Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
C[C@@](CCn1cc(F)c(-c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)cc1=O)(C(=O)O)S(C)(=O)=O
InChiKey
UQTTWFZHDFYXRV-NXWNVOEXSA-N
Route Signature
796a9f0420605ed6edeb31215acd09e6a87962726395ad6cd14790afd9fda14d
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_534217621338e74dae559105",
"signature": "796a9f0420605ed6edeb31215acd09e6a87962726395ad6cd14790afd9fda14d",
"contentHash": "b1864e45959b14c4e61388ac543dab58f39ec3aad196a6644ef8025b47f083d7",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_a3ab1814ca03063398b7aa20",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-01404",
"moleculeId": "sa_5551380a542d274adc88d7bf",
"smiles": "C[C@@](CCn1cc(F)c(-c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)cc1=O)(C(=O)O)S(C)(=O)=O",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_5551380a542d274adc88d7bf",
"inchikey": "UQTTWFZHDFYXRV-NXWNVOEXSA-N",
"smiles": "C[C@@](CCn1cc(F)c(-c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)cc1=O)(C(=O)O)S(C)(=O)=O"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "10161",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_5551380a542d274adc88d7bf",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_5551380a542d274adc88d7bf",
"inchikey": "UQTTWFZHDFYXRV-NXWNVOEXSA-N",
"smiles": "C[C@@](CCn1cc(F)c(-c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)cc1=O)(C(=O)O)S(C)(=O)=O"
},
"smiles": "C[C@@](CCn1cc(F)c(-c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)cc1=O)(C(=O)O)S(C)(=O)=O",
"reactionStepId": "sa_34e67e8e6ce2ba7c47c2f1a0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120232083A1;0278;1269900\",\"rsmi\":\"CC[O:36][C:34]([C@@:2]([CH3:1])([CH2:3][CH2:4][n:5]1[cH:6][c:7]([F:8])[c:9](-[c:10]2[cH:11][cH:12][c:13]([O:14][CH2:15][C@H:16]3[CH2:17][CH2:18][C@H:19]([O:20][CH:21]4[CH2:22][CH2:23][CH2:24][CH2:25][O:26]4)[CH2:27][CH2:28]3)[cH:29][cH:30]2)[cH:31][c:32]1=[O:33])[S:37]([CH3:38])(=[O:39])=[O:40])=[O:35]>CCO.Cl.[Li+].O>[CH3:1][C@@:2]([CH2:3][CH2:4][n:5]1[cH:6][c:7]([F:8])[c:9](-[c:10]2[cH:11][cH:12][c:13]([O:14][CH2:15][C@H:16]3[CH2:17][CH2:18][C@H:19]([O:20][CH:21]4[CH2:22][CH2:23][CH2:24][CH2:25][O:26]4)[CH2:27][CH2:28]3)[cH:29][cH:30]2)[cH:31][c:32]1=[O:33])([C:34](=[O:35])[OH:36])[S:37]([CH3:38])(=[O:39])=[O:40]\"},\"mapped_reaction_smiles\":\"CC[O:36][C:34]([C@@:2]([CH3:1])([CH2:3][CH2:4][n:5]1[cH:6][c:7]([F:8])[c:9](-[c:10]2[cH:11][cH:12][c:13]([O:14][CH2:15][C@H:16]3[CH2:17][CH2:18][C@H:19]([O:20][CH:21]4[CH2:22][CH2:23][CH2:24][CH2:25][O:26]4)[CH2:27][CH2:28]3)[cH:29][cH:30]2)[cH:31][c:32]1=[O:33])[S:37]([CH3:38])(=[O:39])=[O:40])=[O:35]>CCO.Cl.[Li+].O>[CH3:1][C@@:2]([CH2:3][CH2:4][n:5]1[cH:6][c:7]([F:8])[c:9](-[c:10]2[cH:11][cH:12][c:13]([O:14][CH2:15][C@H:16]3[CH2:17][CH2:18][C@H:19]([O:20][CH:21]4[CH2:22][CH2:23][CH2:24][CH2:25][O:26]4)[CH2:27][CH2:28]3)[cH:29][cH:30]2)[cH:31][c:32]1=[O:33])([C:34](=[O:35])[OH:36])[S:37]([CH3:38])(=[O:39])=[O:40]\"}",
