Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
Cn1cnc2c(C#N)nc(-c3ccc(O)c(C(F)(F)F)c3)cc21
InChiKey
BKUOCVXPMUEPRJ-UHFFFAOYSA-N
Route Signature
a3bba6b7fe2f1ce50d0e14806b38f7fc98aa586893a76b474e0595c9b4c57c63
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_8d085e43a3af8c087f6a75a6",
"signature": "a3bba6b7fe2f1ce50d0e14806b38f7fc98aa586893a76b474e0595c9b4c57c63",
"contentHash": "8c380ad085691fa2312fb5d7a5001b535100a444b7fba0f98bc846fb42d369b6",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_b662aeddf3d3c1ae40a5c5fe",
"benchmarkSetId": "7390a9c2522b1c81605e80a42a8de7c7ad9a5797d028633b54904bc78f091bb8",
"targetId": "n5-00278",
"moleculeId": "sa_a5682046bc337f081ec0e92d",
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(O)c(C(F)(F)F)c3)cc21",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_a5682046bc337f081ec0e92d",
"inchikey": "BKUOCVXPMUEPRJ-UHFFFAOYSA-N",
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(O)c(C(F)(F)F)c3)cc21"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "550",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_a5682046bc337f081ec0e92d",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_a5682046bc337f081ec0e92d",
"inchikey": "BKUOCVXPMUEPRJ-UHFFFAOYSA-N",
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(O)c(C(F)(F)F)c3)cc21"
},
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(O)c(C(F)(F)F)c3)cc21",
"reactionStepId": "sa_25f8c96bc1833d7884490237",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0203;914984\",\"rsmi\":\"COCCOC[O:17][c:16]1[c:11]([C:12]([F:13])([F:14])[F:15])[cH:10][c:9](-[c:8]2[cH:7][c:6]3[n:2]([CH3:1])[cH:3][n:4][c:5]3[c:21]([C:22]#[N:23])[n:20]2)[cH:19][cH:18]1>C1CCOC1.Cl.Cl.[Na+]>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8](-[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([OH:17])[cH:18][cH:19]1)[n:20][c:21]2[C:22]#[N:23]\"},\"mapped_reaction_smiles\":\"COCCOC[O:17][c:16]1[c:11]([C:12]([F:13])([F:14])[F:15])[cH:10][c:9](-[c:8]2[cH:7][c:6]3[n:2]([CH3:1])[cH:3][n:4][c:5]3[c:21]([C:22]#[N:23])[n:20]2)[cH:19][cH:18]1>C1CCOC1.Cl.Cl.[Na+]>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8](-[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([OH:17])[cH:18][cH:19]1)[n:20][c:21]2[C:22]#[N:23]\"}",
"reactionStep": {
"id": "sa_25f8c96bc1833d7884490237",
"reactionHash": "d9694889649be89f3e0ebf23350549628b8c817d046b6487cf0bd208b8fbbfe8"
},
"children": [
{
"id": "551",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_6ab1f9fd6a75a9fb2eb414a6",
"parentId": "550",
"isLeaf": false,
"molecule": {
"id": "sa_6ab1f9fd6a75a9fb2eb414a6",
"inchikey": "LUFFQSOBIQCIQS-UHFFFAOYSA-N",
"smiles": "COCCOCOc1ccc(-c2cc3c(ncn3C)c(C#N)n2)cc1C(F)(F)F"
},
"smiles": "COCCOCOc1ccc(-c2cc3c(ncn3C)c(C#N)n2)cc1C(F)(F)F",
