Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)Nc2ccncc2)CC1
InChiKey
YKTYZNUZNWZMQO-SHTZXODSSA-N
Route Signature
734d54f20a7aa0a12f6bd16999c46c0a55e46657d02578c0d4ab053ef88e63a3
Synthesis route with 7 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_31733705e4ccbec8eae81c3e",
"signature": "734d54f20a7aa0a12f6bd16999c46c0a55e46657d02578c0d4ab053ef88e63a3",
"contentHash": "acb72f65d178302836667cb2a0e276a9e2289b995e5b2e1cec8945a9c0f68689",
"length": 7,
"isConvergent": false
},
"target": {
"id": "sa_dd9dcaef02a944e0d87464fd",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00181",
"moleculeId": "sa_691dc96540e906dd4b906d9c",
"smiles": "COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)Nc2ccncc2)CC1",
"routeLength": 7,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_691dc96540e906dd4b906d9c",
"inchikey": "YKTYZNUZNWZMQO-SHTZXODSSA-N",
"smiles": "COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)Nc2ccncc2)CC1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "12667",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_691dc96540e906dd4b906d9c",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_691dc96540e906dd4b906d9c",
"inchikey": "YKTYZNUZNWZMQO-SHTZXODSSA-N",
"smiles": "COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)Nc2ccncc2)CC1"
},
"smiles": "COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)Nc2ccncc2)CC1",
"reactionStepId": "sa_ca93238b2d261edb6684e4e6",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140005164A1;0235;1467207\",\"rsmi\":\"O[C:20]([C@H:19]1[CH2:18][CH2:17][C@H:16]([CH2:15][n:14]2[c:5]3[cH:4][c:3]([O:2][CH3:1])[c:8]([F:9])[cH:7][c:6]3[n:10]([CH3:11])[c:12]2=[O:13])[CH2:30][CH2:29]1)=[O:21].[NH2:22][c:23]1[cH:24][cH:25][n:26][cH:27][cH:28]1>CN(C)C(On1nnc2cccnc21)=[N+](C)C.CN(C)C=O.F[PH](F)(F)(F)(F)F>[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[n:10]([CH3:11])[c:12](=[O:13])[n:14]2[CH2:15][C@H:16]1[CH2:17][CH2:18][C@H:19]([C:20](=[O:21])[NH:22][c:23]2[cH:24][cH:25][n:26][cH:27][cH:28]2)[CH2:29][CH2:30]1\"},\"mapped_reaction_smiles\":\"O[C:20]([C@H:19]1[CH2:18][CH2:17][C@H:16]([CH2:15][n:14]2[c:5]3[cH:4][c:3]([O:2][CH3:1])[c:8]([F:9])[cH:7][c:6]3[n:10]([CH3:11])[c:12]2=[O:13])[CH2:30][CH2:29]1)=[O:21].[NH2:22][c:23]1[cH:24][cH:25][n:26][cH:27][cH:28]1>CN(C)C(On1nnc2cccnc21)=[N+](C)C.CN(C)C=O.F[PH](F)(F)(F)(F)F>[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[n:10]([CH3:11])[c:12](=[O:13])[n:14]2[CH2:15][C@H:16]1[CH2:17][CH2:18][C@H:19]([C:20](=[O:21])[NH:22][c:23]2[cH:24][cH:25][n:26][cH:27][cH:28]2)[CH2:29][CH2:30]1\"}",
"reactionStep": {
"id": "sa_ca93238b2d261edb6684e4e6",
"reactionHash": "36717e9c166c4e0bfa4e34a822b195f5acadaf40835808fe47a513d9d0b17e6e"
},
"children": [
{
"id": "12668",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_68dd5eed4cbeb78252c17670",
"parentId": "12667",
"isLeaf": true,
"molecule": {
"id": "sa_68dd5eed4cbeb78252c17670",
"inchikey": "NUKYPUAOHBNCPY-UHFFFAOYSA-N",
"smiles": "Nc1ccncc1"
},
"smiles": "Nc1ccncc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12669",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_2c05df9b34bcbd7eee7dbab8",
"parentId": "12667",
"isLeaf": false,
