Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1ccc2c(O[C@@H]3C[C@H](NC(=O)OC(C)(C)C)[C@H](C(=O)O)C3)cc(-c3ccccc3)nc2c1
InChiKey
NRWSOMHBZVIREH-NOXFTYBFSA-N
Route Signature
8de1b2a43877d773f7d26780e977ab9154ee24171e88f2f67ecd591cf87246ae
Synthesis route with 4 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_ceac312630c0fb0a0717733a",
"signature": "8de1b2a43877d773f7d26780e977ab9154ee24171e88f2f67ecd591cf87246ae",
"contentHash": "259020044c4260a85c1b9de811a8ed3ee73f3a6f20d5d53120c5458e96bfd00c",
"length": 4,
"isConvergent": false
},
"target": {
"id": "sa_144249862b45b8437ceb85e1",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-06144",
"moleculeId": "sa_51f3e946bee6e78497a5d9dc",
"smiles": "COc1ccc2c(O[C@@H]3C[C@H](NC(=O)OC(C)(C)C)[C@H](C(=O)O)C3)cc(-c3ccccc3)nc2c1",
"routeLength": 4,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_51f3e946bee6e78497a5d9dc",
"inchikey": "NRWSOMHBZVIREH-NOXFTYBFSA-N",
"smiles": "COc1ccc2c(O[C@@H]3C[C@H](NC(=O)OC(C)(C)C)[C@H](C(=O)O)C3)cc(-c3ccccc3)nc2c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "15847",
"routeId": "sa_ceac312630c0fb0a0717733a",
"moleculeId": "sa_51f3e946bee6e78497a5d9dc",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_51f3e946bee6e78497a5d9dc",
"inchikey": "NRWSOMHBZVIREH-NOXFTYBFSA-N",
"smiles": "COc1ccc2c(O[C@@H]3C[C@H](NC(=O)OC(C)(C)C)[C@H](C(=O)O)C3)cc(-c3ccccc3)nc2c1"
},
"smiles": "COc1ccc2c(O[C@@H]3C[C@H](NC(=O)OC(C)(C)C)[C@H](C(=O)O)C3)cc(-c3ccccc3)nc2c1",
"reactionStepId": "sa_4e3983a669003c815bfe663a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080045530A1;0636;550217\",\"rsmi\":\"Cl[c:18]1[c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:8][c:7]2[n:9][c:10](-[c:11]2[cH:12][cH:13][cH:14][cH:15][cH:16]2)[cH:17]1.[OH:19][C@@H:20]1[CH2:21][C@H:22]([NH:23][C:24](=[O:25])[O:26][C:27]([CH3:28])([CH3:29])[CH3:30])[C@H:31]([C:32](=[O:33])[OH:34])[CH2:35]1>CC(C)(C)O.CS(C)=O.O.[K+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]2[c:7]([cH:8]1)[n:9][c:10](-[c:11]1[cH:12][cH:13][cH:14][cH:15][cH:16]1)[cH:17][c:18]2[O:19][C@@H:20]1[CH2:21][C@H:22]([NH:23][C:24](=[O:25])[O:26][C:27]([CH3:28])([CH3:29])[CH3:30])[C@H:31]([C:32](=[O:33])[OH:34])[CH2:35]1\"},\"mapped_reaction_smiles\":\"Cl[c:18]1[c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:8][c:7]2[n:9][c:10](-[c:11]2[cH:12][cH:13][cH:14][cH:15][cH:16]2)[cH:17]1.[OH:19][C@@H:20]1[CH2:21][C@H:22]([NH:23][C:24](=[O:25])[O:26][C:27]([CH3:28])([CH3:29])[CH3:30])[C@H:31]([C:32](=[O:33])[OH:34])[CH2:35]1>CC(C)(C)O.CS(C)=O.O.[K+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]2[c:7]([cH:8]1)[n:9][c:10](-[c:11]1[cH:12][cH:13][cH:14][cH:15][cH:16]1)[cH:17][c:18]2[O:19][C@@H:20]1[CH2:21][C@H:22]([NH:23][C:24](=[O:25])[O:26][C:27]([CH3:28])([CH3:29])[CH3:30])[C@H:31]([C:32](=[O:33])[OH:34])[CH2:35]1\"}",
