Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1ccc(S(=O)(=O)c2c(Cl)cc(Nc3n[nH]c(N)n3)cc2Cl)cc1
InChiKey
GQZPIAVYLPLELS-UHFFFAOYSA-N
Route Signature
9e5f6803b8999c2a664018edca047bb6328288b59d67b0ccce38ca164dc67d2d
Synthesis route with 6 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_1a4ad778bf7170511373c588",
"signature": "9e5f6803b8999c2a664018edca047bb6328288b59d67b0ccce38ca164dc67d2d",
"contentHash": "f6f032972742fed6137a30ea7ffc2ac3aa3bedd346992fccf5be67694bd28cfe",
"length": 6,
"isConvergent": false
},
"target": {
"id": "sa_789aa6a98bfc739da7f4de92",
"benchmarkSetId": "f925e688d731a0ad4e3aa6a505df094f6d3ca64ce3facc312bc5f64731921b33",
"targetId": "n5-01177",
"moleculeId": "sa_73af7b0b0cb34802581259d3",
"smiles": "COc1ccc(S(=O)(=O)c2c(Cl)cc(Nc3n[nH]c(N)n3)cc2Cl)cc1",
"routeLength": 6,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_73af7b0b0cb34802581259d3",
"inchikey": "GQZPIAVYLPLELS-UHFFFAOYSA-N",
"smiles": "COc1ccc(S(=O)(=O)c2c(Cl)cc(Nc3n[nH]c(N)n3)cc2Cl)cc1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "5299",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_73af7b0b0cb34802581259d3",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_73af7b0b0cb34802581259d3",
"inchikey": "GQZPIAVYLPLELS-UHFFFAOYSA-N",
"smiles": "COc1ccc(S(=O)(=O)c2c(Cl)cc(Nc3n[nH]c(N)n3)cc2Cl)cc1"
},
"smiles": "COc1ccc(S(=O)(=O)c2c(Cl)cc(Nc3n[nH]c(N)n3)cc2Cl)cc1",
"reactionStepId": "sa_474d8ffc40f42e08b3182aef",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140242028A1;0286;1569268\",\"rsmi\":\"[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:10]2[c:11]([Cl:12])[cH:13][c:14]([NH:15][c:16]3[n:17][nH:18][c:19]([NH2:20])[n:21]3)[cH:22][c:23]2[Cl:24])[cH:25][cH:26]1.OS(O[OH:9])=[O:8]>CO.CO.ClCCl.[K+].N.O>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7](=[O:8])(=[O:9])[c:10]2[c:11]([Cl:12])[cH:13][c:14]([NH:15][c:16]3[n:17][nH:18][c:19]([NH2:20])[n:21]3)[cH:22][c:23]2[Cl:24])[cH:25][cH:26]1\"},\"mapped_reaction_smiles\":\"[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:10]2[c:11]([Cl:12])[cH:13][c:14]([NH:15][c:16]3[n:17][nH:18][c:19]([NH2:20])[n:21]3)[cH:22][c:23]2[Cl:24])[cH:25][cH:26]1.OS(O[OH:9])=[O:8]>CO.CO.ClCCl.[K+].N.O>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7](=[O:8])(=[O:9])[c:10]2[c:11]([Cl:12])[cH:13][c:14]([NH:15][c:16]3[n:17][nH:18][c:19]([NH2:20])[n:21]3)[cH:22][c:23]2[Cl:24])[cH:25][cH:26]1\"}",
"reactionStep": {
"id": "sa_474d8ffc40f42e08b3182aef",
"reactionHash": "d65f5c0ecd061c970a4d1203f3aa74ac4cd874fded8904f643ebf39c681894e9"
},
"children": [
{
"id": "5300",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_772e3d6f4278e1cff6cf430d",
"parentId": "5299",
"isLeaf": true,
"molecule": {
"id": "sa_772e3d6f4278e1cff6cf430d",
"inchikey": "AYSIGUCDFZQVQT-UHFFFAOYSA-N",
"smiles": "O=S(O)OO"
},
"smiles": "O=S(O)OO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "5301",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_27d743b49291c448c7f828c2",
"parentId": "5299",
"isLeaf": false,
"molecule": {
"id": "sa_27d743b49291c448c7f828c2",
"inchikey": "FGKOEMPAUSGKLA-UHFFFAOYSA-N",
"smiles": "COc1ccc(Sc2c(Cl)cc(Nc3n[nH]c(N)n3)cc2Cl)cc1"
},
"smiles": "COc1ccc(Sc2c(Cl)cc(Nc3n[nH]c(N)n3)cc2Cl)cc1",
