Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
Cc1cc(C(=O)C(=O)c2cc(F)cc(F)c2)ccc1OC(F)F
InChiKey
WTXIIFWYTSNNOV-UHFFFAOYSA-N
Route Signature
9e734ec13d922c936f8170ef06ce69b1750784ac680dd28cb4f83961ba31b17d
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_1e47bcfb73c165ab8699328e",
"signature": "9e734ec13d922c936f8170ef06ce69b1750784ac680dd28cb4f83961ba31b17d",
"contentHash": "d94556b168200b463bd3b225ade2a7a07e1d7fb6d7fcd390f6a956f803993f60",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_6785bc98ec6bb392573ec8cd",
"benchmarkSetId": "7390a9c2522b1c81605e80a42a8de7c7ad9a5797d028633b54904bc78f091bb8",
"targetId": "n5-01916",
"moleculeId": "sa_ecac51ba802deac3bfe149f3",
"smiles": "Cc1cc(C(=O)C(=O)c2cc(F)cc(F)c2)ccc1OC(F)F",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_ecac51ba802deac3bfe149f3",
"inchikey": "WTXIIFWYTSNNOV-UHFFFAOYSA-N",
"smiles": "Cc1cc(C(=O)C(=O)c2cc(F)cc(F)c2)ccc1OC(F)F"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "1617",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_ecac51ba802deac3bfe149f3",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_ecac51ba802deac3bfe149f3",
"inchikey": "WTXIIFWYTSNNOV-UHFFFAOYSA-N",
"smiles": "Cc1cc(C(=O)C(=O)c2cc(F)cc(F)c2)ccc1OC(F)F"
},
"smiles": "Cc1cc(C(=O)C(=O)c2cc(F)cc(F)c2)ccc1OC(F)F",
"reactionStepId": "sa_4a3460f680013d60766d4f58",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160159746A1;0492;1888833\",\"rsmi\":\"[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]([OH:12])[C:13](=[O:14])[c:15]2[cH:16][c:17]([F:18])[cH:19][c:20]([F:21])[cH:22]2)[cH:23]1>CC(=O)O.CC(=O)O[Cu]OC(C)=O.CCOC(C)=O.O.O=[N+]([O-])O.N>[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([C:11](=[O:12])[C:13](=[O:14])[c:15]2[cH:16][c:17]([F:18])[cH:19][c:20]([F:21])[cH:22]2)[cH:23]1\"},\"mapped_reaction_smiles\":\"[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]([OH:12])[C:13](=[O:14])[c:15]2[cH:16][c:17]([F:18])[cH:19][c:20]([F:21])[cH:22]2)[cH:23]1>CC(=O)O.CC(=O)O[Cu]OC(C)=O.CCOC(C)=O.O.O=[N+]([O-])O.N>[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([C:11](=[O:12])[C:13](=[O:14])[c:15]2[cH:16][c:17]([F:18])[cH:19][c:20]([F:21])[cH:22]2)[cH:23]1\"}",
"reactionStep": {
"id": "sa_4a3460f680013d60766d4f58",
"reactionHash": "769ee2dbeda3b12b3ef53cd8c9a20d6e44f4f33b4ef12e1f7873cb85483d5cf1"
},
"children": [
{
"id": "1618",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_ed55e4d283facc378d6b08a9",
"parentId": "1617",
"isLeaf": false,
"molecule": {
"id": "sa_ed55e4d283facc378d6b08a9",
"inchikey": "DENFULYRVCVUPE-UHFFFAOYSA-N",
"smiles": "Cc1cc(C(O)C(=O)c2cc(F)cc(F)c2)ccc1OC(F)F"
},
"smiles": "Cc1cc(C(O)C(=O)c2cc(F)cc(F)c2)ccc1OC(F)F",
