Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1ccc([C@@H](CO)Nc2ncnc3c2CN(c2ccc(C)cn2)CC3)cn1
InChiKey
COHPLRFPNJNJIX-GOSISDBHSA-N
Route Signature
431bb7984320becd9896daf91ebd822e09c3932b7e898bba89370efd8c386cc3
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_0432446dcc410dd5b54b1e1e",
"signature": "431bb7984320becd9896daf91ebd822e09c3932b7e898bba89370efd8c386cc3",
"contentHash": "077428d9d5308906ce491e846ae9a32925aae38d2c065b99c7444686f0205a6c",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_3d9fa10dbd412008e2f0fd0a",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-03050",
"moleculeId": "sa_887a87a1eac7bff97c516ddc",
"smiles": "COc1ccc([C@@H](CO)Nc2ncnc3c2CN(c2ccc(C)cn2)CC3)cn1",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_887a87a1eac7bff97c516ddc",
"inchikey": "COHPLRFPNJNJIX-GOSISDBHSA-N",
"smiles": "COc1ccc([C@@H](CO)Nc2ncnc3c2CN(c2ccc(C)cn2)CC3)cn1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "10967",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_887a87a1eac7bff97c516ddc",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_887a87a1eac7bff97c516ddc",
"inchikey": "COHPLRFPNJNJIX-GOSISDBHSA-N",
"smiles": "COc1ccc([C@@H](CO)Nc2ncnc3c2CN(c2ccc(C)cn2)CC3)cn1"
},
"smiles": "COc1ccc([C@@H](CO)Nc2ncnc3c2CN(c2ccc(C)cn2)CC3)cn1",
"reactionStepId": "sa_d79c0e5fbbe570896bb4a6d7",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110009432A1;0510;1000115\",\"rsmi\":\"Cl[c:11]1[n:12][cH:13][n:14][c:15]2[c:16]1[CH2:17][N:18]([c:19]1[n:20][cH:21][c:22]([CH3:23])[cH:24][cH:25]1)[CH2:26][CH2:27]2.[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]([CH2:8][OH:9])[NH2:10])[cH:28][n:29]1>CC#N.CCN(C(C)C)C(C)C>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]([CH2:8][OH:9])[NH:10][c:11]2[n:12][cH:13][n:14][c:15]3[c:16]2[CH2:17][N:18]([c:19]2[n:20][cH:21][c:22]([CH3:23])[cH:24][cH:25]2)[CH2:26][CH2:27]3)[cH:28][n:29]1\"},\"mapped_reaction_smiles\":\"Cl[c:11]1[n:12][cH:13][n:14][c:15]2[c:16]1[CH2:17][N:18]([c:19]1[n:20][cH:21][c:22]([CH3:23])[cH:24][cH:25]1)[CH2:26][CH2:27]2.[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]([CH2:8][OH:9])[NH2:10])[cH:28][n:29]1>CC#N.CCN(C(C)C)C(C)C>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]([CH2:8][OH:9])[NH:10][c:11]2[n:12][cH:13][n:14][c:15]3[c:16]2[CH2:17][N:18]([c:19]2[n:20][cH:21][c:22]([CH3:23])[cH:24][cH:25]2)[CH2:26][CH2:27]3)[cH:28][n:29]1\"}",
"reactionStep": {
"id": "sa_d79c0e5fbbe570896bb4a6d7",
"reactionHash": "b3b53c7134ed80733e0840f1d9cc1e8ebd1db71295494206735e9e627dcf628b"
},
"children": [
{
"id": "10968",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_e514580c73bcc752ddf19340",
"parentId": "10967",
"isLeaf": false,
"molecule": {
"id": "sa_e514580c73bcc752ddf19340",
"inchikey": "LRJANZYRGCLJOT-UHFFFAOYSA-N",
"smiles": "Cc1ccc(N2CCc3ncnc(Cl)c3C2)nc1"
},