"molecule": {
"id": "sa_2c05df9b34bcbd7eee7dbab8",
"inchikey": "OIEXUKHIOSAWHG-XYPYZODXSA-N",
"smiles": "COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)O)CC1"
},
"smiles": "COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)O)CC1",
"reactionStepId": "sa_ddb8b1c21d8280967ceebe40",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140005164A1;0231;1467206\",\"rsmi\":\"C[O:22][C:20]([C@H:19]1[CH2:18][CH2:17][C@H:16]([CH2:15][n:14]2[c:5]3[cH:4][c:3]([O:2][CH3:1])[c:8]([F:9])[cH:7][c:6]3[n:10]([CH3:11])[c:12]2=[O:13])[CH2:24][CH2:23]1)=[O:21]>C1CCOC1.O.[Li+].O>[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[n:10]([CH3:11])[c:12](=[O:13])[n:14]2[CH2:15][C@H:16]1[CH2:17][CH2:18][C@H:19]([C:20](=[O:21])[OH:22])[CH2:23][CH2:24]1\"},\"mapped_reaction_smiles\":\"C[O:22][C:20]([C@H:19]1[CH2:18][CH2:17][C@H:16]([CH2:15][n:14]2[c:5]3[cH:4][c:3]([O:2][CH3:1])[c:8]([F:9])[cH:7][c:6]3[n:10]([CH3:11])[c:12]2=[O:13])[CH2:24][CH2:23]1)=[O:21]>C1CCOC1.O.[Li+].O>[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[n:10]([CH3:11])[c:12](=[O:13])[n:14]2[CH2:15][C@H:16]1[CH2:17][CH2:18][C@H:19]([C:20](=[O:21])[OH:22])[CH2:23][CH2:24]1\"}",
"reactionStep": {
"id": "sa_ddb8b1c21d8280967ceebe40",
"reactionHash": "e6ce3c405d6c704bcca902d6997dbc40516cac29b9e5cf7cd6fd281e8f167d41"
},
"children": [
{
"id": "12670",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_c4b4e823377ebcbc0cceaf03",
"parentId": "12669",
"isLeaf": false,
"molecule": {
"id": "sa_c4b4e823377ebcbc0cceaf03",
"inchikey": "KEORIKDGDHVDSG-HAQNSBGRSA-N",
"smiles": "COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)OC)CC1"
},
"smiles": "COc1cc2c(cc1F)n(C)c(=O)n2C[C@H]1CC[C@H](C(=O)OC)CC1",
"reactionStepId": "sa_a363440fe6e63e680af85242",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140005164A1;0227;1467205\",\"rsmi\":\"I[CH3:11].[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[nH:10][c:12](=[O:13])[n:14]2[CH2:15][C@H:16]1[CH2:17][CH2:18][C@H:19]([C:20](=[O:21])[O:22][CH3:23])[CH2:24][CH2:25]1>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[n:10]([CH3:11])[c:12](=[O:13])[n:14]2[CH2:15][C@H:16]1[CH2:17][CH2:18][C@H:19]([C:20](=[O:21])[O:22][CH3:23])[CH2:24][CH2:25]1\"},\"mapped_reaction_smiles\":\"I[CH3:11].[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[nH:10][c:12](=[O:13])[n:14]2[CH2:15][C@H:16]1[CH2:17][CH2:18][C@H:19]([C:20](=[O:21])[O:22][CH3:23])[CH2:24][CH2:25]1>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[n:10]([CH3:11])[c:12](=[O:13])[n:14]2[CH2:15][C@H:16]1[CH2:17][CH2:18][C@H:19]([C:20](=[O:21])[O:22][CH3:23])[CH2:24][CH2:25]1\"}",
"reactionStep": {
"id": "sa_a363440fe6e63e680af85242",
"reactionHash": "1a8fbc391fc14913ad632aca7119117131e4b7ed5bd086a04f2430b8d0012671"
},
"children": [
{
"id": "12671",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_29a280a17ccef41c3067af5a",
"parentId": "12670",
"isLeaf": false,
"molecule": {
"id": "sa_29a280a17ccef41c3067af5a",
"inchikey": "DXTXDOUQMLHWJI-XYPYZODXSA-N",
"smiles": "COc1cc2c(cc1F)[nH]c(=O)n2C[C@H]1CC[C@H](C(=O)OC)CC1"
},
"smiles": "COc1cc2c(cc1F)[nH]c(=O)n2C[C@H]1CC[C@H](C(=O)OC)CC1",
