Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1nn2cc(-c3cc4c(OCc5csc(C6(F)CCOCC6)n5)cc(Cl)cc4o3)nc2s1
InChiKey
XAAGLIXHTMLMLA-UHFFFAOYSA-N
Route Signature
a87da8e1ab3b59442706e9fc797179bcd1be521cb8a72415e26b26f499498dfe
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_e22e259b7b8ffac0f8d59c7f",
"signature": "a87da8e1ab3b59442706e9fc797179bcd1be521cb8a72415e26b26f499498dfe",
"contentHash": "d5b8c829cb3ebfec80a9555198dac10b5adaf364dbbfd859cb3a165da3edad44",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_30862a84d00ec6290b4e8897",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00129",
"moleculeId": "sa_d68d4c24908ab5a4ea0b17c5",
"smiles": "COc1nn2cc(-c3cc4c(OCc5csc(C6(F)CCOCC6)n5)cc(Cl)cc4o3)nc2s1",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_d68d4c24908ab5a4ea0b17c5",
"inchikey": "XAAGLIXHTMLMLA-UHFFFAOYSA-N",
"smiles": "COc1nn2cc(-c3cc4c(OCc5csc(C6(F)CCOCC6)n5)cc(Cl)cc4o3)nc2s1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9207",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_d68d4c24908ab5a4ea0b17c5",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_d68d4c24908ab5a4ea0b17c5",
"inchikey": "XAAGLIXHTMLMLA-UHFFFAOYSA-N",
"smiles": "COc1nn2cc(-c3cc4c(OCc5csc(C6(F)CCOCC6)n5)cc(Cl)cc4o3)nc2s1"
},
"smiles": "COc1nn2cc(-c3cc4c(OCc5csc(C6(F)CCOCC6)n5)cc(Cl)cc4o3)nc2s1",
"reactionStepId": "sa_3c8030b479da04ea0df187e2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150094297A1;2152;1672411\",\"rsmi\":\"Br[CH2:18][c:19]1[cH:20][s:21][c:22]([C:23]2([F:24])[CH2:25][CH2:26][O:27][CH2:28][CH2:29]2)[n:30]1.[CH3:1][O:2][c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([cH:12][c:13]([Cl:14])[cH:15][c:16]4[OH:17])[o:31]3)[n:32][c:33]2[s:34]1>CCOC(C)=O.CN(C)C=O.ClCCl.O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([cH:12][c:13]([Cl:14])[cH:15][c:16]4[O:17][CH2:18][c:19]4[cH:20][s:21][c:22]([C:23]5([F:24])[CH2:25][CH2:26][O:27][CH2:28][CH2:29]5)[n:30]4)[o:31]3)[n:32][c:33]2[s:34]1\"},\"mapped_reaction_smiles\":\"Br[CH2:18][c:19]1[cH:20][s:21][c:22]([C:23]2([F:24])[CH2:25][CH2:26][O:27][CH2:28][CH2:29]2)[n:30]1.[CH3:1][O:2][c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([cH:12][c:13]([Cl:14])[cH:15][c:16]4[OH:17])[o:31]3)[n:32][c:33]2[s:34]1>CCOC(C)=O.CN(C)C=O.ClCCl.O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([cH:12][c:13]([Cl:14])[cH:15][c:16]4[O:17][CH2:18][c:19]4[cH:20][s:21][c:22]([C:23]5([F:24])[CH2:25][CH2:26][O:27][CH2:28][CH2:29]5)[n:30]4)[o:31]3)[n:32][c:33]2[s:34]1\"}",
"reactionStep": {
"id": "sa_3c8030b479da04ea0df187e2",
"reactionHash": "867006a4f9e38423b2e8289a3f81e77b0178cc34c76227fda80c2eb04e38e05c"
},
"children": [
{
"id": "9208",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_427f1cca0a4e72a9cd35a9cb",
"parentId": "9207",
"isLeaf": false,
