Dev

.github/workflows/biosim_schema_project-ci.yaml

@@ -4,8 +4,6 @@ on:
   push:
     branches: [main]
   pull_request:
-  schedule:
-    - cron: '0 8 * * 1-5'
   workflow_dispatch:
 
 jobs:

biosim_schema/fieldextraction/extract_summary.py

@@ -18,7 +18,7 @@
 
 import yaml
 
-METADATA_KEYS = ("label", "hint", "typehint", "placeholder", "units")
+METADATA_KEYS = ("label", "hint", "typehint", "placeholder", "units", "example")
 """tuple[str, ...]: Field metadata keys copied from each webform node into the summary."""
 
 
@@ -125,6 +125,7 @@ def _flatten_rows(node, path):
         "placeholder_text": node.get("placeholder", ""),
         "default_unit": node.get("default_unit", ""),
         "data_type": node.get("typehint", ""),
+        "example": node.get("example", ""),
     }
     return [row]
 
@@ -153,6 +154,7 @@ def write_summary_csv(summary, output_path):
         "placeholder_text",
         "default_unit",
         "data_type",
+        "example",
     ]
 
     with open(output_path, "w", newline="", encoding="utf-8") as f:
@@ -203,6 +205,11 @@ def main():
             summary, f, default_flow_style=False, allow_unicode=True, sort_keys=True
         )
 
+    # output as json
+    json_path = yaml_path.with_suffix(".json")
+    with open(json_path, "w") as fp:
+        json.dump(summary, fp)
+
     # flatten and output as csv
     csv_path = yaml_path.with_suffix(".csv")
     write_summary_csv(summary, str(csv_path))

biosim_schema/fieldextraction/extract_webform_fields.py

@@ -165,15 +165,15 @@ def _render_primitive(self, slot):
         if self._get_annotation(slot, "textarea"):
             result["type"] = "textarea"
 
+        example = self._get_annotation(slot, "example")
+        if example:
+            result["example"] = example[0]
+
         if "unit" in slot:
             symbol = slot["unit"]["symbol"]
             result["units"] = [symbol]
             result["label"] += f" ({symbol})"
 
-        if "pattern" in slot:
-            result["placeholder"] = (
-                slot["examples"][0]["value"] if "examples" in slot else None
-            )
         if "pattern" in slot:
             result["pattern"] = slot["pattern"]
         if "examples" in slot:
@@ -208,6 +208,9 @@ def _render_enum(self, slot, enum):
             ],
             "multiple": slot.get("multivalued", False),
         }
+        example = self._get_annotation(slot, "example")
+        if example:
+            result["example"] = example[0]
         return self._apply_ui_annotations(slot, result)
 
     def _render_class_node(self, slot, context):
@@ -266,13 +269,19 @@ def _render_quantity(self, slot, context):
                     "placeholder": vector_placeholder,
                 }
 
-        return {
+        result = {
             "type": "quantity",
             "label": self._get_label(slot),
             "hint": slot.get("description"),
             "fields": fields,
         }
 
+        example = self._get_annotation(slot, "example")
+        if example:
+            result["example"] = example[0]
+
+        return result
+
     # =========================================================
     # TYPE CHECKS
     # =========================================================

biosim_schema/schema/components/biosim_composition.yaml

@@ -59,7 +59,11 @@ slots:
       Concentration of salt in the solution.
     range: ConcentrationQuantity # class
     examples:
-        - value: 1
+      - value: 0.1
+    annotations:
+      example:
+        - value: 0.1
+          value_unit: M
 
   total_atom_count:
     description:
@@ -72,6 +76,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: total_atom_count
+      example:
+        - value: 1
 
   total_molecule_count:
     description:
@@ -84,6 +90,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: total_molecule_count
+      example:
+        - value: 1
 
   atom_count:
     description:
@@ -96,6 +104,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: atom_count
+      example:
+        - value: 1
 
   molecule_count:
     description:
@@ -108,6 +118,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: molecule_count
+      example:
+        - value: 1
 
   monomer_count:
     description:
@@ -120,6 +132,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: monomer_count
+      example:
+        - value: 1
 
   molecular_weight:
     description:
@@ -132,6 +146,9 @@ slots:
         - engine: toptrajparser
           key: molecular_weight
           unit: g/mol
+      example:
+        - value: 18.0
+          value_unit: g/mol
 
   molecule_charge:
     description:
@@ -145,6 +162,9 @@ slots:
         - engine: toptrajparser
           key: molecule_charge
           unit: e
+      example:
+        - value: -1.0
+          value_unit: e
 
   unique_molecule_count:
     description:
@@ -157,6 +177,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: unique_molecule_count
+      example:
+        - value: 1
 
   system_counts:
     description:
@@ -194,6 +216,8 @@ slots:
       database: "PDB"
       prefix: "pdb"
       base_uri: "https://identifiers.org/pdb:"
+      example:
+        - value: "2VB1"
 
   UNIPROT_ID:
     is_a: identifier
@@ -208,6 +232,8 @@ slots:
       database: "UNIPROT"
       prefix: "uniprot"
       base_uri: "https://identifiers.org/uniprot:"
+      example:
+        - value: "P0DP23"
 
   EMDB_ID:
     is_a: identifier
@@ -222,6 +248,8 @@ slots:
       database: "EMDB"
       prefix: "emdb"
       base_uri: "https://identifiers.org/emdb:"
+      example:
+        - value: "EMD-1001"
 
   alphafold_ID:
     is_a: identifier
@@ -235,6 +263,8 @@ slots:
     annotations:
       database: "AlphaFoldDB"
       base_uri: "https://alphafold.ebi.ac.uk/entry/"
+      example:
+        - value: "AF-P12345-F1"
 
   PubChem_CID:
     is_a: identifier
@@ -250,6 +280,8 @@ slots:
       database: "PubChem"
       prefix: "pubchem.compound"
       base_uri: "https://identifiers.org/pubchem.compound:"
+      example:
+        - value: "100101"
 
   InChIKey:
     is_a: identifier
@@ -268,6 +300,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: InChIKey
+      example:
+        - value: "RYYVLZVUVIJVGH-UHFFFAOYSA-N"
 
   SMILES:
     description:
@@ -282,6 +316,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: SMILES
+      example:
+        - value: "CN1C=NC2=C1C(=O)N(C(=O)N2C)C"
 
   InChI:
     description:
@@ -296,6 +332,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: InChI
+      example:
+        - value: "InChI=1S/C8H10N4O2/c1-10-4-9-6-5(10)7(13)12(3)8(14)11(6)2/h4H,1-3H3"
 
   molecular_formula:
     description:
@@ -308,16 +346,28 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: molecular_formula
+      example:
+        - value: "C8H10N4O2"
 
   predicted_structure:
     description:
       Are the molecule positions derived from a prediction?
+    examples:
+      - value: "True"
     range: boolean
+    annotations:
+      example:
+        - value: "True"
 
   modified:
     description:
       Has the initial model been modified from the original?
+    examples:
+      - value: "True"
     range: boolean
+    annotations:
+      example:
+        - value: "True"
 
   protein_sequence:
     description:
@@ -331,6 +381,8 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: protein_sequence
+      example:
+        - value: "DRVYIHPF"
 
   nucleic_sequence:
     description:
@@ -344,3 +396,5 @@ slots:
       engine_mapping:
         - engine: toptrajparser
           key: nucleic_sequence
+      example:
+        - value: "ATGCATCGATCGATCGATCG"