Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
O=C(Nc1cccc(CC2(C(=O)O)CC2)c1)C(c1ccc(Cl)cc1)C1CCCC1
InChiKey
PPUBEFOEKGTQIG-UHFFFAOYSA-N
Route Signature
8dff135f3127d098ebaab8cc8461c5303545b3e1257c9f9f31130d942c3466d5
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_df2a291e91f342953c5d1ab7",
"signature": "8dff135f3127d098ebaab8cc8461c5303545b3e1257c9f9f31130d942c3466d5",
"contentHash": "3f22d0556bdd786ad04267ff0de3a1fa3ddde7d7190970e522c5aebeac851ce0",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_bb6239b8bfbfcead65499f85",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-01752",
"moleculeId": "sa_1db4b4369373b5fe6f677c91",
"smiles": "O=C(Nc1cccc(CC2(C(=O)O)CC2)c1)C(c1ccc(Cl)cc1)C1CCCC1",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_1db4b4369373b5fe6f677c91",
"inchikey": "PPUBEFOEKGTQIG-UHFFFAOYSA-N",
"smiles": "O=C(Nc1cccc(CC2(C(=O)O)CC2)c1)C(c1ccc(Cl)cc1)C1CCCC1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "10438",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_1db4b4369373b5fe6f677c91",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_1db4b4369373b5fe6f677c91",
"inchikey": "PPUBEFOEKGTQIG-UHFFFAOYSA-N",
"smiles": "O=C(Nc1cccc(CC2(C(=O)O)CC2)c1)C(c1ccc(Cl)cc1)C1CCCC1"
},
"smiles": "O=C(Nc1cccc(CC2(C(=O)O)CC2)c1)C(c1ccc(Cl)cc1)C1CCCC1",
"reactionStepId": "sa_2db0aeb059b259a1ce9bc4ff",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120172448A1;0792;1237932\",\"rsmi\":\"CC(C)(C)[O:13][C:11]([C:10]1([CH2:9][c:8]2[cH:7][cH:6][cH:5][c:4]([NH:3][C:2](=[O:1])[CH:17]([c:18]3[cH:19][cH:20][c:21]([Cl:22])[cH:23][cH:24]3)[CH:25]3[CH2:26][CH2:27][CH2:28][CH2:29]3)[cH:16]2)[CH2:14][CH2:15]1)=[O:12]>ClCCl.O.O=C(O)C(F)(F)F>[O:1]=[C:2]([NH:3][c:4]1[cH:5][cH:6][cH:7][c:8]([CH2:9][C:10]2([C:11](=[O:12])[OH:13])[CH2:14][CH2:15]2)[cH:16]1)[CH:17]([c:18]1[cH:19][cH:20][c:21]([Cl:22])[cH:23][cH:24]1)[CH:25]1[CH2:26][CH2:27][CH2:28][CH2:29]1\"},\"mapped_reaction_smiles\":\"CC(C)(C)[O:13][C:11]([C:10]1([CH2:9][c:8]2[cH:7][cH:6][cH:5][c:4]([NH:3][C:2](=[O:1])[CH:17]([c:18]3[cH:19][cH:20][c:21]([Cl:22])[cH:23][cH:24]3)[CH:25]3[CH2:26][CH2:27][CH2:28][CH2:29]3)[cH:16]2)[CH2:14][CH2:15]1)=[O:12]>ClCCl.O.O=C(O)C(F)(F)F>[O:1]=[C:2]([NH:3][c:4]1[cH:5][cH:6][cH:7][c:8]([CH2:9][C:10]2([C:11](=[O:12])[OH:13])[CH2:14][CH2:15]2)[cH:16]1)[CH:17]([c:18]1[cH:19][cH:20][c:21]([Cl:22])[cH:23][cH:24]1)[CH:25]1[CH2:26][CH2:27][CH2:28][CH2:29]1\"}",
"reactionStep": {
"id": "sa_2db0aeb059b259a1ce9bc4ff",
"reactionHash": "91ec3f0eaf5f31715ae96821130967c0206e29217394488fc51a199156590a2a"
},
"children": [
{
"id": "10439",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_f92a2ee1c39a8e6069b85755",
"parentId": "10438",
"isLeaf": false,
"molecule": {
"id": "sa_f92a2ee1c39a8e6069b85755",
