Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CCOC(=O)CC1OB(O)c2cc(OC)cc(Cl)c21
InChiKey
AYXQYZOCYKMMRB-UHFFFAOYSA-N
Route Signature
8b15dab2aa9447ef2fd0f360f2dd960c036912ce07b9cfa9c95c88543571388f
Synthesis route with 6 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_3cbb100bbd8ae4b661a4879c",
"signature": "8b15dab2aa9447ef2fd0f360f2dd960c036912ce07b9cfa9c95c88543571388f",
"contentHash": "81f37d98b231f5e22c0d5ea71722c5698a0526e59092559f89f210ffd00863f7",
"length": 6,
"isConvergent": false
},
"target": {
"id": "sa_1686e6461c8ee3bc4fbcdbde",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00145",
"moleculeId": "sa_157995acce833336571c5625",
"smiles": "CCOC(=O)CC1OB(O)c2cc(OC)cc(Cl)c21",
"routeLength": 6,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_157995acce833336571c5625",
"inchikey": "AYXQYZOCYKMMRB-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CC1OB(O)c2cc(OC)cc(Cl)c21"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "12549",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_157995acce833336571c5625",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_157995acce833336571c5625",
"inchikey": "AYXQYZOCYKMMRB-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CC1OB(O)c2cc(OC)cc(Cl)c21"
},
"smiles": "CCOC(=O)CC1OB(O)c2cc(OC)cc(Cl)c21",
"reactionStepId": "sa_9f1818b984f5417cc6663bcf",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08343944B2;0612;1266120\",\"rsmi\":\"I[CH3:18].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH:7]1[O:8][B:9]([OH:10])[c:11]2[c:12]1[c:13]([Cl:14])[cH:15][c:16]([OH:17])[cH:19]2>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH:7]1[O:8][B:9]([OH:10])[c:11]2[c:12]1[c:13]([Cl:14])[cH:15][c:16]([O:17][CH3:18])[cH:19]2\"},\"mapped_reaction_smiles\":\"I[CH3:18].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH:7]1[O:8][B:9]([OH:10])[c:11]2[c:12]1[c:13]([Cl:14])[cH:15][c:16]([OH:17])[cH:19]2>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH:7]1[O:8][B:9]([OH:10])[c:11]2[c:12]1[c:13]([Cl:14])[cH:15][c:16]([O:17][CH3:18])[cH:19]2\"}",
"reactionStep": {
"id": "sa_9f1818b984f5417cc6663bcf",
"reactionHash": "cadce802d7427d516e11d763dc2fd7a19a1972d114dcd9e9b92497482716839e"
},
"children": [
{
"id": "12550",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_455f0796cf1f9e375fe7739f",
"parentId": "12549",
"isLeaf": false,
"molecule": {
"id": "sa_455f0796cf1f9e375fe7739f",
"inchikey": "IDXXLMJVJQBVQJ-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CC1OB(O)c2cc(O)cc(Cl)c21"
},
"smiles": "CCOC(=O)CC1OB(O)c2cc(O)cc(Cl)c21",
"reactionStepId": "sa_2e6c68222757777d835a3f1c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08343944B2;0509;1266075\",\"rsmi\":\"C1CCC([O:17][c:16]2[cH:15][c:13]([Cl:14])[c:12]3[c:11]([cH:18]2)[B:9]([OH:10])[O:8][CH:7]3[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])OC1>C1CCOC1.Cl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH:7]1[O:8][B:9]([OH:10])[c:11]2[c:12]1[c:13]([Cl:14])[cH:15][c:16]([OH:17])[cH:18]2\"},\"mapped_reaction_smiles\":\"C1CCC([O:17][c:16]2[cH:15][c:13]([Cl:14])[c:12]3[c:11]([cH:18]2)[B:9]([OH:10])[O:8][CH:7]3[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])OC1>C1CCOC1.Cl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH:7]1[O:8][B:9]([OH:10])[c:11]2[c:12]1[c:13]([Cl:14])[cH:15][c:16]([OH:17])[cH:18]2\"}",
"reactionStep": {
"id": "sa_2e6c68222757777d835a3f1c",
"reactionHash": "2c2ad5267924d90a87daae28349ca5ddb34ca79a47a15f3d470bab46ecd872f0"
},
"children": [
{
"id": "12551",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_a10cf598f2bb37a060d3768e",
"parentId": "12550",
"isLeaf": false,
"molecule": {
"id": "sa_a10cf598f2bb37a060d3768e",
