Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
C[C@H]1COc2cc(C(=O)NO)ccc2CN1C(=O)C1CCN(C=O)CC1
InChiKey
VMFNCEGXMMQUKL-LBPRGKRZSA-N
Route Signature
12d76795b2cecb2d906c13b39ae6892485ddcf70b55429015e488525ab75ad55
Synthesis route with 7 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_129c54e766deea69abcb7f8c",
"signature": "12d76795b2cecb2d906c13b39ae6892485ddcf70b55429015e488525ab75ad55",
"contentHash": "2ae45c1cb5086d981969b93f40490031f4c04257ce896ed0382ee2fa0b3ce7de",
"length": 7,
"isConvergent": false
},
"target": {
"id": "sa_65b5f868a634e7b67cc4e07b",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00426",
"moleculeId": "sa_d4986cf99c003b1b6f265a3d",
"smiles": "C[C@H]1COc2cc(C(=O)NO)ccc2CN1C(=O)C1CCN(C=O)CC1",
"routeLength": 7,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_d4986cf99c003b1b6f265a3d",
"inchikey": "VMFNCEGXMMQUKL-LBPRGKRZSA-N",
"smiles": "C[C@H]1COc2cc(C(=O)NO)ccc2CN1C(=O)C1CCN(C=O)CC1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "13264",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_d4986cf99c003b1b6f265a3d",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_d4986cf99c003b1b6f265a3d",
"inchikey": "VMFNCEGXMMQUKL-LBPRGKRZSA-N",
"smiles": "C[C@H]1COc2cc(C(=O)NO)ccc2CN1C(=O)C1CCN(C=O)CC1"
},
"smiles": "C[C@H]1COc2cc(C(=O)NO)ccc2CN1C(=O)C1CCN(C=O)CC1",
"reactionStepId": "sa_18f7843f58b7bd953e650505",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160222028A1;0860;1915339\",\"rsmi\":\"CO[C:10]([c:9]1[cH:8][cH:7][c:6]2[c:5]([cH:14]1)[O:4][CH2:3][C@H:2]([CH3:1])[N:16]([C:17](=[O:18])[CH:19]1[CH2:20][CH2:21][N:22]([CH:23]=[O:24])[CH2:25][CH2:26]1)[CH2:15]2)=[O:11].[NH2:12][OH:13]>C1CCOC1.CO.[Na+].O>[CH3:1][C@H:2]1[CH2:3][O:4][c:5]2[c:6]([cH:7][cH:8][c:9]([C:10](=[O:11])[NH:12][OH:13])[cH:14]2)[CH2:15][N:16]1[C:17](=[O:18])[CH:19]1[CH2:20][CH2:21][N:22]([CH:23]=[O:24])[CH2:25][CH2:26]1\"},\"mapped_reaction_smiles\":\"CO[C:10]([c:9]1[cH:8][cH:7][c:6]2[c:5]([cH:14]1)[O:4][CH2:3][C@H:2]([CH3:1])[N:16]([C:17](=[O:18])[CH:19]1[CH2:20][CH2:21][N:22]([CH:23]=[O:24])[CH2:25][CH2:26]1)[CH2:15]2)=[O:11].[NH2:12][OH:13]>C1CCOC1.CO.[Na+].O>[CH3:1][C@H:2]1[CH2:3][O:4][c:5]2[c:6]([cH:7][cH:8][c:9]([C:10](=[O:11])[NH:12][OH:13])[cH:14]2)[CH2:15][N:16]1[C:17](=[O:18])[CH:19]1[CH2:20][CH2:21][N:22]([CH:23]=[O:24])[CH2:25][CH2:26]1\"}",
"reactionStep": {
"id": "sa_18f7843f58b7bd953e650505",
"reactionHash": "95ff29cdf5452c17f3e3391bb98dee5e446d80a59b72eff755e757e2adb251b0"
},
"children": [
{
"id": "13265",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_04a18e3f07bde82ca29399ee",
"parentId": "13264",
"isLeaf": true,
"molecule": {
"id": "sa_04a18e3f07bde82ca29399ee",
"inchikey": "AVXURJPOCDRRFD-UHFFFAOYSA-N",
"smiles": "NO"
},
"smiles": "NO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13266",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_5568d08c3d55e7e210e70ba3",
"parentId": "13264",
"isLeaf": false,
"molecule": {
"id": "sa_5568d08c3d55e7e210e70ba3",
"inchikey": "UBMBPJMOEPJBBS-ZDUSSCGKSA-N",
"smiles": "COC(=O)c1ccc2c(c1)OC[C@H](C)N(C(=O)C1CCN(C=O)CC1)C2"
},
"smiles": "COC(=O)c1ccc2c(c1)OC[C@H](C)N(C(=O)C1CCN(C=O)CC1)C2",