"reactionStep": {
"id": "sa_34e67e8e6ce2ba7c47c2f1a0",
"reactionHash": "7c817c01c35c31c3b8145348c18aee30450df117cda1ca1b2cf226dd87a0fd92"
},
"children": [
{
"id": "10162",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_c01e5607b806bfcecbb01dd4",
"parentId": "10161",
"isLeaf": false,
"molecule": {
"id": "sa_c01e5607b806bfcecbb01dd4",
"inchikey": "HRPMUNZTLAAQLK-HGYJUNBGSA-N",
"smiles": "CCOC(=O)[C@@](C)(CCn1cc(F)c(-c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)cc1=O)S(C)(=O)=O"
},
"smiles": "CCOC(=O)[C@@](C)(CCn1cc(F)c(-c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)cc1=O)S(C)(=O)=O",
"reactionStepId": "sa_16873a1a440633559f03fd66",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120232083A1;0277;1269899\",\"rsmi\":\"CC1(C)OB([c:15]2[cH:16][cH:17][c:18]([O:19][CH2:20][C@H:21]3[CH2:22][CH2:23][C@H:24]([O:25][CH:26]4[CH2:27][CH2:28][CH2:29][CH2:30][O:31]4)[CH2:32][CH2:33]3)[cH:34][cH:35]2)OC1(C)C.I[c:14]1[c:12]([F:13])[cH:11][n:10]([CH2:9][CH2:8][C@@:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])([CH3:7])[S:39]([CH3:40])(=[O:41])=[O:42])[c:37](=[O:38])[cH:36]1>CC1CCCO1.Cl[Pd]Cl.O.O.O=P(O)(O)O.[Fe+2].[K+].[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C@@:6]([CH3:7])([CH2:8][CH2:9][n:10]1[cH:11][c:12]([F:13])[c:14](-[c:15]2[cH:16][cH:17][c:18]([O:19][CH2:20][C@H:21]3[CH2:22][CH2:23][C@H:24]([O:25][CH:26]4[CH2:27][CH2:28][CH2:29][CH2:30][O:31]4)[CH2:32][CH2:33]3)[cH:34][cH:35]2)[cH:36][c:37]1=[O:38])[S:39]([CH3:40])(=[O:41])=[O:42]\"},\"mapped_reaction_smiles\":\"CC1(C)OB([c:15]2[cH:16][cH:17][c:18]([O:19][CH2:20][C@H:21]3[CH2:22][CH2:23][C@H:24]([O:25][CH:26]4[CH2:27][CH2:28][CH2:29][CH2:30][O:31]4)[CH2:32][CH2:33]3)[cH:34][cH:35]2)OC1(C)C.I[c:14]1[c:12]([F:13])[cH:11][n:10]([CH2:9][CH2:8][C@@:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])([CH3:7])[S:39]([CH3:40])(=[O:41])=[O:42])[c:37](=[O:38])[cH:36]1>CC1CCCO1.Cl[Pd]Cl.O.O.O=P(O)(O)O.[Fe+2].[K+].[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C@@:6]([CH3:7])([CH2:8][CH2:9][n:10]1[cH:11][c:12]([F:13])[c:14](-[c:15]2[cH:16][cH:17][c:18]([O:19][CH2:20][C@H:21]3[CH2:22][CH2:23][C@H:24]([O:25][CH:26]4[CH2:27][CH2:28][CH2:29][CH2:30][O:31]4)[CH2:32][CH2:33]3)[cH:34][cH:35]2)[cH:36][c:37]1=[O:38])[S:39]([CH3:40])(=[O:41])=[O:42]\"}",
"reactionStep": {
"id": "sa_16873a1a440633559f03fd66",
"reactionHash": "c7f2d2b338eee2a94dc89d4304bf726aecc5e9189663f2cdd2322bfd85438b0b"
},
"children": [
{
"id": "10163",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_fdb5947bc7ea32ba28e66109",
"parentId": "10162",
"isLeaf": false,
"molecule": {
"id": "sa_fdb5947bc7ea32ba28e66109",
"inchikey": "SMFTYTRLFIZIPU-NGZATLCBSA-N",
