Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
O=C(Nc1ccc(-c2ccc(C(F)(F)F)cc2Cl)nn1)c1ccc(Oc2cc3c(cc2Cl)C(C(=O)O)CCO3)cc1
InChiKey
NPQGSVSVVBMWIH-UHFFFAOYSA-N
Route Signature
b62d1c89ead0a92e86b3a85a7fa6b96aa269f9f6424ba1c946f14894ae8264d0
Synthesis route with 6 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_13dc27abefce2cdbf096dbbf",
"signature": "b62d1c89ead0a92e86b3a85a7fa6b96aa269f9f6424ba1c946f14894ae8264d0",
"contentHash": "64de98f235f3e7d1d7989124aea4f8afffdbdde37f3634840e7f35d9d75fd0bb",
"length": 6,
"isConvergent": false
},
"target": {
"id": "sa_6a6c5e9131908323c1417105",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-03789",
"moleculeId": "sa_3f3bdd635e0bb5871662f829",
"smiles": "O=C(Nc1ccc(-c2ccc(C(F)(F)F)cc2Cl)nn1)c1ccc(Oc2cc3c(cc2Cl)C(C(=O)O)CCO3)cc1",
"routeLength": 6,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_3f3bdd635e0bb5871662f829",
"inchikey": "NPQGSVSVVBMWIH-UHFFFAOYSA-N",
"smiles": "O=C(Nc1ccc(-c2ccc(C(F)(F)F)cc2Cl)nn1)c1ccc(Oc2cc3c(cc2Cl)C(C(=O)O)CCO3)cc1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "15251",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_3f3bdd635e0bb5871662f829",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_3f3bdd635e0bb5871662f829",
"inchikey": "NPQGSVSVVBMWIH-UHFFFAOYSA-N",
"smiles": "O=C(Nc1ccc(-c2ccc(C(F)(F)F)cc2Cl)nn1)c1ccc(Oc2cc3c(cc2Cl)C(C(=O)O)CCO3)cc1"
},
"smiles": "O=C(Nc1ccc(-c2ccc(C(F)(F)F)cc2Cl)nn1)c1ccc(Oc2cc3c(cc2Cl)C(C(=O)O)CCO3)cc1",
"reactionStepId": "sa_74c015c3c8ce100f29fa55d7",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08785445B2;0692;1486739\",\"rsmi\":\"CC[O:39][C:37]([CH:36]1[c:30]2[cH:29][c:27]([Cl:28])[c:26]([O:25][c:24]3[cH:23][cH:22][c:21]([C:2](=[O:1])[NH:3][c:4]4[cH:5][cH:6][c:7](-[c:8]5[c:9]([Cl:10])[cH:11][c:12]([C:13]([F:14])([F:15])[F:16])[cH:17][cH:18]5)[n:19][n:20]4)[cH:41][cH:40]3)[cH:32][c:31]2[O:33][CH2:34][CH2:35]1)=[O:38]>C1CCOC1.CCO.[Na+].O>[O:1]=[C:2]([NH:3][c:4]1[cH:5][cH:6][c:7](-[c:8]2[c:9]([Cl:10])[cH:11][c:12]([C:13]([F:14])([F:15])[F:16])[cH:17][cH:18]2)[n:19][n:20]1)[c:21]1[cH:22][cH:23][c:24]([O:25][c:26]2[c:27]([Cl:28])[cH:29][c:30]3[c:31]([cH:32]2)[O:33][CH2:34][CH2:35][CH:36]3[C:37](=[O:38])[OH:39])[cH:40][cH:41]1\"},\"mapped_reaction_smiles\":\"CC[O:39][C:37]([CH:36]1[c:30]2[cH:29][c:27]([Cl:28])[c:26]([O:25][c:24]3[cH:23][cH:22][c:21]([C:2](=[O:1])[NH:3][c:4]4[cH:5][cH:6][c:7](-[c:8]5[c:9]([Cl:10])[cH:11][c:12]([C:13]([F:14])([F:15])[F:16])[cH:17][cH:18]5)[n:19][n:20]4)[cH:41][cH:40]3)[cH:32][c:31]2[O:33][CH2:34][CH2:35]1)=[O:38]>C1CCOC1.CCO.[Na+].O>[O:1]=[C:2]([NH:3][c:4]1[cH:5][cH:6][c:7](-[c:8]2[c:9]([Cl:10])[cH:11][c:12]([C:13]([F:14])([F:15])[F:16])[cH:17][cH:18]2)[n:19][n:20]1)[c:21]1[cH:22][cH:23][c:24]([O:25][c:26]2[c:27]([Cl:28])[cH:29][c:30]3[c:31]([cH:32]2)[O:33][CH2:34][CH2:35][CH:36]3[C:37](=[O:38])[OH:39])[cH:40][cH:41]1\"}",
