Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
C=Cn1cc(CNc2ccc(C(C)C)nc2)cn1
InChiKey
BSHKRQGQCBXVRK-UHFFFAOYSA-N
Route Signature
b6ddc7dc6f8e732311b38df73ae7576ead9246fd59898ec26e2556dd5dcfef7c
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_8a2d6ddba4429c5e38837b9e",
"signature": "b6ddc7dc6f8e732311b38df73ae7576ead9246fd59898ec26e2556dd5dcfef7c",
"contentHash": "a5199599df5c6cac2f20345f4c91a3191932ce7c6bdd46e8ed63f5899d4ad397",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_f5ef1dd3f4bd1f8f78d462db",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00306",
"moleculeId": "sa_34b9a4f1351bcce4cd28e2d3",
"smiles": "C=Cn1cc(CNc2ccc(C(C)C)nc2)cn1",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_34b9a4f1351bcce4cd28e2d3",
"inchikey": "BSHKRQGQCBXVRK-UHFFFAOYSA-N",
"smiles": "C=Cn1cc(CNc2ccc(C(C)C)nc2)cn1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9374",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_34b9a4f1351bcce4cd28e2d3",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_34b9a4f1351bcce4cd28e2d3",
"inchikey": "BSHKRQGQCBXVRK-UHFFFAOYSA-N",
"smiles": "C=Cn1cc(CNc2ccc(C(C)C)nc2)cn1"
},
"smiles": "C=Cn1cc(CNc2ccc(C(C)C)nc2)cn1",
"reactionStepId": "sa_8976ee7f84fe5edcf428960e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194640A1;0207;600639\",\"rsmi\":\"O=[CH:6][c:5]1[cH:4][n:3]([CH:2]=[CH2:1])[n:18][cH:17]1.[NH2:7][c:8]1[cH:9][cH:10][c:11]([CH:12]([CH3:13])[CH3:14])[n:15][cH:16]1>CC(=O)O.CC(=O)OB(OC(C)=O)OC(C)=O.ClCCCl.O=C(O)O.[Na+].[Na+]>[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([CH2:6][NH:7][c:8]2[cH:9][cH:10][c:11]([CH:12]([CH3:13])[CH3:14])[n:15][cH:16]2)[cH:17][n:18]1\"},\"mapped_reaction_smiles\":\"O=[CH:6][c:5]1[cH:4][n:3]([CH:2]=[CH2:1])[n:18][cH:17]1.[NH2:7][c:8]1[cH:9][cH:10][c:11]([CH:12]([CH3:13])[CH3:14])[n:15][cH:16]1>CC(=O)O.CC(=O)OB(OC(C)=O)OC(C)=O.ClCCCl.O=C(O)O.[Na+].[Na+]>[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([CH2:6][NH:7][c:8]2[cH:9][cH:10][c:11]([CH:12]([CH3:13])[CH3:14])[n:15][cH:16]2)[cH:17][n:18]1\"}",
"reactionStep": {
"id": "sa_8976ee7f84fe5edcf428960e",
"reactionHash": "ce28c0781f1cb5a1d05a23d17072339830938c2b5280d33eee1ccd8ce23fa819"
},
"children": [
{
"id": "9375",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_8896d6dc2f339a1a3f6c27d1",
"parentId": "9374",
"isLeaf": false,
"molecule": {
"id": "sa_8896d6dc2f339a1a3f6c27d1",
"inchikey": "PRSLZFDVLMBABM-UHFFFAOYSA-N",
"smiles": "C=Cn1cc(C=O)cn1"
},
"smiles": "C=Cn1cc(C=O)cn1",
"reactionStepId": "sa_8897cfd292883c5c8631ccdf",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194640A1;0184;600633\",\"rsmi\":\"[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([CH2:6][OH:7])[cH:8][n:9]1>ClCCl.O=S(=O)(O)O.[Mg+2].[Mn+4].[O-2].[O-2]>[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([CH:6]=[O:7])[cH:8][n:9]1\"},\"mapped_reaction_smiles\":\"[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([CH2:6][OH:7])[cH:8][n:9]1>ClCCl.O=S(=O)(O)O.[Mg+2].[Mn+4].[O-2].[O-2]>[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([CH:6]=[O:7])[cH:8][n:9]1\"}",
