Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COC(=O)Cc1cccc(OCC[C@H](C)OS(=O)(=O)c2ccc(C)cc2)c1
InChiKey
TVBLOCONPORSPL-INIZCTEOSA-N
Route Signature
f8d988d34623269b21652fef01888ffa9b90b985c54deb7b99e96114811b9065
Synthesis route with 3 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_1462d5bc56a4cc52e87e86c3",
"signature": "f8d988d34623269b21652fef01888ffa9b90b985c54deb7b99e96114811b9065",
"contentHash": "aeadad11003191a842c19b236edfd3b085f722ba3cb4237eef0e202c8863ac50",
"length": 3,
"isConvergent": true
},
"target": {
"id": "sa_7a5046a051b3b3204374de6b",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-02322",
"moleculeId": "sa_5d910a2d8f2bd28162082b6e",
"smiles": "COC(=O)Cc1cccc(OCC[C@H](C)OS(=O)(=O)c2ccc(C)cc2)c1",
"routeLength": 3,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_5d910a2d8f2bd28162082b6e",
"inchikey": "TVBLOCONPORSPL-INIZCTEOSA-N",
"smiles": "COC(=O)Cc1cccc(OCC[C@H](C)OS(=O)(=O)c2ccc(C)cc2)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "1856",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_5d910a2d8f2bd28162082b6e",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_5d910a2d8f2bd28162082b6e",
"inchikey": "TVBLOCONPORSPL-INIZCTEOSA-N",
"smiles": "COC(=O)Cc1cccc(OCC[C@H](C)OS(=O)(=O)c2ccc(C)cc2)c1"
},
"smiles": "COC(=O)Cc1cccc(OCC[C@H](C)OS(=O)(=O)c2ccc(C)cc2)c1",
"reactionStepId": "sa_811bb9ddd9d5d0c7282f250f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060041164A1;0281;329926\",\"rsmi\":\"Cl[S:15](=[O:16])(=[O:17])[c:18]1[cH:19][cH:20][c:21]([CH3:22])[cH:23][cH:24]1.[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([O:9][CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14])[cH:25][cH:26][cH:27]1>CCCCCC.CCN(CC)CC.ClCCl.O>[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([O:9][CH2:10][CH2:11][C@H:12]([CH3:13])[O:14][S:15](=[O:16])(=[O:17])[c:18]2[cH:19][cH:20][c:21]([CH3:22])[cH:23][cH:24]2)[cH:25][cH:26][cH:27]1\"},\"mapped_reaction_smiles\":\"Cl[S:15](=[O:16])(=[O:17])[c:18]1[cH:19][cH:20][c:21]([CH3:22])[cH:23][cH:24]1.[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([O:9][CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14])[cH:25][cH:26][cH:27]1>CCCCCC.CCN(CC)CC.ClCCl.O>[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([O:9][CH2:10][CH2:11][C@H:12]([CH3:13])[O:14][S:15](=[O:16])(=[O:17])[c:18]2[cH:19][cH:20][c:21]([CH3:22])[cH:23][cH:24]2)[cH:25][cH:26][cH:27]1\"}",
"reactionStep": {
"id": "sa_811bb9ddd9d5d0c7282f250f",
"reactionHash": "7d38ecc17752263d8518a0c21e08f8136a28d808180e1e9a292824a728ff76a6"
},
"children": [
{
"id": "1857",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_9760c42ebd722814dd345bbd",
"parentId": "1856",
"isLeaf": false,
"molecule": {
"id": "sa_9760c42ebd722814dd345bbd",
"inchikey": "AETUZYOMOMSPRQ-JTQLQIEISA-N",
"smiles": "COC(=O)Cc1cccc(OCC[C@H](C)O)c1"
},
"smiles": "COC(=O)Cc1cccc(OCC[C@H](C)O)c1",
"reactionStepId": "sa_d6ec1cc517feac4c56977a5b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060041164A1;0280;329925\",\"rsmi\":\"Cc1ccc(S(=O)(=O)O[CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14])cc1.[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([OH:9])[cH:15][cH:16][cH:17]1>CCCCCC.CN(C)C=O.O=C(O)O.[Cs+].[Cs+]>[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([O:9][CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14])[cH:15][cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"Cc1ccc(S(=O)(=O)O[CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14])cc1.[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([OH:9])[cH:15][cH:16][cH:17]1>CCCCCC.CN(C)C=O.O=C(O)O.[Cs+].[Cs+]>[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([O:9][CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14])[cH:15][cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_d6ec1cc517feac4c56977a5b",
