Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CNC(=O)NC(=O)C(CC1CCC(OC2CCCCO2)C1)c1ccc(Cl)c(Cl)c1
InChiKey
OXOLRFNZBOZMPZ-UHFFFAOYSA-N
Route Signature
e1c5eaadbb42fa655e048380f4eaef6ed833c9ff74f96187293b757332abe055
Synthesis route with 3 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_744c9e4ec02ae3e512b99ac7",
"signature": "e1c5eaadbb42fa655e048380f4eaef6ed833c9ff74f96187293b757332abe055",
"contentHash": "20504b7b89f058bea63fda20f4af35d84583ff02304c71fc6837976b08e76f01",
"length": 3,
"isConvergent": true
},
"target": {
"id": "sa_d3afa4cbda723757876fa994",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-04077",
"moleculeId": "sa_55c304570586e877505b2913",
"smiles": "CNC(=O)NC(=O)C(CC1CCC(OC2CCCCO2)C1)c1ccc(Cl)c(Cl)c1",
"routeLength": 3,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_55c304570586e877505b2913",
"inchikey": "OXOLRFNZBOZMPZ-UHFFFAOYSA-N",
"smiles": "CNC(=O)NC(=O)C(CC1CCC(OC2CCCCO2)C1)c1ccc(Cl)c(Cl)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "11151",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_55c304570586e877505b2913",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_55c304570586e877505b2913",
"inchikey": "OXOLRFNZBOZMPZ-UHFFFAOYSA-N",
"smiles": "CNC(=O)NC(=O)C(CC1CCC(OC2CCCCO2)C1)c1ccc(Cl)c(Cl)c1"
},
"smiles": "CNC(=O)NC(=O)C(CC1CCC(OC2CCCCO2)C1)c1ccc(Cl)c(Cl)c1",
"reactionStepId": "sa_6a0672ee40aa2e7b84622381",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07259166B2;0272;801771\",\"rsmi\":\"CO[C:6](=[O:7])[CH:8]([CH2:9][CH:10]1[CH2:11][CH2:12][CH:13]([O:14][CH:15]2[CH2:16][CH2:17][CH2:18][CH2:19][O:20]2)[CH2:21]1)[c:22]1[cH:23][c:24]([Cl:25])[c:26]([Cl:27])[cH:28][cH:29]1.[CH3:1][NH:2][C:3](=[O:4])[NH2:5]>CO.CO.CO.[Mg+2]>[CH3:1][NH:2][C:3](=[O:4])[NH:5][C:6](=[O:7])[CH:8]([CH2:9][CH:10]1[CH2:11][CH2:12][CH:13]([O:14][CH:15]2[CH2:16][CH2:17][CH2:18][CH2:19][O:20]2)[CH2:21]1)[c:22]1[cH:23][c:24]([Cl:25])[c:26]([Cl:27])[cH:28][cH:29]1\"},\"mapped_reaction_smiles\":\"CO[C:6](=[O:7])[CH:8]([CH2:9][CH:10]1[CH2:11][CH2:12][CH:13]([O:14][CH:15]2[CH2:16][CH2:17][CH2:18][CH2:19][O:20]2)[CH2:21]1)[c:22]1[cH:23][c:24]([Cl:25])[c:26]([Cl:27])[cH:28][cH:29]1.[CH3:1][NH:2][C:3](=[O:4])[NH2:5]>CO.CO.CO.[Mg+2]>[CH3:1][NH:2][C:3](=[O:4])[NH:5][C:6](=[O:7])[CH:8]([CH2:9][CH:10]1[CH2:11][CH2:12][CH:13]([O:14][CH:15]2[CH2:16][CH2:17][CH2:18][CH2:19][O:20]2)[CH2:21]1)[c:22]1[cH:23][c:24]([Cl:25])[c:26]([Cl:27])[cH:28][cH:29]1\"}",
"reactionStep": {
"id": "sa_6a0672ee40aa2e7b84622381",
"reactionHash": "d75778483f690403c64526f47beb9f8da0cbf936f4847b5ea25eec03f66e24dd"
},
"children": [
{
"id": "11152",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_58ea5f398604748bcb57f3ae",
"parentId": "11151",
"isLeaf": false,
"molecule": {
"id": "sa_58ea5f398604748bcb57f3ae",
"inchikey": "KYEDKMOOLHVUSO-UHFFFAOYSA-N",
"smiles": "COC(=O)C(CC1CCC(OC2CCCCO2)C1)c1ccc(Cl)c(Cl)c1"
},
"smiles": "COC(=O)C(CC1CCC(OC2CCCCO2)C1)c1ccc(Cl)c(Cl)c1",
"reactionStepId": "sa_346f658ee42770cc8f49f049",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07259166B2;0271;801770\",\"rsmi\":\"I[CH2:6][CH:7]1[CH2:8][CH2:9][CH:10]([O:11][CH:12]2[CH2:13][CH2:14][CH2:15][CH2:16][O:17]2)[CH2:18]1.[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:19]1[cH:20][c:21]([Cl:22])[c:23]([Cl:24])[cH:25][cH:26]1>C1CCOC1.CC(C)NC(C)C.CN1CCCN(C)C1=O.CN1CCCN(C)C1=O.[Li+]>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH2:6][CH:7]1[CH2:8][CH2:9][CH:10]([O:11][CH:12]2[CH2:13][CH2:14][CH2:15][CH2:16][O:17]2)[CH2:18]1)[c:19]1[cH:20][c:21]([Cl:22])[c:23]([Cl:24])[cH:25][cH:26]1\"},\"mapped_reaction_smiles\":\"I[CH2:6][CH:7]1[CH2:8][CH2:9][CH:10]([O:11][CH:12]2[CH2:13][CH2:14][CH2:15][CH2:16][O:17]2)[CH2:18]1.[CH3:1][O:2][C:3](=[O:4])[CH2:5][c:19]1[cH:20][c:21]([Cl:22])[c:23]([Cl:24])[cH:25][cH:26]1>C1CCOC1.CC(C)NC(C)C.CN1CCCN(C)C1=O.CN1CCCN(C)C1=O.[Li+]>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH2:6][CH:7]1[CH2:8][CH2:9][CH:10]([O:11][CH:12]2[CH2:13][CH2:14][CH2:15][CH2:16][O:17]2)[CH2:18]1)[c:19]1[cH:20][c:21]([Cl:22])[c:23]([Cl:24])[cH:25][cH:26]1\"}",