"molecule": {
"id": "sa_427f1cca0a4e72a9cd35a9cb",
"inchikey": "VZLONUKFKRQPKQ-UHFFFAOYSA-N",
"smiles": "FC1(c2nc(CBr)cs2)CCOCC1"
},
"smiles": "FC1(c2nc(CBr)cs2)CCOCC1",
"reactionStepId": "sa_db4a0b7a2d9cc5bf8c63014d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150094297A1;1791;1672307\",\"rsmi\":\"O=C1CCC(=O)N1[Br:7].[F:1][C:2]1([c:3]2[n:4][c:5]([CH3:6])[cH:8][s:9]2)[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1>ClC(Cl)(Cl)Cl.ClCCl.O=C(OOC(=O)c1ccccc1)c1ccccc1>[F:1][C:2]1([c:3]2[n:4][c:5]([CH2:6][Br:7])[cH:8][s:9]2)[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1\"},\"mapped_reaction_smiles\":\"O=C1CCC(=O)N1[Br:7].[F:1][C:2]1([c:3]2[n:4][c:5]([CH3:6])[cH:8][s:9]2)[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1>ClC(Cl)(Cl)Cl.ClCCl.O=C(OOC(=O)c1ccccc1)c1ccccc1>[F:1][C:2]1([c:3]2[n:4][c:5]([CH2:6][Br:7])[cH:8][s:9]2)[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1\"}",
"reactionStep": {
"id": "sa_db4a0b7a2d9cc5bf8c63014d",
"reactionHash": "c70db03518866020cf901e08cff48f7f48c43d02aca4e8fe285583d9c1662c3c"
},
"children": [
{
"id": "9209",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_20f41b1437631531b443f69b",
"parentId": "9208",
"isLeaf": false,
"molecule": {
"id": "sa_20f41b1437631531b443f69b",
"inchikey": "NNVDFLWGCBSTPK-UHFFFAOYSA-N",
"smiles": "Cc1csc(C2(F)CCOCC2)n1"
},
"smiles": "Cc1csc(C2(F)CCOCC2)n1",
"reactionStepId": "sa_b2206d2c86567282f94de1b0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150094297A1;1789;1672306\",\"rsmi\":\"CCN(CC)S(F)(F)[F:7].O[C:6]1([c:5]2[s:4][cH:3][c:2]([CH3:1])[n:13]2)[CH2:8][CH2:9][O:10][CH2:11][CH2:12]1>ClCCl.O=C(O)O.[Na+].[Na+]>[CH3:1][c:2]1[cH:3][s:4][c:5]([C:6]2([F:7])[CH2:8][CH2:9][O:10][CH2:11][CH2:12]2)[n:13]1\"},\"mapped_reaction_smiles\":\"CCN(CC)S(F)(F)[F:7].O[C:6]1([c:5]2[s:4][cH:3][c:2]([CH3:1])[n:13]2)[CH2:8][CH2:9][O:10][CH2:11][CH2:12]1>ClCCl.O=C(O)O.[Na+].[Na+]>[CH3:1][c:2]1[cH:3][s:4][c:5]([C:6]2([F:7])[CH2:8][CH2:9][O:10][CH2:11][CH2:12]2)[n:13]1\"}",
"reactionStep": {
"id": "sa_b2206d2c86567282f94de1b0",
"reactionHash": "787bc582b2a867ec84ed15c045dbcc914ed4dadf0f0396421905763d170138b8"
},
"children": [
{
"id": "9210",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_ea36804e09a923c015915fb2",
"parentId": "9209",
"isLeaf": true,
"molecule": {
"id": "sa_ea36804e09a923c015915fb2",
"inchikey": "CSJLBAMHHLJAAS-UHFFFAOYSA-N",
"smiles": "CCN(CC)S(F)(F)F"
},
"smiles": "CCN(CC)S(F)(F)F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9211",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_2aedc7588f1342d948a3f5a6",
"parentId": "9209",
"isLeaf": true,
"molecule": {
"id": "sa_2aedc7588f1342d948a3f5a6",
"inchikey": "YZNZCTLWUSVEOJ-UHFFFAOYSA-N",
"smiles": "Cc1csc(C2(O)CCOCC2)n1"
},