"reactionStepId": "sa_c9278f40aedaf687f540ad66",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0202;914983\",\"rsmi\":\"Cl[c:16]1[cH:17][c:18]2[c:19]([n:20][cH:21][n:22]2[CH3:23])[c:24]([C:25]#[N:26])[n:27]1.OB(O)[c:15]1[cH:14][c:9]([C:10]([F:11])([F:12])[F:13])[c:8]([O:7][CH2:6][O:5][CH2:4][CH2:3][O:2][CH3:1])[cH:29][cH:28]1>C1CCC(P(C2CCCCC2)C2CCCCC2)CC1.C1COCCO1.O.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=P(O)(O)O.[K+].[K+].[K+].[Pd].[Pd]>[CH3:1][O:2][CH2:3][CH2:4][O:5][CH2:6][O:7][c:8]1[c:9]([C:10]([F:11])([F:12])[F:13])[cH:14][c:15](-[c:16]2[cH:17][c:18]3[c:19]([n:20][cH:21][n:22]3[CH3:23])[c:24]([C:25]#[N:26])[n:27]2)[cH:28][cH:29]1\"},\"mapped_reaction_smiles\":\"Cl[c:16]1[cH:17][c:18]2[c:19]([n:20][cH:21][n:22]2[CH3:23])[c:24]([C:25]#[N:26])[n:27]1.OB(O)[c:15]1[cH:14][c:9]([C:10]([F:11])([F:12])[F:13])[c:8]([O:7][CH2:6][O:5][CH2:4][CH2:3][O:2][CH3:1])[cH:29][cH:28]1>C1CCC(P(C2CCCCC2)C2CCCCC2)CC1.C1COCCO1.O.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=P(O)(O)O.[K+].[K+].[K+].[Pd].[Pd]>[CH3:1][O:2][CH2:3][CH2:4][O:5][CH2:6][O:7][c:8]1[c:9]([C:10]([F:11])([F:12])[F:13])[cH:14][c:15](-[c:16]2[cH:17][c:18]3[c:19]([n:20][cH:21][n:22]3[CH3:23])[c:24]([C:25]#[N:26])[n:27]2)[cH:28][cH:29]1\"}",
"reactionStep": {
"id": "sa_c9278f40aedaf687f540ad66",
"reactionHash": "5d30a113c944117adc403b981cda1db7208d58496d76172ff8df385edfec32e3"
},
"children": [
{
"id": "552",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_f452bddbefc72ebcde005e37",
"parentId": "551",
"isLeaf": false,
"molecule": {
"id": "sa_f452bddbefc72ebcde005e37",
"inchikey": "LQHKBWMDRJSRJZ-UHFFFAOYSA-N",
"smiles": "Cn1cnc2c(C#N)nc(Cl)cc21"
},
"smiles": "Cn1cnc2c(C#N)nc(Cl)cc21",
"reactionStepId": "sa_8e34a30b37a3813411b8dc45",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0097;914960\",\"rsmi\":\"CCO[CH:3](OCC)OCC.[CH3:1][NH:2][c:6]1[c:5]([NH2:4])[c:11]([C:12]#[N:13])[n:10][c:8]([Cl:9])[cH:7]1>CC(=O)O.CCOC(C)=O.ClCCl>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8]([Cl:9])[n:10][c:11]2[C:12]#[N:13]\"},\"mapped_reaction_smiles\":\"CCO[CH:3](OCC)OCC.[CH3:1][NH:2][c:6]1[c:5]([NH2:4])[c:11]([C:12]#[N:13])[n:10][c:8]([Cl:9])[cH:7]1>CC(=O)O.CCOC(C)=O.ClCCl>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8]([Cl:9])[n:10][c:11]2[C:12]#[N:13]\"}",
"reactionStep": {
"id": "sa_8e34a30b37a3813411b8dc45",
"reactionHash": "bed769b624a57d127e9e6597caeb243ef3f7c8e8c73522a6c0a9dcc697d458a8"
},
"children": [
{
"id": "553",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_dc98236d967ab0cdbd0fcd04",
"parentId": "552",
"isLeaf": true,
"molecule": {
"id": "sa_dc98236d967ab0cdbd0fcd04",
"inchikey": "GKASDNZWUGIAMG-UHFFFAOYSA-N",
"smiles": "CCOC(OCC)OCC"
},
"smiles": "CCOC(OCC)OCC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "554",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_a168085438356699773f0c7c",
"parentId": "552",
"isLeaf": false,
"molecule": {
"id": "sa_a168085438356699773f0c7c",
"inchikey": "XIZOPJUMQDTYRX-UHFFFAOYSA-N",
"smiles": "CNc1cc(Cl)nc(C#N)c1N"
},
