxonomy/> .
+@prefix schema: <http://schema.org/> .
+@prefix mondo: <http://purl.obolibrary.org/obo/mondo#> .
+@prefix ror: <https://ror.org/> .
+@prefix smoc: <http://smoc.ethz.ch> .
+
+# Classes
+
+smoc:MODO a rdfs:Class ;
+    rdfs:label "Multi-Omics Digital Object" ;
+    rdfs:comment "A digital object which can contain multiple omics data records and samples" .
+
+smoc:CRAMFile a rdfs:Class ;
+    rdfs:label "CRAM file" ;
+    rdfs:comment "A file containing aligned genomic intervals" .
+
+smoc:Array a rdfs:Class ;
+    rdfs:label "Array" ;
+    rdfs:comment "An array inside a Zarr archive containing data and metadata. Part of a digital object." .
+
+smoc:Reference a rdfs:Class ;
+    rdfs:label "Reference genome" ;
+    rdfs:comment "A genome assembly used as reference coordinate system for aligning data records." .
+
+smoc:BioSample a rdfs:Class ;
+    rdfs:label "Biological sample" ;
+    rdfs:comment "A sample of biological material." .
+
+# In practice, we should use http://purl.obolibrary.org/obo/ncbitaxon.owl
+smoc:Taxon a rdfs:Class ;
+    rdfs:label "Taxon" ;
+    rdfs:comment "A taxonomic unit describing a biological entity" .
+
+smoc:OmicsType a rdfs:Class ;
+    rdfs:label "Omics type" ;
+    rdfs:comment "A type of omics field, tied to a biological molecule" .
+
+# Properties
+
+smoc:hasTaxonomicRange a rdf:Property ;
+    rdfs:domain smoc:BioSample, smoc:Reference ;
+    rdfs:range smoc:Taxon ;
+    rdfs:label "has taxonomic range" .
+
+smoc:hasSample a rdf:Property ;
+    rdfs:domain smoc:MODO, smoc:CRAMFile .
+
+smoc:hasRecord a rdf:Property ;
+    rdfs:domain smoc:MODO ;
+    rdfs:range smoc:Record ;
+    rdfs:label "has record" .
+
+smoc:hasReference a rdf:Property ;
+    rdfs:domain smoc:MODO, smoc:Record ;
+    rdfs:range smoc:Reference .
+
+smoc:hasOmicsType a rdf:Property ;
+    rdfs:domain smoc:Array ;
+    rdfs:range smoc:OmicsType .
+
+smoc:hasLocation a rdf:property ;
+    rdfs:domain smoc:MODO, smoc:CRAMFile, smoc:Reference ;
+    rdfs:range xsd:anyURI ;
+    rdfs:label "has location" ;
+    rdfs:comment "The location of a resource, either on the filesystem or online" .
+
+smoc:hasTaxId a rdf:Property ;
+    rdfs:domain smoc:Taxon ;
+    rdfs:range xsd:integer .
+
+# Named individuals
+
+smoc:Genomics a smoc:OmicsType .
+smoc:Transcriptomics a smoc:OmicsType .
+smoc:Proteomics a smoc:OmicsType .
+smoc:Metabolomics a smoc:OmicsType .