"inchikey": "WUELIHZOOIGRDU-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CC1OB(O)c2cc(OC3CCCCO3)cc(Cl)c21"
},
"smiles": "CCOC(=O)CC1OB(O)c2cc(OC3CCCCO3)cc(Cl)c21",
"reactionStepId": "sa_89d96e3bb88710eaa6595254",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08343944B2;0507;1266074\",\"rsmi\":\"Br[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].CC1(C)O[B:9]([c:11]2[c:12]([CH:7]=[O:8])[c:13]([Cl:14])[cH:15][c:16]([O:17][CH:18]3[CH2:19][CH2:20][CH2:21][CH2:22][O:23]3)[cH:24]2)[O:10]C1(C)C>C1CCOC1.C[Si](C)(C)Cl.[Zn]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH:7]1[O:8][B:9]([OH:10])[c:11]2[c:12]1[c:13]([Cl:14])[cH:15][c:16]([O:17][CH:18]1[CH2:19][CH2:20][CH2:21][CH2:22][O:23]1)[cH:24]2\"},\"mapped_reaction_smiles\":\"Br[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].CC1(C)O[B:9]([c:11]2[c:12]([CH:7]=[O:8])[c:13]([Cl:14])[cH:15][c:16]([O:17][CH:18]3[CH2:19][CH2:20][CH2:21][CH2:22][O:23]3)[cH:24]2)[O:10]C1(C)C>C1CCOC1.C[Si](C)(C)Cl.[Zn]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH:7]1[O:8][B:9]([OH:10])[c:11]2[c:12]1[c:13]([Cl:14])[cH:15][c:16]([O:17][CH:18]1[CH2:19][CH2:20][CH2:21][CH2:22][O:23]1)[cH:24]2\"}",
"reactionStep": {
"id": "sa_89d96e3bb88710eaa6595254",
"reactionHash": "b899a1661e357362d20ff4cba6e8bc1f56e64255026b05ac32f5a06506481da4"
},
"children": [
{
"id": "12552",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_399d60540d214e97a6ef975e",
"parentId": "12551",
"isLeaf": false,
"molecule": {
"id": "sa_399d60540d214e97a6ef975e",
"inchikey": "HIUSUCYNGFXUKY-UHFFFAOYSA-N",
"smiles": "CC1(C)OB(c2cc(OC3CCCCO3)cc(Cl)c2C=O)OC1(C)C"
},
"smiles": "CC1(C)OB(c2cc(OC3CCCCO3)cc(Cl)c2C=O)OC1(C)C",
"reactionStepId": "sa_5e9d47b8861baa0c81fb7b85",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08343944B2;0505;1266073\",\"rsmi\":\"CC1(C)OB([B:5]2[O:4][C:2]([CH3:1])([CH3:3])[C:23]([CH3:24])([CH3:25])[O:22]2)OC1(C)C.O=S(=O)(O[c:6]1[cH:7][c:8]([O:9][CH:10]2[CH2:11][CH2:12][CH2:13][CH2:14][O:15]2)[cH:16][c:17]([Cl:18])[c:19]1[CH:20]=[O:21])C(F)(F)F>C1COCCO1.CC(=O)O.Cl[Pd]Cl.[Fe+2].[K+]>[CH3:1][C:2]1([CH3:3])[O:4][B:5]([c:6]2[cH:7][c:8]([O:9][CH:10]3[CH2:11][CH2:12][CH2:13][CH2:14][O:15]3)[cH:16][c:17]([Cl:18])[c:19]2[CH:20]=[O:21])[O:22][C:23]1([CH3:24])[CH3:25]\"},\"mapped_reaction_smiles\":\"CC1(C)OB([B:5]2[O:4][C:2]([CH3:1])([CH3:3])[C:23]([CH3:24])([CH3:25])[O:22]2)OC1(C)C.O=S(=O)(O[c:6]1[cH:7][c:8]([O:9][CH:10]2[CH2:11][CH2:12][CH2:13][CH2:14][O:15]2)[cH:16][c:17]([Cl:18])[c:19]1[CH:20]=[O:21])C(F)(F)F>C1COCCO1.CC(=O)O.Cl[Pd]Cl.[Fe+2].[K+]>[CH3:1][C:2]1([CH3:3])[O:4][B:5]([c:6]2[cH:7][c:8]([O:9][CH:10]3[CH2:11][CH2:12][CH2:13][CH2:14][O:15]3)[cH:16][c:17]([Cl:18])[c:19]2[CH:20]=[O:21])[O:22][C:23]1([CH3:24])[CH3:25]\"}",
"reactionStep": {
"id": "sa_5e9d47b8861baa0c81fb7b85",
"reactionHash": "843f09f608c6579735441ff5e3ef3107fbdd91db86ee2793a7c8e932a690d43b"
},
"children": [
{
"id": "12553",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_e6c301388ac142801d4af5a2",
"parentId": "12552",
"isLeaf": true,
"molecule": {
"id": "sa_e6c301388ac142801d4af5a2",
"inchikey": "IPWKHHSGDUIRAH-UHFFFAOYSA-N",
"smiles": "CC1(C)OB(B2OC(C)(C)C(C)(C)O2)OC1(C)C"
},
"smiles": "CC1(C)OB(B2OC(C)(C)C(C)(C)O2)OC1(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12554",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_34e373eaeb208becd786287c",
"parentId": "12552",
"isLeaf": false,
"molecule": {
"id": "sa_34e373eaeb208becd786287c",
"inchikey": "TYOOBFZLZAHPGO-UHFFFAOYSA-N",
"smiles": "O=Cc1c(Cl)cc(OC2CCCCO2)cc1OS(=O)(=O)C(F)(F)F"
},
"smiles": "O=Cc1c(Cl)cc(OC2CCCCO2)cc1OS(=O)(=O)C(F)(F)F",
