Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CCOC(=O)COc1cccc(CCCn2cc(C(c3ccccc3)c3ccccc3)ccc2=O)c1
InChiKey
WJFHISILQYANNL-UHFFFAOYSA-N
Route Signature
e257f404d6823283b7b2f4a3a08900c94d250865cdcb78d7130dc12b8a8614da
Synthesis route with 6 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_e80a86b4621e77d58a63574c",
"signature": "e257f404d6823283b7b2f4a3a08900c94d250865cdcb78d7130dc12b8a8614da",
"contentHash": "fd3399320fba8c545570213a6f6ec82a3611d7454adfbc58e8cf88b00f96f343",
"length": 6,
"isConvergent": false
},
"target": {
"id": "sa_971ff73c9e3e2400226f9b25",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00128",
"moleculeId": "sa_60bf780dc93ae18c9233d471",
"smiles": "CCOC(=O)COc1cccc(CCCn2cc(C(c3ccccc3)c3ccccc3)ccc2=O)c1",
"routeLength": 6,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_60bf780dc93ae18c9233d471",
"inchikey": "WJFHISILQYANNL-UHFFFAOYSA-N",
"smiles": "CCOC(=O)COc1cccc(CCCn2cc(C(c3ccccc3)c3ccccc3)ccc2=O)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "12489",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_60bf780dc93ae18c9233d471",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_60bf780dc93ae18c9233d471",
"inchikey": "WJFHISILQYANNL-UHFFFAOYSA-N",
"smiles": "CCOC(=O)COc1cccc(CCCn2cc(C(c3ccccc3)c3ccccc3)ccc2=O)c1"
},
"smiles": "CCOC(=O)COc1cccc(CCCn2cc(C(c3ccccc3)c3ccccc3)ccc2=O)c1",
"reactionStepId": "sa_756dc37250af233e66b5f60f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100009991A1;1636;820914\",\"rsmi\":\"I[CH2:13][CH2:12][CH2:11][c:10]1[cH:9][c:8]([O:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])[cH:36][cH:35][cH:34]1.[nH:14]1[cH:15][c:16]([CH:17]([c:18]2[cH:19][cH:20][cH:21][cH:22][cH:23]2)[c:24]2[cH:25][cH:26][cH:27][cH:28][cH:29]2)[cH:30][cH:31][c:32]1=[O:33]>CN(C)C=O.Cl.[HH].[Li+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][n:14]2[cH:15][c:16]([CH:17]([c:18]3[cH:19][cH:20][cH:21][cH:22][cH:23]3)[c:24]3[cH:25][cH:26][cH:27][cH:28][cH:29]3)[cH:30][cH:31][c:32]2=[O:33])[cH:34][cH:35][cH:36]1\"},\"mapped_reaction_smiles\":\"I[CH2:13][CH2:12][CH2:11][c:10]1[cH:9][c:8]([O:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])[cH:36][cH:35][cH:34]1.[nH:14]1[cH:15][c:16]([CH:17]([c:18]2[cH:19][cH:20][cH:21][cH:22][cH:23]2)[c:24]2[cH:25][cH:26][cH:27][cH:28][cH:29]2)[cH:30][cH:31][c:32]1=[O:33]>CN(C)C=O.Cl.[HH].[Li+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][n:14]2[cH:15][c:16]([CH:17]([c:18]3[cH:19][cH:20][cH:21][cH:22][cH:23]3)[c:24]3[cH:25][cH:26][cH:27][cH:28][cH:29]3)[cH:30][cH:31][c:32]2=[O:33])[cH:34][cH:35][cH:36]1\"}",
"reactionStep": {
"id": "sa_756dc37250af233e66b5f60f",
"reactionHash": "d9d2774d5fa4d3e19e94d6144cfe5f13ea1d1ffa9ded8c39724ba2a2e78c97ba"
},
"children": [
{
"id": "12490",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_277661d8b0c1233db8fd997c",
"parentId": "12489",
"isLeaf": true,
"molecule": {
"id": "sa_277661d8b0c1233db8fd997c",
"inchikey": "BYRNFBSYDXQMKZ-UHFFFAOYSA-N",
"smiles": "O=c1ccc(C(c2ccccc2)c2ccccc2)c[nH]1"
},
"smiles": "O=c1ccc(C(c2ccccc2)c2ccccc2)c[nH]1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12491",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_efdc79e6a7143ed2f521c277",
"parentId": "12489",
"isLeaf": false,
"molecule": {
"id": "sa_efdc79e6a7143ed2f521c277",
"inchikey": "VUEMQFAVTGUVIC-UHFFFAOYSA-N",
"smiles": "CCOC(=O)COc1cccc(CCCI)c1"
},
"smiles": "CCOC(=O)COc1cccc(CCCI)c1",