"reactionStep": {
"id": "sa_346f658ee42770cc8f49f049",
"reactionHash": "220d2b0f8b289191d5d4b3a16dfeca4e00a34a7d38a627d33947ea0ca7da5ff9"
},
"children": [
{
"id": "11153",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_3df77923c49375f32f9c9d5c",
"parentId": "11152",
"isLeaf": false,
"molecule": {
"id": "sa_3df77923c49375f32f9c9d5c",
"inchikey": "FWVOAIHAIWHHDM-UHFFFAOYSA-N",
"smiles": "COC(=O)Cc1ccc(Cl)c(Cl)c1"
},
"smiles": "COC(=O)Cc1ccc(Cl)c(Cl)c1",
"reactionStepId": "sa_1c8382db0f5c5ccaf96fca9b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07259166B2;0130;801696\",\"rsmi\":\"O[C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([Cl:9])[c:10]([Cl:11])[cH:12][cH:13]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]([Cl:9])[c:10]([Cl:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"O[C:3](=[O:4])[CH2:5][c:6]1[cH:7][c:8]([Cl:9])[c:10]([Cl:11])[cH:12][cH:13]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]([Cl:9])[c:10]([Cl:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_1c8382db0f5c5ccaf96fca9b",
"reactionHash": "f80ab9e18136db61c3acda47dc71a5c42bcee6418081998d2d27d022eca1ab13"
},
"children": [
{
"id": "11154",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "11153",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11155",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_5ea7c6f1e3d886ea965b7fcd",
"parentId": "11153",
"isLeaf": true,
"molecule": {
"id": "sa_5ea7c6f1e3d886ea965b7fcd",
"inchikey": "ZOUPGSMSNQLUNW-UHFFFAOYSA-N",
"smiles": "O=C(O)Cc1ccc(Cl)c(Cl)c1"
},
"smiles": "O=C(O)Cc1ccc(Cl)c(Cl)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "11156",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_3f29547ae2860e3e03fa31ee",
"parentId": "11152",
"isLeaf": false,
"molecule": {
"id": "sa_3f29547ae2860e3e03fa31ee",
"inchikey": "YTDPWKQTHALLDD-UHFFFAOYSA-N",
"smiles": "ICC1CCC(OC2CCCCO2)C1"
},
"smiles": "ICC1CCC(OC2CCCCO2)C1",
"reactionStepId": "sa_76499e37e7beb7a9adc11f4c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07259166B2;0270;801769\",\"rsmi\":\"[CH:8]1=[CH:9][CH2:10][CH2:11][CH2:12][O:13]1.[I:1][CH2:2][CH:3]1[CH2:4][CH2:5][CH:6]([OH:7])[CH2:14]1>Cc1ccc(S(=O)(=O)O)cc1.ClCCl.c1ccncc1>[I:1][CH2:2][CH:3]1[CH2:4][CH2:5][CH:6]([O:7][CH:8]2[CH2:9][CH2:10][CH2:11][CH2:12][O:13]2)[CH2:14]1\"},\"mapped_reaction_smiles\":\"[CH:8]1=[CH:9][CH2:10][CH2:11][CH2:12][O:13]1.[I:1][CH2:2][CH:3]1[CH2:4][CH2:5][CH:6]([OH:7])[CH2:14]1>Cc1ccc(S(=O)(=O)O)cc1.ClCCl.c1ccncc1>[I:1][CH2:2][CH:3]1[CH2:4][CH2:5][CH:6]([O:7][CH:8]2[CH2:9][CH2:10][CH2:11][CH2:12][O:13]2)[CH2:14]1\"}",
"reactionStep": {
"id": "sa_76499e37e7beb7a9adc11f4c",
"reactionHash": "233a3f6d593cdb6f28bdd02be784181d35ae9f79389ac9ed12541ed5abf4583b"
},
"children": [
{
"id": "11157",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_359472b115a712c065ff6c19",
"parentId": "11156",
"isLeaf": true,
"molecule": {
"id": "sa_359472b115a712c065ff6c19",
"inchikey": "BUDQDWGNQVEFAC-UHFFFAOYSA-N",
"smiles": "C1=COCCC1"
},
"smiles": "C1=COCCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11158",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_77d253adb47f1c7b96d2fdd8",
"parentId": "11156",
"isLeaf": true,
"molecule": {
"id": "sa_77d253adb47f1c7b96d2fdd8",
"inchikey": "SBXXQUQEMOCRDI-UHFFFAOYSA-N",
"smiles": "OC1CCC(CI)C1"
},
"smiles": "OC1CCC(CI)C1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "11159",
"routeId": "sa_744c9e4ec02ae3e512b99ac7",
"moleculeId": "sa_10acb59bb2074e56d539dd33",
"parentId": "11151",
"isLeaf": true,
"molecule": {
"id": "sa_10acb59bb2074e56d539dd33",
"inchikey": "XGEGHDBEHXKFPX-UHFFFAOYSA-N",
"smiles": "CNC(=N)O"
},
"smiles": "CNC(N)=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}