"inchikey": "YGOZTZIAHLODFI-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)C1(Cc2cccc(NC(=O)C(c3ccc(Cl)cc3)C3CCCC3)c2)CC1"
},
"smiles": "CC(C)(C)OC(=O)C1(Cc2cccc(NC(=O)C(c3ccc(Cl)cc3)C3CCCC3)c2)CC1",
"reactionStepId": "sa_0ccfb13075d649704cac4046",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120172448A1;0653;1237908\",\"rsmi\":\"O[C:14](=[O:15])[CH:16]([c:17]1[cH:18][cH:19][c:20]([Cl:21])[cH:22][cH:23]1)[CH:24]1[CH2:25][CH2:26][CH2:27][CH2:28]1.[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([NH2:13])[cH:29][cH:30][cH:31]2)[CH2:32][CH2:33]1>CCN(C(C)C)C(C)C.CN(C)C(On1nnc2cccnc21)=[N+](C)C.CN(C)C=O.F[PH](F)(F)(F)(F)F.O.O=C(O)O.On1nnc2ccccc21.[Na+].[Na+]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([NH:13][C:14](=[O:15])[CH:16]([c:17]3[cH:18][cH:19][c:20]([Cl:21])[cH:22][cH:23]3)[CH:24]3[CH2:25][CH2:26][CH2:27][CH2:28]3)[cH:29][cH:30][cH:31]2)[CH2:32][CH2:33]1\"},\"mapped_reaction_smiles\":\"O[C:14](=[O:15])[CH:16]([c:17]1[cH:18][cH:19][c:20]([Cl:21])[cH:22][cH:23]1)[CH:24]1[CH2:25][CH2:26][CH2:27][CH2:28]1.[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([NH2:13])[cH:29][cH:30][cH:31]2)[CH2:32][CH2:33]1>CCN(C(C)C)C(C)C.CN(C)C(On1nnc2cccnc21)=[N+](C)C.CN(C)C=O.F[PH](F)(F)(F)(F)F.O.O=C(O)O.On1nnc2ccccc21.[Na+].[Na+]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([NH:13][C:14](=[O:15])[CH:16]([c:17]3[cH:18][cH:19][c:20]([Cl:21])[cH:22][cH:23]3)[CH:24]3[CH2:25][CH2:26][CH2:27][CH2:28]3)[cH:29][cH:30][cH:31]2)[CH2:32][CH2:33]1\"}",
"reactionStep": {
"id": "sa_0ccfb13075d649704cac4046",
"reactionHash": "6f634ae493d95cee622ce393ab7fc7ccbc81439ed72133cb3ef22278d1b06fb1"
},
"children": [
{
"id": "10440",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_66ea80fee25e176c26c34bf8",
"parentId": "10439",
"isLeaf": false,
"molecule": {
"id": "sa_66ea80fee25e176c26c34bf8",
"inchikey": "CQPSXVNFHFEGJV-UHFFFAOYSA-N",
"smiles": "O=C(O)C(c1ccc(Cl)cc1)C1CCCC1"
},
"smiles": "O=C(O)C(c1ccc(Cl)cc1)C1CCCC1",
"reactionStepId": "sa_cb1cbc28689bb70d0657f741",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120172448A1;0568;1237894\",\"rsmi\":\"C[O:3][C:2](=[O:1])[CH:4]([c:5]1[cH:6][cH:7][c:8]([Cl:9])[cH:10][cH:11]1)[CH:12]1[CH2:13][CH2:14][CH2:15][CH2:16]1>C1CCOC1.CO.Cl.[Na+].O>[O:1]=[C:2]([OH:3])[CH:4]([c:5]1[cH:6][cH:7][c:8]([Cl:9])[cH:10][cH:11]1)[CH:12]1[CH2:13][CH2:14][CH2:15][CH2:16]1\"},\"mapped_reaction_smiles\":\"C[O:3][C:2](=[O:1])[CH:4]([c:5]1[cH:6][cH:7][c:8]([Cl:9])[cH:10][cH:11]1)[CH:12]1[CH2:13][CH2:14][CH2:15][CH2:16]1>C1CCOC1.CO.Cl.[Na+].O>[O:1]=[C:2]([OH:3])[CH:4]([c:5]1[cH:6][cH:7][c:8]([Cl:9])[cH:10][cH:11]1)[CH:12]1[CH2:13][CH2:14][CH2:15][CH2:16]1\"}",
"reactionStep": {
"id": "sa_cb1cbc28689bb70d0657f741",
"reactionHash": "733e6a7c855d0d89a37ea9cbab9ca1ac545101f91fd7a88b2f8aaa239d5358cf"
