Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
FC(F)(F)c1ccc(Br)c(SC2CCOC(c3ccc(Cl)cc3)C2)c1
InChiKey
ZSOJXMPHZONUCE-UHFFFAOYSA-N
Route Signature
1b1d5bac07f95d64be823b7fb78a5c9ebe32864d8949f643aafd1eac4098d12b
Synthesis route with 3 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_e5d3659a231de093a5973bfa",
"signature": "1b1d5bac07f95d64be823b7fb78a5c9ebe32864d8949f643aafd1eac4098d12b",
"contentHash": "cf82fee6fb1b1ac7805d2daab14c88039fc0aae99a8eecba8c9931750f2d2376",
"length": 3,
"isConvergent": true
},
"target": {
"id": "sa_d20daa5120e91d0a9394057e",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-02866",
"moleculeId": "sa_c736722f03f3c064f96449db",
"smiles": "FC(F)(F)c1ccc(Br)c(SC2CCOC(c3ccc(Cl)cc3)C2)c1",
"routeLength": 3,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_c736722f03f3c064f96449db",
"inchikey": "ZSOJXMPHZONUCE-UHFFFAOYSA-N",
"smiles": "FC(F)(F)c1ccc(Br)c(SC2CCOC(c3ccc(Cl)cc3)C2)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "10864",
"routeId": "sa_e5d3659a231de093a5973bfa",
"moleculeId": "sa_c736722f03f3c064f96449db",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_c736722f03f3c064f96449db",
"inchikey": "ZSOJXMPHZONUCE-UHFFFAOYSA-N",
"smiles": "FC(F)(F)c1ccc(Br)c(SC2CCOC(c3ccc(Cl)cc3)C2)c1"
},
"smiles": "FC(F)(F)c1ccc(Br)c(SC2CCOC(c3ccc(Cl)cc3)C2)c1",
"reactionStepId": "sa_0114c9d20be2c128d6f363b2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150291573A1;0280;1767381\",\"rsmi\":\"CS(=O)(=O)O[CH:9]1[CH2:10][CH2:11][O:12][CH:13]([c:14]2[cH:15][cH:16][c:17]([Cl:18])[cH:19][cH:20]2)[CH2:21]1.[F:1][C:2]([F:3])([F:4])[c:5]1[cH:6][c:7]([SH:8])[c:22]([Br:23])[cH:24][cH:25]1>CCOC(C)=O.CN(C)C=O.O.O=C(O)O.[K+].[K+]>[F:1][C:2]([F:3])([F:4])[c:5]1[cH:6][c:7]([S:8][CH:9]2[CH2:10][CH2:11][O:12][CH:13]([c:14]3[cH:15][cH:16][c:17]([Cl:18])[cH:19][cH:20]3)[CH2:21]2)[c:22]([Br:23])[cH:24][cH:25]1\"},\"mapped_reaction_smiles\":\"CS(=O)(=O)O[CH:9]1[CH2:10][CH2:11][O:12][CH:13]([c:14]2[cH:15][cH:16][c:17]([Cl:18])[cH:19][cH:20]2)[CH2:21]1.[F:1][C:2]([F:3])([F:4])[c:5]1[cH:6][c:7]([SH:8])[c:22]([Br:23])[cH:24][cH:25]1>CCOC(C)=O.CN(C)C=O.O.O=C(O)O.[K+].[K+]>[F:1][C:2]([F:3])([F:4])[c:5]1[cH:6][c:7]([S:8][CH:9]2[CH2:10][CH2:11][O:12][CH:13]([c:14]3[cH:15][cH:16][c:17]([Cl:18])[cH:19][cH:20]3)[CH2:21]2)[c:22]([Br:23])[cH:24][cH:25]1\"}",
"reactionStep": {
"id": "sa_0114c9d20be2c128d6f363b2",
"reactionHash": "19de7e5e5f18e9e8a2e105799242e3fb6910827886ea5f59936480f11ce525ca"
},
"children": [
{
"id": "10865",
"routeId": "sa_e5d3659a231de093a5973bfa",
"moleculeId": "sa_2bdffaa470ef66e081c7ba4e",
"parentId": "10864",
"isLeaf": false,
"molecule": {
"id": "sa_2bdffaa470ef66e081c7ba4e",
"inchikey": "JQCUGOGTRJTGNS-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)OC1CCOC(c2ccc(Cl)cc2)C1"
},
"smiles": "CS(=O)(=O)OC1CCOC(c2ccc(Cl)cc2)C1",
"reactionStepId": "sa_713103ccfdd91760ecaa63dc",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150291573A1;0263;1767376\",\"rsmi\":\"Cl[S:2]([CH3:1])(=[O:3])=[O:4].[OH:5][CH:6]1[CH2:7][CH2:8][O:9][CH:10]([c:11]2[cH:12][cH:13][c:14]([Cl:15])[cH:16][cH:17]2)[CH2:18]1>ClCCl.O>[CH3:1][S:2](=[O:3])(=[O:4])[O:5][CH:6]1[CH2:7][CH2:8][O:9][CH:10]([c:11]2[cH:12][cH:13][c:14]([Cl:15])[cH:16][cH:17]2)[CH2:18]1\"},\"mapped_reaction_smiles\":\"Cl[S:2]([CH3:1])(=[O:3])=[O:4].[OH:5][CH:6]1[CH2:7][CH2:8][O:9][CH:10]([c:11]2[cH:12][cH:13][c:14]([Cl:15])[cH:16][cH:17]2)[CH2:18]1>ClCCl.O>[CH3:1][S:2](=[O:3])(=[O:4])[O:5][CH:6]1[CH2:7][CH2:8][O:9][CH:10]([c:11]2[cH:12][cH:13][c:14]([Cl:15])[cH:16][cH:17]2)[CH2:18]1\"}",
"reactionStep": {
