Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1cc(OCCCS(C)(=O)=O)ccc1N
InChiKey
WGRXXVJBRWLNAN-UHFFFAOYSA-N
Route Signature
70f85f134aafe6caa0e7960b9a1d01c25ffc27c9fc786dd4e7c2c28dc2f91d23
Synthesis route with 3 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_23912d483542051a462c1f05",
"signature": "70f85f134aafe6caa0e7960b9a1d01c25ffc27c9fc786dd4e7c2c28dc2f91d23",
"contentHash": "dc25710d3ea6c2729f7fd4f502c99b637dfacd4df22e59413462932a4e004600",
"length": 3,
"isConvergent": true
},
"target": {
"id": "sa_f9a98b9b2e040dd21ee88846",
"benchmarkSetId": "7390a9c2522b1c81605e80a42a8de7c7ad9a5797d028633b54904bc78f091bb8",
"targetId": "n5-03169",
"moleculeId": "sa_0a4b360006c2c01218343803",
"smiles": "COc1cc(OCCCS(C)(=O)=O)ccc1N",
"routeLength": 3,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_0a4b360006c2c01218343803",
"inchikey": "WGRXXVJBRWLNAN-UHFFFAOYSA-N",
"smiles": "COc1cc(OCCCS(C)(=O)=O)ccc1N"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 4
},
"rootNode": {
"id": "2122",
"routeId": "sa_23912d483542051a462c1f05",
"moleculeId": "sa_0a4b360006c2c01218343803",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_0a4b360006c2c01218343803",
"inchikey": "WGRXXVJBRWLNAN-UHFFFAOYSA-N",
"smiles": "COc1cc(OCCCS(C)(=O)=O)ccc1N"
},
"smiles": "COc1cc(OCCCS(C)(=O)=O)ccc1N",
"reactionStepId": "sa_07ceb093ec9088aafdd6f1e2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110130398A1;0707;1063577\",\"rsmi\":\"O=[N+:5]([O-])[c:4]1[c:3]([O:2][CH3:1])[cH:17][c:8]([O:9][CH2:10][CH2:11][CH2:12][S:13]([CH3:14])(=[O:15])=[O:16])[cH:7][cH:6]1>CO.[Pd]>[CH3:1][O:2][c:3]1[c:4]([NH2:5])[cH:6][cH:7][c:8]([O:9][CH2:10][CH2:11][CH2:12][S:13]([CH3:14])(=[O:15])=[O:16])[cH:17]1\"},\"mapped_reaction_smiles\":\"O=[N+:5]([O-])[c:4]1[c:3]([O:2][CH3:1])[cH:17][c:8]([O:9][CH2:10][CH2:11][CH2:12][S:13]([CH3:14])(=[O:15])=[O:16])[cH:7][cH:6]1>CO.[Pd]>[CH3:1][O:2][c:3]1[c:4]([NH2:5])[cH:6][cH:7][c:8]([O:9][CH2:10][CH2:11][CH2:12][S:13]([CH3:14])(=[O:15])=[O:16])[cH:17]1\"}",
"reactionStep": {
"id": "sa_07ceb093ec9088aafdd6f1e2",
"reactionHash": "d069343f045b1952641b4404e27b12b7d1f9447a29c479b48efa7079408af6b3"
},
"children": [
{
"id": "2123",
"routeId": "sa_23912d483542051a462c1f05",
"moleculeId": "sa_ac797b86226ceb390988daca",
"parentId": "2122",
"isLeaf": false,
"molecule": {
"id": "sa_ac797b86226ceb390988daca",
"inchikey": "QEMWOHHSPHLSTP-UHFFFAOYSA-N",
"smiles": "COc1cc(OCCCS(C)(=O)=O)ccc1[N+](=O)[O-]"
},
"smiles": "COc1cc(OCCCS(C)(=O)=O)ccc1[N+](=O)[O-]",
"reactionStepId": "sa_3de8816a80dc2b1b7ea8d002",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110130398A1;0706;1063576\",\"rsmi\":\"CS(=O)(=O)O[CH2:12][CH2:13][CH2:14][S:15]([CH3:16])(=[O:17])=[O:18].[CH3:1][O:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[cH:8][cH:9][c:10]([OH:11])[cH:19]1>CN(C)C=O.O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[cH:8][cH:9][c:10]([O:11][CH2:12][CH2:13][CH2:14][S:15]([CH3:16])(=[O:17])=[O:18])[cH:19]1\"},\"mapped_reaction_smiles\":\"CS(=O)(=O)O[CH2:12][CH2:13][CH2:14][S:15]([CH3:16])(=[O:17])=[O:18].[CH3:1][O:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[cH:8][cH:9][c:10]([OH:11])[cH:19]1>CN(C)C=O.O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[cH:8][cH:9][c:10]([O:11][CH2:12][CH2:13][CH2:14][S:15]([CH3:16])(=[O:17])=[O:18])[cH:19]1\"}",
"reactionStep": {
"id": "sa_3de8816a80dc2b1b7ea8d002",