"reactionStep": {
"id": "sa_8897cfd292883c5c8631ccdf",
"reactionHash": "be2a51b1934ed1103f543e8bebe4df4296312032a8a35e1fc9a04d5e5eadf6a4"
},
"children": [
{
"id": "9376",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_7432efa2af62cf9f74b7f9c7",
"parentId": "9375",
"isLeaf": false,
"molecule": {
"id": "sa_7432efa2af62cf9f74b7f9c7",
"inchikey": "NNLHOACGXCWDKA-UHFFFAOYSA-N",
"smiles": "C=Cn1cc(CO)cn1"
},
"smiles": "C=Cn1cc(CO)cn1",
"reactionStepId": "sa_7a34486bac74c2586516fce0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194640A1;0181;600632\",\"rsmi\":\"CCO[C:6]([c:5]1[cH:4][n:3]([CH:2]=[CH2:1])[n:9][cH:8]1)=[O:7]>CC(C)C[Al+]CC(C)C.CCOCC.CO.Cc1ccccc1.O.O.O.O.O=C(O)C(O)C(O)C(=O)O.[HH].[K+].[Na+]>[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([CH2:6][OH:7])[cH:8][n:9]1\"},\"mapped_reaction_smiles\":\"CCO[C:6]([c:5]1[cH:4][n:3]([CH:2]=[CH2:1])[n:9][cH:8]1)=[O:7]>CC(C)C[Al+]CC(C)C.CCOCC.CO.Cc1ccccc1.O.O.O.O.O=C(O)C(O)C(O)C(=O)O.[HH].[K+].[Na+]>[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([CH2:6][OH:7])[cH:8][n:9]1\"}",
"reactionStep": {
"id": "sa_7a34486bac74c2586516fce0",
"reactionHash": "40d217361faa4d0778eeadd5c3d34d14e3780275e557539988e77151b938c254"
},
"children": [
{
"id": "9377",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_4351d8a1aa9f59ecec84450b",
"parentId": "9376",
"isLeaf": false,
"molecule": {
"id": "sa_4351d8a1aa9f59ecec84450b",
"inchikey": "NYERVSDEKOEYRS-UHFFFAOYSA-N",
"smiles": "C=Cn1cc(C(=O)OCC)cn1"
},
"smiles": "C=Cn1cc(C(=O)OCC)cn1",
"reactionStepId": "sa_7f063590789669ce61c37338",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194640A1;0175;600630\",\"rsmi\":\"Cl[CH2:1][CH2:2][n:3]1[cH:4][c:5]([C:6](=[O:7])[O:8][CH2:9][CH3:10])[cH:11][n:12]1>C1CCC2=NCCCN2CC1.CS(C)=O.O>[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([C:6](=[O:7])[O:8][CH2:9][CH3:10])[cH:11][n:12]1\"},\"mapped_reaction_smiles\":\"Cl[CH2:1][CH2:2][n:3]1[cH:4][c:5]([C:6](=[O:7])[O:8][CH2:9][CH3:10])[cH:11][n:12]1>C1CCC2=NCCCN2CC1.CS(C)=O.O>[CH2:1]=[CH:2][n:3]1[cH:4][c:5]([C:6](=[O:7])[O:8][CH2:9][CH3:10])[cH:11][n:12]1\"}",
"reactionStep": {
"id": "sa_7f063590789669ce61c37338",
"reactionHash": "18b0ae503468e28818edee90efcb342bf19a3264d6eefa360bd7fbdfc64ffd67"
},
"children": [
{
"id": "9378",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_94e3a137480bf13b7f4a622c",
"parentId": "9377",
"isLeaf": true,
"molecule": {
"id": "sa_94e3a137480bf13b7f4a622c",
"inchikey": "CQEZIEMQWNYOSD-UHFFFAOYSA-N",
"smiles": "CCOC(=O)c1cnn(CCCl)c1"
},
"smiles": "CCOC(=O)c1cnn(CCCl)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "9379",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_ca950308503ccbf500e1c40c",
"parentId": "9374",
"isLeaf": false,
"molecule": {
"id": "sa_ca950308503ccbf500e1c40c",
"inchikey": "XYGFISRAXLLACA-UHFFFAOYSA-N",
"smiles": "CC(C)c1ccc(N)cn1"
