Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
NC1=NC2(c3cc(NC(=O)c4ccc(Cl)cn4)ccc3F)CC2COC1
InChiKey
HOPLUAKMYRGQPD-UHFFFAOYSA-N
Route Signature
a0e0b01ea6d713f28a0e08536bbf9c0c8750d2a3934e77346461639f8b674944
Synthesis route with 4 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_41ee8e342f75401539c60b58",
"signature": "a0e0b01ea6d713f28a0e08536bbf9c0c8750d2a3934e77346461639f8b674944",
"contentHash": "aca5f385acddfc80d979e7c223a454883ef5926af7c5e6842678e9967656a5fd",
"length": 4,
"isConvergent": false
},
"target": {
"id": "sa_f87dfa1233b0944655f71e8e",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-03732",
"moleculeId": "sa_3a829f2ca42a06a115fb0872",
"smiles": "NC1=NC2(c3cc(NC(=O)c4ccc(Cl)cn4)ccc3F)CC2COC1",
"routeLength": 4,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_3a829f2ca42a06a115fb0872",
"inchikey": "HOPLUAKMYRGQPD-UHFFFAOYSA-N",
"smiles": "NC1=NC2(c3cc(NC(=O)c4ccc(Cl)cn4)ccc3F)CC2COC1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "15230",
"routeId": "sa_41ee8e342f75401539c60b58",
"moleculeId": "sa_3a829f2ca42a06a115fb0872",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_3a829f2ca42a06a115fb0872",
"inchikey": "HOPLUAKMYRGQPD-UHFFFAOYSA-N",
"smiles": "NC1=NC2(c3cc(NC(=O)c4ccc(Cl)cn4)ccc3F)CC2COC1"
},
"smiles": "NC1=NC2(c3cc(NC(=O)c4ccc(Cl)cn4)ccc3F)CC2COC1",
"reactionStepId": "sa_b000d50b99f2391e4cd6910e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140045820A1;0847;1485408\",\"rsmi\":\"S=[C:2]1[NH:3][C:4]2([c:5]3[c:6]([F:7])[cH:8][cH:9][c:10]([NH:11][C:12](=[O:13])[c:14]4[n:15][cH:16][c:17]([Cl:18])[cH:19][cH:20]4)[cH:21]3)[CH2:22][CH:23]2[CH2:24][O:25][CH2:26]1.[NH3:1]>CC(C)(C)OO.CO>[NH2:1][C:2]1=[N:3][C:4]2([c:5]3[c:6]([F:7])[cH:8][cH:9][c:10]([NH:11][C:12](=[O:13])[c:14]4[n:15][cH:16][c:17]([Cl:18])[cH:19][cH:20]4)[cH:21]3)[CH2:22][CH:23]2[CH2:24][O:25][CH2:26]1\"},\"mapped_reaction_smiles\":\"S=[C:2]1[NH:3][C:4]2([c:5]3[c:6]([F:7])[cH:8][cH:9][c:10]([NH:11][C:12](=[O:13])[c:14]4[n:15][cH:16][c:17]([Cl:18])[cH:19][cH:20]4)[cH:21]3)[CH2:22][CH:23]2[CH2:24][O:25][CH2:26]1.[NH3:1]>CC(C)(C)OO.CO>[NH2:1][C:2]1=[N:3][C:4]2([c:5]3[c:6]([F:7])[cH:8][cH:9][c:10]([NH:11][C:12](=[O:13])[c:14]4[n:15][cH:16][c:17]([Cl:18])[cH:19][cH:20]4)[cH:21]3)[CH2:22][CH:23]2[CH2:24][O:25][CH2:26]1\"}",
"reactionStep": {
"id": "sa_b000d50b99f2391e4cd6910e",
"reactionHash": "c45b52f2fd7954894b7f50057611e6e3fbf3f1ea48f8a6e85fbc4a1820ce4894"
},
"children": [
{
"id": "15231",
"routeId": "sa_41ee8e342f75401539c60b58",
"moleculeId": "sa_c9679fdd876f32f86b77fb69",
"parentId": "15230",
"isLeaf": true,
"molecule": {
"id": "sa_c9679fdd876f32f86b77fb69",
"inchikey": "QGZKDVFQNNGYKY-UHFFFAOYSA-N",
"smiles": "N"
},
"smiles": "N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15232",
"routeId": "sa_41ee8e342f75401539c60b58",
