Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
Cc1c(C(Cl)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12
InChiKey
CECPEDZKKGRXFX-UHFFFAOYSA-N
Route Signature
2508b545561707e8c03cd781fbfd9c559feceb20738deda7249b1b13bc8175d5
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_30584e80d586beccbf12ee8e",
"signature": "2508b545561707e8c03cd781fbfd9c559feceb20738deda7249b1b13bc8175d5",
"contentHash": "b72d1edf83c0bf8026d9c6840f0d3c4924522ed0cd80b626a5e8d6ed941be3bf",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_aa286d7609f3cdf31f28ebc6",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00489",
"moleculeId": "sa_775f98e7fa05c1efced718d5",
"smiles": "Cc1c(C(Cl)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_775f98e7fa05c1efced718d5",
"inchikey": "CECPEDZKKGRXFX-UHFFFAOYSA-N",
"smiles": "Cc1c(C(Cl)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "757",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_775f98e7fa05c1efced718d5",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_775f98e7fa05c1efced718d5",
"inchikey": "CECPEDZKKGRXFX-UHFFFAOYSA-N",
"smiles": "Cc1c(C(Cl)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12"
},
"smiles": "Cc1c(C(Cl)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12",
"reactionStepId": "sa_8ff47db3375de2cddf70a2ad",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120270865A2;2530;1290983\",\"rsmi\":\"O=S(Cl)[Cl:5].O[CH:4]([c:3]1[c:2]([CH3:1])[c:14]2[c:13]([o:12]1)[cH:26][cH:25][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:15]2)[CH:6]1[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]1>C1CCOC1.O=C(O)O.[Na+]>[CH3:1][c:2]1[c:3]([CH:4]([Cl:5])[CH:6]2[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]2)[o:12][c:13]2[c:14]1[cH:15][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:25][cH:26]2\"},\"mapped_reaction_smiles\":\"O=S(Cl)[Cl:5].O[CH:4]([c:3]1[c:2]([CH3:1])[c:14]2[c:13]([o:12]1)[cH:26][cH:25][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:15]2)[CH:6]1[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]1>C1CCOC1.O=C(O)O.[Na+]>[CH3:1][c:2]1[c:3]([CH:4]([Cl:5])[CH:6]2[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]2)[o:12][c:13]2[c:14]1[cH:15][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:25][cH:26]2\"}",
"reactionStep": {
"id": "sa_8ff47db3375de2cddf70a2ad",
"reactionHash": "5ce480c07b8560b08a371af1dba7d1fa5c583cef2be706274a55b6b590fdc604"
},
"children": [
{
"id": "758",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_cd67ce42f230ef1a4063353c",
"parentId": "757",
"isLeaf": true,
"molecule": {
"id": "sa_cd67ce42f230ef1a4063353c",
"inchikey": "FYSNRJHAOHDILO-UHFFFAOYSA-N",
"smiles": "O=S(Cl)Cl"
},
"smiles": "O=S(Cl)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "759",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_114cefe75a035c973a7d93b9",
"parentId": "757",
"isLeaf": false,
"molecule": {
"id": "sa_114cefe75a035c973a7d93b9",
"inchikey": "XZWBDPFANNBOTA-UHFFFAOYSA-N",
"smiles": "Cc1c(C(O)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12"
},
"smiles": "Cc1c(C(O)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12",
"reactionStepId": "sa_b374e4eb1484c31974cad3ea",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120270865A2;2528;1290982\",\"rsmi\":\"[CH3:1][c:2]1[c:3]([C:4](=[O:5])[CH:6]2[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]2)[o:12][c:13]2[c:14]1[cH:15][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:25][cH:26]2>C1CCOC1.CO.O.B.[Na+]>[CH3:1][c:2]1[c:3]([CH:4]([OH:5])[CH:6]2[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]2)[o:12][c:13]2[c:14]1[cH:15][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:25][cH:26]2\"},\"mapped_reaction_smiles\":\"[CH3:1][c:2]1[c:3]([C:4](=[O:5])[CH:6]2[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]2)[o:12][c:13]2[c:14]1[cH:15][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:25][cH:26]2>C1CCOC1.CO.O.B.[Na+]>[CH3:1][c:2]1[c:3]([CH:4]([OH:5])[CH:6]2[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]2)[o:12][c:13]2[c:14]1[cH:15][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:25][cH:26]2\"}",
"reactionStep": {
"id": "sa_b374e4eb1484c31974cad3ea",
"reactionHash": "5e03943eabed1cad997692befaf05de32a5c3439c512807a2177ae7073fa05ed"
},
"children": [
{
"id": "760",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_94dff958b3093ce10d78ad69",
"parentId": "759",
"isLeaf": false,
"molecule": {
"id": "sa_94dff958b3093ce10d78ad69",
"inchikey": "BBDWMKITERISML-UHFFFAOYSA-N",
"smiles": "Cc1c(C(=O)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12"
},
"smiles": "Cc1c(C(=O)C2CCCCC2)oc2ccc(OCc3ccccc3)cc12",