"smiles": "CC1(C)OB(c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)OC1(C)C"
},
"smiles": "CC1(C)OB(c2ccc(OC[C@H]3CC[C@H](OC4CCCCO4)CC3)cc2)OC1(C)C",
"reactionStepId": "sa_777788eb4069587b145a01e0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120232083A1;0276;1269898\",\"rsmi\":\"O[c:9]1[cH:8][cH:7][c:6]([B:5]2[O:4][C:2]([CH3:1])([CH3:3])[C:28]([CH3:29])([CH3:30])[O:27]2)[cH:26][cH:25]1.[OH:10][CH2:11][C@H:12]1[CH2:13][CH2:14][C@H:15]([O:16][CH:17]2[CH2:18][CH2:19][CH2:20][CH2:21][O:22]2)[CH2:23][CH2:24]1>C1CCOC1.CC(C)OC(=O)N=NC(=O)OC(C)C.CCN(CC)CC.O.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][C:2]1([CH3:3])[O:4][B:5]([c:6]2[cH:7][cH:8][c:9]([O:10][CH2:11][C@H:12]3[CH2:13][CH2:14][C@H:15]([O:16][CH:17]4[CH2:18][CH2:19][CH2:20][CH2:21][O:22]4)[CH2:23][CH2:24]3)[cH:25][cH:26]2)[O:27][C:28]1([CH3:29])[CH3:30]\"},\"mapped_reaction_smiles\":\"O[c:9]1[cH:8][cH:7][c:6]([B:5]2[O:4][C:2]([CH3:1])([CH3:3])[C:28]([CH3:29])([CH3:30])[O:27]2)[cH:26][cH:25]1.[OH:10][CH2:11][C@H:12]1[CH2:13][CH2:14][C@H:15]([O:16][CH:17]2[CH2:18][CH2:19][CH2:20][CH2:21][O:22]2)[CH2:23][CH2:24]1>C1CCOC1.CC(C)OC(=O)N=NC(=O)OC(C)C.CCN(CC)CC.O.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][C:2]1([CH3:3])[O:4][B:5]([c:6]2[cH:7][cH:8][c:9]([O:10][CH2:11][C@H:12]3[CH2:13][CH2:14][C@H:15]([O:16][CH:17]4[CH2:18][CH2:19][CH2:20][CH2:21][O:22]4)[CH2:23][CH2:24]3)[cH:25][cH:26]2)[O:27][C:28]1([CH3:29])[CH3:30]\"}",
"reactionStep": {
"id": "sa_777788eb4069587b145a01e0",
"reactionHash": "76fcbc4937fd333192ffa45dc361dbb90c13e82faeb0031f22a225f672748dd8"
},
"children": [
{
"id": "10164",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_8abfda130f58505f511e73c7",
"parentId": "10163",
"isLeaf": true,
"molecule": {
"id": "sa_8abfda130f58505f511e73c7",
"inchikey": "BICZJRAGTCRORZ-UHFFFAOYSA-N",
"smiles": "CC1(C)OB(c2ccc(O)cc2)OC1(C)C"
},
"smiles": "CC1(C)OB(c2ccc(O)cc2)OC1(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10165",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_f1f5e6872114813793398e88",
"parentId": "10163",
"isLeaf": true,
"molecule": {
"id": "sa_f1f5e6872114813793398e88",
"inchikey": "KFVPDYTZZTZGFJ-FQVSMOOPSA-N",
"smiles": "OC[C@H]1CC[C@H](OC2CCCCO2)CC1"
},
"smiles": "OC[C@H]1CC[C@H](OC2CCCCO2)CC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "10166",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_9e101020b5de432ca874fb78",
"parentId": "10162",
"isLeaf": false,
"molecule": {
"id": "sa_9e101020b5de432ca874fb78",
"inchikey": "WFCTXFNOSNPPJX-CYBMUJFWSA-N",
"smiles": "CCOC(=O)[C@@](C)(CCn1cc(F)c(I)cc1=O)S(C)(=O)=O"
},
"smiles": "CCOC(=O)[C@@](C)(CCn1cc(F)c(I)cc1=O)S(C)(=O)=O",