"smiles": "CNc1cc(Cl)nc(C#N)c1N",
"reactionStepId": "sa_2e223742baef49fd39f9bb46",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0096;914959\",\"rsmi\":\"O=[N+:5]([O-])[c:4]1[c:3]([NH:2][CH3:1])[cH:12][c:10]([Cl:11])[n:9][c:6]1[C:7]#[N:8]>CCO.CCOC(C)=O.Cl[Sn]Cl.O.O.N.O>[CH3:1][NH:2][c:3]1[c:4]([NH2:5])[c:6]([C:7]#[N:8])[n:9][c:10]([Cl:11])[cH:12]1\"},\"mapped_reaction_smiles\":\"O=[N+:5]([O-])[c:4]1[c:3]([NH:2][CH3:1])[cH:12][c:10]([Cl:11])[n:9][c:6]1[C:7]#[N:8]>CCO.CCOC(C)=O.Cl[Sn]Cl.O.O.N.O>[CH3:1][NH:2][c:3]1[c:4]([NH2:5])[c:6]([C:7]#[N:8])[n:9][c:10]([Cl:11])[cH:12]1\"}",
"reactionStep": {
"id": "sa_2e223742baef49fd39f9bb46",
"reactionHash": "2a6e4617c79dde22c0db26768e044bd552b12ac75914d7ab28b3db3e7931ca0f"
},
"children": [
{
"id": "555",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_a3e8a23b90fdec9b24be7c1f",
"parentId": "554",
"isLeaf": false,
"molecule": {
"id": "sa_a3e8a23b90fdec9b24be7c1f",
"inchikey": "CPPJTEVGUHCBOT-UHFFFAOYSA-N",
"smiles": "CNc1cc(Cl)nc(C#N)c1[N+](=O)[O-]"
},
"smiles": "CNc1cc(Cl)nc(C#N)c1[N+](=O)[O-]",
"reactionStepId": "sa_668c54e6e82442029b629fb7",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0094;914958\",\"rsmi\":\"I[CH3:1].[NH2:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[c:8]([C:9]#[N:10])[n:11][c:12]([Cl:13])[cH:14]1>CC#N.CCOC(C)=O.O=C(O)O.[K+].[K+]>[CH3:1][NH:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[c:8]([C:9]#[N:10])[n:11][c:12]([Cl:13])[cH:14]1\"},\"mapped_reaction_smiles\":\"I[CH3:1].[NH2:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[c:8]([C:9]#[N:10])[n:11][c:12]([Cl:13])[cH:14]1>CC#N.CCOC(C)=O.O=C(O)O.[K+].[K+]>[CH3:1][NH:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[c:8]([C:9]#[N:10])[n:11][c:12]([Cl:13])[cH:14]1\"}",
"reactionStep": {
"id": "sa_668c54e6e82442029b629fb7",
"reactionHash": "7cac1780efc1a60db73d56c7d1ed84bd97ca1330b5d52fd97d70e3d87ce18b87"
},
"children": [
{
"id": "556",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "555",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "557",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_b4409e3ca75920fc970d0ea5",
"parentId": "555",
"isLeaf": true,
"molecule": {
"id": "sa_b4409e3ca75920fc970d0ea5",
"inchikey": "KAYQVFYDILZZJH-UHFFFAOYSA-N",
"smiles": "N#Cc1nc(Cl)cc(N)c1[N+](=O)[O-]"
},
"smiles": "N#Cc1nc(Cl)cc(N)c1[N+](=O)[O-]",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "558",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_a9da395b3a4ea51e8c6ead25",
"parentId": "551",
"isLeaf": false,
"molecule": {
"id": "sa_a9da395b3a4ea51e8c6ead25",
"inchikey": "QOVRQYBHDTTXQD-UHFFFAOYSA-N",
"smiles": "COCCOCOc1ccc(B(O)O)cc1C(F)(F)F"
},
"smiles": "COCCOCOc1ccc(B(O)O)cc1C(F)(F)F",