"moleculeId": "sa_055667251bf6f3e3d3c55235",
"parentId": "15230",
"isLeaf": false,
"molecule": {
"id": "sa_055667251bf6f3e3d3c55235",
"inchikey": "RFJOUSQNSUXQNU-UHFFFAOYSA-N",
"smiles": "O=C(Nc1ccc(F)c(C23CC2COCC(=S)N3)c1)c1ccc(Cl)cn1"
},
"smiles": "O=C(Nc1ccc(F)c(C23CC2COCC(=S)N3)c1)c1ccc(Cl)cn1",
"reactionStepId": "sa_98a45a1f1925908dbfd75a7a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140045820A1;0794;1485392\",\"rsmi\":\"O[C:2](=[O:1])[c:20]1[n:21][cH:22][c:23]([Cl:24])[cH:25][cH:26]1.[NH2:3][c:4]1[cH:5][c:6]([C:7]23[CH2:8][CH:9]2[CH2:10][O:11][CH2:12][C:13](=[S:14])[NH:15]3)[c:16]([F:17])[cH:18][cH:19]1>CCN(C(C)C)C(C)C.CN(C)C(On1nnc2cccnc21)=[N+](C)C.ClCCl.F[PH](F)(F)(F)(F)F>[O:1]=[C:2]([NH:3][c:4]1[cH:5][c:6]([C:7]23[CH2:8][CH:9]2[CH2:10][O:11][CH2:12][C:13](=[S:14])[NH:15]3)[c:16]([F:17])[cH:18][cH:19]1)[c:20]1[n:21][cH:22][c:23]([Cl:24])[cH:25][cH:26]1\"},\"mapped_reaction_smiles\":\"O[C:2](=[O:1])[c:20]1[n:21][cH:22][c:23]([Cl:24])[cH:25][cH:26]1.[NH2:3][c:4]1[cH:5][c:6]([C:7]23[CH2:8][CH:9]2[CH2:10][O:11][CH2:12][C:13](=[S:14])[NH:15]3)[c:16]([F:17])[cH:18][cH:19]1>CCN(C(C)C)C(C)C.CN(C)C(On1nnc2cccnc21)=[N+](C)C.ClCCl.F[PH](F)(F)(F)(F)F>[O:1]=[C:2]([NH:3][c:4]1[cH:5][c:6]([C:7]23[CH2:8][CH:9]2[CH2:10][O:11][CH2:12][C:13](=[S:14])[NH:15]3)[c:16]([F:17])[cH:18][cH:19]1)[c:20]1[n:21][cH:22][c:23]([Cl:24])[cH:25][cH:26]1\"}",
"reactionStep": {
"id": "sa_98a45a1f1925908dbfd75a7a",
"reactionHash": "bbfbc6b1a85c02df02e037198852732e6670c8c61c5865a1292187ae5dc426ae"
},
"children": [
{
"id": "15233",
"routeId": "sa_41ee8e342f75401539c60b58",
"moleculeId": "sa_f68dcaa50d0bef9d8ccb5661",
"parentId": "15232",
"isLeaf": true,
"molecule": {
"id": "sa_f68dcaa50d0bef9d8ccb5661",
"inchikey": "GJLOKYIYZIOIPN-UHFFFAOYSA-N",
"smiles": "O=C(O)c1ccc(Cl)cn1"
},
"smiles": "O=C(O)c1ccc(Cl)cn1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15234",
"routeId": "sa_41ee8e342f75401539c60b58",
"moleculeId": "sa_6c947cffdf15c269087674b6",
"parentId": "15232",
"isLeaf": false,
"molecule": {
"id": "sa_6c947cffdf15c269087674b6",
"inchikey": "YLOYFABJONHLHC-UHFFFAOYSA-N",
"smiles": "Nc1ccc(F)c(C23CC2COCC(=S)N3)c1"
},
"smiles": "Nc1ccc(F)c(C23CC2COCC(=S)N3)c1",
"reactionStepId": "sa_7cd327ac1355fa6db9213488",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140045820A1;0790;1485391\",\"rsmi\":\"c1ccc(C(c2ccccc2)=[N:1][c:2]2[cH:3][c:4]([C:5]34[CH2:6][CH:7]3[CH2:8][O:9][CH2:10][C:11](=[S:12])[NH:13]4)[c:14]([F:15])[cH:16][cH:17]2)cc1>C1COCCO1.Cl.O=C(O)O.[Na+]>[NH2:1][c:2]1[cH:3][c:4]([C:5]23[CH2:6][CH:7]2[CH2:8][O:9][CH2:10][C:11](=[S:12])[NH:13]3)[c:14]([F:15])[cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"c1ccc(C(c2ccccc2)=[N:1][c:2]2[cH:3][c:4]([C:5]34[CH2:6][CH:7]3[CH2:8][O:9][CH2:10][C:11](=[S:12])[NH:13]4)[c:14]([F:15])[cH:16][cH:17]2)cc1>C1COCCO1.Cl.O=C(O)O.[Na+]>[NH2:1][c:2]1[cH:3][c:4]([C:5]23[CH2:6][CH:7]2[CH2:8][O:9][CH2:10][C:11](=[S:12])[NH:13]3)[c:14]([F:15])[cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_7cd327ac1355fa6db9213488",