"reactionStepId": "sa_f94b0cef16dc23fc5eedacb5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100009991A1;0935;820886\",\"rsmi\":\"CS(=O)(=O)O[CH2:13][CH2:12][CH2:11][c:10]1[cH:9][c:8]([O:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])[cH:17][cH:16][cH:15]1.[IH:14]>CC(C)=O.CCOC(C)=O.[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][I:14])[cH:15][cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"CS(=O)(=O)O[CH2:13][CH2:12][CH2:11][c:10]1[cH:9][c:8]([O:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])[cH:17][cH:16][cH:15]1.[IH:14]>CC(C)=O.CCOC(C)=O.[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][I:14])[cH:15][cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_f94b0cef16dc23fc5eedacb5",
"reactionHash": "f2cb23af1c0f4640996a127756928e617ee37c66d414eaf95097cc8066c432d3"
},
"children": [
{
"id": "12492",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_8a3b3f353ab97b3e33ce5980",
"parentId": "12491",
"isLeaf": false,
"molecule": {
"id": "sa_8a3b3f353ab97b3e33ce5980",
"inchikey": "ILCJEJWGUSXGKM-UHFFFAOYSA-N",
"smiles": "CCOC(=O)COc1cccc(CCCOS(C)(=O)=O)c1"
},
"smiles": "CCOC(=O)COc1cccc(CCCOS(C)(=O)=O)c1",
"reactionStepId": "sa_d35ff35a872c04a04e120073",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100009991A1;0791;820868\",\"rsmi\":\"Cl[S:15]([CH3:16])(=[O:17])=[O:18].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][OH:14])[cH:19][cH:20][cH:21]1>ClCCl.O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][O:14][S:15]([CH3:16])(=[O:17])=[O:18])[cH:19][cH:20][cH:21]1\"},\"mapped_reaction_smiles\":\"Cl[S:15]([CH3:16])(=[O:17])=[O:18].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][OH:14])[cH:19][cH:20][cH:21]1>ClCCl.O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][O:14][S:15]([CH3:16])(=[O:17])=[O:18])[cH:19][cH:20][cH:21]1\"}",
"reactionStep": {
"id": "sa_d35ff35a872c04a04e120073",
"reactionHash": "37c79f9dba96af509bfd7b8be658d2a821e4824f151e8afda7ca4b978c3d307b"
},
"children": [
{
"id": "12493",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "12492",
"isLeaf": true,
"molecule": {
"id": "sa_d2a31ea58046b00856f61ca5",
"inchikey": "QARBMVPHQWIHKH-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)Cl"
},
"smiles": "CS(=O)(=O)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12494",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_e555c05ff4dad43813493847",
"parentId": "12492",
"isLeaf": false,
"molecule": {
"id": "sa_e555c05ff4dad43813493847",
"inchikey": "ZZGYFELVHJVLKI-UHFFFAOYSA-N",
"smiles": "CCOC(=O)COc1cccc(CCCO)c1"
},
"smiles": "CCOC(=O)COc1cccc(CCCO)c1",
"reactionStepId": "sa_d2606977be5f7f327552721b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100009991A1;0522;820848\",\"rsmi\":\"Br[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][OH:14])[cH:15][cH:16][cH:17]1>CC#N.O.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][OH:14])[cH:15][cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"Br[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][OH:14])[cH:15][cH:16][cH:17]1>CC#N.O.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[cH:9][c:10]([CH2:11][CH2:12][CH2:13][OH:14])[cH:15][cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_d2606977be5f7f327552721b",
"reactionHash": "290c485926dc05cab4798a9f43618590bcf8f6ab3938fd89b4c9d0444aaa90e7"
},
"children": [
{
"id": "12495",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_6170bddd2f4a4137325c4a17",