"reactionStep": {
"id": "sa_74c015c3c8ce100f29fa55d7",
"reactionHash": "63a499d503f2f4e18716e973917a8caba0fd449612aa2b7fed58e20166af24be"
},
"children": [
{
"id": "15252",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_f9bf01f51e996cb06e91e51f",
"parentId": "15251",
"isLeaf": false,
"molecule": {
"id": "sa_f9bf01f51e996cb06e91e51f",
"inchikey": "PNMRPHWIGZWCDG-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C1CCOc2cc(Oc3ccc(C(=O)Nc4ccc(-c5ccc(C(F)(F)F)cc5Cl)nn4)cc3)c(Cl)cc21"
},
"smiles": "CCOC(=O)C1CCOc2cc(Oc3ccc(C(=O)Nc4ccc(-c5ccc(C(F)(F)F)cc5Cl)nn4)cc3)c(Cl)cc21",
"reactionStepId": "sa_ccdd4f8bdde1e1562a353b44",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08785445B2;0691;1486738\",\"rsmi\":\"Cl[c:24]1[cH:23][cH:22][c:21]([NH:20][C:18]([c:17]2[cH:16][cH:15][c:14]([O:13][c:12]3[cH:11][c:10]4[c:43]([cH:42][c:40]3[Cl:41])[CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[CH2:7][CH2:8][O:9]4)[cH:39][cH:38]2)=[O:19])[n:37][n:36]1.OB(O)[c:25]1[c:26]([Cl:27])[cH:28][c:29]([C:30]([F:31])([F:32])[F:33])[cH:34][cH:35]1>Cc1ccccc1.O=C(O)O.[Na+].[Na+].c1ccc([PH](c2ccccc2)(c2ccccc2)[Pd]([PH](c2ccccc2)(c2ccccc2)c2ccccc2)([PH](c2ccccc2)(c2ccccc2)c2ccccc2)[PH](c2ccccc2)(c2ccccc2)c2ccccc2)cc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([O:13][c:14]3[cH:15][cH:16][c:17]([C:18](=[O:19])[NH:20][c:21]4[cH:22][cH:23][c:24](-[c:25]5[c:26]([Cl:27])[cH:28][c:29]([C:30]([F:31])([F:32])[F:33])[cH:34][cH:35]5)[n:36][n:37]4)[cH:38][cH:39]3)[c:40]([Cl:41])[cH:42][c:43]21\"},\"mapped_reaction_smiles\":\"Cl[c:24]1[cH:23][cH:22][c:21]([NH:20][C:18]([c:17]2[cH:16][cH:15][c:14]([O:13][c:12]3[cH:11][c:10]4[c:43]([cH:42][c:40]3[Cl:41])[CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[CH2:7][CH2:8][O:9]4)[cH:39][cH:38]2)=[O:19])[n:37][n:36]1.OB(O)[c:25]1[c:26]([Cl:27])[cH:28][c:29]([C:30]([F:31])([F:32])[F:33])[cH:34][cH:35]1>Cc1ccccc1.O=C(O)O.[Na+].[Na+].c1ccc([PH](c2ccccc2)(c2ccccc2)[Pd]([PH](c2ccccc2)(c2ccccc2)c2ccccc2)([PH](c2ccccc2)(c2ccccc2)c2ccccc2)[PH](c2ccccc2)(c2ccccc2)c2ccccc2)cc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([O:13][c:14]3[cH:15][cH:16][c:17]([C:18](=[O:19])[NH:20][c:21]4[cH:22][cH:23][c:24](-[c:25]5[c:26]([Cl:27])[cH:28][c:29]([C:30]([F:31])([F:32])[F:33])[cH:34][cH:35]5)[n:36][n:37]4)[cH:38][cH:39]3)[c:40]([Cl:41])[cH:42][c:43]21\"}",
"reactionStep": {
