Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CC(C)(C)OC(=O)NC1(C(=O)N[C@@H](Cc2ccc(-c3cccc(OS(C)(=O)=O)c3)cc2)C(N)=O)CCOCC1
InChiKey
UFMYEYREBOGNBR-QFIPXVFZSA-N
Route Signature
bc16ce2cb7152721afb45d08d331bb5901dace5f7ef108e6848eee4c625f4ca2
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_97a19d13346db1c53b6edf67",
"signature": "bc16ce2cb7152721afb45d08d331bb5901dace5f7ef108e6848eee4c625f4ca2",
"contentHash": "dd56fb70039aae53c1b2b4fcc302cbe5c870de5bcf99419ce9aec09bfad545b5",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_12c937e1cc34dd62ed17b7bf",
"benchmarkSetId": "7390a9c2522b1c81605e80a42a8de7c7ad9a5797d028633b54904bc78f091bb8",
"targetId": "n5-03978",
"moleculeId": "sa_ae9ab0bb73d493577873fa4b",
"smiles": "CC(C)(C)OC(=O)NC1(C(=O)N[C@@H](Cc2ccc(-c3cccc(OS(C)(=O)=O)c3)cc2)C(N)=O)CCOCC1",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_ae9ab0bb73d493577873fa4b",
"inchikey": "UFMYEYREBOGNBR-QFIPXVFZSA-N",
"smiles": "CC(C)(C)OC(=O)NC1(C(=O)N[C@@H](Cc2ccc(-c3cccc(OS(C)(=O)=O)c3)cc2)C(N)=O)CCOCC1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "2465",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_ae9ab0bb73d493577873fa4b",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_ae9ab0bb73d493577873fa4b",
"inchikey": "UFMYEYREBOGNBR-QFIPXVFZSA-N",
"smiles": "CC(C)(C)OC(=O)NC1(C(=O)N[C@@H](Cc2ccc(-c3cccc(OS(C)(=O)=O)c3)cc2)C(N)=O)CCOCC1"
},
"smiles": "CC(C)(C)OC(=O)NC1(C(=O)N[C@@H](Cc2ccc(-c3cccc(OS(C)(=O)=O)c3)cc2)C(N)=O)CCOCC1",
"reactionStepId": "sa_86e968be4734ea5d2a77a8bd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100286118A1;0393;969974\",\"rsmi\":\"I[c:18]1[cH:17][cH:16][c:15]([CH2:14][C@H:13]([NH:12][C:10]([C:9]2([NH:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:35][CH2:36][O:37][CH2:38][CH2:39]2)=[O:11])[C:32]([NH2:33])=[O:34])[cH:31][cH:30]1.OB(O)[c:19]1[cH:20][c:21]([O:22][S:23]([CH3:24])(=[O:25])=[O:26])[cH:27][cH:28][cH:29]1>CC#N.O.O=C(O)O.[K+].[K+]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C:9]1([C:10](=[O:11])[NH:12][C@@H:13]([CH2:14][c:15]2[cH:16][cH:17][c:18](-[c:19]3[cH:20][c:21]([O:22][S:23]([CH3:24])(=[O:25])=[O:26])[cH:27][cH:28][cH:29]3)[cH:30][cH:31]2)[C:32]([NH2:33])=[O:34])[CH2:35][CH2:36][O:37][CH2:38][CH2:39]1\"},\"mapped_reaction_smiles\":\"I[c:18]1[cH:17][cH:16][c:15]([CH2:14][C@H:13]([NH:12][C:10]([C:9]2([NH:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:35][CH2:36][O:37][CH2:38][CH2:39]2)=[O:11])[C:32]([NH2:33])=[O:34])[cH:31][cH:30]1.OB(O)[c:19]1[cH:20][c:21]([O:22][S:23]([CH3:24])(=[O:25])=[O:26])[cH:27][cH:28][cH:29]1>CC#N.O.O=C(O)O.[K+].[K+]>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C:9]1([C:10](=[O:11])[NH:12][C@@H:13]([CH2:14][c:15]2[cH:16][cH:17][c:18](-[c:19]3[cH:20][c:21]([O:22][S:23]([CH3:24])(=[O:25])=[O:26])[cH:27][cH:28][cH:29]3)[cH:30][cH:31]2)[C:32]([NH2:33])=[O:34])[CH2:35][CH2:36][O:37][CH2:38][CH2:39]1\"}",
"reactionStep": {
"id": "sa_86e968be4734ea5d2a77a8bd",
"reactionHash": "a9850a38402788ad771476c7057a1a2197e37d468ab8db65cea4b61c13a13f06"
},
"children": [
{
"id": "2466",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_003aaac270ce0d23213e8837",
"parentId": "2465",
"isLeaf": false,
"molecule": {
"id": "sa_003aaac270ce0d23213e8837",
"inchikey": "GHNNPRUUZNXUGI-HNNXBMFYSA-N",
"smiles": "CC(C)(C)OC(=O)NC1(C(=O)N[C@@H](Cc2ccc(I)cc2)C(N)=O)CCOCC1"
