Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CC1C(=O)Oc2c(Oc3ccccc3F)cccc21
InChiKey
GQONSSBYJRMZLB-UHFFFAOYSA-N
Route Signature
7766dfd712831b87e526b5f5f262fb609a4bab993e63eb0c70ba08300f1dbf36
Synthesis route with 8 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_fb009325de976bb02e66dddf",
"signature": "7766dfd712831b87e526b5f5f262fb609a4bab993e63eb0c70ba08300f1dbf36",
"contentHash": "f2de2fb390d51e9ed16a004f42d6ba4c2d5eb04300d23f8fe885a6c445dd3473",
"length": 8,
"isConvergent": false
},
"target": {
"id": "sa_e2b1459ffa0495ed7c7430a9",
"benchmarkSetId": "a82783729b577c36f2e09a2b6fdd55ae9542aed5546571d67ef9cb74dc21f70a",
"targetId": "n5-00225",
"moleculeId": "sa_ddfac5000e96b853ee048dfc",
"smiles": "CC1C(=O)Oc2c(Oc3ccccc3F)cccc21",
"routeLength": 8,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_ddfac5000e96b853ee048dfc",
"inchikey": "GQONSSBYJRMZLB-UHFFFAOYSA-N",
"smiles": "CC1C(=O)Oc2c(Oc3ccccc3F)cccc21"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "17839",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_ddfac5000e96b853ee048dfc",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_ddfac5000e96b853ee048dfc",
"inchikey": "GQONSSBYJRMZLB-UHFFFAOYSA-N",
"smiles": "CC1C(=O)Oc2c(Oc3ccccc3F)cccc21"
},
"smiles": "CC1C(=O)Oc2c(Oc3ccccc3F)cccc21",
"reactionStepId": "sa_1bbf696e73534dbf56b582a2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US04367238;;103216\",\"rsmi\":\"CO[c:6]1[c:7]([CH:2]([CH3:1])[C:3](=[O:4])[OH:5])[cH:8][cH:9][cH:10][c:11]1[O:12][c:13]1[c:14]([F:15])[cH:16][cH:17][cH:18][cH:19]1>CC(=O)OC(C)=O.I.O=S(O)O.[Na+]>[CH3:1][CH:2]1[C:3](=[O:4])[O:5][c:6]2[c:7]1[cH:8][cH:9][cH:10][c:11]2[O:12][c:13]1[c:14]([F:15])[cH:16][cH:17][cH:18][cH:19]1\"},\"mapped_reaction_smiles\":\"CO[c:6]1[c:7]([CH:2]([CH3:1])[C:3](=[O:4])[OH:5])[cH:8][cH:9][cH:10][c:11]1[O:12][c:13]1[c:14]([F:15])[cH:16][cH:17][cH:18][cH:19]1>CC(=O)OC(C)=O.I.O=S(O)O.[Na+]>[CH3:1][CH:2]1[C:3](=[O:4])[O:5][c:6]2[c:7]1[cH:8][cH:9][cH:10][c:11]2[O:12][c:13]1[c:14]([F:15])[cH:16][cH:17][cH:18][cH:19]1\"}",
"reactionStep": {
"id": "sa_1bbf696e73534dbf56b582a2",
"reactionHash": "2e8034f103ff69762e6d3883183919d63cc70f847075530e38fddf68bc3041c9"
},
"children": [
{
"id": "17840",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_e8c0ea5fd8470687b24ee8a5",
"parentId": "17839",
"isLeaf": false,
"molecule": {
"id": "sa_e8c0ea5fd8470687b24ee8a5",
"inchikey": "ZORMWWKHZNZGFS-UHFFFAOYSA-N",
"smiles": "COc1c(Oc2ccccc2F)cccc1C(C)C(=O)O"
},
"smiles": "COc1c(Oc2ccccc2F)cccc1C(C)C(=O)O",