"reactionStep": {
"id": "sa_4e3983a669003c815bfe663a",
"reactionHash": "42a67502da3467e60fb1270afd9d0cd737ac732f2a97f323a510446126c04704"
},
"children": [
{
"id": "15848",
"routeId": "sa_ceac312630c0fb0a0717733a",
"moleculeId": "sa_13608d97f4613a42d4822140",
"parentId": "15847",
"isLeaf": true,
"molecule": {
"id": "sa_13608d97f4613a42d4822140",
"inchikey": "BAZSITKSXXHTNS-UHFFFAOYSA-N",
"smiles": "COc1ccc2c(Cl)cc(-c3ccccc3)nc2c1"
},
"smiles": "COc1ccc2c(Cl)cc(-c3ccccc3)nc2c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15849",
"routeId": "sa_ceac312630c0fb0a0717733a",
"moleculeId": "sa_897f012503591f64310de7dc",
"parentId": "15847",
"isLeaf": false,
"molecule": {
"id": "sa_897f012503591f64310de7dc",
"inchikey": "HUGPKOMETVWYPN-RNJXMRFFSA-N",
"smiles": "CC(C)(C)OC(=O)N[C@H]1C[C@@H](O)C[C@H]1C(=O)O"
},
"smiles": "CC(C)(C)OC(=O)N[C@H]1C[C@@H](O)C[C@H]1C(=O)O",
"reactionStepId": "sa_29d454b1564596d674a3d7a5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080045530A1;0624;550212\",\"rsmi\":\"[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C@H:9]1[CH2:10][C:11](=[O:12])[CH2:13][C@H:14]1[C:15](=[O:16])[OH:17]>CCOC(C)=O.CO.Cl.B.[Na+]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C@H:9]1[CH2:10][C@@H:11]([OH:12])[CH2:13][C@H:14]1[C:15](=[O:16])[OH:17]\"},\"mapped_reaction_smiles\":\"[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C@H:9]1[CH2:10][C:11](=[O:12])[CH2:13][C@H:14]1[C:15](=[O:16])[OH:17]>CCOC(C)=O.CO.Cl.B.[Na+]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C@H:9]1[CH2:10][C@@H:11]([OH:12])[CH2:13][C@H:14]1[C:15](=[O:16])[OH:17]\"}",
"reactionStep": {
"id": "sa_29d454b1564596d674a3d7a5",
"reactionHash": "e194f987c433c5512a237826eafc68e88b128f56c355be67103170caf11249b4"
},
"children": [
{
"id": "15850",
"routeId": "sa_ceac312630c0fb0a0717733a",
"moleculeId": "sa_d559c005208a3e75a4fe7196",
"parentId": "15849",
"isLeaf": false,
"molecule": {
"id": "sa_d559c005208a3e75a4fe7196",
"inchikey": "UMPVGBFVGCYACA-SFYZADRCSA-N",
"smiles": "CC(C)(C)OC(=O)N[C@H]1CC(=O)C[C@H]1C(=O)O"
},
"smiles": "CC(C)(C)OC(=O)N[C@H]1CC(=O)C[C@H]1C(=O)O",
"reactionStepId": "sa_8356d59c265ac019d5081155",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080045530A1;0622;550211\",\"rsmi\":\"C=[C:11]1[CH2:10][C@H:9]([NH:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[C@H:14]([C:15](=[O:16])[OH:17])[CH2:13]1.[O-][O+]=[O:12]>CO.CSC>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C@H:9]1[CH2:10][C:11](=[O:12])[CH2:13][C@H:14]1[C:15](=[O:16])[OH:17]\"},\"mapped_reaction_smiles\":\"C=[C:11]1[CH2:10][C@H:9]([NH:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[C@H:14]([C:15](=[O:16])[OH:17])[CH2:13]1.[O-][O+]=[O:12]>CO.CSC>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C@H:9]1[CH2:10][C:11](=[O:12])[CH2:13][C@H:14]1[C:15](=[O:16])[OH:17]\"}",
