Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
O[C@H](CNCCC1=CCCCC1)COc1cccc(-c2noc3cc(F)ccc23)c1
InChiKey
GEWLAZDHXKQKMU-HXUWFJFHSA-N
Route Signature
858d72668c22556f9ebd39f4643bf637ec54116a1c0aa0508eb92fbba72e8167
Synthesis route with 7 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_1ba357c20b70db1c4adcc914",
"signature": "858d72668c22556f9ebd39f4643bf637ec54116a1c0aa0508eb92fbba72e8167",
"contentHash": "a855160310330f5e62b38478567f85307b6fb28acc6ea0f726714c96001ead6e",
"length": 7,
"isConvergent": false
},
"target": {
"id": "sa_ba3d94e44520d944c9358c93",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00236",
"moleculeId": "sa_64248c3ac0da0beddd7130aa",
"smiles": "O[C@H](CNCCC1=CCCCC1)COc1cccc(-c2noc3cc(F)ccc23)c1",
"routeLength": 7,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_64248c3ac0da0beddd7130aa",
"inchikey": "GEWLAZDHXKQKMU-HXUWFJFHSA-N",
"smiles": "O[C@H](CNCCC1=CCCCC1)COc1cccc(-c2noc3cc(F)ccc23)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "12903",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_64248c3ac0da0beddd7130aa",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_64248c3ac0da0beddd7130aa",
"inchikey": "GEWLAZDHXKQKMU-HXUWFJFHSA-N",
"smiles": "O[C@H](CNCCC1=CCCCC1)COc1cccc(-c2noc3cc(F)ccc23)c1"
},
"smiles": "O[C@H](CNCCC1=CCCCC1)COc1cccc(-c2noc3cc(F)ccc23)c1",
"reactionStepId": "sa_9cd14e18316dfb71462502a2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20050107377A1;0351;250401\",\"rsmi\":\"[NH2:4][CH2:5][CH2:6][C:7]1=[CH:8][CH2:9][CH2:10][CH2:11][CH2:12]1.[O:1]1[C@@H:2]([CH2:13][O:14][c:15]2[cH:16][c:17](-[c:18]3[n:19][o:20][c:21]4[c:22]3[cH:23][cH:24][c:25]([F:26])[cH:27]4)[cH:28][cH:29][cH:30]2)[CH2:3]1>CC(Cl)Cl.CCO>[OH:1][C@H:2]([CH2:3][NH:4][CH2:5][CH2:6][C:7]1=[CH:8][CH2:9][CH2:10][CH2:11][CH2:12]1)[CH2:13][O:14][c:15]1[cH:16][c:17](-[c:18]2[n:19][o:20][c:21]3[c:22]2[cH:23][cH:24][c:25]([F:26])[cH:27]3)[cH:28][cH:29][cH:30]1\"},\"mapped_reaction_smiles\":\"[NH2:4][CH2:5][CH2:6][C:7]1=[CH:8][CH2:9][CH2:10][CH2:11][CH2:12]1.[O:1]1[C@@H:2]([CH2:13][O:14][c:15]2[cH:16][c:17](-[c:18]3[n:19][o:20][c:21]4[c:22]3[cH:23][cH:24][c:25]([F:26])[cH:27]4)[cH:28][cH:29][cH:30]2)[CH2:3]1>CC(Cl)Cl.CCO>[OH:1][C@H:2]([CH2:3][NH:4][CH2:5][CH2:6][C:7]1=[CH:8][CH2:9][CH2:10][CH2:11][CH2:12]1)[CH2:13][O:14][c:15]1[cH:16][c:17](-[c:18]2[n:19][o:20][c:21]3[c:22]2[cH:23][cH:24][c:25]([F:26])[cH:27]3)[cH:28][cH:29][cH:30]1\"}",
"reactionStep": {
"id": "sa_9cd14e18316dfb71462502a2",
"reactionHash": "44a398841f94c03f5e4ad7469bc911dc6e00a47a183ab95b9533306b56acfeab"
},
"children": [
{
"id": "12904",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_8d52819c515370a0dd402040",
"parentId": "12903",
"isLeaf": true,
"molecule": {
"id": "sa_8d52819c515370a0dd402040",
"inchikey": "IUDMXOOVKMKODN-UHFFFAOYSA-N",
"smiles": "NCCC1=CCCCC1"
},
"smiles": "NCCC1=CCCCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12905",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_9c9e818880ebe56bc1c55627",
