Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COC(=O)C(C)n1ccc2cc(OCCCOc3ccc(C(N)=S)cn3)ccc21
InChiKey
XPJLXCYHNHHXIU-UHFFFAOYSA-N
Route Signature
c7271a50945e218473475dbb50de04880b88451d1def7f155fbb0fe479cd90f5
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_255afd640017df68db28761f",
"signature": "c7271a50945e218473475dbb50de04880b88451d1def7f155fbb0fe479cd90f5",
"contentHash": "5a4d8c5e10bbd48761be3f2925674677ec6147d51776f5ae62b80af553d6244a",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_5a67fdbd203a429770348181",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-02300",
"moleculeId": "sa_147372ee55e0436fe9a76873",
"smiles": "COC(=O)C(C)n1ccc2cc(OCCCOc3ccc(C(N)=S)cn3)ccc21",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_147372ee55e0436fe9a76873",
"inchikey": "XPJLXCYHNHHXIU-UHFFFAOYSA-N",
"smiles": "COC(=O)C(C)n1ccc2cc(OCCCOc3ccc(C(N)=S)cn3)ccc21"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "10693",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_147372ee55e0436fe9a76873",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_147372ee55e0436fe9a76873",
"inchikey": "XPJLXCYHNHHXIU-UHFFFAOYSA-N",
"smiles": "COC(=O)C(C)n1ccc2cc(OCCCOc3ccc(C(N)=S)cn3)ccc21"
},
"smiles": "COC(=O)C(C)n1ccc2cc(OCCCOc3ccc(C(N)=S)cn3)ccc21",
"reactionStepId": "sa_ba29e6fa427b131fbec5f839",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090298854A1;0387;798893\",\"rsmi\":\"[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][CH2:15][CH2:16][O:17][c:18]3[n:19][cH:20][c:21]([C:22]#[N:23])[cH:25][cH:26]3)[cH:27][cH:28][c:29]12.[SH2:24]>CCNCC.CN(C)C=O>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][CH2:15][CH2:16][O:17][c:18]3[n:19][cH:20][c:21]([C:22]([NH2:23])=[S:24])[cH:25][cH:26]3)[cH:27][cH:28][c:29]12\"},\"mapped_reaction_smiles\":\"[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][CH2:15][CH2:16][O:17][c:18]3[n:19][cH:20][c:21]([C:22]#[N:23])[cH:25][cH:26]3)[cH:27][cH:28][c:29]12.[SH2:24]>CCNCC.CN(C)C=O>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][CH2:15][CH2:16][O:17][c:18]3[n:19][cH:20][c:21]([C:22]([NH2:23])=[S:24])[cH:25][cH:26]3)[cH:27][cH:28][c:29]12\"}",
"reactionStep": {
"id": "sa_ba29e6fa427b131fbec5f839",
"reactionHash": "fa4d6e23c61f69e1859fdf49ae746d36514c2b51b1f61e543059cf0cc42f6fd3"
},
"children": [
{
"id": "10694",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_d5fd173a5c174d54e424ac84",
"parentId": "10693",
"isLeaf": true,
"molecule": {
"id": "sa_d5fd173a5c174d54e424ac84",
"inchikey": "RWSOTUBLDIXVET-UHFFFAOYSA-N",
"smiles": "S"
},
"smiles": "S",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10695",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_b7c4a4922333b95ed2276896",
"parentId": "10693",
"isLeaf": false,
"molecule": {
"id": "sa_b7c4a4922333b95ed2276896",
"inchikey": "UDUUYGSDMHEREE-UHFFFAOYSA-N",
"smiles": "COC(=O)C(C)n1ccc2cc(OCCCOc3ccc(C#N)cn3)ccc21"
},
"smiles": "COC(=O)C(C)n1ccc2cc(OCCCOc3ccc(C#N)cn3)ccc21",
