メニュー
Encode reaction SMILES into DRFP fingerprint features for BO.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Orchestrate an end-to-end chemistry or materials optimization study from a plain-English research question to BO execution and a paper draft.
BO execution layer — initializes a run from a resolved experiment spec, records observations, and continues through suggest/observe/report.
Initialize a BO run from a dataset or explicit search-space JSON.
Generate a final BO report and summarize optimization status.
Run an external evaluator loop for a BO run using a pre-provisioned backend id.
Design and stabilize an expensive or fragile chemistry evaluator before BO setup.
| name | bo-encode-drfp |
| description | Encode reaction SMILES into DRFP fingerprint features for BO. |
Use this skill when the user has a CSV with reaction SMILES and wants to convert it into numerical fingerprint features suitable for the BO engine.
uv run python -m bo_workflow.converters.reaction_drfp encode \
--input <CSV_PATH> --output-dir <DIR>
Optional flags: --rxn-col <COL> (default rxn_smiles), --n-bits <N> (default 128).
features_csv — path to the encoded features CSV (fingerprint bit columns + passthrough columns)catalog_csv — path to the catalog CSV (maps fingerprint rows back to original reaction SMILES)reactions — number of reactions encodedfingerprint_bits — number of bit columns generatedpassthrough_columns — non-SMILES columns carried through from the inputfeatures.csv is ready to pass directly to init --dataset.catalog.csv is needed later by decode to map BO suggestions back to real reactions.features.csv.