Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COCCCOc1ccnc(CSc2nc3ccccc3[nH]2)c1C
InChiKey
BSXAHDOWMOSVAP-UHFFFAOYSA-N
Route Signature
b1118799e30765542f3f5cb0406ac8d147d9d1b2132c03bcbdb3f2545c15db86
Synthesis route with 5 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_0082f3e13a39610198831aa9",
"signature": "b1118799e30765542f3f5cb0406ac8d147d9d1b2132c03bcbdb3f2545c15db86",
"contentHash": "ca4428883fc222aef57ab4bc8198b0b641ca775dfb4a545b2d240c93954ca5d1",
"length": 5,
"isConvergent": false
},
"target": {
"id": "sa_5c1042e6667b08833ae97135",
"benchmarkSetId": "f925e688d731a0ad4e3aa6a505df094f6d3ca64ce3facc312bc5f64731921b33",
"targetId": "n5-00318",
"moleculeId": "sa_aace3081602f2ac4c76fa078",
"smiles": "COCCCOc1ccnc(CSc2nc3ccccc3[nH]2)c1C",
"routeLength": 5,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_aace3081602f2ac4c76fa078",
"inchikey": "BSXAHDOWMOSVAP-UHFFFAOYSA-N",
"smiles": "COCCCOc1ccnc(CSc2nc3ccccc3[nH]2)c1C"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 5
},
"rootNode": {
"id": "3995",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_aace3081602f2ac4c76fa078",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_aace3081602f2ac4c76fa078",
"inchikey": "BSXAHDOWMOSVAP-UHFFFAOYSA-N",
"smiles": "COCCCOc1ccnc(CSc2nc3ccccc3[nH]2)c1C"
},
"smiles": "COCCCOc1ccnc(CSc2nc3ccccc3[nH]2)c1C",
"reactionStepId": "sa_8e33ff8b211e48eb73a1df0b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US05998445;;458204\",\"rsmi\":\"Cl[CH2:11][c:10]1[c:8]([CH3:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:24][cH:23][n:22]1.[SH:12][c:13]1[n:14][c:15]2[c:16]([cH:17][cH:18][cH:19][cH:20]2)[nH:21]1>CCO.[Na+].O>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH2:11][S:12][c:13]2[n:14][c:15]3[c:16]([cH:17][cH:18][cH:19][cH:20]3)[nH:21]2)[n:22][cH:23][cH:24]1\"},\"mapped_reaction_smiles\":\"Cl[CH2:11][c:10]1[c:8]([CH3:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:24][cH:23][n:22]1.[SH:12][c:13]1[n:14][c:15]2[c:16]([cH:17][cH:18][cH:19][cH:20]2)[nH:21]1>CCO.[Na+].O>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH2:11][S:12][c:13]2[n:14][c:15]3[c:16]([cH:17][cH:18][cH:19][cH:20]3)[nH:21]2)[n:22][cH:23][cH:24]1\"}",
"reactionStep": {
"id": "sa_8e33ff8b211e48eb73a1df0b",
"reactionHash": "26d169ace5349e60c7440e250484d776b5e09d0d6f2af946361046583562db70"
},
"children": [
{
"id": "3996",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_b8b6e282b4f52eeec3f31b74",
"parentId": "3995",
"isLeaf": false,
"molecule": {
"id": "sa_b8b6e282b4f52eeec3f31b74",
"inchikey": "XPYNCLYLFSMFQE-UHFFFAOYSA-N",
"smiles": "COCCCOc1ccnc(CCl)c1C"
},
"smiles": "COCCCOc1ccnc(CCl)c1C",
"reactionStepId": "sa_cd56b781ebeece59b23494b2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US05998445;;458203\",\"rsmi\":\"O=S(Cl)[Cl:12].O[CH2:11][c:10]1[c:8]([CH3:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:15][cH:14][n:13]1>ClCCl>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH2:11][Cl:12])[n:13][cH:14][cH:15]1\"},\"mapped_reaction_smiles\":\"O=S(Cl)[Cl:12].O[CH2:11][c:10]1[c:8]([CH3:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:15][cH:14][n:13]1>ClCCl>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH2:11][Cl:12])[n:13][cH:14][cH:15]1\"}",
"reactionStep": {
"id": "sa_cd56b781ebeece59b23494b2",
"reactionHash": "953d6dfea56d2be179b0bc3f6d159e078ae2a9fac184258fb6a08c51b355bdce"
},
"children": [
{
"id": "3997",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_cd67ce42f230ef1a4063353c",
"parentId": "3996",
"isLeaf": true,
"molecule": {
"id": "sa_cd67ce42f230ef1a4063353c",
"inchikey": "FYSNRJHAOHDILO-UHFFFAOYSA-N",
"smiles": "O=S(Cl)Cl"
},
"smiles": "O=S(Cl)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "3998",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_65a1650896ad85e0e0e89c6e",
"parentId": "3996",
"isLeaf": false,
"molecule": {
"id": "sa_65a1650896ad85e0e0e89c6e",
"inchikey": "OLBSXXZEMRBFIG-UHFFFAOYSA-N",
"smiles": "COCCCOc1ccnc(CO)c1C"
},
"smiles": "COCCCOc1ccnc(CO)c1C",