"reactionStepId": "sa_15c059d97787b503e8d3d4de",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140242028A1;0273;1569265\",\"rsmi\":\"CS/[C:14]([NH:13][c:12]1[cH:11][c:9]([Cl:10])[c:8]([S:7][c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:24][cH:23]2)[c:21]([Cl:22])[cH:20]1)=[N:19]\\\\[C:17]#[N:18].[NH2:15][NH2:16]>CCO.CO.ClCCl.N.O>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([NH:13][c:14]3[n:15][nH:16][c:17]([NH2:18])[n:19]3)[cH:20][c:21]2[Cl:22])[cH:23][cH:24]1\"},\"mapped_reaction_smiles\":\"CS/[C:14]([NH:13][c:12]1[cH:11][c:9]([Cl:10])[c:8]([S:7][c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:24][cH:23]2)[c:21]([Cl:22])[cH:20]1)=[N:19]\\\\[C:17]#[N:18].[NH2:15][NH2:16]>CCO.CO.ClCCl.N.O>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([NH:13][c:14]3[n:15][nH:16][c:17]([NH2:18])[n:19]3)[cH:20][c:21]2[Cl:22])[cH:23][cH:24]1\"}",
"reactionStep": {
"id": "sa_15c059d97787b503e8d3d4de",
"reactionHash": "b65b939faff54085940871f14529625693dd3935e21be778fbe79d0695ef99f3"
},
"children": [
{
"id": "5302",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_1dbd39501b068ced2c8ff086",
"parentId": "5301",
"isLeaf": false,
"molecule": {
"id": "sa_1dbd39501b068ced2c8ff086",
"inchikey": "KZMQEECZMQIIHX-UHFFFAOYSA-N",
"smiles": "COc1ccc(Sc2c(Cl)cc(N/C(=N/C#N)SC)cc2Cl)cc1"
},
"smiles": "COc1ccc(Sc2c(Cl)cc(N/C(=N/C#N)SC)cc2Cl)cc1",
"reactionStepId": "sa_ed315a4b058f738a93c8a5b7",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140242028A1;0271;1569264\",\"rsmi\":\"I[CH3:19].[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([N:13]=[C:14]=[S:18])[cH:20][c:21]2[Cl:22])[cH:23][cH:24]1.[NH2:15][C:16]#[N:17]>CO.CO.Cc1ccccc1.[Na+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([NH:13]/[C:14](=[N:15]/[C:16]#[N:17])[S:18][CH3:19])[cH:20][c:21]2[Cl:22])[cH:23][cH:24]1\"},\"mapped_reaction_smiles\":\"I[CH3:19].[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([N:13]=[C:14]=[S:18])[cH:20][c:21]2[Cl:22])[cH:23][cH:24]1.[NH2:15][C:16]#[N:17]>CO.CO.Cc1ccccc1.[Na+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([NH:13]/[C:14](=[N:15]/[C:16]#[N:17])[S:18][CH3:19])[cH:20][c:21]2[Cl:22])[cH:23][cH:24]1\"}",
"reactionStep": {
"id": "sa_ed315a4b058f738a93c8a5b7",
"reactionHash": "a91e3e3bdeb20a57edc2d696dc23cf1c5675dc4f9701470f511fda5cf5179db6"
},
"children": [
{
"id": "5303",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "5302",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "5304",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_2a28d419b038a1f968c89b91",
"parentId": "5302",
"isLeaf": false,
"molecule": {
"id": "sa_2a28d419b038a1f968c89b91",
"inchikey": "UOECQQKUXOPVJM-UHFFFAOYSA-N",
"smiles": "COc1ccc(Sc2c(Cl)cc(N=C=S)cc2Cl)cc1"
},
"smiles": "COc1ccc(Sc2c(Cl)cc(N=C=S)cc2Cl)cc1",
"reactionStepId": "sa_5e7788506799cbc93db9f011",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140242028A1;0269;1569263\",\"rsmi\":\"[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([NH2:13])[cH:16][c:17]2[Cl:18])[cH:19][cH:20]1.c1cn([C:14](n2ccnc2)=[S:15])cn1>ClCCl>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([N:13]=[C:14]=[S:15])[cH:16][c:17]2[Cl:18])[cH:19][cH:20]1\"},\"mapped_reaction_smiles\":\"[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([NH2:13])[cH:16][c:17]2[Cl:18])[cH:19][cH:20]1.c1cn([C:14](n2ccnc2)=[S:15])cn1>ClCCl>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([N:13]=[C:14]=[S:15])[cH:16][c:17]2[Cl:18])[cH:19][cH:20]1\"}",
"reactionStep": {
"id": "sa_5e7788506799cbc93db9f011",
"reactionHash": "d38d66ec1cd1215ba9164905d2b67b234dc9aeef457bf457135dcdd0134aa3ab"
},
"children": [
{
"id": "5305",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_34bce63f42134278cdbcc029",
"parentId": "5304",
"isLeaf": true,
"molecule": {
"id": "sa_34bce63f42134278cdbcc029",
"inchikey": "RAFNCPHFRHZCPS-UHFFFAOYSA-N",
"smiles": "S=C(n1ccnc1)n1ccnc1"
},
"smiles": "S=C(n1ccnc1)n1ccnc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "5306",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_e297556b82f203059b4556a7",
"parentId": "5304",