"reactionStepId": "sa_c0891ac01ebbaa69f62542df",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120270865A2;1692;1290665\",\"rsmi\":\"Br[CH2:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]1.O=[C:2]([CH3:1])[c:14]1[c:13]([OH:12])[cH:26][cH:25][c:16]([O:17][CH2:18][c:19]2[cH:20][cH:21][cH:22][cH:23][cH:24]2)[cH:15]1>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][c:2]1[c:3]([C:4](=[O:5])[CH:6]2[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]2)[o:12][c:13]2[c:14]1[cH:15][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:25][cH:26]2\"},\"mapped_reaction_smiles\":\"Br[CH2:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]1.O=[C:2]([CH3:1])[c:14]1[c:13]([OH:12])[cH:26][cH:25][c:16]([O:17][CH2:18][c:19]2[cH:20][cH:21][cH:22][cH:23][cH:24]2)[cH:15]1>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][c:2]1[c:3]([C:4](=[O:5])[CH:6]2[CH2:7][CH2:8][CH2:9][CH2:10][CH2:11]2)[o:12][c:13]2[c:14]1[cH:15][c:16]([O:17][CH2:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1)[cH:25][cH:26]2\"}",
"reactionStep": {
"id": "sa_c0891ac01ebbaa69f62542df",
"reactionHash": "62f628578892e4397f7e5c18f039c7f86fd2d236cd7d63089fed122e6f769bc2"
},
"children": [
{
"id": "761",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_36d3bc1bc1d8948770c6a438",
"parentId": "760",
"isLeaf": false,
"molecule": {
"id": "sa_36d3bc1bc1d8948770c6a438",
"inchikey": "ADLIDZNESKOPIP-UHFFFAOYSA-N",
"smiles": "O=C(CBr)C1CCCCC1"
},
"smiles": "O=C(CBr)C1CCCCC1",
"reactionStepId": "sa_141f6ce40e86c77ee62b0acf",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120270865A2;1530;1290605\",\"rsmi\":\"Br[Br:4].[O:1]=[C:2]([CH3:3])[CH:5]1[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10]1>CO.O=S(O)O.[Na+].[Na+]>[O:1]=[C:2]([CH2:3][Br:4])[CH:5]1[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10]1\"},\"mapped_reaction_smiles\":\"Br[Br:4].[O:1]=[C:2]([CH3:3])[CH:5]1[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10]1>CO.O=S(O)O.[Na+].[Na+]>[O:1]=[C:2]([CH2:3][Br:4])[CH:5]1[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10]1\"}",
"reactionStep": {
"id": "sa_141f6ce40e86c77ee62b0acf",
"reactionHash": "3a61a2ca29a95b7eba1231c932f04c8a0d9dcf256b8799e765c4b814cb390625"
},
"children": [
{
"id": "762",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_24211e89e565c162ea935f73",
"parentId": "761",
"isLeaf": true,
"molecule": {
"id": "sa_24211e89e565c162ea935f73",
"inchikey": "GDTBXPJZTBHREO-UHFFFAOYSA-N",
"smiles": "BrBr"
},
"smiles": "BrBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "763",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_3589958c73ffa35d5004a258",
"parentId": "761",
"isLeaf": true,
"molecule": {
"id": "sa_3589958c73ffa35d5004a258",
"inchikey": "RIFKADJTWUGDOV-UHFFFAOYSA-N",
"smiles": "CC(=O)C1CCCCC1"
},
"smiles": "CC(=O)C1CCCCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "764",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_dc44b441cdcbf148ca77ab70",
"parentId": "760",
"isLeaf": false,
"molecule": {
"id": "sa_dc44b441cdcbf148ca77ab70",
"inchikey": "LAFHMZQSDSXTBN-UHFFFAOYSA-N",
"smiles": "CC(=O)c1cc(OCc2ccccc2)ccc1O"
},
"smiles": "CC(=O)c1cc(OCc2ccccc2)ccc1O",
"reactionStepId": "sa_679c6e89fa20d98201e6f42f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120270865A2;1690;1290664\",\"rsmi\":\"Br[CH2:11][c:12]1[cH:13][cH:14][cH:15][cH:16][cH:17]1.[CH3:1][C:2](=[O:3])[c:4]1[c:5]([OH:6])[cH:7][cH:8][c:9]([OH:10])[cH:18]1>CC#N.O=C(O)O.[K+].[K+]>[CH3:1][C:2](=[O:3])[c:4]1[c:5]([OH:6])[cH:7][cH:8][c:9]([O:10][CH2:11][c:12]2[cH:13][cH:14][cH:15][cH:16][cH:17]2)[cH:18]1\"},\"mapped_reaction_smiles\":\"Br[CH2:11][c:12]1[cH:13][cH:14][cH:15][cH:16][cH:17]1.[CH3:1][C:2](=[O:3])[c:4]1[c:5]([OH:6])[cH:7][cH:8][c:9]([OH:10])[cH:18]1>CC#N.O=C(O)O.[K+].[K+]>[CH3:1][C:2](=[O:3])[c:4]1[c:5]([OH:6])[cH:7][cH:8][c:9]([O:10][CH2:11][c:12]2[cH:13][cH:14][cH:15][cH:16][cH:17]2)[cH:18]1\"}",
"reactionStep": {
"id": "sa_679c6e89fa20d98201e6f42f",
"reactionHash": "d05bb62c1ea6a3c76c97544320577f5dfbee79319780c5aaadc0139f10098a00"
},
"children": [
{
"id": "765",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_4ff2e4de9d80150de333c065",
"parentId": "764",
"isLeaf": true,
"molecule": {
"id": "sa_4ff2e4de9d80150de333c065",
"inchikey": "AGEZXYOZHKGVCM-UHFFFAOYSA-N",
"smiles": "BrCc1ccccc1"
},
"smiles": "BrCc1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "766",
"routeId": "sa_30584e80d586beccbf12ee8e",
"moleculeId": "sa_f345583d1f16bbf1df081a97",
"parentId": "764",
"isLeaf": true,
"molecule": {
"id": "sa_f345583d1f16bbf1df081a97",
"inchikey": "WLDWSGZHNBANIO-UHFFFAOYSA-N",
"smiles": "CC(=O)c1cc(O)ccc1O"
},
"smiles": "CC(=O)c1cc(O)ccc1O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}