"reactionStepId": "sa_ec064c42b2360a849e69c381",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US04367238;;103215\",\"rsmi\":\"CC[O:9][C:7]([C:5](C#N)([c:4]1[c:3]([O:2][CH3:1])[c:13]([O:14][c:15]2[c:16]([F:17])[cH:18][cH:19][cH:20][cH:21]2)[cH:12][cH:11][cH:10]1)[CH3:6])=[O:8]>CCO.O.[K+].O>[CH3:1][O:2][c:3]1[c:4]([CH:5]([CH3:6])[C:7](=[O:8])[OH:9])[cH:10][cH:11][cH:12][c:13]1[O:14][c:15]1[c:16]([F:17])[cH:18][cH:19][cH:20][cH:21]1\"},\"mapped_reaction_smiles\":\"CC[O:9][C:7]([C:5](C#N)([c:4]1[c:3]([O:2][CH3:1])[c:13]([O:14][c:15]2[c:16]([F:17])[cH:18][cH:19][cH:20][cH:21]2)[cH:12][cH:11][cH:10]1)[CH3:6])=[O:8]>CCO.O.[K+].O>[CH3:1][O:2][c:3]1[c:4]([CH:5]([CH3:6])[C:7](=[O:8])[OH:9])[cH:10][cH:11][cH:12][c:13]1[O:14][c:15]1[c:16]([F:17])[cH:18][cH:19][cH:20][cH:21]1\"}",
"reactionStep": {
"id": "sa_ec064c42b2360a849e69c381",
"reactionHash": "a33e273802742032469f55cf84a6fc7c8c51a39a54b92ab0ec6d22601defa3c4"
},
"children": [
{
"id": "17841",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_c7b257adb7705d6740e5fe94",
"parentId": "17840",
"isLeaf": false,
"molecule": {
"id": "sa_c7b257adb7705d6740e5fe94",
"inchikey": "RVIFNJCSZWWVPX-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(C)(C#N)c1cccc(Oc2ccccc2F)c1OC"
},
"smiles": "CCOC(=O)C(C)(C#N)c1cccc(Oc2ccccc2F)c1OC",
"reactionStepId": "sa_1dbb4d4b4420dccf5b0de7e4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US04367238;;103214\",\"rsmi\":\"I[CH3:7].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([C:8]#[N:9])[c:10]1[c:11]([O:12][CH3:13])[c:14]([O:15][c:16]2[c:17]([F:18])[cH:19][cH:20][cH:21][cH:22]2)[cH:23][cH:24][cH:25]1>[HH].[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C:6]([CH3:7])([C:8]#[N:9])[c:10]1[c:11]([O:12][CH3:13])[c:14]([O:15][c:16]2[c:17]([F:18])[cH:19][cH:20][cH:21][cH:22]2)[cH:23][cH:24][cH:25]1\"},\"mapped_reaction_smiles\":\"I[CH3:7].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([C:8]#[N:9])[c:10]1[c:11]([O:12][CH3:13])[c:14]([O:15][c:16]2[c:17]([F:18])[cH:19][cH:20][cH:21][cH:22]2)[cH:23][cH:24][cH:25]1>[HH].[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C:6]([CH3:7])([C:8]#[N:9])[c:10]1[c:11]([O:12][CH3:13])[c:14]([O:15][c:16]2[c:17]([F:18])[cH:19][cH:20][cH:21][cH:22]2)[cH:23][cH:24][cH:25]1\"}",
"reactionStep": {
"id": "sa_1dbb4d4b4420dccf5b0de7e4",
"reactionHash": "afd1ae96860783c56162311b7e92c430ac9e65f0ac27603974e1b5ceed852de6"
},
"children": [
{
"id": "17842",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_329e62ea3ba558a22104c76b",
"parentId": "17841",
"isLeaf": false,
"molecule": {
"id": "sa_329e62ea3ba558a22104c76b",
"inchikey": "HOTKZNLBBALAMO-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(C#N)c1cccc(Oc2ccccc2F)c1OC"