"id": "sa_ccdd4f8bdde1e1562a353b44",
"reactionHash": "75d41cd5d662275306502198d019f9b99b3a546ca1d0cdab7872995f2ea8867b"
},
"children": [
{
"id": "15253",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_297f529e2bad8b0e3b94a869",
"parentId": "15252",
"isLeaf": false,
"molecule": {
"id": "sa_297f529e2bad8b0e3b94a869",
"inchikey": "BOVHUGQZPMBJPL-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C1CCOc2cc(Oc3ccc(C(=O)Nc4ccc(Cl)nn4)cc3)c(Cl)cc21"
},
"smiles": "CCOC(=O)C1CCOc2cc(Oc3ccc(C(=O)Nc4ccc(Cl)nn4)cc3)c(Cl)cc21",
"reactionStepId": "sa_16c22ac657c4f9ac057d6984",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08785445B2;0690;1486737\",\"rsmi\":\"O[C:18]([c:17]1[cH:16][cH:15][c:14]([O:13][c:12]2[cH:11][c:10]3[c:33]([cH:32][c:30]2[Cl:31])[CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[CH2:7][CH2:8][O:9]3)[cH:29][cH:28]1)=[O:19].[NH2:20][c:21]1[cH:22][cH:23][c:24]([Cl:25])[n:26][n:27]1>CCOC(C)=O.CN(C)C=O.ClCCCl.O=C(Cl)C(=O)Cl.c1ccncc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([O:13][c:14]3[cH:15][cH:16][c:17]([C:18](=[O:19])[NH:20][c:21]4[cH:22][cH:23][c:24]([Cl:25])[n:26][n:27]4)[cH:28][cH:29]3)[c:30]([Cl:31])[cH:32][c:33]21\"},\"mapped_reaction_smiles\":\"O[C:18]([c:17]1[cH:16][cH:15][c:14]([O:13][c:12]2[cH:11][c:10]3[c:33]([cH:32][c:30]2[Cl:31])[CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[CH2:7][CH2:8][O:9]3)[cH:29][cH:28]1)=[O:19].[NH2:20][c:21]1[cH:22][cH:23][c:24]([Cl:25])[n:26][n:27]1>CCOC(C)=O.CN(C)C=O.ClCCCl.O=C(Cl)C(=O)Cl.c1ccncc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([O:13][c:14]3[cH:15][cH:16][c:17]([C:18](=[O:19])[NH:20][c:21]4[cH:22][cH:23][c:24]([Cl:25])[n:26][n:27]4)[cH:28][cH:29]3)[c:30]([Cl:31])[cH:32][c:33]21\"}",
"reactionStep": {
"id": "sa_16c22ac657c4f9ac057d6984",
"reactionHash": "a166c392f00d1531aae4431934996897ddf43201b1aac08a1b757f2e422fd9b6"
},
"children": [
{
"id": "15254",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_98680df4905421f909e4f8d5",
"parentId": "15253",
"isLeaf": true,
"molecule": {
"id": "sa_98680df4905421f909e4f8d5",
"inchikey": "DTXVKPOKPFWSFF-UHFFFAOYSA-N",
"smiles": "N=c1ccc(Cl)n[nH]1"
},
"smiles": "Nc1ccc(Cl)nn1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15255",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_99986464da4bb340726aeec5",
"parentId": "15253",
"isLeaf": false,
"molecule": {
"id": "sa_99986464da4bb340726aeec5",
"inchikey": "WREVNSQSYUJJKJ-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C1CCOc2cc(Oc3ccc(C(=O)O)cc3)c(Cl)cc21"
},
"smiles": "CCOC(=O)C1CCOc2cc(Oc3ccc(C(=O)O)cc3)c(Cl)cc21",