},
"smiles": "CC(C)(C)OC(=O)NC1(C(=O)N[C@@H](Cc2ccc(I)cc2)C(N)=O)CCOCC1",
"reactionStepId": "sa_146b1254da96e5fbc7c4f647",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100286118A1;0628;970027\",\"rsmi\":\"O[C:10]([C:9]1([NH:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:25][CH2:26][O:27][CH2:28][CH2:29]1)=[O:11].[NH2:12][C@@H:13]([CH2:14][c:15]1[cH:16][cH:17][c:18]([I:19])[cH:20][cH:21]1)[C:22]([NH2:23])=[O:24]>CCCP1(=O)OP(=O)(CCC)OP(=O)(CCC)O1.CCN(C(C)C)C(C)C.CN(C)C=O>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C:9]1([C:10](=[O:11])[NH:12][C@@H:13]([CH2:14][c:15]2[cH:16][cH:17][c:18]([I:19])[cH:20][cH:21]2)[C:22]([NH2:23])=[O:24])[CH2:25][CH2:26][O:27][CH2:28][CH2:29]1\"},\"mapped_reaction_smiles\":\"O[C:10]([C:9]1([NH:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:25][CH2:26][O:27][CH2:28][CH2:29]1)=[O:11].[NH2:12][C@@H:13]([CH2:14][c:15]1[cH:16][cH:17][c:18]([I:19])[cH:20][cH:21]1)[C:22]([NH2:23])=[O:24]>CCCP1(=O)OP(=O)(CCC)OP(=O)(CCC)O1.CCN(C(C)C)C(C)C.CN(C)C=O>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C:9]1([C:10](=[O:11])[NH:12][C@@H:13]([CH2:14][c:15]2[cH:16][cH:17][c:18]([I:19])[cH:20][cH:21]2)[C:22]([NH2:23])=[O:24])[CH2:25][CH2:26][O:27][CH2:28][CH2:29]1\"}",
"reactionStep": {
"id": "sa_146b1254da96e5fbc7c4f647",
"reactionHash": "c8ad34b4ec1ea8c88d78d9a99d2ef3f8c08181c5d019e73072f5e8dc553ae2f2"
},
"children": [
{
"id": "2467",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_703716157a64692ba1482f3e",
"parentId": "2466",
"isLeaf": false,
"molecule": {
"id": "sa_703716157a64692ba1482f3e",
"inchikey": "AQQGIRLSOBZONA-QMMMGPOBSA-N",
"smiles": "NC(=O)[C@@H](N)Cc1ccc(I)cc1"
},
"smiles": "NC(=O)[C@@H](N)Cc1ccc(I)cc1",
"reactionStepId": "sa_4dd38a695d2fcd158d90f7fd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100286118A1;0234;969943\",\"rsmi\":\"CC(C)(C)OC(=O)[NH:5][C@H:4]([C:2]([NH2:1])=[O:3])[CH2:6][c:7]1[cH:8][cH:9][c:10]([I:11])[cH:12][cH:13]1>ClCCl.O=C(O)C(F)(F)F>[NH2:1][C:2](=[O:3])[C@@H:4]([NH2:5])[CH2:6][c:7]1[cH:8][cH:9][c:10]([I:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"CC(C)(C)OC(=O)[NH:5][C@H:4]([C:2]([NH2:1])=[O:3])[CH2:6][c:7]1[cH:8][cH:9][c:10]([I:11])[cH:12][cH:13]1>ClCCl.O=C(O)C(F)(F)F>[NH2:1][C:2](=[O:3])[C@@H:4]([NH2:5])[CH2:6][c:7]1[cH:8][cH:9][c:10]([I:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_4dd38a695d2fcd158d90f7fd",
"reactionHash": "9646b178d7b648221353662d7f59dbd0c01c21835841a09efa5c17e1456935e0"
},
"children": [
{
"id": "2468",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_7f350cddf4590791a186a1f4",
"parentId": "2467",
"isLeaf": false,
"molecule": {
"id": "sa_7f350cddf4590791a186a1f4",
"inchikey": "FGLIDWYLHHPLPF-NSHDSACASA-N",
"smiles": "CC(C)(C)OC(=O)N[C@@H](Cc1ccc(I)cc1)C(N)=O"
},
"smiles": "CC(C)(C)OC(=O)N[C@@H](Cc1ccc(I)cc1)C(N)=O",
"reactionStepId": "sa_7f6dc72a9d97d2d738309ae5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100286118A1;0267;969947\",\"rsmi\":\"O[C:18]([C@@H:9]([NH:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:10][c:11]1[cH:12][cH:13][c:14]([I:15])[cH:16][cH:17]1)=[O:20].[NH3:19]>CCN1CCOCC1.CN(C)C(On1nnc2ccccc21)=[N+](C)C.CN(C)C=O.F[B-](F)(F)F.O>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C@@H:9]([CH2:10][c:11]1[cH:12][cH:13][c:14]([I:15])[cH:16][cH:17]1)[C:18]([NH2:19])=[O:20]\"},\"mapped_reaction_smiles\":\"O[C:18]([C@@H:9]([NH:8][C:6]([O:5][C:2]([CH3:1])([CH3:3])[CH3:4])=[O:7])[CH2:10][c:11]1[cH:12][cH:13][c:14]([I:15])[cH:16][cH:17]1)=[O:20].[NH3:19]>CCN1CCOCC1.CN(C)C(On1nnc2ccccc21)=[N+](C)C.CN(C)C=O.F[B-](F)(F)F.O>[CH3:1][C:2]([CH3:3])([CH3:4])[O:5][C:6](=[O:7])[NH:8][C@@H:9]([CH2:10][c:11]1[cH:12][cH:13][c:14]([I:15])[cH:16][cH:17]1)[C:18]([NH2:19])=[O:20]\"}",