},
"smiles": "CCOC(=O)C(C#N)c1cccc(Oc2ccccc2F)c1OC",
"reactionStepId": "sa_d895db839c68e0c5f3f23e55",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US04367238;;103213\",\"rsmi\":\"CCO[C:4]([O:3][CH2:2][CH3:1])=[O:5].[CH2:6]([C:7]#[N:8])[c:9]1[c:10]([O:11][CH3:12])[c:13]([O:14][c:15]2[c:16]([F:17])[cH:18][cH:19][cH:20][cH:21]2)[cH:22][cH:23][cH:24]1>CCO.CCO.Cc1ccccc1.[Na+].[Na]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([C:7]#[N:8])[c:9]1[c:10]([O:11][CH3:12])[c:13]([O:14][c:15]2[c:16]([F:17])[cH:18][cH:19][cH:20][cH:21]2)[cH:22][cH:23][cH:24]1\"},\"mapped_reaction_smiles\":\"CCO[C:4]([O:3][CH2:2][CH3:1])=[O:5].[CH2:6]([C:7]#[N:8])[c:9]1[c:10]([O:11][CH3:12])[c:13]([O:14][c:15]2[c:16]([F:17])[cH:18][cH:19][cH:20][cH:21]2)[cH:22][cH:23][cH:24]1>CCO.CCO.Cc1ccccc1.[Na+].[Na]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([C:7]#[N:8])[c:9]1[c:10]([O:11][CH3:12])[c:13]([O:14][c:15]2[c:16]([F:17])[cH:18][cH:19][cH:20][cH:21]2)[cH:22][cH:23][cH:24]1\"}",
"reactionStep": {
"id": "sa_d895db839c68e0c5f3f23e55",
"reactionHash": "9fb74db90b90b2c66824697d324b8873286278da63928d3d3bb1b9a17954b99d"
},
"children": [
{
"id": "17843",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_91890083a0a02bf2d259ca48",
"parentId": "17842",
"isLeaf": false,
"molecule": {
"id": "sa_91890083a0a02bf2d259ca48",
"inchikey": "JGUWXDSFNDOPOD-UHFFFAOYSA-N",
"smiles": "COc1c(CC#N)cccc1Oc1ccccc1F"
},
"smiles": "COc1c(CC#N)cccc1Oc1ccccc1F",
"reactionStepId": "sa_9596e929180d340698625933",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US04367238;;103212\",\"rsmi\":\"Br[CH2:5][c:4]1[c:3]([O:2][CH3:1])[c:11]([O:12][c:13]2[c:14]([F:15])[cH:16][cH:17][cH:18][cH:19]2)[cH:10][cH:9][cH:8]1.[CH:6]#[N:7]>CS(C)=O.[Na+]>[CH3:1][O:2][c:3]1[c:4]([CH2:5][C:6]#[N:7])[cH:8][cH:9][cH:10][c:11]1[O:12][c:13]1[c:14]([F:15])[cH:16][cH:17][cH:18][cH:19]1\"},\"mapped_reaction_smiles\":\"Br[CH2:5][c:4]1[c:3]([O:2][CH3:1])[c:11]([O:12][c:13]2[c:14]([F:15])[cH:16][cH:17][cH:18][cH:19]2)[cH:10][cH:9][cH:8]1.[CH:6]#[N:7]>CS(C)=O.[Na+]>[CH3:1][O:2][c:3]1[c:4]([CH2:5][C:6]#[N:7])[cH:8][cH:9][cH:10][c:11]1[O:12][c:13]1[c:14]([F:15])[cH:16][cH:17][cH:18][cH:19]1\"}",
"reactionStep": {
"id": "sa_9596e929180d340698625933",
"reactionHash": "5d29b05fd61bf96afef8a1aed4acbe39c1b11396fbcd41ef9d1eda046867dc7c"
},
"children": [
{
"id": "17844",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_5995aff3aeff665a1f3e984d",
"parentId": "17843",
"isLeaf": true,
"molecule": {
"id": "sa_5995aff3aeff665a1f3e984d",
"inchikey": "LELOWRISYMNNSU-UHFFFAOYSA-N",
"smiles": "C#N"