"parentId": "12494",
"isLeaf": true,
"molecule": {
"id": "sa_6170bddd2f4a4137325c4a17",
"inchikey": "PQJJJMRNHATNKG-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CBr"
},
"smiles": "CCOC(=O)CBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12496",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_68afc73714778b9674bd9ed0",
"parentId": "12494",
"isLeaf": false,
"molecule": {
"id": "sa_68afc73714778b9674bd9ed0",
"inchikey": "TVQDIGAZKJXXLX-UHFFFAOYSA-N",
"smiles": "OCCCc1cccc(O)c1"
},
"smiles": "OCCCc1cccc(O)c1",
"reactionStepId": "sa_91774bf916c36d0ebd42eaf5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100009991A1;0859;820872\",\"rsmi\":\"CCO[C:2](=[O:1])[CH2:3][CH2:4][c:5]1[cH:6][cH:7][cH:8][c:9]([OH:10])[cH:11]1>CC(C)C[AlH]CC(C)C.ClCCl.O=C(O)[C@H](O)[C@@H](O)C(=O)O.[K+].[Na+]>[OH:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][cH:8][c:9]([OH:10])[cH:11]1\"},\"mapped_reaction_smiles\":\"CCO[C:2](=[O:1])[CH2:3][CH2:4][c:5]1[cH:6][cH:7][cH:8][c:9]([OH:10])[cH:11]1>CC(C)C[AlH]CC(C)C.ClCCl.O=C(O)[C@H](O)[C@@H](O)C(=O)O.[K+].[Na+]>[OH:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][cH:8][c:9]([OH:10])[cH:11]1\"}",
"reactionStep": {
"id": "sa_91774bf916c36d0ebd42eaf5",
"reactionHash": "49681defb7367d07e5e341589b4966f5b6d4692b2e6c3bc09cfe3b922f6d9479"
},
"children": [
{
"id": "12497",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_9e7873e8853ad2f99ea3b5df",
"parentId": "12496",
"isLeaf": false,
"molecule": {
"id": "sa_9e7873e8853ad2f99ea3b5df",
"inchikey": "ZECGNJSXCCKHDX-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCc1cccc(O)c1"
},
"smiles": "CCOC(=O)CCc1cccc(O)c1",
"reactionStepId": "sa_21ffc50f6b16cb448eb52407",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100009991A1;0782;820866\",\"rsmi\":\"O[C:4](=[O:5])[CH2:6][CH2:7][c:8]1[cH:9][c:10]([OH:11])[cH:12][cH:13][cH:14]1.[CH3:1][CH2:2][OH:3]>O=S(=O)(O)O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][c:8]1[cH:9][c:10]([OH:11])[cH:12][cH:13][cH:14]1\"},\"mapped_reaction_smiles\":\"O[C:4](=[O:5])[CH2:6][CH2:7][c:8]1[cH:9][c:10]([OH:11])[cH:12][cH:13][cH:14]1.[CH3:1][CH2:2][OH:3]>O=S(=O)(O)O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][c:8]1[cH:9][c:10]([OH:11])[cH:12][cH:13][cH:14]1\"}",
"reactionStep": {
"id": "sa_21ffc50f6b16cb448eb52407",
"reactionHash": "3a86399001986068e494a49b8afe9136f541b2c5b79d40c41b8a66c541f5827f"
},
"children": [
{
"id": "12498",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_afaca116b303dc7d01346819",
"parentId": "12497",
"isLeaf": true,
"molecule": {
"id": "sa_afaca116b303dc7d01346819",
"inchikey": "LFQSCWFLJHTTHZ-UHFFFAOYSA-N",
"smiles": "CCO"
},
"smiles": "CCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12499",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_b0a285aad9a8a868894aded4",
"parentId": "12497",
"isLeaf": true,
"molecule": {
"id": "sa_b0a285aad9a8a868894aded4",
"inchikey": "QVWAEZJXDYOKEH-UHFFFAOYSA-N",
"smiles": "O=C(O)CCc1cccc(O)c1"
},
"smiles": "O=C(O)CCc1cccc(O)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
},
{
"id": "12500",
"routeId": "sa_e80a86b4621e77d58a63574c",
"moleculeId": "sa_bc906e425e53d363266dfe60",
"parentId": "12491",
"isLeaf": true,
"molecule": {
"id": "sa_bc906e425e53d363266dfe60",
"inchikey": "XMBWDFGMSWQBCA-UHFFFAOYSA-N",
"smiles": "I"
},
"smiles": "I",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}