"reactionStep": {
"id": "sa_8356d59c265ac019d5081155",
"reactionHash": "16786d725af189326abe11962c7db176cbe9c98a08ed244b67325a403aca3ebd"
},
"children": [
{
"id": "15851",
"routeId": "sa_ceac312630c0fb0a0717733a",
"moleculeId": "sa_b7fca47917403333b4aa2ef7",
"parentId": "15850",
"isLeaf": true,
"molecule": {
"id": "sa_b7fca47917403333b4aa2ef7",
"inchikey": "CBENFWSGALASAD-UHFFFAOYSA-N",
"smiles": "O=[O+][O-]"
},
"smiles": "O=[O+][O-]",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15852",
"routeId": "sa_ceac312630c0fb0a0717733a",
"moleculeId": "sa_540ed9741626f4cfa853fb9d",
"parentId": "15850",
"isLeaf": false,
"molecule": {
"id": "sa_540ed9741626f4cfa853fb9d",
"inchikey": "XDCPEAITKWRVEB-BDAKNGLRSA-N",
"smiles": "C=C1C[C@H](NC(=O)OC(C)(C)C)[C@H](C(=O)O)C1"
},
"smiles": "C=C1C[C@H](NC(=O)OC(C)(C)C)[C@H](C(=O)O)C1",
"reactionStepId": "sa_5e83bf97b65590065157abe3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080045530A1;0620;550210\",\"rsmi\":\"CC(C)(C)OC(=O)O[C:6](=[O:7])[O:8][C:9]([CH3:10])([CH3:11])[CH3:12].[CH2:1]=[C:2]1[CH2:3][C@H:4]([NH2:5])[C@H:13]([C:14](=[O:15])[OH:16])[CH2:17]1>C1COCCO1.CCN(CC)CC.O>[CH2:1]=[C:2]1[CH2:3][C@H:4]([NH:5][C:6](=[O:7])[O:8][C:9]([CH3:10])([CH3:11])[CH3:12])[C@H:13]([C:14](=[O:15])[OH:16])[CH2:17]1\"},\"mapped_reaction_smiles\":\"CC(C)(C)OC(=O)O[C:6](=[O:7])[O:8][C:9]([CH3:10])([CH3:11])[CH3:12].[CH2:1]=[C:2]1[CH2:3][C@H:4]([NH2:5])[C@H:13]([C:14](=[O:15])[OH:16])[CH2:17]1>C1COCCO1.CCN(CC)CC.O>[CH2:1]=[C:2]1[CH2:3][C@H:4]([NH:5][C:6](=[O:7])[O:8][C:9]([CH3:10])([CH3:11])[CH3:12])[C@H:13]([C:14](=[O:15])[OH:16])[CH2:17]1\"}",
"reactionStep": {
"id": "sa_5e83bf97b65590065157abe3",
"reactionHash": "e7cedc49ee791df6f09ec5693ff7f56275f5d9659d3da00aa6f25bf34085301c"
},
"children": [
{
"id": "15853",
"routeId": "sa_ceac312630c0fb0a0717733a",
"moleculeId": "sa_b273d4d4546165bca2b249b5",
"parentId": "15852",
"isLeaf": true,
"molecule": {
"id": "sa_b273d4d4546165bca2b249b5",
"inchikey": "DYHSDKLCOJIUFX-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)OC(=O)OC(C)(C)C"
},
"smiles": "CC(C)(C)OC(=O)OC(=O)OC(C)(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "15854",
"routeId": "sa_ceac312630c0fb0a0717733a",
"moleculeId": "sa_e15791892e5fc11dd6836837",
"parentId": "15852",
"isLeaf": true,
"molecule": {
"id": "sa_e15791892e5fc11dd6836837",
"inchikey": "RKOUGZGFAYMUIO-RITPCOANSA-N",
"smiles": "C=C1C[C@H](N)[C@H](C(=O)O)C1"
},
"smiles": "C=C1C[C@H](N)[C@H](C(=O)O)C1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}