},
"smiles": "C#N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "17845",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_b3a7683ba5e0cbb0e6bd4aea",
"parentId": "17843",
"isLeaf": false,
"molecule": {
"id": "sa_b3a7683ba5e0cbb0e6bd4aea",
"inchikey": "MVMJGZPJTRGUIS-UHFFFAOYSA-N",
"smiles": "COc1c(CBr)cccc1Oc1ccccc1F"
},
"smiles": "COc1c(CBr)cccc1Oc1ccccc1F",
"reactionStepId": "sa_4139e7639e7a7d7beee7a602",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US04367238;;103211\",\"rsmi\":\"O=C1CCC(=O)N1[Br:18].[CH3:1][O:2][c:3]1[c:4]([O:5][c:6]2[c:7]([F:8])[cH:9][cH:10][cH:11][cH:12]2)[cH:13][cH:14][cH:15][c:16]1[CH3:17]>CC(C)(C#N)N=NC(C)(C)C#N.c1ccccc1>[CH3:1][O:2][c:3]1[c:4]([O:5][c:6]2[c:7]([F:8])[cH:9][cH:10][cH:11][cH:12]2)[cH:13][cH:14][cH:15][c:16]1[CH2:17][Br:18]\"},\"mapped_reaction_smiles\":\"O=C1CCC(=O)N1[Br:18].[CH3:1][O:2][c:3]1[c:4]([O:5][c:6]2[c:7]([F:8])[cH:9][cH:10][cH:11][cH:12]2)[cH:13][cH:14][cH:15][c:16]1[CH3:17]>CC(C)(C#N)N=NC(C)(C)C#N.c1ccccc1>[CH3:1][O:2][c:3]1[c:4]([O:5][c:6]2[c:7]([F:8])[cH:9][cH:10][cH:11][cH:12]2)[cH:13][cH:14][cH:15][c:16]1[CH2:17][Br:18]\"}",
"reactionStep": {
"id": "sa_4139e7639e7a7d7beee7a602",
"reactionHash": "c0d025ef7bce20c1fe2a530b4e712c51499aec2859465774f711c9bb66d0c9c3"
},
"children": [
{
"id": "17846",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_212bb502208673ae87b916e6",
"parentId": "17845",
"isLeaf": false,
"molecule": {
"id": "sa_212bb502208673ae87b916e6",
"inchikey": "DZMFNHFDSQUNQJ-UHFFFAOYSA-N",
"smiles": "COc1c(C)cccc1Oc1ccccc1F"
},
"smiles": "COc1c(C)cccc1Oc1ccccc1F",
"reactionStepId": "sa_d29f6512cf7d90e5c9afc12c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US04367238;;103210\",\"rsmi\":\"COS(=O)(=O)O[CH3:1].[OH:2][c:3]1[c:4]([O:5][c:6]2[c:7]([F:8])[cH:9][cH:10][cH:11][cH:12]2)[cH:13][cH:14][cH:15][c:16]1[CH3:17]>[K+].O>[CH3:1][O:2][c:3]1[c:4]([O:5][c:6]2[c:7]([F:8])[cH:9][cH:10][cH:11][cH:12]2)[cH:13][cH:14][cH:15][c:16]1[CH3:17]\"},\"mapped_reaction_smiles\":\"COS(=O)(=O)O[CH3:1].[OH:2][c:3]1[c:4]([O:5][c:6]2[c:7]([F:8])[cH:9][cH:10][cH:11][cH:12]2)[cH:13][cH:14][cH:15][c:16]1[CH3:17]>[K+].O>[CH3:1][O:2][c:3]1[c:4]([O:5][c:6]2[c:7]([F:8])[cH:9][cH:10][cH:11][cH:12]2)[cH:13][cH:14][cH:15][c:16]1[CH3:17]\"}",
"reactionStep": {
"id": "sa_d29f6512cf7d90e5c9afc12c",
"reactionHash": "833e4408ca40071ffd635989a8b83e2c7fc9b5b925fd4ce6961762b52fcdb948"
},
"children": [
{
"id": "17847",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_593fd09433db80d5dc575b2c",
"parentId": "17846",
"isLeaf": true,
"molecule": {
"id": "sa_593fd09433db80d5dc575b2c",