"reactionHash": "a21121727a2e75a030807950c511dbb263cf32cc79db66bbda6baf2e896bf2ee"
},
"children": [
{
"id": "1858",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_9bb1f2462a1db83dea1686bf",
"parentId": "1857",
"isLeaf": false,
"molecule": {
"id": "sa_9bb1f2462a1db83dea1686bf",
"inchikey": "AMDDOQIUPAINLH-UHFFFAOYSA-N",
"smiles": "COC(=O)Cc1cccc(O)c1"
},
"smiles": "COC(=O)Cc1cccc(O)c1",
"reactionStepId": "sa_21afbe62deee8f9e6ebfc771",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060041164A1;0263;329921\",\"rsmi\":\"O[C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([OH:9])[cH:10][cH:11][cH:12]1.[CH3:1][OH:2]>O=S(=O)(O)O>[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([OH:9])[cH:10][cH:11][cH:12]1\"},\"mapped_reaction_smiles\":\"O[C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([OH:9])[cH:10][cH:11][cH:12]1.[CH3:1][OH:2]>O=S(=O)(O)O>[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([OH:9])[cH:10][cH:11][cH:12]1\"}",
"reactionStep": {
"id": "sa_21afbe62deee8f9e6ebfc771",
"reactionHash": "83a2209f5d41461a306d7c803a8ae4808b998d1befdc84dd5064891defb79f07"
},
"children": [
{
"id": "1859",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_1760c1f30c9da9ec68cd8449",
"parentId": "1858",
"isLeaf": true,
"molecule": {
"id": "sa_1760c1f30c9da9ec68cd8449",
"inchikey": "FVMDYYGIDFPZAX-UHFFFAOYSA-N",
"smiles": "O=C(O)Cc1cccc(O)c1"
},
"smiles": "O=C(O)Cc1cccc(O)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "1860",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "1858",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "1861",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_97a8cf81991470a1df529df4",
"parentId": "1857",
"isLeaf": false,
"molecule": {
"id": "sa_97a8cf81991470a1df529df4",
"inchikey": "HELSCPRKLIJMBU-JTQLQIEISA-N",
"smiles": "Cc1ccc(S(=O)(=O)OCC[C@H](C)O)cc1"
},
"smiles": "Cc1ccc(S(=O)(=O)OCC[C@H](C)O)cc1",
"reactionStepId": "sa_6df69d68229cfde48fad2abd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060041164A1;0272;329924\",\"rsmi\":\"Cl[S:6]([c:5]1[cH:4][cH:3][c:2]([CH3:1])[cH:16][cH:15]1)(=[O:7])=[O:8].[OH:9][CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14]>CCN(CC)CC.ClCCl.O>[CH3:1][c:2]1[cH:3][cH:4][c:5]([S:6](=[O:7])(=[O:8])[O:9][CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14])[cH:15][cH:16]1\"},\"mapped_reaction_smiles\":\"Cl[S:6]([c:5]1[cH:4][cH:3][c:2]([CH3:1])[cH:16][cH:15]1)(=[O:7])=[O:8].[OH:9][CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14]>CCN(CC)CC.ClCCl.O>[CH3:1][c:2]1[cH:3][cH:4][c:5]([S:6](=[O:7])(=[O:8])[O:9][CH2:10][CH2:11][C@H:12]([CH3:13])[OH:14])[cH:15][cH:16]1\"}",
"reactionStep": {
"id": "sa_6df69d68229cfde48fad2abd",
"reactionHash": "71937893df064d2a827a4825addeafd212e7beaf9f4079b0e5332c911f033aa2"
},
"children": [
{
"id": "1862",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_b225825768a4e835451d87e9",
"parentId": "1861",
"isLeaf": true,
"molecule": {
"id": "sa_b225825768a4e835451d87e9",
"inchikey": "PUPZLCDOIYMWBV-BYPYZUCNSA-N",
"smiles": "C[C@H](O)CCO"
},
"smiles": "C[C@H](O)CCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "1863",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_28189ad2d33238c7f987ecf5",
"parentId": "1861",
"isLeaf": true,
"molecule": {
"id": "sa_28189ad2d33238c7f987ecf5",
"inchikey": "YYROPELSRYBVMQ-UHFFFAOYSA-N",
"smiles": "Cc1ccc(S(=O)(=O)Cl)cc1"
},
"smiles": "Cc1ccc(S(=O)(=O)Cl)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "1864",
"routeId": "sa_1462d5bc56a4cc52e87e86c3",
"moleculeId": "sa_28189ad2d33238c7f987ecf5",
"parentId": "1856",
"isLeaf": true,
"molecule": {
"id": "sa_28189ad2d33238c7f987ecf5",
"inchikey": "YYROPELSRYBVMQ-UHFFFAOYSA-N",
"smiles": "Cc1ccc(S(=O)(=O)Cl)cc1"
},
"smiles": "Cc1ccc(S(=O)(=O)Cl)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}