"reactionStepId": "sa_33b19eab79521ccd91f4eeb2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160222028A1;0858;1915338\",\"rsmi\":\"CCO[CH:19]=[O:20].[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][N:12]([C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][NH:18][CH2:21][CH2:22]1)[C@@H:23]([CH3:24])[CH2:25][O:26]2>>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][N:12]([C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][N:18]([CH:19]=[O:20])[CH2:21][CH2:22]1)[C@@H:23]([CH3:24])[CH2:25][O:26]2\"},\"mapped_reaction_smiles\":\"CCO[CH:19]=[O:20].[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][N:12]([C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][NH:18][CH2:21][CH2:22]1)[C@@H:23]([CH3:24])[CH2:25][O:26]2>>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][N:12]([C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][N:18]([CH:19]=[O:20])[CH2:21][CH2:22]1)[C@@H:23]([CH3:24])[CH2:25][O:26]2\"}",
"reactionStep": {
"id": "sa_33b19eab79521ccd91f4eeb2",
"reactionHash": "def1b022129b07acad4f1ac519a3117b668c8d6505aa94d35909295b1898763d"
},
"children": [
{
"id": "13267",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_1224d2f50c2f7f3c1abed6a5",
"parentId": "13266",
"isLeaf": false,
"molecule": {
"id": "sa_1224d2f50c2f7f3c1abed6a5",
"inchikey": "AWZCKTPQEMUWBC-LBPRGKRZSA-N",
"smiles": "COC(=O)c1ccc2c(c1)OC[C@H](C)N(C(=O)C1CCNCC1)C2"
},
"smiles": "COC(=O)c1ccc2c(c1)OC[C@H](C)N(C(=O)C1CCNCC1)C2",
"reactionStepId": "sa_ca40a61a02aa43406103456a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160222028A1;0852;1915337\",\"rsmi\":\"CC(C)(C)OC(=O)[N:18]1[CH2:17][CH2:16][CH:15]([C:13]([N:12]2[CH2:11][c:8]3[c:7]([cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:10][cH:9]3)[O:24][CH2:23][C@@H:21]2[CH3:22])=[O:14])[CH2:20][CH2:19]1>ClCCl.O=C(O)C(F)(F)F>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][N:12]([C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][NH:18][CH2:19][CH2:20]1)[C@@H:21]([CH3:22])[CH2:23][O:24]2\"},\"mapped_reaction_smiles\":\"CC(C)(C)OC(=O)[N:18]1[CH2:17][CH2:16][CH:15]([C:13]([N:12]2[CH2:11][c:8]3[c:7]([cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:10][cH:9]3)[O:24][CH2:23][C@@H:21]2[CH3:22])=[O:14])[CH2:20][CH2:19]1>ClCCl.O=C(O)C(F)(F)F>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][N:12]([C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][NH:18][CH2:19][CH2:20]1)[C@@H:21]([CH3:22])[CH2:23][O:24]2\"}",
"reactionStep": {
"id": "sa_ca40a61a02aa43406103456a",
"reactionHash": "a3720fe12cbb3cff313aebd0be92cb35be1e1ee05d9d96ffb39190074e6c2677"
},
"children": [
{
"id": "13268",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_dc52e7a08aa84f34d01c2cbc",
"parentId": "13267",
"isLeaf": false,
"molecule": {
"id": "sa_dc52e7a08aa84f34d01c2cbc",
"inchikey": "RAEWCHNBUISMBI-HNNXBMFYSA-N",
"smiles": "COC(=O)c1ccc2c(c1)OC[C@H](C)N(C(=O)C1CCN(C(=O)OC(C)(C)C)CC1)C2"
},
"smiles": "COC(=O)c1ccc2c(c1)OC[C@H](C)N(C(=O)C1CCN(C(=O)OC(C)(C)C)CC1)C2",