"reactionStepId": "sa_3832b6425d68a9ed8a1cb9a3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140005164A1;0223;1467204\",\"rsmi\":\"ClC(Cl)(Cl)O[C:11](OC(Cl)(Cl)Cl)=[O:12].[CH3:1][O:2][c:3]1[cH:4][c:5]([NH:13][CH2:14][C@H:15]2[CH2:16][CH2:17][C@H:18]([C:19](=[O:20])[O:21][CH3:22])[CH2:23][CH2:24]2)[c:6]([NH2:10])[cH:7][c:8]1[F:9]>C1CCOC1.O>[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[nH:10][c:11](=[O:12])[n:13]2[CH2:14][C@H:15]1[CH2:16][CH2:17][C@H:18]([C:19](=[O:20])[O:21][CH3:22])[CH2:23][CH2:24]1\"},\"mapped_reaction_smiles\":\"ClC(Cl)(Cl)O[C:11](OC(Cl)(Cl)Cl)=[O:12].[CH3:1][O:2][c:3]1[cH:4][c:5]([NH:13][CH2:14][C@H:15]2[CH2:16][CH2:17][C@H:18]([C:19](=[O:20])[O:21][CH3:22])[CH2:23][CH2:24]2)[c:6]([NH2:10])[cH:7][c:8]1[F:9]>C1CCOC1.O>[CH3:1][O:2][c:3]1[cH:4][c:5]2[c:6]([cH:7][c:8]1[F:9])[nH:10][c:11](=[O:12])[n:13]2[CH2:14][C@H:15]1[CH2:16][CH2:17][C@H:18]([C:19](=[O:20])[O:21][CH3:22])[CH2:23][CH2:24]1\"}",
"reactionStep": {
"id": "sa_3832b6425d68a9ed8a1cb9a3",
"reactionHash": "10f03cd97a9eb76573da9947993e8043bcbdee12f5b64dd9a9480ed44e56aad5"
},
"children": [
{
"id": "12672",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_e099a2631f85df43ed74f652",
"parentId": "12671",
"isLeaf": false,
"molecule": {
"id": "sa_e099a2631f85df43ed74f652",
"inchikey": "RCFBIAZDUFBXFV-XYPYZODXSA-N",
"smiles": "COc1cc(NC[C@H]2CC[C@H](C(=O)OC)CC2)c(N)cc1F"
},
"smiles": "COc1cc(NC[C@H]2CC[C@H](C(=O)OC)CC2)c(N)cc1F",
"reactionStepId": "sa_00b2450739776ede0fb3c475",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140005164A1;0220;1467203\",\"rsmi\":\"O=[N+:19]([O-])[c:18]1[c:5]([NH:6][CH2:7][C@H:8]2[CH2:9][CH2:10][C@H:11]([C:12](=[O:13])[O:14][CH3:15])[CH2:16][CH2:17]2)[cH:4][c:3]([O:2][CH3:1])[c:21]([F:22])[cH:20]1>CCO.[H][H].[Pd]>[CH3:1][O:2][c:3]1[cH:4][c:5]([NH:6][CH2:7][C@H:8]2[CH2:9][CH2:10][C@H:11]([C:12](=[O:13])[O:14][CH3:15])[CH2:16][CH2:17]2)[c:18]([NH2:19])[cH:20][c:21]1[F:22]\"},\"mapped_reaction_smiles\":\"O=[N+:19]([O-])[c:18]1[c:5]([NH:6][CH2:7][C@H:8]2[CH2:9][CH2:10][C@H:11]([C:12](=[O:13])[O:14][CH3:15])[CH2:16][CH2:17]2)[cH:4][c:3]([O:2][CH3:1])[c:21]([F:22])[cH:20]1>CCO.[H][H].[Pd]>[CH3:1][O:2][c:3]1[cH:4][c:5]([NH:6][CH2:7][C@H:8]2[CH2:9][CH2:10][C@H:11]([C:12](=[O:13])[O:14][CH3:15])[CH2:16][CH2:17]2)[c:18]([NH2:19])[cH:20][c:21]1[F:22]\"}",
"reactionStep": {
"id": "sa_00b2450739776ede0fb3c475",
"reactionHash": "f039733408b8162c139b31738d27fe224493797449d6d8409dd432ef06c32cae"
},
"children": [
{
"id": "12673",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_18f3c404ade7d08d06ac1195",
"parentId": "12672",
"isLeaf": false,
"molecule": {
"id": "sa_18f3c404ade7d08d06ac1195",
"inchikey": "WSZYDUZFMDOHEJ-XYPYZODXSA-N",
"smiles": "COc1cc(NC[C@H]2CC[C@H](C(=O)OC)CC2)c([N+](=O)[O-])cc1F"
},
"smiles": "COc1cc(NC[C@H]2CC[C@H](C(=O)OC)CC2)c([N+](=O)[O-])cc1F",
