Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1ccccc1-c1noc(-c2ccc(N3CCOCC3)c(C)c2)n1
InChiKey
SDENUICKKROWCC-UHFFFAOYSA-N
Route Signature
ce5438cb19866bfd4f88f545201641b10f6cd4cb301a3ad8ff060023c88160af
Synthesis route with 3 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_30dac2d2881af908e3864ebb",
"signature": "ce5438cb19866bfd4f88f545201641b10f6cd4cb301a3ad8ff060023c88160af",
"contentHash": "a343feedde16a9151830f0d5d1aa2081988a6dc5094da8b8de71b9748ce4b462",
"length": 3,
"isConvergent": true
},
"target": {
"id": "sa_8d697e023c8b89516f575f06",
"benchmarkSetId": "7390a9c2522b1c81605e80a42a8de7c7ad9a5797d028633b54904bc78f091bb8",
"targetId": "n5-05610",
"moleculeId": "sa_16a42ec72c6805bdc7b491b4",
"smiles": "COc1ccccc1-c1noc(-c2ccc(N3CCOCC3)c(C)c2)n1",
"routeLength": 3,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_16a42ec72c6805bdc7b491b4",
"inchikey": "SDENUICKKROWCC-UHFFFAOYSA-N",
"smiles": "COc1ccccc1-c1noc(-c2ccc(N3CCOCC3)c(C)c2)n1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 4
},
"rootNode": {
"id": "2849",
"routeId": "sa_30dac2d2881af908e3864ebb",
"moleculeId": "sa_16a42ec72c6805bdc7b491b4",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_16a42ec72c6805bdc7b491b4",
"inchikey": "SDENUICKKROWCC-UHFFFAOYSA-N",
"smiles": "COc1ccccc1-c1noc(-c2ccc(N3CCOCC3)c(C)c2)n1"
},
"smiles": "COc1ccccc1-c1noc(-c2ccc(N3CCOCC3)c(C)c2)n1",
"reactionStepId": "sa_e299c333bfc1abb29f583ceb",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20130109676A1;0577;1361143\",\"rsmi\":\"O=[C:8](O)[c:9]1[cH:10][c:11]([CH3:12])[c:13]([N:14]2[CH2:15][CH2:16][O:17][CH2:18][CH2:19]2)[cH:20][cH:21]1.[CH3:1][O:2][c:3]1[c:4]([C:5](=[N:6][OH:7])[NH2:22])[cH:23][cH:24][cH:25][cH:26]1>CCN(C(C)C)C(C)C.O=C(Cl)C(=O)Cl>[CH3:1][O:2][c:3]1[c:4](-[c:5]2[n:6][o:7][c:8](-[c:9]3[cH:10][c:11]([CH3:12])[c:13]([N:14]4[CH2:15][CH2:16][O:17][CH2:18][CH2:19]4)[cH:20][cH:21]3)[n:22]2)[cH:23][cH:24][cH:25][cH:26]1\"},\"mapped_reaction_smiles\":\"O=[C:8](O)[c:9]1[cH:10][c:11]([CH3:12])[c:13]([N:14]2[CH2:15][CH2:16][O:17][CH2:18][CH2:19]2)[cH:20][cH:21]1.[CH3:1][O:2][c:3]1[c:4]([C:5](=[N:6][OH:7])[NH2:22])[cH:23][cH:24][cH:25][cH:26]1>CCN(C(C)C)C(C)C.O=C(Cl)C(=O)Cl>[CH3:1][O:2][c:3]1[c:4](-[c:5]2[n:6][o:7][c:8](-[c:9]3[cH:10][c:11]([CH3:12])[c:13]([N:14]4[CH2:15][CH2:16][O:17][CH2:18][CH2:19]4)[cH:20][cH:21]3)[n:22]2)[cH:23][cH:24][cH:25][cH:26]1\"}",
"reactionStep": {
"id": "sa_e299c333bfc1abb29f583ceb",
"reactionHash": "b1498e4ae18f7dcd74c39f22557f0896afa2f1f5ac724c9f5444883c94f2c689"
},
"children": [
{
"id": "2850",
"routeId": "sa_30dac2d2881af908e3864ebb",
"moleculeId": "sa_7ef326d1e095bd9552244518",
"parentId": "2849",
"isLeaf": false,
"molecule": {
"id": "sa_7ef326d1e095bd9552244518",
"inchikey": "NFAJEYBUPFIZNQ-UHFFFAOYSA-N",
"smiles": "COc1ccccc1/C(N)=N/O"
},
"smiles": "COc1ccccc1C(N)=NO",
"reactionStepId": "sa_af092ac49ac882d42164d910",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20130109676A1;0222;1361062\",\"rsmi\":\"[CH3:1][O:2][c:3]1[c:4]([C:5]#[N:6])[cH:9][cH:10][cH:11][cH:12]1.[NH2:7][OH:8]>CCO>[CH3:1][O:2][c:3]1[c:4]([C:5]([NH2:6])=[N:7][OH:8])[cH:9][cH:10][cH:11][cH:12]1\"},\"mapped_reaction_smiles\":\"[CH3:1][O:2][c:3]1[c:4]([C:5]#[N:6])[cH:9][cH:10][cH:11][cH:12]1.[NH2:7][OH:8]>CCO>[CH3:1][O:2][c:3]1[c:4]([C:5]([NH2:6])=[N:7][OH:8])[cH:9][cH:10][cH:11][cH:12]1\"}",
"reactionStep": {
"id": "sa_af092ac49ac882d42164d910",
"reactionHash": "66cb7ffd28962e2cf7bca2ade395ba734a409c427dec4c0e3d757c4928e2f8b0"
},
"children": [
{
"id": "2851",
"routeId": "sa_30dac2d2881af908e3864ebb",
"moleculeId": "sa_04a18e3f07bde82ca29399ee",
"parentId": "2850",
"isLeaf": true,
"molecule": {
"id": "sa_04a18e3f07bde82ca29399ee",
"inchikey": "AVXURJPOCDRRFD-UHFFFAOYSA-N",