},
"children": [
{
"id": "10441",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_4e52c7405559a9f87276ff00",
"parentId": "10440",
"isLeaf": true,
"molecule": {
"id": "sa_4e52c7405559a9f87276ff00",
"inchikey": "YLXUMTWZCCMYGE-UHFFFAOYSA-N",
"smiles": "COC(=O)C(c1ccc(Cl)cc1)C1CCCC1"
},
"smiles": "COC(=O)C(c1ccc(Cl)cc1)C1CCCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "10442",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_2e9560fe881dbf017b18dda7",
"parentId": "10439",
"isLeaf": false,
"molecule": {
"id": "sa_2e9560fe881dbf017b18dda7",
"inchikey": "FKIGGVQHZMJOHQ-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)C1(Cc2cccc(N)c2)CC1"
},
"smiles": "CC(C)(C)OC(=O)C1(Cc2cccc(N)c2)CC1",
"reactionStepId": "sa_387136abee71e2505d516090",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120172448A1;0317;1237864\",\"rsmi\":\"c1ccc(C[NH:13][c:12]2[cH:11][c:10]([CH2:9][C:8]3([C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:17][CH2:18]3)[cH:16][cH:15][cH:14]2)cc1>C1CCOC1.CCO.[Pd]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([NH2:13])[cH:14][cH:15][cH:16]2)[CH2:17][CH2:18]1\"},\"mapped_reaction_smiles\":\"c1ccc(C[NH:13][c:12]2[cH:11][c:10]([CH2:9][C:8]3([C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:17][CH2:18]3)[cH:16][cH:15][cH:14]2)cc1>C1CCOC1.CCO.[Pd]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([NH2:13])[cH:14][cH:15][cH:16]2)[CH2:17][CH2:18]1\"}",
"reactionStep": {
"id": "sa_387136abee71e2505d516090",
"reactionHash": "5e082380b3a58ccd292b894dcc4146c9739ca0922717dccfc8501955769731c7"
},
"children": [
{
"id": "10443",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_9382bc78319cba87665eafd1",
"parentId": "10442",
"isLeaf": false,
"molecule": {
"id": "sa_9382bc78319cba87665eafd1",
"inchikey": "YXWCFHCSYNDHLC-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)C1(Cc2cccc(NCc3ccccc3)c2)CC1"
},
"smiles": "CC(C)(C)OC(=O)C1(Cc2cccc(NCc3ccccc3)c2)CC1",
"reactionStepId": "sa_94e48a0ee5602c448d4af2ee",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120172448A1;0310;1237862\",\"rsmi\":\"Br[c:12]1[cH:11][c:10]([CH2:9][C:8]2([C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:24][CH2:25]2)[cH:23][cH:22][cH:21]1.[NH2:13][CH2:14][c:15]1[cH:16][cH:17][cH:18][cH:19][cH:20]1>CC(C)(C)O.Cc1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.[Na+].[Pd].[Pd].c1ccc(P(c2ccccc2)c2ccc3ccccc3c2-c2c(P(c3ccccc3)c3ccccc3)ccc3ccccc23)cc1>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([NH:13][CH2:14][c:15]3[cH:16][cH:17][cH:18][cH:19][cH:20]3)[cH:21][cH:22][cH:23]2)[CH2:24][CH2:25]1\"},\"mapped_reaction_smiles\":\"Br[c:12]1[cH:11][c:10]([CH2:9][C:8]2([C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:24][CH2:25]2)[cH:23][cH:22][cH:21]1.[NH2:13][CH2:14][c:15]1[cH:16][cH:17][cH:18][cH:19][cH:20]1>CC(C)(C)O.Cc1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.[Na+].[Pd].[Pd].c1ccc(P(c2ccccc2)c2ccc3ccccc3c2-c2c(P(c3ccccc3)c3ccccc3)ccc3ccccc23)cc1>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([NH:13][CH2:14][c:15]3[cH:16][cH:17][cH:18][cH:19][cH:20]3)[cH:21][cH:22][cH:23]2)[CH2:24][CH2:25]1\"}",