"reactionStepId": "sa_5cf49a4cc3d9f339c89c309e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08785445B2;0521;1486677\",\"rsmi\":\"CC(C)(C)[O:20][C:18]([c:17]1[cH:16][cH:15][c:14]([O:13][c:12]2[cH:11][c:10]3[c:26]([cH:25][c:23]2[Cl:24])[CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[CH2:7][CH2:8][O:9]3)[cH:22][cH:21]1)=[O:19]>CCOC(C)=O.Cl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([O:13][c:14]3[cH:15][cH:16][c:17]([C:18](=[O:19])[OH:20])[cH:21][cH:22]3)[c:23]([Cl:24])[cH:25][c:26]21\"},\"mapped_reaction_smiles\":\"CC(C)(C)[O:20][C:18]([c:17]1[cH:16][cH:15][c:14]([O:13][c:12]2[cH:11][c:10]3[c:26]([cH:25][c:23]2[Cl:24])[CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[CH2:7][CH2:8][O:9]3)[cH:22][cH:21]1)=[O:19]>CCOC(C)=O.Cl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([O:13][c:14]3[cH:15][cH:16][c:17]([C:18](=[O:19])[OH:20])[cH:21][cH:22]3)[c:23]([Cl:24])[cH:25][c:26]21\"}",
"reactionStep": {
"id": "sa_5cf49a4cc3d9f339c89c309e",
"reactionHash": "8833b2da2547991c92e2b64ab8e3e46daad236c95f7ee4eb2a8719a6cb2b8de2"
},
"children": [
{
"id": "15256",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_72b19276badcec95e67232c7",
"parentId": "15255",
"isLeaf": false,
"molecule": {
"id": "sa_72b19276badcec95e67232c7",
"inchikey": "LKHBRRLGUNKYKV-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C1CCOc2cc(Oc3ccc(C(=O)OC(C)(C)C)cc3)c(Cl)cc21"
},
"smiles": "CCOC(=O)C1CCOc2cc(Oc3ccc(C(=O)OC(C)(C)C)cc3)c(Cl)cc21",
"reactionStepId": "sa_9b145e76b8376a7a4dfac6b2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08785445B2;0520;1486676\",\"rsmi\":\"Br[c:14]1[cH:15][cH:16][c:17]([C:18](=[O:19])[O:20][C:21]([CH3:22])([CH3:23])[CH3:24])[cH:25][cH:26]1.[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([OH:13])[c:27]([Cl:28])[cH:29][c:30]21>C.C1COCCO1.CCOC(C)=O.CN(C)CC(=O)O.Cl.O=C(O)O.[Cs+].[Cs+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([O:13][c:14]3[cH:15][cH:16][c:17]([C:18](=[O:19])[O:20][C:21]([CH3:22])([CH3:23])[CH3:24])[cH:25][cH:26]3)[c:27]([Cl:28])[cH:29][c:30]21\"},\"mapped_reaction_smiles\":\"Br[c:14]1[cH:15][cH:16][c:17]([C:18](=[O:19])[O:20][C:21]([CH3:22])([CH3:23])[CH3:24])[cH:25][cH:26]1.[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([OH:13])[c:27]([Cl:28])[cH:29][c:30]21>C.C1COCCO1.CCOC(C)=O.CN(C)CC(=O)O.Cl.O=C(O)O.[Cs+].[Cs+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([O:13][c:14]3[cH:15][cH:16][c:17]([C:18](=[O:19])[O:20][C:21]([CH3:22])([CH3:23])[CH3:24])[cH:25][cH:26]3)[c:27]([Cl:28])[cH:29][c:30]21\"}",
"reactionStep": {
"id": "sa_9b145e76b8376a7a4dfac6b2",
"reactionHash": "f4c444ef1d3160762773449f2993849d75f93a2b1d725d25850bc372132761e1"