"smiles": "Cc1csc(C2(O)CCOCC2)n1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "9212",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_ccdcf23ac83e7a68bfa4f2e5",
"parentId": "9208",
"isLeaf": true,
"molecule": {
"id": "sa_ccdcf23ac83e7a68bfa4f2e5",
"inchikey": "PCLIMKBDDGJMGD-UHFFFAOYSA-N",
"smiles": "O=C1CCC(=O)N1Br"
},
"smiles": "O=C1CCC(=O)N1Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "9213",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_0ce183021ba14d2e93028112",
"parentId": "9207",
"isLeaf": false,
"molecule": {
"id": "sa_0ce183021ba14d2e93028112",
"inchikey": "YZZFXDXYPYKSOC-UHFFFAOYSA-N",
"smiles": "COc1nn2cc(-c3cc4c(O)cc(Cl)cc4o3)nc2s1"
},
"smiles": "COc1nn2cc(-c3cc4c(O)cc(Cl)cc4o3)nc2s1",
"reactionStepId": "sa_7d3cf9c893306ef2bc2ad223",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150094297A1;2144;1672410\",\"rsmi\":\"c1ccc(C[O:12][c:11]2[c:10]3[cH:9][c:8](-[c:7]4[cH:6][n:5]5[n:4][c:3]([O:2][CH3:1])[s:21][c:20]5[n:19]4)[o:18][c:17]3[cH:16][c:14]([Cl:15])[cH:13]2)cc1>Cc1cc(C)c(C)c(C)c1C.ClB(Cl)Cl.ClCCl.O.O=C(O)O.[Na+]>[CH3:1][O:2][c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([OH:12])[cH:13][c:14]([Cl:15])[cH:16][c:17]4[o:18]3)[n:19][c:20]2[s:21]1\"},\"mapped_reaction_smiles\":\"c1ccc(C[O:12][c:11]2[c:10]3[cH:9][c:8](-[c:7]4[cH:6][n:5]5[n:4][c:3]([O:2][CH3:1])[s:21][c:20]5[n:19]4)[o:18][c:17]3[cH:16][c:14]([Cl:15])[cH:13]2)cc1>Cc1cc(C)c(C)c(C)c1C.ClB(Cl)Cl.ClCCl.O.O=C(O)O.[Na+]>[CH3:1][O:2][c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([OH:12])[cH:13][c:14]([Cl:15])[cH:16][c:17]4[o:18]3)[n:19][c:20]2[s:21]1\"}",
"reactionStep": {
"id": "sa_7d3cf9c893306ef2bc2ad223",
"reactionHash": "65b4310d2cbbd3b357ba3e8b33d5fa69ce07ae4085da4609bcd98cafdd26e30f"
},
"children": [
{
"id": "9214",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_e6d5f0dc722decbe9b087700",
"parentId": "9213",
"isLeaf": false,
"molecule": {
"id": "sa_e6d5f0dc722decbe9b087700",
"inchikey": "GTSNMFZVVWGEKE-UHFFFAOYSA-N",
"smiles": "COc1nn2cc(-c3cc4c(OCc5ccccc5)cc(Cl)cc4o3)nc2s1"
},
"smiles": "COc1nn2cc(-c3cc4c(OCc5ccccc5)cc(Cl)cc4o3)nc2s1",
"reactionStepId": "sa_2f80dcd3c23ad8816d515ce3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150094297A1;2142;1672409\",\"rsmi\":\"Br[c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([cH:12][c:13]([Cl:14])[cH:15][c:16]4[O:17][CH2:18][c:19]4[cH:20][cH:21][cH:22][cH:23][cH:24]4)[o:25]3)[n:26][c:27]2[s:28]1.[CH3:1][OH:2]>CCOC(C)=O.CO.ClCCl.[Na+]>[CH3:1][O:2][c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([cH:12][c:13]([Cl:14])[cH:15][c:16]4[O:17][CH2:18][c:19]4[cH:20][cH:21][cH:22][cH:23][cH:24]4)[o:25]3)[n:26][c:27]2[s:28]1\"},\"mapped_reaction_smiles\":\"Br[c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([cH:12][c:13]([Cl:14])[cH:15][c:16]4[O:17][CH2:18][c:19]4[cH:20][cH:21][cH:22][cH:23][cH:24]4)[o:25]3)[n:26][c:27]2[s:28]1.[CH3:1][OH:2]>CCOC(C)=O.CO.ClCCl.[Na+]>[CH3:1][O:2][c:3]1[n:4][n:5]2[cH:6][c:7](-[c:8]3[cH:9][c:10]4[c:11]([cH:12][c:13]([Cl:14])[cH:15][c:16]4[O:17][CH2:18][c:19]4[cH:20][cH:21][cH:22][cH:23][cH:24]4)[o:25]3)[n:26][c:27]2[s:28]1\"}",