"reactionHash": "fe94f8737f04908477627ad641e51216d9b736e02ea6e64cb31b1652ed5d6d8c"
},
"children": [
{
"id": "2124",
"routeId": "sa_23912d483542051a462c1f05",
"moleculeId": "sa_5064f2661fbdf7738237f09e",
"parentId": "2123",
"isLeaf": false,
"molecule": {
"id": "sa_5064f2661fbdf7738237f09e",
"inchikey": "BZQGPGKJLOOSFU-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)CCCOS(C)(=O)=O"
},
"smiles": "CS(=O)(=O)CCCOS(C)(=O)=O",
"reactionStepId": "sa_8d4c9d9891c3a454e867aff6",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110130398A1;0705;1063575\",\"rsmi\":\"Cl[S:9]([CH3:10])(=[O:11])=[O:12].[CH3:1][S:2](=[O:3])(=[O:4])[CH2:5][CH2:6][CH2:7][OH:8]>CCN(CC)CC.ClCCl.O>[CH3:1][S:2](=[O:3])(=[O:4])[CH2:5][CH2:6][CH2:7][O:8][S:9]([CH3:10])(=[O:11])=[O:12]\"},\"mapped_reaction_smiles\":\"Cl[S:9]([CH3:10])(=[O:11])=[O:12].[CH3:1][S:2](=[O:3])(=[O:4])[CH2:5][CH2:6][CH2:7][OH:8]>CCN(CC)CC.ClCCl.O>[CH3:1][S:2](=[O:3])(=[O:4])[CH2:5][CH2:6][CH2:7][O:8][S:9]([CH3:10])(=[O:11])=[O:12]\"}",
"reactionStep": {
"id": "sa_8d4c9d9891c3a454e867aff6",
"reactionHash": "d3206b6fe61a79bec42b57af8757e4d5c1bff4328bdcfeefe9ba095361fac7d8"
},
"children": [
{
"id": "2125",
"routeId": "sa_23912d483542051a462c1f05",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "2124",
"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": "2126",
"routeId": "sa_23912d483542051a462c1f05",
"moleculeId": "sa_ec4342ae6bd4b63f33bd3603",
"parentId": "2124",
"isLeaf": true,
"molecule": {
"id": "sa_ec4342ae6bd4b63f33bd3603",
"inchikey": "XPXXXQZNUQAFQY-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)CCCO"
},
"smiles": "CS(=O)(=O)CCCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "2127",
"routeId": "sa_23912d483542051a462c1f05",
"moleculeId": "sa_a1f2b1c9bdfdf28f9545388b",
"parentId": "2123",
"isLeaf": false,
"molecule": {
"id": "sa_a1f2b1c9bdfdf28f9545388b",
"inchikey": "VDQSACYMBGQMFC-UHFFFAOYSA-N",
"smiles": "COc1cc(O)ccc1[N+](=O)[O-]"
},
"smiles": "COc1cc(O)ccc1[N+](=O)[O-]",
"reactionStepId": "sa_9737e5329f7b6963a124d74b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20110130398A1;0566;1063525\",\"rsmi\":\"F[c:10]1[cH:9][cH:8][c:4]([N+:5](=[O:6])[O-:7])[c:3]([O:2][CH3:1])[cH:12]1.[OH2:11]>CS(C)=O.Cl.[Na+]>[CH3:1][O:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[cH:8][cH:9][c:10]([OH:11])[cH:12]1\"},\"mapped_reaction_smiles\":\"F[c:10]1[cH:9][cH:8][c:4]([N+:5](=[O:6])[O-:7])[c:3]([O:2][CH3:1])[cH:12]1.[OH2:11]>CS(C)=O.Cl.[Na+]>[CH3:1][O:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[cH:8][cH:9][c:10]([OH:11])[cH:12]1\"}",
"reactionStep": {
"id": "sa_9737e5329f7b6963a124d74b",
"reactionHash": "ba9328a0b090988b9e7ecadbba7154817ef07751f342afd7bfa1b3e5388847cd"
},
"children": [
{
"id": "2128",
"routeId": "sa_23912d483542051a462c1f05",
"moleculeId": "sa_a2b9e7713e49d6e0b999d99a",
"parentId": "2127",
"isLeaf": true,
"molecule": {
"id": "sa_a2b9e7713e49d6e0b999d99a",
"inchikey": "WLKUSVNHZXUEFO-UHFFFAOYSA-N",
"smiles": "COc1cc(F)ccc1[N+](=O)[O-]"
},
"smiles": "COc1cc(F)ccc1[N+](=O)[O-]",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "2129",
"routeId": "sa_23912d483542051a462c1f05",
"moleculeId": "sa_106b35b8a76bbe73829a0a69",
"parentId": "2127",
"isLeaf": true,
"molecule": {
"id": "sa_106b35b8a76bbe73829a0a69",
"inchikey": "XLYOFNOQVPJJNP-UHFFFAOYSA-N",
"smiles": "O"
},
"smiles": "O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}