"reactionStepId": "sa_c59c46db5367ead935866205",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160222028A1;0850;1915336\",\"rsmi\":\"O[C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][N:18]([C:19](=[O:20])[O:21][C:22]([CH3:23])([CH3:24])[CH3:25])[CH2:26][CH2:27]1.[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][NH:12][C@@H:28]([CH3:29])[CH2:30][O:31]2>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>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][N:12]([C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][N:18]([C:19](=[O:20])[O:21][C:22]([CH3:23])([CH3:24])[CH3:25])[CH2:26][CH2:27]1)[C@@H:28]([CH3:29])[CH2:30][O:31]2\"},\"mapped_reaction_smiles\":\"O[C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][N:18]([C:19](=[O:20])[O:21][C:22]([CH3:23])([CH3:24])[CH3:25])[CH2:26][CH2:27]1.[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][NH:12][C@@H:28]([CH3:29])[CH2:30][O:31]2>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>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][N:12]([C:13](=[O:14])[CH:15]1[CH2:16][CH2:17][N:18]([C:19](=[O:20])[O:21][C:22]([CH3:23])([CH3:24])[CH3:25])[CH2:26][CH2:27]1)[C@@H:28]([CH3:29])[CH2:30][O:31]2\"}",
"reactionStep": {
"id": "sa_c59c46db5367ead935866205",
"reactionHash": "6e118f76ad5b46f9eca43c7652ac48a0248af716186761df5af8b2fb3c4cbe12"
},
"children": [
{
"id": "13269",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_f999758ee1972150a0141711",
"parentId": "13268",
"isLeaf": false,
"molecule": {
"id": "sa_f999758ee1972150a0141711",
"inchikey": "CLMVOBREWTYAIQ-QMMMGPOBSA-N",
"smiles": "COC(=O)c1ccc2c(c1)OC[C@H](C)NC2"
},
"smiles": "COC(=O)c1ccc2c(c1)OC[C@H](C)NC2",
"reactionStepId": "sa_f69bc3d8921bf1bbba80edc8",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160222028A1;0837;1915334\",\"rsmi\":\"Br[c:7]1[cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:10][cH:9][c:8]1[CH2:11][NH:12][C@@H:13]([CH3:14])[CH2:15][OH:16]>CC(C)O.O=C(O)O.[Cu]I.[K+].[K+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][NH:12][C@@H:13]([CH3:14])[CH2:15][O:16]2\"},\"mapped_reaction_smiles\":\"Br[c:7]1[cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:10][cH:9][c:8]1[CH2:11][NH:12][C@@H:13]([CH3:14])[CH2:15][OH:16]>CC(C)O.O=C(O)O.[Cu]I.[K+].[K+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]2[c:8]([cH:9][cH:10]1)[CH2:11][NH:12][C@@H:13]([CH3:14])[CH2:15][O:16]2\"}",
"reactionStep": {
"id": "sa_f69bc3d8921bf1bbba80edc8",
"reactionHash": "23ee77bd74e5401f11fd9d5d258c1667834b7e477bada54f92e0fcac3ede2402"
},
"children": [
{
"id": "13270",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_afe2e5d95fb756f8052977f0",
"parentId": "13269",
"isLeaf": false,
"molecule": {
"id": "sa_afe2e5d95fb756f8052977f0",
"inchikey": "HEOCDEHMXDVNAC-QMMMGPOBSA-N",
"smiles": "COC(=O)c1ccc(CN[C@@H](C)CO)c(Br)c1"
},
"smiles": "COC(=O)c1ccc(CN[C@@H](C)CO)c(Br)c1",
"reactionStepId": "sa_652724ae6c1f3d4dfef477a6",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160222028A1;0835;1915333\",\"rsmi\":\"Br[CH2:10][c:9]1[c:7]([Br:8])[cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:17][cH:16]1.[NH2:11][C@@H:12]([CH3:13])[CH2:14][OH:15]>C1CCOC1.O=C(O)O.[K+].[K+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([Br:8])[c:9]([CH2:10][NH:11][C@@H:12]([CH3:13])[CH2:14][OH:15])[cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"Br[CH2:10][c:9]1[c:7]([Br:8])[cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:17][cH:16]1.[NH2:11][C@@H:12]([CH3:13])[CH2:14][OH:15]>C1CCOC1.O=C(O)O.[K+].[K+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([Br:8])[c:9]([CH2:10][NH:11][C@@H:12]([CH3:13])[CH2:14][OH:15])[cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_652724ae6c1f3d4dfef477a6",
