Chemical structures (spec/18 section 18.6) and biological sequences (18.7) tied to
the words of a paper. Minor change: two new body kinds, optional properties and
seven rules, with no valid file made invalid.
- annotation schema: structure (SMILES or SMARTS, role, identity, written, label,
accessions, force-field terms) and sequence (alphabet, role, identity, start,
organism, regions, variants); body_kind in sql/store.sql; nine terms in the
JSON-LD context; rules layer.structure.{value,identity,term} and
layer.sequence.{value,identity,region,variant}.
- paperspec.structures reads the atoms and bonds of a SMILES or SMARTS with the
standard library, so a term's atoms are checked without a toolkit; checked against
RDKit on a corpus and random texts. paperspec.sequences checks alphabets,
identities, regions and variants.
- fixtures/records/chemistry (on the main example) and biology (on the draft, which
gains a last sentence), vectors/structures.jsonl and vectors/sequences.jsonl;
check.py runs both layers and the vectors; counts, guides and CHANGELOG updated.
- the prose check no longer takes organism for a UK spelling.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01B8cL4zN4XpaQF5cBtASzfq
71 lines
1.6 KiB
Plaintext
71 lines
1.6 KiB
Plaintext
{
|
|
"@context": {
|
|
"@version": 1.1,
|
|
"sct": "https://paperspec.scient.ing/vocab#",
|
|
"format": "sct:format",
|
|
"kind": "sct:kind",
|
|
"status": "sct:status",
|
|
"receipt": "sct:receipt",
|
|
"layer": {
|
|
"@id": "sct:layer",
|
|
"@type": "@id"
|
|
},
|
|
"audience": "sct:audience",
|
|
"visibility": "sct:visibility",
|
|
"purpose": "sct:purpose",
|
|
"project": "sct:project",
|
|
"docs": {
|
|
"@id": "sct:docs",
|
|
"@container": "@set"
|
|
},
|
|
"pin": "sct:pin",
|
|
"role": "sct:role",
|
|
"symbol": "sct:symbol",
|
|
"key": "sct:symbolKey",
|
|
"verdict": "sct:verdict",
|
|
"reason": "sct:reason",
|
|
"reference": "sct:reference",
|
|
"note": "sct:note",
|
|
"proposer": {
|
|
"@id": "sct:proposedBy",
|
|
"@type": "@json"
|
|
},
|
|
"identity": "sct:identity",
|
|
"written": "sct:written",
|
|
"alphabet": "sct:alphabet",
|
|
"organism": "sct:organism",
|
|
"start": "sct:start",
|
|
"accessions": {
|
|
"@id": "sct:accessions",
|
|
"@type": "@json"
|
|
},
|
|
"terms": {
|
|
"@id": "sct:structureTerms",
|
|
"@type": "@json"
|
|
},
|
|
"regions": {
|
|
"@id": "sct:regions",
|
|
"@type": "@json"
|
|
},
|
|
"variants": {
|
|
"@id": "sct:variants",
|
|
"@type": "@json"
|
|
},
|
|
"for": "sct:questionFor",
|
|
"category": "sct:category",
|
|
"generator": "sct:generatedBy",
|
|
"exercise": {
|
|
"@id": "sct:exercise",
|
|
"@type": "@json"
|
|
},
|
|
"anchor": {
|
|
"@id": "sct:anchor",
|
|
"@type": "@json"
|
|
},
|
|
"AnchorSelector": "sct:AnchorSelector",
|
|
"rights_use": "sct:rightsUse",
|
|
"total": "as:totalItems",
|
|
"as": "https://www.w3.org/ns/activitystreams#"
|
|
}
|
|
}
|