"reactionStep": {
"id": "sa_2f80dcd3c23ad8816d515ce3",
"reactionHash": "181db7f117221772a10a50e3d13df38f206f1d857edb7d8ff2235a3be8851a61"
},
"children": [
{
"id": "9215",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_6989bd3b4570be6ec2bf9ee4",
"parentId": "9214",
"isLeaf": false,
"molecule": {
"id": "sa_6989bd3b4570be6ec2bf9ee4",
"inchikey": "FOZWIAVQOLNSAV-UHFFFAOYSA-N",
"smiles": "Clc1cc(OCc2ccccc2)c2cc(-c3cn4nc(Br)sc4n3)oc2c1"
},
"smiles": "Clc1cc(OCc2ccccc2)c2cc(-c3cn4nc(Br)sc4n3)oc2c1",
"reactionStepId": "sa_2e37f1ab414516146b907832",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150094297A1;2140;1672408\",\"rsmi\":\"O=[C:8]([c:7]1[cH:6][c:5]2[c:4]([cH:3][c:2]([Cl:1])[cH:27][c:18]2[O:19][CH2:20][c:21]2[cH:22][cH:23][cH:24][cH:25][cH:26]2)[o:17]1)[CH2:9]Br.[n:10]1[n:11][c:12]([Br:13])[s:14][c:15]1[NH2:16]>CC(C)O>[Cl:1][c:2]1[cH:3][c:4]2[c:5]([cH:6][c:7](-[c:8]3[cH:9][n:10]4[n:11][c:12]([Br:13])[s:14][c:15]4[n:16]3)[o:17]2)[c:18]([O:19][CH2:20][c:21]2[cH:22][cH:23][cH:24][cH:25][cH:26]2)[cH:27]1\"},\"mapped_reaction_smiles\":\"O=[C:8]([c:7]1[cH:6][c:5]2[c:4]([cH:3][c:2]([Cl:1])[cH:27][c:18]2[O:19][CH2:20][c:21]2[cH:22][cH:23][cH:24][cH:25][cH:26]2)[o:17]1)[CH2:9]Br.[n:10]1[n:11][c:12]([Br:13])[s:14][c:15]1[NH2:16]>CC(C)O>[Cl:1][c:2]1[cH:3][c:4]2[c:5]([cH:6][c:7](-[c:8]3[cH:9][n:10]4[n:11][c:12]([Br:13])[s:14][c:15]4[n:16]3)[o:17]2)[c:18]([O:19][CH2:20][c:21]2[cH:22][cH:23][cH:24][cH:25][cH:26]2)[cH:27]1\"}",
"reactionStep": {
"id": "sa_2e37f1ab414516146b907832",
"reactionHash": "2fcaeafadfc5c59d333087df03907d5d68f924df4084ede9994ba5ec52c7ed95"
},
"children": [
{
"id": "9216",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_f01f5346e2011f4775fafe58",
"parentId": "9215",
"isLeaf": true,
"molecule": {
"id": "sa_f01f5346e2011f4775fafe58",
"inchikey": "GLYQQFBHCFPEEU-UHFFFAOYSA-N",
"smiles": "Nc1nnc(Br)s1"
},
"smiles": "Nc1nnc(Br)s1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9217",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_fcfbc1d5c355322411a13001",
"parentId": "9215",
"isLeaf": true,
"molecule": {
"id": "sa_fcfbc1d5c355322411a13001",
"inchikey": "YDWSXTUCYBQKCL-UHFFFAOYSA-N",
"smiles": "O=C(CBr)c1cc2c(OCc3ccccc3)cc(Cl)cc2o1"
},
"smiles": "O=C(CBr)c1cc2c(OCc3ccccc3)cc(Cl)cc2o1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "9218",
"routeId": "sa_e22e259b7b8ffac0f8d59c7f",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "9214",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}