"reactionStep": {
"id": "sa_7f6dc72a9d97d2d738309ae5",
"reactionHash": "58a1f06fd9a377be43b46e62f37ad5878de0c4657486af4ffcdd0e583e01bfda"
},
"children": [
{
"id": "2469",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_7e5b2acdd2ea8e0692a23ac3",
"parentId": "2468",
"isLeaf": true,
"molecule": {
"id": "sa_7e5b2acdd2ea8e0692a23ac3",
"inchikey": "JZLZDBGQWRBTHN-NSHDSACASA-N",
"smiles": "CC(C)(C)OC(=O)N[C@@H](Cc1ccc(I)cc1)C(=O)O"
},
"smiles": "CC(C)(C)OC(=O)N[C@@H](Cc1ccc(I)cc1)C(=O)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "2470",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_c9679fdd876f32f86b77fb69",
"parentId": "2468",
"isLeaf": true,
"molecule": {
"id": "sa_c9679fdd876f32f86b77fb69",
"inchikey": "QGZKDVFQNNGYKY-UHFFFAOYSA-N",
"smiles": "N"
},
"smiles": "N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "2471",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_25ae57131d4b29d922799be2",
"parentId": "2466",
"isLeaf": true,
"molecule": {
"id": "sa_25ae57131d4b29d922799be2",
"inchikey": "SPPDKPRJPFTBEV-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(O)=NC1(C(=O)O)CCOCC1"
},
"smiles": "CC(C)(C)OC(=O)NC1(C(=O)O)CCOCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "2472",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_a334fb0675997e5c63e19c8d",
"parentId": "2465",
"isLeaf": false,
"molecule": {
"id": "sa_a334fb0675997e5c63e19c8d",
"inchikey": "YPTSULVFDYITAQ-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)Oc1cccc(B(O)O)c1"
},
"smiles": "CS(=O)(=O)Oc1cccc(B(O)O)c1",
"reactionStepId": "sa_ffda3d765498a06601606f2e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100286118A1;0390;969973\",\"rsmi\":\"Cl[S:2]([CH3:1])(=[O:3])=[O:4].[OH:5][c:6]1[cH:7][cH:8][cH:9][c:10]([B:11]([OH:12])[OH:13])[cH:14]1>CCOC(C)=O.O.c1ccncc1>[CH3:1][S:2](=[O:3])(=[O:4])[O:5][c:6]1[cH:7][cH:8][cH:9][c:10]([B:11]([OH:12])[OH:13])[cH:14]1\"},\"mapped_reaction_smiles\":\"Cl[S:2]([CH3:1])(=[O:3])=[O:4].[OH:5][c:6]1[cH:7][cH:8][cH:9][c:10]([B:11]([OH:12])[OH:13])[cH:14]1>CCOC(C)=O.O.c1ccncc1>[CH3:1][S:2](=[O:3])(=[O:4])[O:5][c:6]1[cH:7][cH:8][cH:9][c:10]([B:11]([OH:12])[OH:13])[cH:14]1\"}",
"reactionStep": {
"id": "sa_ffda3d765498a06601606f2e",
"reactionHash": "ed34a0d6183090f6bcf2367ddff0e740caf20db97b1650ae27c49df785653cea"
},
"children": [
{
"id": "2473",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "2472",
"isLeaf": true,
"molecule": {
"id": "sa_d2a31ea58046b00856f61ca5",
"inchikey": "QARBMVPHQWIHKH-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)Cl"
},
"smiles": "CS(=O)(=O)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "2474",
"routeId": "sa_97a19d13346db1c53b6edf67",
"moleculeId": "sa_efcfbf76c9cd0c3311305435",
"parentId": "2472",
"isLeaf": true,
"molecule": {
"id": "sa_efcfbf76c9cd0c3311305435",
"inchikey": "WFWQWTPAPNEOFE-UHFFFAOYSA-N",
"smiles": "OB(O)c1cccc(O)c1"
},
"smiles": "OB(O)c1cccc(O)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}