"parentId": "12903",
"isLeaf": false,
"molecule": {
"id": "sa_9c9e818880ebe56bc1c55627",
"inchikey": "PPTOJSVCXIFKRB-ZDUSSCGKSA-N",
"smiles": "Fc1ccc2c(-c3cccc(OC[C@H]4CO4)c3)noc2c1"
},
"smiles": "Fc1ccc2c(-c3cccc(OC[C@H]4CO4)c3)noc2c1",
"reactionStepId": "sa_dfd662acf8546868ea9652a6",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20050107377A1;0190;250337\",\"rsmi\":\"Cc1ccc(S(=O)(=O)[O:12][CH2:13][C@H:14]2[CH2:15][O:16]2)cc1.O[c:11]1[cH:10][c:9](-[c:8]2[c:5]3[c:4]([cH:3][c:2]([F:1])[cH:7][cH:6]3)[o:21][n:20]2)[cH:19][cH:18][cH:17]1>CN(C)C=O.O.[HH].[Na+]>[F:1][c:2]1[cH:3][c:4]2[c:5]([cH:6][cH:7]1)[c:8](-[c:9]1[cH:10][c:11]([O:12][CH2:13][C@H:14]3[CH2:15][O:16]3)[cH:17][cH:18][cH:19]1)[n:20][o:21]2\"},\"mapped_reaction_smiles\":\"Cc1ccc(S(=O)(=O)[O:12][CH2:13][C@H:14]2[CH2:15][O:16]2)cc1.O[c:11]1[cH:10][c:9](-[c:8]2[c:5]3[c:4]([cH:3][c:2]([F:1])[cH:7][cH:6]3)[o:21][n:20]2)[cH:19][cH:18][cH:17]1>CN(C)C=O.O.[HH].[Na+]>[F:1][c:2]1[cH:3][c:4]2[c:5]([cH:6][cH:7]1)[c:8](-[c:9]1[cH:10][c:11]([O:12][CH2:13][C@H:14]3[CH2:15][O:16]3)[cH:17][cH:18][cH:19]1)[n:20][o:21]2\"}",
"reactionStep": {
"id": "sa_dfd662acf8546868ea9652a6",
"reactionHash": "f8d85fa870f387d3144c83a06ded2be77d3e00e7531f134082695a226ab20657"
},
"children": [
{
"id": "12906",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_ba101af3905b0d8a977d80ef",
"parentId": "12905",
"isLeaf": false,
"molecule": {
"id": "sa_ba101af3905b0d8a977d80ef",
"inchikey": "COYZSMFBUVAOBZ-UHFFFAOYSA-N",
"smiles": "Oc1cccc(-c2noc3cc(F)ccc23)c1"
},
"smiles": "Oc1cccc(-c2noc3cc(F)ccc23)c1",
"reactionStepId": "sa_d5ce1c7656e30342ea608c57",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20050107377A1;0186;250335\",\"rsmi\":\"C[O:1][c:2]1[cH:3][c:4](-[c:5]2[n:6][o:7][c:8]3[c:9]2[cH:10][cH:11][c:12]([F:13])[cH:14]3)[cH:15][cH:16][cH:17]1>BrB(Br)Br.ClCCl>[OH:1][c:2]1[cH:3][c:4](-[c:5]2[n:6][o:7][c:8]3[c:9]2[cH:10][cH:11][c:12]([F:13])[cH:14]3)[cH:15][cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"C[O:1][c:2]1[cH:3][c:4](-[c:5]2[n:6][o:7][c:8]3[c:9]2[cH:10][cH:11][c:12]([F:13])[cH:14]3)[cH:15][cH:16][cH:17]1>BrB(Br)Br.ClCCl>[OH:1][c:2]1[cH:3][c:4](-[c:5]2[n:6][o:7][c:8]3[c:9]2[cH:10][cH:11][c:12]([F:13])[cH:14]3)[cH:15][cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_d5ce1c7656e30342ea608c57",
"reactionHash": "cdae99be29b5691230b31d43e50491672891414fd400da1f541c25115ae841e6"
},
"children": [
{
"id": "12907",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_bde04505e3905338397d11d0",
"parentId": "12906",
"isLeaf": false,
"molecule": {
"id": "sa_bde04505e3905338397d11d0",
"inchikey": "XLYWAODZJZGVFU-UHFFFAOYSA-N",
"smiles": "COc1cccc(-c2noc3cc(F)ccc23)c1"
},
"smiles": "COc1cccc(-c2noc3cc(F)ccc23)c1",
