Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
O=C(Cl)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O
InChiKey
QIQNEGAIHWOMFH-UHFFFAOYSA-N
Route Signature
b3c12828b55905de7d129dd9a80c2c73c0712b728ae4ec699b794fa5a29675e5
Synthesis route with 5 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_e1e322947dfb34ec6ecef800",
"signature": "b3c12828b55905de7d129dd9a80c2c73c0712b728ae4ec699b794fa5a29675e5",
"contentHash": "b47a5700392669eb040305e4882dee0c1daf8ca7bfaa684cd3d5010517803864",
"length": 5,
"isConvergent": false
},
"target": {
"id": "sa_5f3b78af2d985825fe493935",
"benchmarkSetId": "f925e688d731a0ad4e3aa6a505df094f6d3ca64ce3facc312bc5f64731921b33",
"targetId": "n5-01407",
"moleculeId": "sa_ed99ce7d58104ac4f88b609c",
"smiles": "O=C(Cl)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O",
"routeLength": 5,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_ed99ce7d58104ac4f88b609c",
"inchikey": "QIQNEGAIHWOMFH-UHFFFAOYSA-N",
"smiles": "O=C(Cl)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 3
},
"rootNode": {
"id": "5534",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_ed99ce7d58104ac4f88b609c",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_ed99ce7d58104ac4f88b609c",
"inchikey": "QIQNEGAIHWOMFH-UHFFFAOYSA-N",
"smiles": "O=C(Cl)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O"
},
"smiles": "O=C(Cl)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O",
"reactionStepId": "sa_a66f0ed4415803c1829da59b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150190389A1;0701;1718311\",\"rsmi\":\"O=C(Cl)C(=O)[Cl:3].O[C:2](=[O:1])[CH2:4][CH2:5][O:6][CH2:7][CH2:8][O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][N:15]1[C:16](=[O:17])[c:18]2[cH:19][cH:20][cH:21][cH:22][c:23]2[C:24]1=[O:25]>CN(C)C=O.ClCCl>[O:1]=[C:2]([Cl:3])[CH2:4][CH2:5][O:6][CH2:7][CH2:8][O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][N:15]1[C:16](=[O:17])[c:18]2[cH:19][cH:20][cH:21][cH:22][c:23]2[C:24]1=[O:25]\"},\"mapped_reaction_smiles\":\"O=C(Cl)C(=O)[Cl:3].O[C:2](=[O:1])[CH2:4][CH2:5][O:6][CH2:7][CH2:8][O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][N:15]1[C:16](=[O:17])[c:18]2[cH:19][cH:20][cH:21][cH:22][c:23]2[C:24]1=[O:25]>CN(C)C=O.ClCCl>[O:1]=[C:2]([Cl:3])[CH2:4][CH2:5][O:6][CH2:7][CH2:8][O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][N:15]1[C:16](=[O:17])[c:18]2[cH:19][cH:20][cH:21][cH:22][c:23]2[C:24]1=[O:25]\"}",
"reactionStep": {
"id": "sa_a66f0ed4415803c1829da59b",
"reactionHash": "ba75abe8c20a8f44eb2ebac8a931cab282e17de99a8d757017fdcb3608e5d251"
},
"children": [
{
"id": "5535",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_83e7d4ec882b44062b48ca58",
"parentId": "5534",
"isLeaf": true,
"molecule": {
"id": "sa_83e7d4ec882b44062b48ca58",
"inchikey": "CTSLXHKWHWQRSH-UHFFFAOYSA-N",
"smiles": "O=C(Cl)C(=O)Cl"
},
"smiles": "O=C(Cl)C(=O)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "5536",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_4e513a44e35fbe3d74625270",
"parentId": "5534",
"isLeaf": false,
"molecule": {
"id": "sa_4e513a44e35fbe3d74625270",
"inchikey": "XMSDRSYXLUAWFR-UHFFFAOYSA-N",
"smiles": "O=C(O)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O"
},
"smiles": "O=C(O)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O",