"reactionStepId": "sa_e81f7bd7d36bc91a7460f747",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090298854A1;0385;798892\",\"rsmi\":\"O[c:12]1[cH:11][c:10]2[cH:9][cH:8][n:7]([CH:5]([C:3]([O:2][CH3:1])=[O:4])[CH3:6])[c:28]2[cH:27][cH:26]1.[OH:13][CH2:14][CH2:15][CH2:16][O:17][c:18]1[n:19][cH:20][c:21]([C:22]#[N:23])[cH:24][cH:25]1>ClCCl.O=C(N=NC(=O)N1CCCCC1)N1CCCCC1.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][CH2:15][CH2:16][O:17][c:18]3[n:19][cH:20][c:21]([C:22]#[N:23])[cH:24][cH:25]3)[cH:26][cH:27][c:28]12\"},\"mapped_reaction_smiles\":\"O[c:12]1[cH:11][c:10]2[cH:9][cH:8][n:7]([CH:5]([C:3]([O:2][CH3:1])=[O:4])[CH3:6])[c:28]2[cH:27][cH:26]1.[OH:13][CH2:14][CH2:15][CH2:16][O:17][c:18]1[n:19][cH:20][c:21]([C:22]#[N:23])[cH:24][cH:25]1>ClCCl.O=C(N=NC(=O)N1CCCCC1)N1CCCCC1.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][CH2:15][CH2:16][O:17][c:18]3[n:19][cH:20][c:21]([C:22]#[N:23])[cH:24][cH:25]3)[cH:26][cH:27][c:28]12\"}",
"reactionStep": {
"id": "sa_e81f7bd7d36bc91a7460f747",
"reactionHash": "ace14b309c597f0db29b8db250e3e13e1e8e1e9e7b038394b6baec8f74ff9151"
},
"children": [
{
"id": "10696",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_fb3c2db35c9bd3f74b7bc93a",
"parentId": "10695",
"isLeaf": false,
"molecule": {
"id": "sa_fb3c2db35c9bd3f74b7bc93a",
"inchikey": "CTBJVXRDMYHRFU-UHFFFAOYSA-N",
"smiles": "COC(=O)C(C)n1ccc2cc(O)ccc21"
},
"smiles": "COC(=O)C(C)n1ccc2cc(O)ccc21",
"reactionStepId": "sa_8d255d9e37124d6f8783a949",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090298854A1;0242;798854\",\"rsmi\":\"c1ccc(C[O:13][c:12]2[cH:11][c:10]3[cH:9][cH:8][n:7]([CH:5]([C:3]([O:2][CH3:1])=[O:4])[CH3:6])[c:16]3[cH:15][cH:14]2)cc1>CCO.O=CO.N.O.O.[Pd+2]>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([OH:13])[cH:14][cH:15][c:16]12\"},\"mapped_reaction_smiles\":\"c1ccc(C[O:13][c:12]2[cH:11][c:10]3[cH:9][cH:8][n:7]([CH:5]([C:3]([O:2][CH3:1])=[O:4])[CH3:6])[c:16]3[cH:15][cH:14]2)cc1>CCO.O=CO.N.O.O.[Pd+2]>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([OH:13])[cH:14][cH:15][c:16]12\"}",
"reactionStep": {
"id": "sa_8d255d9e37124d6f8783a949",
"reactionHash": "97b30e3561e81bd0b31373b5b8f815659cfc97e85a03a909f8b01b3301c1dc59"
},
"children": [
{
"id": "10697",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_a2892396b81c491f9f784b85",
"parentId": "10696",
"isLeaf": false,
"molecule": {
"id": "sa_a2892396b81c491f9f784b85",
"inchikey": "VQDGYYXTLNUTIV-UHFFFAOYSA-N",
"smiles": "COC(=O)C(C)n1ccc2cc(OCc3ccccc3)ccc21"
},
"smiles": "COC(=O)C(C)n1ccc2cc(OCc3ccccc3)ccc21",