},
"smiles": "CC(C)c1ccc(N)cn1",
"reactionStepId": "sa_973be10b6602f6cf2c2846fd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194640A1;0278;600651\",\"rsmi\":\"CC(C)(C)OC(=O)[NH:8][c:7]1[cH:6][cH:5][c:4]([CH:2]([CH3:1])[CH3:3])[n:10][cH:9]1>C1COCCO1.CCOCC.Cl>[CH3:1][CH:2]([CH3:3])[c:4]1[cH:5][cH:6][c:7]([NH2:8])[cH:9][n:10]1\"},\"mapped_reaction_smiles\":\"CC(C)(C)OC(=O)[NH:8][c:7]1[cH:6][cH:5][c:4]([CH:2]([CH3:1])[CH3:3])[n:10][cH:9]1>C1COCCO1.CCOCC.Cl>[CH3:1][CH:2]([CH3:3])[c:4]1[cH:5][cH:6][c:7]([NH2:8])[cH:9][n:10]1\"}",
"reactionStep": {
"id": "sa_973be10b6602f6cf2c2846fd",
"reactionHash": "756eab270fe5ccd6996a1001f9fb18ad7f1a68b9110509fab9b236763b8e273d"
},
"children": [
{
"id": "9380",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_f701da8c264a64fd15767275",
"parentId": "9379",
"isLeaf": false,
"molecule": {
"id": "sa_f701da8c264a64fd15767275",
"inchikey": "GPMORISKRMLPFN-UHFFFAOYSA-N",
"smiles": "CC(C)c1ccc(NC(=O)OC(C)(C)C)cn1"
},
"smiles": "CC(C)c1ccc(NC(=O)OC(C)(C)C)cn1",
"reactionStepId": "sa_bfb3802b37b33b43fc7c9280",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194640A1;0276;600650\",\"rsmi\":\"O[C:9]([c:7]1[cH:6][cH:5][c:4]([CH:2]([CH3:1])[CH3:3])[n:17][cH:16]1)=[O:10].[N-]=[N+]=[N:8]P(=O)(c1ccccc1)c1ccccc1.[OH:11][C:12]([CH3:13])([CH3:14])[CH3:15]>CCN(CC)CC>[CH3:1][CH:2]([CH3:3])[c:4]1[cH:5][cH:6][c:7]([NH:8][C:9](=[O:10])[O:11][C:12]([CH3:13])([CH3:14])[CH3:15])[cH:16][n:17]1\"},\"mapped_reaction_smiles\":\"O[C:9]([c:7]1[cH:6][cH:5][c:4]([CH:2]([CH3:1])[CH3:3])[n:17][cH:16]1)=[O:10].[N-]=[N+]=[N:8]P(=O)(c1ccccc1)c1ccccc1.[OH:11][C:12]([CH3:13])([CH3:14])[CH3:15]>CCN(CC)CC>[CH3:1][CH:2]([CH3:3])[c:4]1[cH:5][cH:6][c:7]([NH:8][C:9](=[O:10])[O:11][C:12]([CH3:13])([CH3:14])[CH3:15])[cH:16][n:17]1\"}",
"reactionStep": {
"id": "sa_bfb3802b37b33b43fc7c9280",
"reactionHash": "24bd37197ea2b29cdb335139fa6e828624ae5c71ed42745254cb6a4b63cc9524"
},
"children": [
{
"id": "9381",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_339f109b29d21e95632a74f6",
"parentId": "9380",
"isLeaf": true,
"molecule": {
"id": "sa_339f109b29d21e95632a74f6",
"inchikey": "DKGAVHZHDRPRBM-UHFFFAOYSA-N",
"smiles": "CC(C)(C)O"
},
"smiles": "CC(C)(C)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9382",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_b2e7e70131d8726a166b6104",
"parentId": "9380",
"isLeaf": true,
"molecule": {
"id": "sa_b2e7e70131d8726a166b6104",
"inchikey": "MKRTXPORKIRPDG-UHFFFAOYSA-N",
"smiles": "[N-]=[N+]=NP(=O)(c1ccccc1)c1ccccc1"
},
"smiles": "[N-]=[N+]=NP(=O)(c1ccccc1)c1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9383",
"routeId": "sa_8a2d6ddba4429c5e38837b9e",
"moleculeId": "sa_d5daa68242a789c42b7be71a",
"parentId": "9380",
"isLeaf": true,
"molecule": {
"id": "sa_d5daa68242a789c42b7be71a",
"inchikey": "XVWRBXILGFEMKA-UHFFFAOYSA-N",
"smiles": "CC(C)c1ccc(C(=O)O)cn1"
},
"smiles": "CC(C)c1ccc(C(=O)O)cn1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}