"reactionStepId": "sa_d916808654e0c57083204d89",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120232083A1;0208;1269883\",\"rsmi\":\"Br[CH2:9][CH2:8][C@@:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])([CH3:7])[S:19]([CH3:20])(=[O:21])=[O:22].[nH:10]1[cH:11][c:12]([F:13])[c:14]([I:15])[cH:16][c:17]1=[O:18]>C1CCOC1.O=C(O)O.[Cs+].[Cs+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C@@:6]([CH3:7])([CH2:8][CH2:9][n:10]1[cH:11][c:12]([F:13])[c:14]([I:15])[cH:16][c:17]1=[O:18])[S:19]([CH3:20])(=[O:21])=[O:22]\"},\"mapped_reaction_smiles\":\"Br[CH2:9][CH2:8][C@@:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])([CH3:7])[S:19]([CH3:20])(=[O:21])=[O:22].[nH:10]1[cH:11][c:12]([F:13])[c:14]([I:15])[cH:16][c:17]1=[O:18]>C1CCOC1.O=C(O)O.[Cs+].[Cs+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C@@:6]([CH3:7])([CH2:8][CH2:9][n:10]1[cH:11][c:12]([F:13])[c:14]([I:15])[cH:16][c:17]1=[O:18])[S:19]([CH3:20])(=[O:21])=[O:22]\"}",
"reactionStep": {
"id": "sa_d916808654e0c57083204d89",
"reactionHash": "1b336093a83e0d76d635cc3177215b7591e80512a0bf74d52f604e1d47a95903"
},
"children": [
{
"id": "10167",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_805273204fef288197bd34ce",
"parentId": "10166",
"isLeaf": true,
"molecule": {
"id": "sa_805273204fef288197bd34ce",
"inchikey": "DRDIKYRQXJWIIX-MRVPVSSYSA-N",
"smiles": "CCOC(=O)[C@@](C)(CCBr)S(C)(=O)=O"
},
"smiles": "CCOC(=O)[C@@](C)(CCBr)S(C)(=O)=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10168",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_169ddd71c1b48866661d14c8",
"parentId": "10166",
"isLeaf": false,
"molecule": {
"id": "sa_169ddd71c1b48866661d14c8",
"inchikey": "MFEDNNMGKYTJLJ-UHFFFAOYSA-N",
"smiles": "Oc1cc(I)c(F)cn1"
},
"smiles": "O=c1cc(I)c(F)c[nH]1",
"reactionStepId": "sa_00a4e3f8c4a475cbb055e564",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120232083A1;0207;1269882\",\"rsmi\":\"F[c:2]1[cH:3][c:4]([I:5])[c:6]([F:7])[cH:8][n:9]1.[OH2:1]>C1COCCO1.Cl>[O:1]=[c:2]1[cH:3][c:4]([I:5])[c:6]([F:7])[cH:8][nH:9]1\"},\"mapped_reaction_smiles\":\"F[c:2]1[cH:3][c:4]([I:5])[c:6]([F:7])[cH:8][n:9]1.[OH2:1]>C1COCCO1.Cl>[O:1]=[c:2]1[cH:3][c:4]([I:5])[c:6]([F:7])[cH:8][nH:9]1\"}",
"reactionStep": {
"id": "sa_00a4e3f8c4a475cbb055e564",
"reactionHash": "eab53a12e9a9ad783eeff246bd07e17d7a53c4739b2a4e3a8d892a4401f19534"
},
"children": [
{
"id": "10169",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_b6773e2f5fa4512821252600",
"parentId": "10168",
"isLeaf": true,
"molecule": {
"id": "sa_b6773e2f5fa4512821252600",
"inchikey": "OBVRKNZQNKGNTQ-UHFFFAOYSA-N",
"smiles": "Fc1cc(I)c(F)cn1"
},
"smiles": "Fc1cc(I)c(F)cn1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10170",
"routeId": "sa_534217621338e74dae559105",
"moleculeId": "sa_106b35b8a76bbe73829a0a69",
"parentId": "10168",
"isLeaf": true,
"molecule": {
"id": "sa_106b35b8a76bbe73829a0a69",
"inchikey": "XLYOFNOQVPJJNP-UHFFFAOYSA-N",
"smiles": "O"
},
"smiles": "O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}