"reactionStepId": "sa_93339ebf9f4e238c9032e14d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160159746A1;0490;1888832\",\"rsmi\":\"C1CS[C:13]([CH:11]([c:10]2[cH:9][cH:8][c:3]([O:4][CH:5]([F:6])[F:7])[c:2]([CH3:1])[cH:23]2)[OH:12])([c:15]2[cH:16][c:17]([F:18])[cH:19][c:20]([F:21])[cH:22]2)SC1.O=C(Oc1c(I)cccc1OC(C(F)(F)F)=[O:14])C(F)(F)F>CC#N.CCCCCC.CCOC(C)=O.CCOC(C)=O.O>[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]([OH:12])[C:13](=[O:14])[c:15]2[cH:16][c:17]([F:18])[cH:19][c:20]([F:21])[cH:22]2)[cH:23]1\"},\"mapped_reaction_smiles\":\"C1CS[C:13]([CH:11]([c:10]2[cH:9][cH:8][c:3]([O:4][CH:5]([F:6])[F:7])[c:2]([CH3:1])[cH:23]2)[OH:12])([c:15]2[cH:16][c:17]([F:18])[cH:19][c:20]([F:21])[cH:22]2)SC1.O=C(Oc1c(I)cccc1OC(C(F)(F)F)=[O:14])C(F)(F)F>CC#N.CCCCCC.CCOC(C)=O.CCOC(C)=O.O>[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]([OH:12])[C:13](=[O:14])[c:15]2[cH:16][c:17]([F:18])[cH:19][c:20]([F:21])[cH:22]2)[cH:23]1\"}",
"reactionStep": {
"id": "sa_93339ebf9f4e238c9032e14d",
"reactionHash": "231e8e4613e1e7b3b9c9ba4afc64a5a34122c9de7de4016d81b48578d989dbdd"
},
"children": [
{
"id": "1619",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_ec368def0531627b4d42603e",
"parentId": "1618",
"isLeaf": false,
"molecule": {
"id": "sa_ec368def0531627b4d42603e",
"inchikey": "PRNSIZCNIIYVKM-UHFFFAOYSA-N",
"smiles": "Cc1cc(C(O)C2(c3cc(F)cc(F)c3)SCCCS2)ccc1OC(F)F"
},
"smiles": "Cc1cc(C(O)C2(c3cc(F)cc(F)c3)SCCCS2)ccc1OC(F)F",
"reactionStepId": "sa_31cee8a334aae8331a9249c0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160159746A1;0488;1888831\",\"rsmi\":\"[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]=[O:12])[cH:27]1.[CH:13]1([c:14]2[cH:15][c:16]([F:17])[cH:18][c:19]([F:20])[cH:21]2)[S:22][CH2:23][CH2:24][CH2:25][S:26]1>C1CCOC1.[Li]CCCC>[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]([OH:12])[C:13]2([c:14]3[cH:15][c:16]([F:17])[cH:18][c:19]([F:20])[cH:21]3)[S:22][CH2:23][CH2:24][CH2:25][S:26]2)[cH:27]1\"},\"mapped_reaction_smiles\":\"[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]=[O:12])[cH:27]1.[CH:13]1([c:14]2[cH:15][c:16]([F:17])[cH:18][c:19]([F:20])[cH:21]2)[S:22][CH2:23][CH2:24][CH2:25][S:26]1>C1CCOC1.[Li]CCCC>[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]([OH:12])[C:13]2([c:14]3[cH:15][c:16]([F:17])[cH:18][c:19]([F:20])[cH:21]3)[S:22][CH2:23][CH2:24][CH2:25][S:26]2)[cH:27]1\"}",
"reactionStep": {
"id": "sa_31cee8a334aae8331a9249c0",
"reactionHash": "d2a7a53b920346c73d380a0ab234501d161954bdbe84d1bb10030ad4d8b61019"
},
"children": [
{
"id": "1620",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_320fbd7e7a4e6049956fd007",
"parentId": "1619",
"isLeaf": false,
"molecule": {
"id": "sa_320fbd7e7a4e6049956fd007",
"inchikey": "BIQULEZGYCYXIT-UHFFFAOYSA-N",
"smiles": "Cc1cc(C=O)ccc1OC(F)F"
},
"smiles": "Cc1cc(C=O)ccc1OC(F)F",
"reactionStepId": "sa_165315cd635e340eef4665df",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160159746A1;0485;1888830\",\"rsmi\":\"O=C(O)[C:5](Cl)([F:6])[F:7].[CH3:1][c:2]1[c:3]([OH:4])[cH:8][cH:9][c:10]([CH:11]=[O:12])[cH:13]1>CN(C)C=O.O.O=C(O)O.[K+].[K+].[Na+]>[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]=[O:12])[cH:13]1\"},\"mapped_reaction_smiles\":\"O=C(O)[C:5](Cl)([F:6])[F:7].[CH3:1][c:2]1[c:3]([OH:4])[cH:8][cH:9][c:10]([CH:11]=[O:12])[cH:13]1>CN(C)C=O.O.O=C(O)O.[K+].[K+].[Na+]>[CH3:1][c:2]1[c:3]([O:4][CH:5]([F:6])[F:7])[cH:8][cH:9][c:10]([CH:11]=[O:12])[cH:13]1\"}",