"reactionHash": "b147312b2a4f4dab3e6389c479d3848730a9693f7d7efc9c0b3eb8dcc5f3ffe7"
},
"children": [
{
"id": "15235",
"routeId": "sa_41ee8e342f75401539c60b58",
"moleculeId": "sa_79bb0dca379fa73c7c9847da",
"parentId": "15234",
"isLeaf": false,
"molecule": {
"id": "sa_79bb0dca379fa73c7c9847da",
"inchikey": "HJVBLTGWFQUELV-UHFFFAOYSA-N",
"smiles": "Fc1ccc(N=C(c2ccccc2)c2ccccc2)cc1C12CC1COCC(=S)N2"
},
"smiles": "Fc1ccc(N=C(c2ccccc2)c2ccccc2)cc1C12CC1COCC(=S)N2",
"reactionStepId": "sa_992352045c5944b9b0c9ad03",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140045820A1;0786;1485390\",\"rsmi\":\"COc1ccc(P2(=S)SP(c3ccc(OC)cc3)(=[S:11])S2)cc1.O=[C:10]1[CH2:9][O:8][CH2:7][CH:6]2[C:4]([c:3]3[c:2]([F:1])[cH:30][cH:29][c:14]([N:15]=[C:16]([c:17]4[cH:18][cH:19][cH:20][cH:21][cH:22]4)[c:23]4[cH:24][cH:25][cH:26][cH:27][cH:28]4)[cH:13]3)([CH2:5]2)[NH:12]1>C1COCCO1.O=C(O)O.[Na+]>[F:1][c:2]1[c:3]([C:4]23[CH2:5][CH:6]2[CH2:7][O:8][CH2:9][C:10](=[S:11])[NH:12]3)[cH:13][c:14]([N:15]=[C:16]([c:17]2[cH:18][cH:19][cH:20][cH:21][cH:22]2)[c:23]2[cH:24][cH:25][cH:26][cH:27][cH:28]2)[cH:29][cH:30]1\"},\"mapped_reaction_smiles\":\"COc1ccc(P2(=S)SP(c3ccc(OC)cc3)(=[S:11])S2)cc1.O=[C:10]1[CH2:9][O:8][CH2:7][CH:6]2[C:4]([c:3]3[c:2]([F:1])[cH:30][cH:29][c:14]([N:15]=[C:16]([c:17]4[cH:18][cH:19][cH:20][cH:21][cH:22]4)[c:23]4[cH:24][cH:25][cH:26][cH:27][cH:28]4)[cH:13]3)([CH2:5]2)[NH:12]1>C1COCCO1.O=C(O)O.[Na+]>[F:1][c:2]1[c:3]([C:4]23[CH2:5][CH:6]2[CH2:7][O:8][CH2:9][C:10](=[S:11])[NH:12]3)[cH:13][c:14]([N:15]=[C:16]([c:17]2[cH:18][cH:19][cH:20][cH:21][cH:22]2)[c:23]2[cH:24][cH:25][cH:26][cH:27][cH:28]2)[cH:29][cH:30]1\"}",
"reactionStep": {
"id": "sa_992352045c5944b9b0c9ad03",
"reactionHash": "501f5d07c36cd880933e5d3d95b45cea64ff315825e28f79836d8b14c59b7707"
},
"children": [
{
"id": "15236",
"routeId": "sa_41ee8e342f75401539c60b58",
"moleculeId": "sa_fec89fa580d2d7c82276231c",
"parentId": "15235",
"isLeaf": true,
"molecule": {
"id": "sa_fec89fa580d2d7c82276231c",
"inchikey": "CFHGBZLNZZVTAY-UHFFFAOYSA-N",
"smiles": "COc1ccc(P2(=S)SP(=S)(c3ccc(OC)cc3)S2)cc1"
},
"smiles": "COc1ccc(P2(=S)SP(=S)(c3ccc(OC)cc3)S2)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15237",
"routeId": "sa_41ee8e342f75401539c60b58",
"moleculeId": "sa_a8aadd8b10aa89be76cb337f",
"parentId": "15235",
"isLeaf": true,
"molecule": {
"id": "sa_a8aadd8b10aa89be76cb337f",
"inchikey": "GVOHXQSLMXWNLS-UHFFFAOYSA-N",
"smiles": "O=C1COCC2CC2(c2cc(N=C(c3ccccc3)c3ccccc3)ccc2F)N1"
},
"smiles": "O=C1COCC2CC2(c2cc(N=C(c3ccccc3)c3ccccc3)ccc2F)N1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}