"reactionStepId": "sa_f48c3370eb7188b714963562",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08343944B2;0503;1266072\",\"rsmi\":\"O=S(=O)(O[S:6](=[O:7])(=[O:8])[C:9]([F:10])([F:11])[F:12])C(F)(F)F.[O:1]=[CH:2][c:3]1[c:4]([OH:5])[cH:13][c:14]([O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][c:23]1[Cl:24]>ClCCl.c1ccncc1>[O:1]=[CH:2][c:3]1[c:4]([O:5][S:6](=[O:7])(=[O:8])[C:9]([F:10])([F:11])[F:12])[cH:13][c:14]([O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][c:23]1[Cl:24]\"},\"mapped_reaction_smiles\":\"O=S(=O)(O[S:6](=[O:7])(=[O:8])[C:9]([F:10])([F:11])[F:12])C(F)(F)F.[O:1]=[CH:2][c:3]1[c:4]([OH:5])[cH:13][c:14]([O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][c:23]1[Cl:24]>ClCCl.c1ccncc1>[O:1]=[CH:2][c:3]1[c:4]([O:5][S:6](=[O:7])(=[O:8])[C:9]([F:10])([F:11])[F:12])[cH:13][c:14]([O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][c:23]1[Cl:24]\"}",
"reactionStep": {
"id": "sa_f48c3370eb7188b714963562",
"reactionHash": "8db6789098c5565d51ce40c296d7999912d79cd782909eaa221a6155d34f2dab"
},
"children": [
{
"id": "12555",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_90d265c6de1f4a132506c508",
"parentId": "12554",
"isLeaf": false,
"molecule": {
"id": "sa_90d265c6de1f4a132506c508",
"inchikey": "NVXMTHNQSJCODP-UHFFFAOYSA-N",
"smiles": "O=Cc1c(O)cc(OC2CCCCO2)cc1Cl"
},
"smiles": "O=Cc1c(O)cc(OC2CCCCO2)cc1Cl",
"reactionStepId": "sa_032b7cafc0e6860f464e506a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08343944B2;0501;1266071\",\"rsmi\":\"[CH:9]1=[CH:10][CH2:11][CH2:12][CH2:13][O:14]1.[O:1]=[CH:2][c:3]1[c:4]([OH:5])[cH:6][c:7]([OH:8])[cH:15][c:16]1[Cl:17]>ClCCl>[O:1]=[CH:2][c:3]1[c:4]([OH:5])[cH:6][c:7]([O:8][CH:9]2[CH2:10][CH2:11][CH2:12][CH2:13][O:14]2)[cH:15][c:16]1[Cl:17]\"},\"mapped_reaction_smiles\":\"[CH:9]1=[CH:10][CH2:11][CH2:12][CH2:13][O:14]1.[O:1]=[CH:2][c:3]1[c:4]([OH:5])[cH:6][c:7]([OH:8])[cH:15][c:16]1[Cl:17]>ClCCl>[O:1]=[CH:2][c:3]1[c:4]([OH:5])[cH:6][c:7]([O:8][CH:9]2[CH2:10][CH2:11][CH2:12][CH2:13][O:14]2)[cH:15][c:16]1[Cl:17]\"}",
"reactionStep": {
"id": "sa_032b7cafc0e6860f464e506a",
"reactionHash": "e509548cb1bbaf2824437c9fbe98b39a9b6bd8cfe844a6f60ff4439523402801"
},
"children": [
{
"id": "12556",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_359472b115a712c065ff6c19",
"parentId": "12555",
"isLeaf": true,
"molecule": {
"id": "sa_359472b115a712c065ff6c19",
"inchikey": "BUDQDWGNQVEFAC-UHFFFAOYSA-N",
"smiles": "C1=COCCC1"
},
"smiles": "C1=COCCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12557",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_1e986ddbafe371d64fcb9fa7",
"parentId": "12555",
"isLeaf": true,
"molecule": {
"id": "sa_1e986ddbafe371d64fcb9fa7",
"inchikey": "IEBZIQWQUFKXMM-UHFFFAOYSA-N",
"smiles": "O=Cc1c(O)cc(O)cc1Cl"
},
"smiles": "O=Cc1c(O)cc(O)cc1Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "12558",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_d8869d189c1f39359fac1c8b",
"parentId": "12554",
"isLeaf": true,
"molecule": {
"id": "sa_d8869d189c1f39359fac1c8b",
"inchikey": "WJKHJLXJJJATHN-UHFFFAOYSA-N",
"smiles": "O=S(=O)(OS(=O)(=O)C(F)(F)F)C(F)(F)F"
},
"smiles": "O=S(=O)(OS(=O)(=O)C(F)(F)F)C(F)(F)F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "12559",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_6170bddd2f4a4137325c4a17",
"parentId": "12551",
"isLeaf": true,
"molecule": {
"id": "sa_6170bddd2f4a4137325c4a17",
"inchikey": "PQJJJMRNHATNKG-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CBr"
},
"smiles": "CCOC(=O)CBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "12560",
"routeId": "sa_3cbb100bbd8ae4b661a4879c",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "12549",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}