"reactionStepId": "sa_06b4a0a3b4a691aa96cfc23c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20050107377A1;0184;250334\",\"rsmi\":\"F[c:11]1[c:12]([C:8]([c:7]2[cH:6][cH:5][cH:4][c:3]([O:2][CH3:1])[cH:18]2)=[N:9][OH:10])[cH:13][cH:14][c:15]([F:16])[cH:17]1>C1CCOC1.CC(C)(C)O.CCOC(C)=O.O.[K+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7](-[c:8]2[n:9][o:10][c:11]3[c:12]2[cH:13][cH:14][c:15]([F:16])[cH:17]3)[cH:18]1\"},\"mapped_reaction_smiles\":\"F[c:11]1[c:12]([C:8]([c:7]2[cH:6][cH:5][cH:4][c:3]([O:2][CH3:1])[cH:18]2)=[N:9][OH:10])[cH:13][cH:14][c:15]([F:16])[cH:17]1>C1CCOC1.CC(C)(C)O.CCOC(C)=O.O.[K+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7](-[c:8]2[n:9][o:10][c:11]3[c:12]2[cH:13][cH:14][c:15]([F:16])[cH:17]3)[cH:18]1\"}",
"reactionStep": {
"id": "sa_06b4a0a3b4a691aa96cfc23c",
"reactionHash": "e3a054e1dafc60a683c782420eeb3ab849b6dfa31372c90a534793e729d598a8"
},
"children": [
{
"id": "12908",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_abd0fa03c8c5a10f51acfb43",
"parentId": "12907",
"isLeaf": false,
"molecule": {
"id": "sa_abd0fa03c8c5a10f51acfb43",
"inchikey": "FCVLOKMREAKKQA-UHFFFAOYSA-N",
"smiles": "COc1cccc(C(=NO)c2ccc(F)cc2F)c1"
},
"smiles": "COc1cccc(C(=NO)c2ccc(F)cc2F)c1",
"reactionStepId": "sa_87ca0e31c04cfdc72cf34276",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20050107377A1;0182;250333\",\"rsmi\":\"O=[C:8]([c:7]1[cH:6][cH:5][cH:4][c:3]([O:2][CH3:1])[cH:19]1)[c:11]1[c:12]([F:13])[cH:14][c:15]([F:16])[cH:17][cH:18]1.[NH2:9][OH:10]>CCCCCCC.CCOC(C)=O.Cl.c1ccncc1>[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7]([C:8](=[N:9][OH:10])[c:11]2[c:12]([F:13])[cH:14][c:15]([F:16])[cH:17][cH:18]2)[cH:19]1\"},\"mapped_reaction_smiles\":\"O=[C:8]([c:7]1[cH:6][cH:5][cH:4][c:3]([O:2][CH3:1])[cH:19]1)[c:11]1[c:12]([F:13])[cH:14][c:15]([F:16])[cH:17][cH:18]1.[NH2:9][OH:10]>CCCCCCC.CCOC(C)=O.Cl.c1ccncc1>[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7]([C:8](=[N:9][OH:10])[c:11]2[c:12]([F:13])[cH:14][c:15]([F:16])[cH:17][cH:18]2)[cH:19]1\"}",
"reactionStep": {
"id": "sa_87ca0e31c04cfdc72cf34276",
"reactionHash": "be7df77191fa503d8d47eeef41b6b01d9028a54fa086ec48b197de9509102134"
},
"children": [
{
"id": "12909",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_04a18e3f07bde82ca29399ee",
"parentId": "12908",
"isLeaf": true,
"molecule": {
"id": "sa_04a18e3f07bde82ca29399ee",
"inchikey": "AVXURJPOCDRRFD-UHFFFAOYSA-N",
"smiles": "NO"
},
"smiles": "NO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12910",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_07165a5b7abccde2910fb2b2",
"parentId": "12908",
"isLeaf": false,
"molecule": {
"id": "sa_07165a5b7abccde2910fb2b2",
"inchikey": "NRHGFTWHTHCFCP-UHFFFAOYSA-N",
"smiles": "COc1cccc(C(=O)c2ccc(F)cc2F)c1"
},
"smiles": "COc1cccc(C(=O)c2ccc(F)cc2F)c1",