"smiles": "NO"
},
"smiles": "NO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "2852",
"routeId": "sa_30dac2d2881af908e3864ebb",
"moleculeId": "sa_dfd5c3e8806733e49aa34ea0",
"parentId": "2850",
"isLeaf": true,
"molecule": {
"id": "sa_dfd5c3e8806733e49aa34ea0",
"inchikey": "FSTPMFASNVISBU-UHFFFAOYSA-N",
"smiles": "COc1ccccc1C#N"
},
"smiles": "COc1ccccc1C#N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "2853",
"routeId": "sa_30dac2d2881af908e3864ebb",
"moleculeId": "sa_8f0bb7842be188fde417d409",
"parentId": "2849",
"isLeaf": false,
"molecule": {
"id": "sa_8f0bb7842be188fde417d409",
"inchikey": "WFJKSKWRBZDCKE-UHFFFAOYSA-N",
"smiles": "Cc1cc(C(=O)O)ccc1N1CCOCC1"
},
"smiles": "Cc1cc(C(=O)O)ccc1N1CCOCC1",
"reactionStepId": "sa_aedd129b469641e370974671",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20130109676A1;0343;1361095\",\"rsmi\":\"C[O:15][C:13]([c:12]1[cH:11][cH:10][c:3]([N:4]2[CH2:5][CH2:6][O:7][CH2:8][CH2:9]2)[c:2]([CH3:1])[cH:16]1)=[O:14]>C1CCOC1.O.[Li+].O>[CH3:1][c:2]1[c:3]([N:4]2[CH2:5][CH2:6][O:7][CH2:8][CH2:9]2)[cH:10][cH:11][c:12]([C:13](=[O:14])[OH:15])[cH:16]1\"},\"mapped_reaction_smiles\":\"C[O:15][C:13]([c:12]1[cH:11][cH:10][c:3]([N:4]2[CH2:5][CH2:6][O:7][CH2:8][CH2:9]2)[c:2]([CH3:1])[cH:16]1)=[O:14]>C1CCOC1.O.[Li+].O>[CH3:1][c:2]1[c:3]([N:4]2[CH2:5][CH2:6][O:7][CH2:8][CH2:9]2)[cH:10][cH:11][c:12]([C:13](=[O:14])[OH:15])[cH:16]1\"}",
"reactionStep": {
"id": "sa_aedd129b469641e370974671",
"reactionHash": "b06baeba8a913352689c3158e395711b60afa7fb07f72fc0fcb1aa741c53ebc5"
},
"children": [
{
"id": "2854",
"routeId": "sa_30dac2d2881af908e3864ebb",
"moleculeId": "sa_4fcdc6588f1ecd5a49ffa7f3",
"parentId": "2853",
"isLeaf": false,
"molecule": {
"id": "sa_4fcdc6588f1ecd5a49ffa7f3",
"inchikey": "PUWGRZKIWMAQQD-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(N2CCOCC2)c(C)c1"
},
"smiles": "COC(=O)c1ccc(N2CCOCC2)c(C)c1",
"reactionStepId": "sa_ead9a58ce9fbf16861e3f0b4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20130109676A1;0341;1361094\",\"rsmi\":\"Br[c:9]1[c:7]([CH3:8])[cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:17][cH:16]1.[NH:10]1[CH2:11][CH2:12][O:13][CH2:14][CH2:15]1>C1COCCO1.CC(=O)O.CC(=O)O.O=C(O)O.[Cs+].[Cs+].[Pd+2].c1ccc(P(c2ccccc2)c2ccc3ccccc3c2-c2c(P(c3ccccc3)c3ccccc3)ccc3ccccc23)cc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([CH3:8])[c:9]([N:10]2[CH2:11][CH2:12][O:13][CH2:14][CH2:15]2)[cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"Br[c:9]1[c:7]([CH3:8])[cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:17][cH:16]1.[NH:10]1[CH2:11][CH2:12][O:13][CH2:14][CH2:15]1>C1COCCO1.CC(=O)O.CC(=O)O.O=C(O)O.[Cs+].[Cs+].[Pd+2].c1ccc(P(c2ccccc2)c2ccc3ccccc3c2-c2c(P(c3ccccc3)c3ccccc3)ccc3ccccc23)cc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([CH3:8])[c:9]([N:10]2[CH2:11][CH2:12][O:13][CH2:14][CH2:15]2)[cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_ead9a58ce9fbf16861e3f0b4",
"reactionHash": "876fb833a051b8dab74b438169d586787f0f20ad3544fb23a032dacaadf225e0"
},
"children": [
{
"id": "2855",
"routeId": "sa_30dac2d2881af908e3864ebb",
"moleculeId": "sa_8d0b36724811920116bcf228",
"parentId": "2854",
"isLeaf": true,
"molecule": {
"id": "sa_8d0b36724811920116bcf228",
"inchikey": "GTZTYNPAPQKIIR-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(Br)c(C)c1"
},
"smiles": "COC(=O)c1ccc(Br)c(C)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "2856",
"routeId": "sa_30dac2d2881af908e3864ebb",
"moleculeId": "sa_39d71c291f7fdf13918cc969",
"parentId": "2854",
"isLeaf": true,
"molecule": {
"id": "sa_39d71c291f7fdf13918cc969",
"inchikey": "YNAVUWVOSKDBBP-UHFFFAOYSA-N",
"smiles": "C1COCCN1"
},
"smiles": "C1COCCN1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}