"isLeaf": false,
"molecule": {
"id": "sa_e297556b82f203059b4556a7",
"inchikey": "VHOFNFMQWBQKMB-UHFFFAOYSA-N",
"smiles": "COc1ccc(Sc2c(Cl)cc(N)cc2Cl)cc1"
},
"smiles": "COc1ccc(Sc2c(Cl)cc(N)cc2Cl)cc1",
"reactionStepId": "sa_1760ee85d9ee5e93fa5febf8",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140242028A1;0267;1569262\",\"rsmi\":\"O=[N+:13]([O-])[c:12]1[cH:11][c:9]([Cl:10])[c:8]([S:7][c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:18][cH:17]2)[c:15]([Cl:16])[cH:14]1>CO.Cl.[Fe].N>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([NH2:13])[cH:14][c:15]2[Cl:16])[cH:17][cH:18]1\"},\"mapped_reaction_smiles\":\"O=[N+:13]([O-])[c:12]1[cH:11][c:9]([Cl:10])[c:8]([S:7][c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:18][cH:17]2)[c:15]([Cl:16])[cH:14]1>CO.Cl.[Fe].N>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([NH2:13])[cH:14][c:15]2[Cl:16])[cH:17][cH:18]1\"}",
"reactionStep": {
"id": "sa_1760ee85d9ee5e93fa5febf8",
"reactionHash": "f642cb199e803d98fad5af5d58d4104d41a3d96fc1cb07a6af64d8747b367118"
},
"children": [
{
"id": "5307",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_07a5abeddc94e77a740c736e",
"parentId": "5306",
"isLeaf": false,
"molecule": {
"id": "sa_07a5abeddc94e77a740c736e",
"inchikey": "RGPISIVSBZUNTD-UHFFFAOYSA-N",
"smiles": "COc1ccc(Sc2c(Cl)cc([N+](=O)[O-])cc2Cl)cc1"
},
"smiles": "COc1ccc(Sc2c(Cl)cc([N+](=O)[O-])cc2Cl)cc1",
"reactionStepId": "sa_5c9f439c2cb1cbcc16919610",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140242028A1;0265;1569261\",\"rsmi\":\"F[c:8]1[c:9]([Cl:10])[cH:11][c:12]([N+:13](=[O:14])[O-:15])[cH:16][c:17]1[Cl:18].[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([SH:7])[cH:19][cH:20]1>CN(C)C=O.O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([N+:13](=[O:14])[O-:15])[cH:16][c:17]2[Cl:18])[cH:19][cH:20]1\"},\"mapped_reaction_smiles\":\"F[c:8]1[c:9]([Cl:10])[cH:11][c:12]([N+:13](=[O:14])[O-:15])[cH:16][c:17]1[Cl:18].[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([SH:7])[cH:19][cH:20]1>CN(C)C=O.O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([S:7][c:8]2[c:9]([Cl:10])[cH:11][c:12]([N+:13](=[O:14])[O-:15])[cH:16][c:17]2[Cl:18])[cH:19][cH:20]1\"}",
"reactionStep": {
"id": "sa_5c9f439c2cb1cbcc16919610",
"reactionHash": "b236e5772bfcefc10a1a8656852dca78e3f6897cb92d58f82ec92dcadece43f4"
},
"children": [
{
"id": "5308",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_b7afe34180b405d116d93d76",
"parentId": "5307",
"isLeaf": true,
"molecule": {
"id": "sa_b7afe34180b405d116d93d76",
"inchikey": "NIFAOMSJMGEFTQ-UHFFFAOYSA-N",
"smiles": "COc1ccc(S)cc1"
},
"smiles": "COc1ccc(S)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "5309",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_b718cbacdc05b9827ee52412",
"parentId": "5307",
"isLeaf": true,
"molecule": {
"id": "sa_b718cbacdc05b9827ee52412",
"inchikey": "VMAATSFMXSMKPG-UHFFFAOYSA-N",
"smiles": "O=[N+]([O-])c1cc(Cl)c(F)c(Cl)c1"
},
"smiles": "O=[N+]([O-])c1cc(Cl)c(F)c(Cl)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "5310",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_62f711f20d17f88290141ede",
"parentId": "5302",
"isLeaf": true,
"molecule": {
"id": "sa_62f711f20d17f88290141ede",
"inchikey": "XZMCDFZZKTWFGF-UHFFFAOYSA-N",
"smiles": "N#CN"
},
"smiles": "N#CN",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "5311",
"routeId": "sa_1a4ad778bf7170511373c588",
"moleculeId": "sa_681b90bfe3789a310096845b",
"parentId": "5301",
"isLeaf": true,
"molecule": {
"id": "sa_681b90bfe3789a310096845b",
"inchikey": "OAKJQQAXSVQMHS-UHFFFAOYSA-N",
"smiles": "NN"
},
"smiles": "NN",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}