"reactionStep": {
"id": "sa_94e48a0ee5602c448d4af2ee",
"reactionHash": "b81356959356f09c05ad53b83ce7534ef760a48b78580db1921c231350f7dece"
},
"children": [
{
"id": "10444",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_a1c0f3f3ef8aac5d73a130b9",
"parentId": "10443",
"isLeaf": false,
"molecule": {
"id": "sa_a1c0f3f3ef8aac5d73a130b9",
"inchikey": "HDPJTAVBPTYOES-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)C1(Cc2cccc(Br)c2)CC1"
},
"smiles": "CC(C)(C)OC(=O)C1(Cc2cccc(Br)c2)CC1",
"reactionStepId": "sa_df15dd009effa4d45c0762e3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120172448A1;0303;1237860\",\"rsmi\":\"Br[CH2:9][c:10]1[cH:11][c:12]([Br:13])[cH:14][cH:15][cH:16]1.[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[CH:8]1[CH2:17][CH2:18]1>C1CCOC1.CC(C)NC(C)C.Cl.[Li]CCCC.N>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([Br:13])[cH:14][cH:15][cH:16]2)[CH2:17][CH2:18]1\"},\"mapped_reaction_smiles\":\"Br[CH2:9][c:10]1[cH:11][c:12]([Br:13])[cH:14][cH:15][cH:16]1.[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[CH:8]1[CH2:17][CH2:18]1>C1CCOC1.CC(C)NC(C)C.Cl.[Li]CCCC.N>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[C:8]1([CH2:9][c:10]2[cH:11][c:12]([Br:13])[cH:14][cH:15][cH:16]2)[CH2:17][CH2:18]1\"}",
"reactionStep": {
"id": "sa_df15dd009effa4d45c0762e3",
"reactionHash": "17243c53751e7f35d988858389eaf65b335aa6ade02bc2e421127554867a456a"
},
"children": [
{
"id": "10445",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_3bca115a0954e26d36d44c5c",
"parentId": "10444",
"isLeaf": true,
"molecule": {
"id": "sa_3bca115a0954e26d36d44c5c",
"inchikey": "FTEAAYMAQFBUJJ-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)C1CC1"
},
"smiles": "CC(C)(C)OC(=O)C1CC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10446",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_f8981467c37441f1262df82d",
"parentId": "10444",
"isLeaf": true,
"molecule": {
"id": "sa_f8981467c37441f1262df82d",
"inchikey": "ZPCJPJQUVRIILS-UHFFFAOYSA-N",
"smiles": "BrCc1cccc(Br)c1"
},
"smiles": "BrCc1cccc(Br)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "10447",
"routeId": "sa_df2a291e91f342953c5d1ab7",
"moleculeId": "sa_6b16c9b5e9c18df10e07c892",
"parentId": "10443",
"isLeaf": true,
"molecule": {
"id": "sa_6b16c9b5e9c18df10e07c892",
"inchikey": "WGQKYBSKWIADBV-UHFFFAOYSA-N",
"smiles": "NCc1ccccc1"
},
"smiles": "NCc1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}