"reactionStepId": "sa_a0dec9eb7fd573c0eb13a1ac",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150190389A1;0700;1718310\",\"rsmi\":\"CC(C)(C)[O:3][C:2](=[O:1])[CH2:4][CH2:5][O:6][CH2:7][CH2:8][O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][N:15]1[C:16](=[O:17])[c:18]2[cH:19][cH:20][cH:21][cH:22][c:23]2[C:24]1=[O:25]>O=C(O)C(F)(F)F>[O:1]=[C:2]([OH:3])[CH2:4][CH2:5][O:6][CH2:7][CH2:8][O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][N:15]1[C:16](=[O:17])[c:18]2[cH:19][cH:20][cH:21][cH:22][c:23]2[C:24]1=[O:25]\"},\"mapped_reaction_smiles\":\"CC(C)(C)[O:3][C:2](=[O:1])[CH2:4][CH2:5][O:6][CH2:7][CH2:8][O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][N:15]1[C:16](=[O:17])[c:18]2[cH:19][cH:20][cH:21][cH:22][c:23]2[C:24]1=[O:25]>O=C(O)C(F)(F)F>[O:1]=[C:2]([OH:3])[CH2:4][CH2:5][O:6][CH2:7][CH2:8][O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][N:15]1[C:16](=[O:17])[c:18]2[cH:19][cH:20][cH:21][cH:22][c:23]2[C:24]1=[O:25]\"}",
"reactionStep": {
"id": "sa_a0dec9eb7fd573c0eb13a1ac",
"reactionHash": "dc7740e025233336b0ce6b55578fa484d181f981ca2ac9e151631c29787a407e"
},
"children": [
{
"id": "5537",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_2b3334c53fbf8fe9f25568d5",
"parentId": "5536",
"isLeaf": false,
"molecule": {
"id": "sa_2b3334c53fbf8fe9f25568d5",
"inchikey": "FLOUBLHRSDODDD-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O"
},
"smiles": "CC(C)(C)OC(=O)CCOCCOCCOCCN1C(=O)c2ccccc2C1=O",
"reactionStepId": "sa_a60eeed4373534f20b28fecd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150190389A1;0699;1718309\",\"rsmi\":\"Cc1ccc(S(=O)(=O)O[CH2:18][CH2:17][O:16][CH2:15][CH2:14][O:13][CH2:12][CH2:11][O:10][CH2:9][CH2:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])cc1.[NH:19]1[C:20](=[O:21])[c:22]2[cH:23][cH:24][cH:25][cH:26][c:27]2[C:28]1=[O:29]>CN(C)C=O.O.[K]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[CH2:8][CH2:9][O:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][N:19]1[C:20](=[O:21])[c:22]2[cH:23][cH:24][cH:25][cH:26][c:27]2[C:28]1=[O:29]\"},\"mapped_reaction_smiles\":\"Cc1ccc(S(=O)(=O)O[CH2:18][CH2:17][O:16][CH2:15][CH2:14][O:13][CH2:12][CH2:11][O:10][CH2:9][CH2:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])cc1.[NH:19]1[C:20](=[O:21])[c:22]2[cH:23][cH:24][cH:25][cH:26][c:27]2[C:28]1=[O:29]>CN(C)C=O.O.[K]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[CH2:8][CH2:9][O:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][N:19]1[C:20](=[O:21])[c:22]2[cH:23][cH:24][cH:25][cH:26][c:27]2[C:28]1=[O:29]\"}",
"reactionStep": {
"id": "sa_a60eeed4373534f20b28fecd",
"reactionHash": "ef471b04a0ba8ab0e62f55ad2588cb45091138aef9768ea130253ddc1f00eee2"
},
"children": [
{
"id": "5538",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_a5041422c4a53ad707c3b7c9",
"parentId": "5537",
"isLeaf": false,
"molecule": {
"id": "sa_a5041422c4a53ad707c3b7c9",
"inchikey": "AAQWIVKRAHBPDM-UHFFFAOYSA-N",
"smiles": "Cc1ccc(S(=O)(=O)OCCOCCOCCOCCC(=O)OC(C)(C)C)cc1"
},
"smiles": "Cc1ccc(S(=O)(=O)OCCOCCOCCOCCC(=O)OC(C)(C)C)cc1",