"reactionStepId": "sa_480ffa59c14c0503dd51f664",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0200;914982\",\"rsmi\":\"Br[c:15]1[cH:14][c:9]([C:10]([F:11])([F:12])[F:13])[c:8]([O:7][CH2:6][O:5][CH2:4][CH2:3][O:2][CH3:1])[cH:20][cH:19]1.CC(C)O[B:16]([O:17]C(C)C)[O:18]C(C)C>C1CCOC1.O.[Li]CCCC>[CH3:1][O:2][CH2:3][CH2:4][O:5][CH2:6][O:7][c:8]1[c:9]([C:10]([F:11])([F:12])[F:13])[cH:14][c:15]([B:16]([OH:17])[OH:18])[cH:19][cH:20]1\"},\"mapped_reaction_smiles\":\"Br[c:15]1[cH:14][c:9]([C:10]([F:11])([F:12])[F:13])[c:8]([O:7][CH2:6][O:5][CH2:4][CH2:3][O:2][CH3:1])[cH:20][cH:19]1.CC(C)O[B:16]([O:17]C(C)C)[O:18]C(C)C>C1CCOC1.O.[Li]CCCC>[CH3:1][O:2][CH2:3][CH2:4][O:5][CH2:6][O:7][c:8]1[c:9]([C:10]([F:11])([F:12])[F:13])[cH:14][c:15]([B:16]([OH:17])[OH:18])[cH:19][cH:20]1\"}",
"reactionStep": {
"id": "sa_480ffa59c14c0503dd51f664",
"reactionHash": "80333b76c467df2559e2883a0f07ded6b46930e2eb292cea4c2db8a9c21cf60b"
},
"children": [
{
"id": "559",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_c607ad7efd678c88e848e08e",
"parentId": "558",
"isLeaf": false,
"molecule": {
"id": "sa_c607ad7efd678c88e848e08e",
"inchikey": "ITACEYFYAGBACM-UHFFFAOYSA-N",
"smiles": "COCCOCOc1ccc(Br)cc1C(F)(F)F"
},
"smiles": "COCCOCOc1ccc(Br)cc1C(F)(F)F",
"reactionStepId": "sa_bf1cecd3094adeb55b0c43fb",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0199;914981\",\"rsmi\":\"Cl[CH2:6][O:5][CH2:4][CH2:3][O:2][CH3:1].[OH:7][c:8]1[c:9]([C:10]([F:11])([F:12])[F:13])[cH:14][c:15]([Br:16])[cH:17][cH:18]1>C1CCOC1.[HH].[Na+]>[CH3:1][O:2][CH2:3][CH2:4][O:5][CH2:6][O:7][c:8]1[c:9]([C:10]([F:11])([F:12])[F:13])[cH:14][c:15]([Br:16])[cH:17][cH:18]1\"},\"mapped_reaction_smiles\":\"Cl[CH2:6][O:5][CH2:4][CH2:3][O:2][CH3:1].[OH:7][c:8]1[c:9]([C:10]([F:11])([F:12])[F:13])[cH:14][c:15]([Br:16])[cH:17][cH:18]1>C1CCOC1.[HH].[Na+]>[CH3:1][O:2][CH2:3][CH2:4][O:5][CH2:6][O:7][c:8]1[c:9]([C:10]([F:11])([F:12])[F:13])[cH:14][c:15]([Br:16])[cH:17][cH:18]1\"}",
"reactionStep": {
"id": "sa_bf1cecd3094adeb55b0c43fb",
"reactionHash": "852cf1afe8d9b2fe7b5948ab669dcf361bb221b12da36e217609558aca014a31"
},
"children": [
{
"id": "560",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_e1282bacce16e1c0d121bc00",
"parentId": "559",
"isLeaf": true,
"molecule": {
"id": "sa_e1282bacce16e1c0d121bc00",
"inchikey": "BIAAQBNMRITRDV-UHFFFAOYSA-N",
"smiles": "COCCOCCl"
},
"smiles": "COCCOCCl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "561",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_fef5e5067818860d5e3b1251",
"parentId": "559",
"isLeaf": true,
"molecule": {
"id": "sa_fef5e5067818860d5e3b1251",
"inchikey": "PDPGERGWEOJVDC-UHFFFAOYSA-N",
"smiles": "Oc1ccc(Br)cc1C(F)(F)F"
},
"smiles": "Oc1ccc(Br)cc1C(F)(F)F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "562",
"routeId": "sa_8d085e43a3af8c087f6a75a6",
"moleculeId": "sa_0c3a1c72e8778c8e8b205e29",
"parentId": "558",
"isLeaf": true,
"molecule": {
"id": "sa_0c3a1c72e8778c8e8b205e29",
"inchikey": "NHDIQVFFNDKAQU-UHFFFAOYSA-N",
"smiles": "CC(C)OB(OC(C)C)OC(C)C"
},
"smiles": "CC(C)OB(OC(C)C)OC(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}