"reactionStepId": "sa_65bb9c3875884a609099eee5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20050107377A1;0180;250332\",\"rsmi\":\"[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7]([CH:8]([OH:9])[c:10]2[c:11]([F:12])[cH:13][c:14]([F:15])[cH:16][cH:17]2)[cH:18]1>CCCCCCC.CCOC(C)=O.Cc1ccccc1.[Mn+2].[O-2]>[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7]([C:8](=[O:9])[c:10]2[c:11]([F:12])[cH:13][c:14]([F:15])[cH:16][cH:17]2)[cH:18]1\"},\"mapped_reaction_smiles\":\"[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7]([CH:8]([OH:9])[c:10]2[c:11]([F:12])[cH:13][c:14]([F:15])[cH:16][cH:17]2)[cH:18]1>CCCCCCC.CCOC(C)=O.Cc1ccccc1.[Mn+2].[O-2]>[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7]([C:8](=[O:9])[c:10]2[c:11]([F:12])[cH:13][c:14]([F:15])[cH:16][cH:17]2)[cH:18]1\"}",
"reactionStep": {
"id": "sa_65bb9c3875884a609099eee5",
"reactionHash": "73a0629877be94aca0d6f90927fa40fc7c0d8a36bfa2042b5f2e4d79b0bb2e83"
},
"children": [
{
"id": "12911",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_1ff61e4de075dabb91102d9e",
"parentId": "12910",
"isLeaf": false,
"molecule": {
"id": "sa_1ff61e4de075dabb91102d9e",
"inchikey": "RJCFFLRAMVAIEJ-UHFFFAOYSA-N",
"smiles": "COc1cccc(C(O)c2ccc(F)cc2F)c1"
},
"smiles": "COc1cccc(C(O)c2ccc(F)cc2F)c1",
"reactionStepId": "sa_54a332190f79f7cc189fd3fd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20050107377A1;0178;250331\",\"rsmi\":\"Br[c:7]1[cH:6][cH:5][cH:4][c:3]([O:2][CH3:1])[cH:18]1.[CH:8](=[O:9])[c:10]1[c:11]([F:12])[cH:13][c:14]([F:15])[cH:16][cH:17]1>C1CCOC1.[Li]CCCC>[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7]([CH:8]([OH:9])[c:10]2[c:11]([F:12])[cH:13][c:14]([F:15])[cH:16][cH:17]2)[cH:18]1\"},\"mapped_reaction_smiles\":\"Br[c:7]1[cH:6][cH:5][cH:4][c:3]([O:2][CH3:1])[cH:18]1.[CH:8](=[O:9])[c:10]1[c:11]([F:12])[cH:13][c:14]([F:15])[cH:16][cH:17]1>C1CCOC1.[Li]CCCC>[CH3:1][O:2][c:3]1[cH:4][cH:5][cH:6][c:7]([CH:8]([OH:9])[c:10]2[c:11]([F:12])[cH:13][c:14]([F:15])[cH:16][cH:17]2)[cH:18]1\"}",
"reactionStep": {
"id": "sa_54a332190f79f7cc189fd3fd",
"reactionHash": "f5a8bf6186417f6111f5a39a5796d0fc085308328bc2e955bf48d89efa111ea7"
},
"children": [
{
"id": "12912",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_79e90ad0f369905aa0fd2aed",
"parentId": "12911",
"isLeaf": true,
"molecule": {
"id": "sa_79e90ad0f369905aa0fd2aed",
"inchikey": "PLDWAJLZAAHOGG-UHFFFAOYSA-N",
"smiles": "COc1cccc(Br)c1"
},
"smiles": "COc1cccc(Br)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12913",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_c1556b2348b500d9c4c81510",
"parentId": "12911",
"isLeaf": true,
"molecule": {
"id": "sa_c1556b2348b500d9c4c81510",
"inchikey": "WCGPCBACLBHDCI-UHFFFAOYSA-N",
"smiles": "O=Cc1ccc(F)cc1F"
},
"smiles": "O=Cc1ccc(F)cc1F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
]
},
{
"id": "12914",
"routeId": "sa_1ba357c20b70db1c4adcc914",
"moleculeId": "sa_1de62fea8626a08b4c23e0b5",
"parentId": "12905",
"isLeaf": true,
"molecule": {
"id": "sa_1de62fea8626a08b4c23e0b5",
"inchikey": "NOQXXYIGRPAZJC-SECBINFHSA-N",
"smiles": "Cc1ccc(S(=O)(=O)OC[C@H]2CO2)cc1"
},
"smiles": "Cc1ccc(S(=O)(=O)OC[C@H]2CO2)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}