Document BERTose WURCS input contract

README.md

@@ -42,7 +42,9 @@ No Hugging Face token is required for this BERTose checkpoint now that the repos
 
 ## Input
 
-Provide one WURCS glycan string or a CSV batch with a WURCS column. The notebook examples use `wurcs` as the column name.
+Provide one WURCS glycan string or a CSV batch with `sample_id,wurcs`.
+
+Free-text glycan names, common names, SNFG drawings, and IUPAC-condensed strings are not parsed directly by this checkpoint. Convert those inputs to WURCS first, then run BERTose embedding inference.
 
 ## Output
 
@@ -50,6 +52,6 @@ Dense glycan embeddings. The companion notebook defaults to `[CLS]` pooling and
 
 ## Notes
 
-This repository does not perform IUPAC-condensed to WURCS conversion. For now, provide WURCS directly.
+This repository does not perform IUPAC-condensed/name-to-WURCS conversion. For now, provide WURCS directly.
 
 License metadata is currently `other`; update it when the final release license and citation text are chosen.

SHA256SUMS

@@ -1,5 +1,5 @@
 622368f62c23e97e9137c277eaadcc93ee3901cbb420b591422bb1c2e19689a5  ./.gitattributes
-d81f5b4dfbbd391dcec904fae940c8ebaa3fcdd780948cc3b95e55d9cebc8204  ./README.md
+11a88cad448bbd2926bc9be6fc61dfdd2ad268adb1252f140e9016e03a9cd859  ./README.md
 9ff260796c28e9f254d87da95592c686874d3954429d926d99afd2a8f9b6c08f  ./checkpoints/bertose_glycan_encoder.pt
 d5854b5960b949bee17dcae3078ad15641dd24516a6c73835784518d73adf979  ./config.json
 6a56e6f73b8f874470ecde6e538f3f5029ae23aa6c10559817d1c2a8b59b7c0f  ./requirements.txt