"id": "sa_713103ccfdd91760ecaa63dc",
"reactionHash": "3c204b4e2fd6974b980f93db73d4062babe9bb88da179123a8b2efea1410eff7"
},
"children": [
{
"id": "10866",
"routeId": "sa_e5d3659a231de093a5973bfa",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "10865",
"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": "10867",
"routeId": "sa_e5d3659a231de093a5973bfa",
"moleculeId": "sa_074958c4e5c129d724737985",
"parentId": "10865",
"isLeaf": false,
"molecule": {
"id": "sa_074958c4e5c129d724737985",
"inchikey": "SMDAPVBKEBEABV-UHFFFAOYSA-N",
"smiles": "OC1CCOC(c2ccc(Cl)cc2)C1"
},
"smiles": "OC1CCOC(c2ccc(Cl)cc2)C1",
"reactionStepId": "sa_d68f33185cd3420f25bfc056",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150291573A1;0262;1767375\",\"rsmi\":\"[CH:2]([CH2:3][CH2:4][OH:5])=[CH2:14].[O:1]=[CH:6][c:7]1[cH:8][cH:9][c:10]([Cl:11])[cH:12][cH:13]1>O=C(O)O.O=S(=O)(O)O.[Na+]>[OH:1][CH:2]1[CH2:3][CH2:4][O:5][CH:6]([c:7]2[cH:8][cH:9][c:10]([Cl:11])[cH:12][cH:13]2)[CH2:14]1\"},\"mapped_reaction_smiles\":\"[CH:2]([CH2:3][CH2:4][OH:5])=[CH2:14].[O:1]=[CH:6][c:7]1[cH:8][cH:9][c:10]([Cl:11])[cH:12][cH:13]1>O=C(O)O.O=S(=O)(O)O.[Na+]>[OH:1][CH:2]1[CH2:3][CH2:4][O:5][CH:6]([c:7]2[cH:8][cH:9][c:10]([Cl:11])[cH:12][cH:13]2)[CH2:14]1\"}",
"reactionStep": {
"id": "sa_d68f33185cd3420f25bfc056",
"reactionHash": "a2d75e15f748e5b20fd9b6494ba4151a3263858982dca95322ad422b61862e02"
},
"children": [
{
"id": "10868",
"routeId": "sa_e5d3659a231de093a5973bfa",
"moleculeId": "sa_95255078a9b1044823d7ec55",
"parentId": "10867",
"isLeaf": true,
"molecule": {
"id": "sa_95255078a9b1044823d7ec55",
"inchikey": "AVPYQKSLYISFPO-UHFFFAOYSA-N",
"smiles": "O=Cc1ccc(Cl)cc1"
},
"smiles": "O=Cc1ccc(Cl)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10869",
"routeId": "sa_e5d3659a231de093a5973bfa",
"moleculeId": "sa_cbf5e05f585e1078cc2f8c1e",
"parentId": "10867",
"isLeaf": true,
"molecule": {
"id": "sa_cbf5e05f585e1078cc2f8c1e",
"inchikey": "ZSPTYLOMNJNZNG-UHFFFAOYSA-N",
"smiles": "C=CCCO"
},
"smiles": "C=CCCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "10870",
"routeId": "sa_e5d3659a231de093a5973bfa",
"moleculeId": "sa_1e08cb6a4cd3080751dc8cf1",
"parentId": "10864",
"isLeaf": false,
"molecule": {
"id": "sa_1e08cb6a4cd3080751dc8cf1",
"inchikey": "ZXVCDJUEVOLNEV-UHFFFAOYSA-N",
"smiles": "FC(F)(F)c1ccc(Br)c(S)c1"
},
"smiles": "FC(F)(F)c1ccc(Br)c(S)c1",
"reactionStepId": "sa_6d39a26417a2cbbe134b9c25",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150291573A1;0279;1767380\",\"rsmi\":\"O=[S:8](=O)(Cl)[c:7]1[cH:6][c:5]([C:2]([F:1])([F:3])[F:4])[cH:12][cH:11][c:9]1[Br:10]>CN(C)C=O.Cl.ClCCl.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[F:1][C:2]([F:3])([F:4])[c:5]1[cH:6][c:7]([SH:8])[c:9]([Br:10])[cH:11][cH:12]1\"},\"mapped_reaction_smiles\":\"O=[S:8](=O)(Cl)[c:7]1[cH:6][c:5]([C:2]([F:1])([F:3])[F:4])[cH:12][cH:11][c:9]1[Br:10]>CN(C)C=O.Cl.ClCCl.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[F:1][C:2]([F:3])([F:4])[c:5]1[cH:6][c:7]([SH:8])[c:9]([Br:10])[cH:11][cH:12]1\"}",
"reactionStep": {
"id": "sa_6d39a26417a2cbbe134b9c25",
"reactionHash": "9b19fe51491c34edd2c1981fbca1f1b4bcf7589f453fa7943640785d3419ea2a"
},
"children": [
{
"id": "10871",
"routeId": "sa_e5d3659a231de093a5973bfa",
"moleculeId": "sa_28df3dc86d84bc202dece4e4",
"parentId": "10870",
"isLeaf": true,
"molecule": {
"id": "sa_28df3dc86d84bc202dece4e4",
"inchikey": "CBIFOAHDKKGDAC-UHFFFAOYSA-N",
"smiles": "O=S(=O)(Cl)c1cc(C(F)(F)F)ccc1Br"
},
"smiles": "O=S(=O)(Cl)c1cc(C(F)(F)F)ccc1Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}