"reactionStep": {
"id": "sa_165315cd635e340eef4665df",
"reactionHash": "9edf78126263d47551e50e3c50d6d953ab72d02753d678707e5ca6b8d3c15f76"
},
"children": [
{
"id": "1621",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_54d48885d9bdcc0f731e6f6a",
"parentId": "1620",
"isLeaf": true,
"molecule": {
"id": "sa_54d48885d9bdcc0f731e6f6a",
"inchikey": "BAKYASSDAXQKKY-UHFFFAOYSA-N",
"smiles": "Cc1cc(C=O)ccc1O"
},
"smiles": "Cc1cc(C=O)ccc1O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "1622",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_41afe83c884379b07a698690",
"parentId": "1620",
"isLeaf": true,
"molecule": {
"id": "sa_41afe83c884379b07a698690",
"inchikey": "OAWAZQITIZDJRB-UHFFFAOYSA-N",
"smiles": "O=C(O)C(F)(F)Cl"
},
"smiles": "O=C(O)C(F)(F)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "1623",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_69539592d2085f1b172cd486",
"parentId": "1619",
"isLeaf": false,
"molecule": {
"id": "sa_69539592d2085f1b172cd486",
"inchikey": "KNUPWGDSGBKKQB-UHFFFAOYSA-N",
"smiles": "Fc1cc(F)cc(C2SCCCS2)c1"
},
"smiles": "Fc1cc(F)cc(C2SCCCS2)c1",
"reactionStepId": "sa_aca7200e267176a67fdf2e12",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160159746A1;0469;1888824\",\"rsmi\":\"O=[CH:8][c:7]1[cH:6][c:4]([F:5])[cH:3][c:2]([F:1])[cH:14]1.[SH:9][CH2:10][CH2:11][CH2:12][SH:13]>CCCCCC.CCOC(C)=O.COC.ClCCl>[F:1][c:2]1[cH:3][c:4]([F:5])[cH:6][c:7]([CH:8]2[S:9][CH2:10][CH2:11][CH2:12][S:13]2)[cH:14]1\"},\"mapped_reaction_smiles\":\"O=[CH:8][c:7]1[cH:6][c:4]([F:5])[cH:3][c:2]([F:1])[cH:14]1.[SH:9][CH2:10][CH2:11][CH2:12][SH:13]>CCCCCC.CCOC(C)=O.COC.ClCCl>[F:1][c:2]1[cH:3][c:4]([F:5])[cH:6][c:7]([CH:8]2[S:9][CH2:10][CH2:11][CH2:12][S:13]2)[cH:14]1\"}",
"reactionStep": {
"id": "sa_aca7200e267176a67fdf2e12",
"reactionHash": "d229c62aa8128d5d45250ffdd4ca8113643ccbbba84751aac8cb62d63b557911"
},
"children": [
{
"id": "1624",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_63f88a94d2d289b25262852a",
"parentId": "1623",
"isLeaf": true,
"molecule": {
"id": "sa_63f88a94d2d289b25262852a",
"inchikey": "ASOFZHSTJHGQDT-UHFFFAOYSA-N",
"smiles": "O=Cc1cc(F)cc(F)c1"
},
"smiles": "O=Cc1cc(F)cc(F)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "1625",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_664674fabe490a95c70b2238",
"parentId": "1623",
"isLeaf": true,
"molecule": {
"id": "sa_664674fabe490a95c70b2238",
"inchikey": "ZJLMKPKYJBQJNH-UHFFFAOYSA-N",
"smiles": "SCCCS"
},
"smiles": "SCCCS",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "1626",
"routeId": "sa_1e47bcfb73c165ab8699328e",
"moleculeId": "sa_93f12b893855b2dd3b9d4a1f",
"parentId": "1618",
"isLeaf": true,
"molecule": {
"id": "sa_93f12b893855b2dd3b9d4a1f",
"inchikey": "WSEYRYIQSMUYMG-UHFFFAOYSA-N",
"smiles": "O=C(Oc1cccc(I)c1OC(=O)C(F)(F)F)C(F)(F)F"
},
"smiles": "O=C(Oc1cccc(I)c1OC(=O)C(F)(F)F)C(F)(F)F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}