"reactionStepId": "sa_6f566bc0d30963b4f3888bce",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150190389A1;0698;1718308\",\"rsmi\":\"Cl[S:6]([c:5]1[cH:4][cH:3][c:2]([CH3:1])[cH:29][cH:28]1)(=[O:7])=[O:8].[OH:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][O:15][CH2:16][CH2:17][O:18][CH2:19][CH2:20][C:21](=[O:22])[O:23][C:24]([CH3:25])([CH3:26])[CH3:27]>c1ccncc1>[CH3:1][c:2]1[cH:3][cH:4][c:5]([S:6](=[O:7])(=[O:8])[O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][O:15][CH2:16][CH2:17][O:18][CH2:19][CH2:20][C:21](=[O:22])[O:23][C:24]([CH3:25])([CH3:26])[CH3:27])[cH:28][cH:29]1\"},\"mapped_reaction_smiles\":\"Cl[S:6]([c:5]1[cH:4][cH:3][c:2]([CH3:1])[cH:29][cH:28]1)(=[O:7])=[O:8].[OH:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][O:15][CH2:16][CH2:17][O:18][CH2:19][CH2:20][C:21](=[O:22])[O:23][C:24]([CH3:25])([CH3:26])[CH3:27]>c1ccncc1>[CH3:1][c:2]1[cH:3][cH:4][c:5]([S:6](=[O:7])(=[O:8])[O:9][CH2:10][CH2:11][O:12][CH2:13][CH2:14][O:15][CH2:16][CH2:17][O:18][CH2:19][CH2:20][C:21](=[O:22])[O:23][C:24]([CH3:25])([CH3:26])[CH3:27])[cH:28][cH:29]1\"}",
"reactionStep": {
"id": "sa_6f566bc0d30963b4f3888bce",
"reactionHash": "ea1d5c23ea29120a15c8da24f7a3385d09723a11e2b0099b3027e802d3c1a4d9"
},
"children": [
{
"id": "5539",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_b42449044b86bc2b4d0ebd37",
"parentId": "5538",
"isLeaf": false,
"molecule": {
"id": "sa_b42449044b86bc2b4d0ebd37",
"inchikey": "KSXVEOLRERRELV-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)CCOCCOCCOCCO"
},
"smiles": "CC(C)(C)OC(=O)CCOCCOCCOCCO",
"reactionStepId": "sa_651fcc1f9f755ba7dbd6d93f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150190389A1;0697;1718307\",\"rsmi\":\"[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[CH:8]=[CH2:9].[OH:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][OH:19]>C1CCOC1.Cl.[Na].[Na]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[CH2:8][CH2:9][O:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][OH:19]\"},\"mapped_reaction_smiles\":\"[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[CH:8]=[CH2:9].[OH:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][OH:19]>C1CCOC1.Cl.[Na].[Na]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[CH2:8][CH2:9][O:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][OH:19]\"}",
"reactionStep": {
"id": "sa_651fcc1f9f755ba7dbd6d93f",
"reactionHash": "7409e70b5b5558a7802506e62d8840cf60c3c6b1d6d2f5a5f06194d9e8e6a8f8"
},
"children": [
{
"id": "5540",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_43021b3c4d107e3a8c19ba64",
"parentId": "5539",
"isLeaf": true,
"molecule": {
"id": "sa_43021b3c4d107e3a8c19ba64",
"inchikey": "ISXSCDLOGDJUNJ-UHFFFAOYSA-N",
"smiles": "C=CC(=O)OC(C)(C)C"
},
"smiles": "C=CC(=O)OC(C)(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "5541",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_dc25bb8527467cc0eac59290",
"parentId": "5539",
"isLeaf": true,
"molecule": {
"id": "sa_dc25bb8527467cc0eac59290",
"inchikey": "ZIBGPFATKBEMQZ-UHFFFAOYSA-N",
"smiles": "OCCOCCOCCO"
},
"smiles": "OCCOCCOCCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "5542",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_28189ad2d33238c7f987ecf5",
"parentId": "5538",
"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": "5543",
"routeId": "sa_e1e322947dfb34ec6ecef800",
"moleculeId": "sa_55c000779ce0b3d5072b008b",
"parentId": "5537",
"isLeaf": true,
"molecule": {
"id": "sa_55c000779ce0b3d5072b008b",
"inchikey": "XKJCHHZQLQNZHY-UHFFFAOYSA-N",
"smiles": "O=C1N=C(O)c2ccccc21"
},
"smiles": "O=C1NC(=O)c2ccccc21",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}