"inchikey": "VAYGXNSJCAHWJZ-UHFFFAOYSA-N",
"smiles": "COS(=O)(=O)OC"
},
"smiles": "COS(=O)(=O)OC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "17848",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_a652c3626fda5c0c978ed8b8",
"parentId": "17846",
"isLeaf": false,
"molecule": {
"id": "sa_a652c3626fda5c0c978ed8b8",
"inchikey": "VYJZOCGACRZCTA-UHFFFAOYSA-N",
"smiles": "Cc1cccc(Oc2ccccc2F)c1O"
},
"smiles": "Cc1cccc(Oc2ccccc2F)c1O",
"reactionStepId": "sa_c7d2782d341e30a4bad2bca0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US04367238;;103209\",\"rsmi\":\"N[c:15]1[c:2]([CH3:1])[cH:3][cH:4][cH:5][c:6]1[O:7][c:8]1[c:9]([F:10])[cH:11][cH:12][cH:13][cH:14]1.O=N[OH:16]>CC(=O)O.Cl.F[B-](F)(F)F.O.[H+].[Na+]>[CH3:1][c:2]1[cH:3][cH:4][cH:5][c:6]([O:7][c:8]2[c:9]([F:10])[cH:11][cH:12][cH:13][cH:14]2)[c:15]1[OH:16]\"},\"mapped_reaction_smiles\":\"N[c:15]1[c:2]([CH3:1])[cH:3][cH:4][cH:5][c:6]1[O:7][c:8]1[c:9]([F:10])[cH:11][cH:12][cH:13][cH:14]1.O=N[OH:16]>CC(=O)O.Cl.F[B-](F)(F)F.O.[H+].[Na+]>[CH3:1][c:2]1[cH:3][cH:4][cH:5][c:6]([O:7][c:8]2[c:9]([F:10])[cH:11][cH:12][cH:13][cH:14]2)[c:15]1[OH:16]\"}",
"reactionStep": {
"id": "sa_c7d2782d341e30a4bad2bca0",
"reactionHash": "4da173cf6d7eec7f7cf76f4f991a6f5a06d685f8c024e4c2f9cf55dfa341bb90"
},
"children": [
{
"id": "17849",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_81c0446884d57a7253ff6b54",
"parentId": "17848",
"isLeaf": true,
"molecule": {
"id": "sa_81c0446884d57a7253ff6b54",
"inchikey": "IOVCWXUNBOPUCH-UHFFFAOYSA-N",
"smiles": "[O-]N=[OH+]"
},
"smiles": "O=NO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "17850",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_cf129d9d13147cec43f34be7",
"parentId": "17848",
"isLeaf": true,
"molecule": {
"id": "sa_cf129d9d13147cec43f34be7",
"inchikey": "WWTGLSSZIPVFTD-UHFFFAOYSA-N",
"smiles": "Cc1cccc(Oc2ccccc2F)c1N"
},
"smiles": "Cc1cccc(Oc2ccccc2F)c1N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "17851",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_ccdcf23ac83e7a68bfa4f2e5",
"parentId": "17845",
"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": "17852",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_7e4afe56af889ce8927f5228",
"parentId": "17842",
"isLeaf": true,
"molecule": {
"id": "sa_7e4afe56af889ce8927f5228",
"inchikey": "OIFBSDVPJOWBCH-UHFFFAOYSA-N",
"smiles": "CCOC(=O)OCC"
},
"smiles": "CCOC(=O)OCC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "17853",
"routeId": "sa_fb009325de976bb02e66dddf",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "17841",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}