},
"children": [
{
"id": "15257",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_5ed9c87044282787554536dd",
"parentId": "15256",
"isLeaf": true,
"molecule": {
"id": "sa_5ed9c87044282787554536dd",
"inchikey": "BFJJYXUCGYOXDM-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)c1ccc(Br)cc1"
},
"smiles": "CC(C)(C)OC(=O)c1ccc(Br)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15258",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_bf326f2f9b731d18bbab81f8",
"parentId": "15256",
"isLeaf": false,
"molecule": {
"id": "sa_bf326f2f9b731d18bbab81f8",
"inchikey": "RXVPHMIRHIHSOQ-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C1CCOc2cc(O)c(Cl)cc21"
},
"smiles": "CCOC(=O)C1CCOc2cc(O)c(Cl)cc21",
"reactionStepId": "sa_b49d6d755ecc9fc9caacbd2f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08785445B2;0519;1486675\",\"rsmi\":\"O[C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([OH:13])[c:14]([Cl:15])[cH:16][c:17]21.[CH3:1][CH2:2][OH:3]>CCOC(C)=O.O=S(=O)(O)O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([OH:13])[c:14]([Cl:15])[cH:16][c:17]21\"},\"mapped_reaction_smiles\":\"O[C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([OH:13])[c:14]([Cl:15])[cH:16][c:17]21.[CH3:1][CH2:2][OH:3]>CCOC(C)=O.O=S(=O)(O)O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]1[CH2:7][CH2:8][O:9][c:10]2[cH:11][c:12]([OH:13])[c:14]([Cl:15])[cH:16][c:17]21\"}",
"reactionStep": {
"id": "sa_b49d6d755ecc9fc9caacbd2f",
"reactionHash": "d3dfb3ad34d866de74c70866bd01a0d020a7d1678c0a20f78e3fc1499f1a65e8"
},
"children": [
{
"id": "15259",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_afaca116b303dc7d01346819",
"parentId": "15258",
"isLeaf": true,
"molecule": {
"id": "sa_afaca116b303dc7d01346819",
"inchikey": "LFQSCWFLJHTTHZ-UHFFFAOYSA-N",
"smiles": "CCO"
},
"smiles": "CCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15260",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_c0e794673d41f8abf25bbef8",
"parentId": "15258",
"isLeaf": true,
"molecule": {
"id": "sa_c0e794673d41f8abf25bbef8",
"inchikey": "ZBWHVZZJKGPNDS-UHFFFAOYSA-N",
"smiles": "O=C(O)C1CCOc2cc(O)c(Cl)cc21"
},
"smiles": "O=C(O)C1CCOc2cc(O)c(Cl)cc21",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
},
{
"id": "15261",
"routeId": "sa_13dc27abefce2cdbf096dbbf",
"moleculeId": "sa_cf2a9bac468363bde7abcedc",
"parentId": "15252",
"isLeaf": true,
"molecule": {
"id": "sa_cf2a9bac468363bde7abcedc",
"inchikey": "JKSUCAFAUNSPLO-UHFFFAOYSA-N",
"smiles": "OB(O)c1ccc(C(F)(F)F)cc1Cl"
},
"smiles": "OB(O)c1ccc(C(F)(F)F)cc1Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}