"reactionStepId": "sa_43f5bd939bc27e630d18450f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090298854A1;0229;798851\",\"rsmi\":\"Br[CH:5]([C:3]([O:2][CH3:1])=[O:4])[CH3:6].[nH:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][c:15]3[cH:16][cH:17][cH:18][cH:19][cH:20]3)[cH:21][cH:22][c:23]12>CN(C)C=O.[HH].[Na+]>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][c:15]3[cH:16][cH:17][cH:18][cH:19][cH:20]3)[cH:21][cH:22][c:23]12\"},\"mapped_reaction_smiles\":\"Br[CH:5]([C:3]([O:2][CH3:1])=[O:4])[CH3:6].[nH:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][c:15]3[cH:16][cH:17][cH:18][cH:19][cH:20]3)[cH:21][cH:22][c:23]12>CN(C)C=O.[HH].[Na+]>[CH3:1][O:2][C:3](=[O:4])[CH:5]([CH3:6])[n:7]1[cH:8][cH:9][c:10]2[cH:11][c:12]([O:13][CH2:14][c:15]3[cH:16][cH:17][cH:18][cH:19][cH:20]3)[cH:21][cH:22][c:23]12\"}",
"reactionStep": {
"id": "sa_43f5bd939bc27e630d18450f",
"reactionHash": "87ffd6fd4dc1bf179eeac4422a69961b4fc4c8590cb9322284bc48f080a430f9"
},
"children": [
{
"id": "10698",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_d9c88484ede4fc96f6f53c27",
"parentId": "10697",
"isLeaf": true,
"molecule": {
"id": "sa_d9c88484ede4fc96f6f53c27",
"inchikey": "ACEONLNNWKIPTM-UHFFFAOYSA-N",
"smiles": "COC(=O)C(C)Br"
},
"smiles": "COC(=O)C(C)Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10699",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_5e621dc7ca7a29b19da88187",
"parentId": "10697",
"isLeaf": true,
"molecule": {
"id": "sa_5e621dc7ca7a29b19da88187",
"inchikey": "JCQLPDZCNSVBMS-UHFFFAOYSA-N",
"smiles": "c1ccc(COc2ccc3[nH]ccc3c2)cc1"
},
"smiles": "c1ccc(COc2ccc3[nH]ccc3c2)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "10700",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_13b7e282146ef711d6ac2eee",
"parentId": "10695",
"isLeaf": false,
"molecule": {
"id": "sa_13b7e282146ef711d6ac2eee",
"inchikey": "IIXZSCDZSAREES-UHFFFAOYSA-N",
"smiles": "N#Cc1ccc(OCCCO)nc1"
},
"smiles": "N#Cc1ccc(OCCCO)nc1",
"reactionStepId": "sa_508c15e220d1e7b4517841c5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090298854A1;0383;798891\",\"rsmi\":\"Cl[c:6]1[n:5][cH:4][c:3]([C:2]#[N:1])[cH:13][cH:12]1.[OH:7][CH2:8][CH2:9][CH2:10][OH:11]>CN(C)C=O.O.[HH].[Na+]>[N:1]#[C:2][c:3]1[cH:4][n:5][c:6]([O:7][CH2:8][CH2:9][CH2:10][OH:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"Cl[c:6]1[n:5][cH:4][c:3]([C:2]#[N:1])[cH:13][cH:12]1.[OH:7][CH2:8][CH2:9][CH2:10][OH:11]>CN(C)C=O.O.[HH].[Na+]>[N:1]#[C:2][c:3]1[cH:4][n:5][c:6]([O:7][CH2:8][CH2:9][CH2:10][OH:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_508c15e220d1e7b4517841c5",
"reactionHash": "53bab151fbb034c32b91520cf7824edb0e2639db79931d37eddf94941c19b70b"
},
"children": [
{
"id": "10701",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_f8319834b271ad351548cac1",
"parentId": "10700",
"isLeaf": true,
"molecule": {
"id": "sa_f8319834b271ad351548cac1",
"inchikey": "ORIQLMBUPMABDV-UHFFFAOYSA-N",
"smiles": "N#Cc1ccc(Cl)nc1"
},
"smiles": "N#Cc1ccc(Cl)nc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10702",
"routeId": "sa_255afd640017df68db28761f",
"moleculeId": "sa_ec3027e2a90b5027a85d1459",
"parentId": "10700",
"isLeaf": true,
"molecule": {
"id": "sa_ec3027e2a90b5027a85d1459",
"inchikey": "YPFDHNVEDLHUCE-UHFFFAOYSA-N",
"smiles": "OCCCO"
},
"smiles": "OCCCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}