"reactionStepId": "sa_fddaab6cfdd4dc85e5a9be10",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US05998445;;458202\",\"rsmi\":\"CC(=O)[O:12][CH2:11][c:10]1[c:8]([CH3:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:15][cH:14][n:13]1>CCO.[Na+].O>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH2:11][OH:12])[n:13][cH:14][cH:15]1\"},\"mapped_reaction_smiles\":\"CC(=O)[O:12][CH2:11][c:10]1[c:8]([CH3:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:15][cH:14][n:13]1>CCO.[Na+].O>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH2:11][OH:12])[n:13][cH:14][cH:15]1\"}",
"reactionStep": {
"id": "sa_fddaab6cfdd4dc85e5a9be10",
"reactionHash": "2f84feca038bf74a62b627fbe91ca1306e693c6a0f6ff9eb244c8eb56f34e813"
},
"children": [
{
"id": "3999",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_bbd437d35a42a1a27ee1e516",
"parentId": "3998",
"isLeaf": false,
"molecule": {
"id": "sa_bbd437d35a42a1a27ee1e516",
"inchikey": "MCHZMEXSIPGEDJ-UHFFFAOYSA-N",
"smiles": "COCCCOc1ccnc(COC(C)=O)c1C"
},
"smiles": "COCCCOc1ccnc(COC(C)=O)c1C",
"reactionStepId": "sa_e61231a03fa304d5ac2f776d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US05998445;;458201\",\"rsmi\":\"CC(=O)[O:12][C:13]([CH3:14])=[O:15].[O-][n+:16]1[c:10]([CH3:11])[c:8]([CH3:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:18][cH:17]1>>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH2:11][O:12][C:13]([CH3:14])=[O:15])[n:16][cH:17][cH:18]1\"},\"mapped_reaction_smiles\":\"CC(=O)[O:12][C:13]([CH3:14])=[O:15].[O-][n+:16]1[c:10]([CH3:11])[c:8]([CH3:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:18][cH:17]1>>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH2:11][O:12][C:13]([CH3:14])=[O:15])[n:16][cH:17][cH:18]1\"}",
"reactionStep": {
"id": "sa_e61231a03fa304d5ac2f776d",
"reactionHash": "112e5b68c8c9f06eb1578e6f9b5f1180c7d4fc5c84248a9b06f848846764299c"
},
"children": [
{
"id": "4000",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_112784b383ee73e9118e5f80",
"parentId": "3999",
"isLeaf": false,
"molecule": {
"id": "sa_112784b383ee73e9118e5f80",
"inchikey": "NZQKWDSCDLYKDF-UHFFFAOYSA-N",
"smiles": "COCCCOc1cc[n+]([O-])c(C)c1C"
},
"smiles": "COCCCOc1cc[n+]([O-])c(C)c1C",
"reactionStepId": "sa_2982fd091b97af17b335702f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US05998445;;458200\",\"rsmi\":\"Cl[c:7]1[c:8]([CH3:9])[c:10]([CH3:11])[n+:12]([O-:13])[cH:14][cH:15]1.[CH3:1][O:2][CH2:3][CH2:4][CH2:5][OH:6]>CS(C)=O.[HH].[Na+]>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH3:11])[n+:12]([O-:13])[cH:14][cH:15]1\"},\"mapped_reaction_smiles\":\"Cl[c:7]1[c:8]([CH3:9])[c:10]([CH3:11])[n+:12]([O-:13])[cH:14][cH:15]1.[CH3:1][O:2][CH2:3][CH2:4][CH2:5][OH:6]>CS(C)=O.[HH].[Na+]>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([CH3:9])[c:10]([CH3:11])[n+:12]([O-:13])[cH:14][cH:15]1\"}",
"reactionStep": {
"id": "sa_2982fd091b97af17b335702f",
"reactionHash": "4188f802304b3451077ddf482b6a924c9e10a737fe17d5c5e6ada37e16c8080a"
},
"children": [
{
"id": "4001",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_5940ecd4737edca6a5296282",
"parentId": "4000",
"isLeaf": true,
"molecule": {
"id": "sa_5940ecd4737edca6a5296282",
"inchikey": "JDFDHBSESGTDAL-UHFFFAOYSA-N",
"smiles": "COCCCO"
},
"smiles": "COCCCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "4002",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_860f13ac38cab3f44cd3d70e",
"parentId": "4000",
"isLeaf": true,
"molecule": {
"id": "sa_860f13ac38cab3f44cd3d70e",
"inchikey": "MCUYHRNUDDANSO-UHFFFAOYSA-N",
"smiles": "Cc1c(Cl)cc[n+]([O-])c1C"
},
"smiles": "Cc1c(Cl)cc[n+]([O-])c1C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "4003",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_a7893fcf81826693d9b4bed4",
"parentId": "3999",
"isLeaf": true,
"molecule": {
"id": "sa_a7893fcf81826693d9b4bed4",
"inchikey": "WFDIJRYMOXRFFG-UHFFFAOYSA-N",
"smiles": "CC(=O)OC(C)=O"
},
"smiles": "CC(=O)OC(C)=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "4004",
"routeId": "sa_0082f3e13a39610198831aa9",
"moleculeId": "sa_40b64d20223d1358efada2f7",
"parentId": "3995",
"isLeaf": true,
"molecule": {
"id": "sa_40b64d20223d1358efada2f7",
"inchikey": "YHMYGUUIMTVXNW-UHFFFAOYSA-N",
"smiles": "Sc1nc2ccccc2[nH]1"
},
"smiles": "Sc1nc2ccccc2[nH]1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}