"reactionStepId": "sa_60b674ea165481a29638cc06",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140005164A1;0216;1467202\",\"rsmi\":\"F[c:5]1[cH:4][c:3]([O:2][CH3:1])[c:23]([F:24])[cH:22][c:18]1[N+:19](=[O:20])[O-:21].[NH2:6][CH2:7][C@H:8]1[CH2:9][CH2:10][C@H:11]([C:12](=[O:13])[O:14][CH3:15])[CH2:16][CH2:17]1>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([NH:6][CH2:7][C@H:8]2[CH2:9][CH2:10][C@H:11]([C:12](=[O:13])[O:14][CH3:15])[CH2:16][CH2:17]2)[c:18]([N+:19](=[O:20])[O-:21])[cH:22][c:23]1[F:24]\"},\"mapped_reaction_smiles\":\"F[c:5]1[cH:4][c:3]([O:2][CH3:1])[c:23]([F:24])[cH:22][c:18]1[N+:19](=[O:20])[O-:21].[NH2:6][CH2:7][C@H:8]1[CH2:9][CH2:10][C@H:11]([C:12](=[O:13])[O:14][CH3:15])[CH2:16][CH2:17]1>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([NH:6][CH2:7][C@H:8]2[CH2:9][CH2:10][C@H:11]([C:12](=[O:13])[O:14][CH3:15])[CH2:16][CH2:17]2)[c:18]([N+:19](=[O:20])[O-:21])[cH:22][c:23]1[F:24]\"}",
"reactionStep": {
"id": "sa_60b674ea165481a29638cc06",
"reactionHash": "8cd2ff4306d124e65f4bf7e6556a6749e934fd8955eb4117a7285dd33bf343f9"
},
"children": [
{
"id": "12674",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_ae5a42d22e689b72abff20af",
"parentId": "12673",
"isLeaf": true,
"molecule": {
"id": "sa_ae5a42d22e689b72abff20af",
"inchikey": "NSIXHHAVJIMVTD-ZKCHVHJHSA-N",
"smiles": "COC(=O)[C@H]1CC[C@H](CN)CC1"
},
"smiles": "COC(=O)[C@H]1CC[C@H](CN)CC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12675",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_91fd1b99d92686a694458e6a",
"parentId": "12673",
"isLeaf": false,
"molecule": {
"id": "sa_91fd1b99d92686a694458e6a",
"inchikey": "OEODGYCZRSHEBE-UHFFFAOYSA-N",
"smiles": "COc1cc(F)c([N+](=O)[O-])cc1F"
},
"smiles": "COc1cc(F)c([N+](=O)[O-])cc1F",
"reactionStepId": "sa_f845aee6ff6a8c7418c88188",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140005164A1;0212;1467201\",\"rsmi\":\"I[CH3:1].[OH:2][c:3]1[c:4]([F:5])[cH:6][c:7]([N+:8](=[O:9])[O-:10])[c:11]([F:12])[cH:13]1>C1COCCOCCOCCOCCOCCO1.CCC(C)=O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[c:4]([F:5])[cH:6][c:7]([N+:8](=[O:9])[O-:10])[c:11]([F:12])[cH:13]1\"},\"mapped_reaction_smiles\":\"I[CH3:1].[OH:2][c:3]1[c:4]([F:5])[cH:6][c:7]([N+:8](=[O:9])[O-:10])[c:11]([F:12])[cH:13]1>C1COCCOCCOCCOCCOCCO1.CCC(C)=O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[c:4]([F:5])[cH:6][c:7]([N+:8](=[O:9])[O-:10])[c:11]([F:12])[cH:13]1\"}",
"reactionStep": {
"id": "sa_f845aee6ff6a8c7418c88188",
"reactionHash": "0c78cfd48b05c285e7e8fe1a161ed26a2326391a5441843fb162969cc9d57e2b"
},
"children": [
{
"id": "12676",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "12675",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12677",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_4214ffbef1ef23217d65e909",
"parentId": "12675",
"isLeaf": true,
"molecule": {
"id": "sa_4214ffbef1ef23217d65e909",
"inchikey": "WOQWWNJQZLYLMC-UHFFFAOYSA-N",
"smiles": "O=[N+]([O-])c1cc(F)c(O)cc1F"
},
"smiles": "O=[N+]([O-])c1cc(F)c(O)cc1F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "12678",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_229d14c9e484394c3a8786c2",
"parentId": "12671",
"isLeaf": true,
"molecule": {
"id": "sa_229d14c9e484394c3a8786c2",
"inchikey": "UCPYLLCMEDAXFR-UHFFFAOYSA-N",
"smiles": "O=C(OC(Cl)(Cl)Cl)OC(Cl)(Cl)Cl"
},
"smiles": "O=C(OC(Cl)(Cl)Cl)OC(Cl)(Cl)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "12679",
"routeId": "sa_31733705e4ccbec8eae81c3e",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "12670",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}