"smiles": "Cc1ccc(N2CCc3ncnc(Cl)c3C2)nc1",
"reactionStepId": "sa_6bb98ae43fd4ce97fd28b800",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110009432A1;0369;1000074\",\"rsmi\":\"O=P(Cl)(Cl)[Cl:13].O=[c:12]1[c:10]2[c:9]([n:16][cH:15][nH:14]1)[CH2:8][CH2:7][N:6]([c:5]1[n:4][cH:3][c:2]([CH3:1])[cH:18][cH:17]1)[CH2:11]2>CN(C)c1ccccc1.ClCCCl.ClCCl.O=C(O)O.[Na+]>[CH3:1][c:2]1[cH:3][n:4][c:5]([N:6]2[CH2:7][CH2:8][c:9]3[c:10]([c:12]([Cl:13])[n:14][cH:15][n:16]3)[CH2:11]2)[cH:17][cH:18]1\"},\"mapped_reaction_smiles\":\"O=P(Cl)(Cl)[Cl:13].O=[c:12]1[c:10]2[c:9]([n:16][cH:15][nH:14]1)[CH2:8][CH2:7][N:6]([c:5]1[n:4][cH:3][c:2]([CH3:1])[cH:18][cH:17]1)[CH2:11]2>CN(C)c1ccccc1.ClCCCl.ClCCl.O=C(O)O.[Na+]>[CH3:1][c:2]1[cH:3][n:4][c:5]([N:6]2[CH2:7][CH2:8][c:9]3[c:10]([c:12]([Cl:13])[n:14][cH:15][n:16]3)[CH2:11]2)[cH:17][cH:18]1\"}",
"reactionStep": {
"id": "sa_6bb98ae43fd4ce97fd28b800",
"reactionHash": "61899de63b3651438fa4a2516895508cb05122086370e4d1632174c06cd3e921"
},
"children": [
{
"id": "10969",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_193460a0b0beeb07d4abcb3a",
"parentId": "10968",
"isLeaf": false,
"molecule": {
"id": "sa_193460a0b0beeb07d4abcb3a",
"inchikey": "VWSPMHNPEFIUMD-UHFFFAOYSA-N",
"smiles": "Cc1ccc(N2CCc3nc[nH]c(=O)c3C2)nc1"
},
"smiles": "Cc1ccc(N2CCc3nc[nH]c(=O)c3C2)nc1",
"reactionStepId": "sa_d33075c5beafec5e8c2bed29",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110009432A1;0366;1000073\",\"rsmi\":\"Cl[c:5]1[n:4][cH:3][c:2]([CH3:1])[cH:18][cH:17]1.[NH:6]1[CH2:7][CH2:8][c:9]2[c:10]([c:12](=[O:13])[nH:14][cH:15][n:16]2)[CH2:11]1>C1COCCO1.CC(=O)N(C)C.CC(C)O.CCN(C(C)C)C(C)C.ClC(Cl)Cl>[CH3:1][c:2]1[cH:3][n:4][c:5]([N:6]2[CH2:7][CH2:8][c:9]3[c:10]([c:12](=[O:13])[nH:14][cH:15][n:16]3)[CH2:11]2)[cH:17][cH:18]1\"},\"mapped_reaction_smiles\":\"Cl[c:5]1[n:4][cH:3][c:2]([CH3:1])[cH:18][cH:17]1.[NH:6]1[CH2:7][CH2:8][c:9]2[c:10]([c:12](=[O:13])[nH:14][cH:15][n:16]2)[CH2:11]1>C1COCCO1.CC(=O)N(C)C.CC(C)O.CCN(C(C)C)C(C)C.ClC(Cl)Cl>[CH3:1][c:2]1[cH:3][n:4][c:5]([N:6]2[CH2:7][CH2:8][c:9]3[c:10]([c:12](=[O:13])[nH:14][cH:15][n:16]3)[CH2:11]2)[cH:17][cH:18]1\"}",
"reactionStep": {
"id": "sa_d33075c5beafec5e8c2bed29",
"reactionHash": "c0d13fac4c436e0a51ffe62173066a09dc0a523c8638550043e213107276ef3a"
},
"children": [
{
"id": "10970",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_926f855f954a75bef5dbb4b8",
"parentId": "10969",
"isLeaf": true,
"molecule": {
"id": "sa_926f855f954a75bef5dbb4b8",
"inchikey": "VXLYOURCUVQYLN-UHFFFAOYSA-N",
"smiles": "Cc1ccc(Cl)nc1"
},
"smiles": "Cc1ccc(Cl)nc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10971",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_d50425509c32343367b2043b",
"parentId": "10969",
"isLeaf": false,
"molecule": {
"id": "sa_d50425509c32343367b2043b",
"inchikey": "XYYZKOFIMYHHAG-UHFFFAOYSA-N",
"smiles": "O=c1[nH]cnc2c1CNCC2"
},