"reactionHash": "24c9fbddf4b9c5c4b15364757194b52aa5a87909a490841c2485717ebb10cfc4"
},
"children": [
{
"id": "13271",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_15f08009c8d9968359bfe3bd",
"parentId": "13270",
"isLeaf": true,
"molecule": {
"id": "sa_15f08009c8d9968359bfe3bd",
"inchikey": "BKMMTJMQCTUHRP-VKHMYHEASA-N",
"smiles": "C[C@H](N)CO"
},
"smiles": "C[C@H](N)CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13272",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_73db80c4f2eba91baa5caa05",
"parentId": "13270",
"isLeaf": false,
"molecule": {
"id": "sa_73db80c4f2eba91baa5caa05",
"inchikey": "CFJQBNFFHMBNKQ-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(CBr)c(Br)c1"
},
"smiles": "COC(=O)c1ccc(CBr)c(Br)c1",
"reactionStepId": "sa_0f730276491d5659a1faa69d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160222028A1;0591;1915258\",\"rsmi\":\"O=C1CCC(=O)N1[Br:11].[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([Br:8])[c:9]([CH3:10])[cH:12][cH:13]1>ClC(Cl)(Cl)Cl.O=C(OOC(=O)c1ccccc1)c1ccccc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([Br:8])[c:9]([CH2:10][Br:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"O=C1CCC(=O)N1[Br:11].[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([Br:8])[c:9]([CH3:10])[cH:12][cH:13]1>ClC(Cl)(Cl)Cl.O=C(OOC(=O)c1ccccc1)c1ccccc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([Br:8])[c:9]([CH2:10][Br:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_0f730276491d5659a1faa69d",
"reactionHash": "1561a2b6ccf57aa38c114d28cd86e01a085441b7e0825852654a9d9f49086877"
},
"children": [
{
"id": "13273",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_4eb1b6355dc51931e0dcc650",
"parentId": "13272",
"isLeaf": true,
"molecule": {
"id": "sa_4eb1b6355dc51931e0dcc650",
"inchikey": "MASRAGFWFYHMFI-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(C)c(Br)c1"
},
"smiles": "COC(=O)c1ccc(C)c(Br)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13274",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_ccdcf23ac83e7a68bfa4f2e5",
"parentId": "13272",
"isLeaf": true,
"molecule": {
"id": "sa_ccdcf23ac83e7a68bfa4f2e5",
"inchikey": "PCLIMKBDDGJMGD-UHFFFAOYSA-N",
"smiles": "O=C1CCC(=O)N1Br"
},
"smiles": "O=C1CCC(=O)N1Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "13275",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_dc27c9e8a13a89af1784a25f",
"parentId": "13268",
"isLeaf": true,
"molecule": {
"id": "sa_dc27c9e8a13a89af1784a25f",
"inchikey": "JWOHBPPVVDQMKB-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)N1CCC(C(=O)O)CC1"
},
"smiles": "CC(C)(C)OC(=O)N1CCC(C(=O)O)CC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "13276",
"routeId": "sa_129c54e766deea69abcb7f8c",
"moleculeId": "sa_fe35c93b34b37939ff23116d",
"parentId": "13266",
"isLeaf": true,
"molecule": {
"id": "sa_fe35c93b34b37939ff23116d",
"inchikey": "WBJINCZRORDGAQ-UHFFFAOYSA-N",
"smiles": "CCOC=O"
},
"smiles": "CCOC=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}