"smiles": "O=c1[nH]cnc2c1CNCC2",
"reactionStepId": "sa_52d2d267c3cc00b370e35d9f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110009432A1;0364;1000072\",\"rsmi\":\"c1ccc(C[N:9]2[CH2:8][c:7]3[c:2](=[O:1])[nH:3][cH:4][n:5][c:6]3[CH2:11][CH2:10]2)cc1>CCN(CC)CC.CO.O=CO.O.O.[Pd+2]>[O:1]=[c:2]1[nH:3][cH:4][n:5][c:6]2[c:7]1[CH2:8][NH:9][CH2:10][CH2:11]2\"},\"mapped_reaction_smiles\":\"c1ccc(C[N:9]2[CH2:8][c:7]3[c:2](=[O:1])[nH:3][cH:4][n:5][c:6]3[CH2:11][CH2:10]2)cc1>CCN(CC)CC.CO.O=CO.O.O.[Pd+2]>[O:1]=[c:2]1[nH:3][cH:4][n:5][c:6]2[c:7]1[CH2:8][NH:9][CH2:10][CH2:11]2\"}",
"reactionStep": {
"id": "sa_52d2d267c3cc00b370e35d9f",
"reactionHash": "9ea9a151266498ed621cc2a18e1fce50cb5a556aafbe30ea96b35bf0da1e7335"
},
"children": [
{
"id": "10972",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_0f28da4734c1f9151a4172fc",
"parentId": "10971",
"isLeaf": true,
"molecule": {
"id": "sa_0f28da4734c1f9151a4172fc",
"inchikey": "PVNGDFHKRAIVTC-UHFFFAOYSA-N",
"smiles": "O=c1nc[nH]c2c1CN(Cc1ccccc1)CC2"
},
"smiles": "O=c1[nH]cnc2c1CN(Cc1ccccc1)CC2",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "10973",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_312a7cd3d48a055e9bc98180",
"parentId": "10968",
"isLeaf": true,
"molecule": {
"id": "sa_312a7cd3d48a055e9bc98180",
"inchikey": "XHXFXVLFKHQFAL-UHFFFAOYSA-N",
"smiles": "O=P(Cl)(Cl)Cl"
},
"smiles": "O=P(Cl)(Cl)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "10974",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_f3f8cd225c8d7de5e02b3ee2",
"parentId": "10967",
"isLeaf": false,
"molecule": {
"id": "sa_f3f8cd225c8d7de5e02b3ee2",
"inchikey": "SJUXJJWKCNDGED-SSDOTTSWSA-N",
"smiles": "COc1ccc([C@H](N)CO)cn1"
},
"smiles": "COc1ccc([C@H](N)CO)cn1",
"reactionStepId": "sa_1cf988f8384a135019f241b1",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110009432A1;0411;1000086\",\"rsmi\":\"[N-]=[N+]=[N:8][C@@H:7]([c:6]1[cH:5][cH:4][c:3]([O:2][CH3:1])[n:12][cH:11]1)[CH2:9][OH:10]>CCOC(C)=O.[Pd]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@H:7]([NH2:8])[CH2:9][OH:10])[cH:11][n:12]1\"},\"mapped_reaction_smiles\":\"[N-]=[N+]=[N:8][C@@H:7]([c:6]1[cH:5][cH:4][c:3]([O:2][CH3:1])[n:12][cH:11]1)[CH2:9][OH:10]>CCOC(C)=O.[Pd]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@H:7]([NH2:8])[CH2:9][OH:10])[cH:11][n:12]1\"}",
"reactionStep": {
"id": "sa_1cf988f8384a135019f241b1",
"reactionHash": "c2b9cf65fb9a061f834442df72e5cee3896db2c8f52f40f1c5cd3dc61887aacf"
},
"children": [
{
"id": "10975",
"routeId": "sa_0432446dcc410dd5b54b1e1e",
"moleculeId": "sa_c1c86c6e8f32b7ac6fe08941",
"parentId": "10974",
"isLeaf": true,
"molecule": {
"id": "sa_c1c86c6e8f32b7ac6fe08941",
"inchikey": "ATNIIJUAAJVSTB-SSDOTTSWSA-N",
"smiles": "COc1ccc([C@@H](CO)N=[N+]=[N-])cn1"
},
"smiles": "COc1ccc([C@@H](CO)N=[N+]=[N-])cn1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}