Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
N#CCc1cc(F)c2c(c1)OCO2
InChiKey
FOVHYKNKGPLBQY-UHFFFAOYSA-N
Route Signature
4a035e3d73da593d0d286086035054039fcb40614a39edad2447c85b7d7bd6ff
Synthesis route with 5 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_8951393394296d8c1b66ef8c",
"signature": "4a035e3d73da593d0d286086035054039fcb40614a39edad2447c85b7d7bd6ff",
"contentHash": "3d53db5fa7e1e689d7f94dcd97adb2dcb187aa52023ab200e399a2ad9e0d144d",
"length": 5,
"isConvergent": false
},
"target": {
"id": "sa_762795d06403f85815b35aac",
"benchmarkSetId": "f925e688d731a0ad4e3aa6a505df094f6d3ca64ce3facc312bc5f64731921b33",
"targetId": "n5-06738",
"moleculeId": "sa_aedfe82d9b47058eab90454c",
"smiles": "N#CCc1cc(F)c2c(c1)OCO2",
"routeLength": 5,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_aedfe82d9b47058eab90454c",
"inchikey": "FOVHYKNKGPLBQY-UHFFFAOYSA-N",
"smiles": "N#CCc1cc(F)c2c(c1)OCO2"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 2
},
"rootNode": {
"id": "8100",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_aedfe82d9b47058eab90454c",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_aedfe82d9b47058eab90454c",
"inchikey": "FOVHYKNKGPLBQY-UHFFFAOYSA-N",
"smiles": "N#CCc1cc(F)c2c(c1)OCO2"
},
"smiles": "N#CCc1cc(F)c2c(c1)OCO2",
"reactionStepId": "sa_5d04ae32c42c56e9088b9e91",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160271105A1;0434;1934873\",\"rsmi\":\"Cl[CH2:3][c:4]1[cH:5][c:6]2[c:7]([c:11]([F:12])[cH:13]1)[O:8][CH2:9][O:10]2.[N:1]#[CH:2]>CS(C)=O.O.[Na+]>[N:1]#[C:2][CH2:3][c:4]1[cH:5][c:6]2[c:7]([c:11]([F:12])[cH:13]1)[O:8][CH2:9][O:10]2\"},\"mapped_reaction_smiles\":\"Cl[CH2:3][c:4]1[cH:5][c:6]2[c:7]([c:11]([F:12])[cH:13]1)[O:8][CH2:9][O:10]2.[N:1]#[CH:2]>CS(C)=O.O.[Na+]>[N:1]#[C:2][CH2:3][c:4]1[cH:5][c:6]2[c:7]([c:11]([F:12])[cH:13]1)[O:8][CH2:9][O:10]2\"}",
"reactionStep": {
"id": "sa_5d04ae32c42c56e9088b9e91",
"reactionHash": "207dcc597acc91f25ffd87fd66fa2cf41b5f73ff9d942d4b69cad3cfeb67a5cb"
},
"children": [
{
"id": "8101",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_5995aff3aeff665a1f3e984d",
"parentId": "8100",
"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": "8102",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_83baf2427ac4a528f90b1722",
"parentId": "8100",
"isLeaf": false,
"molecule": {
"id": "sa_83baf2427ac4a528f90b1722",
"inchikey": "WOTGRYKCSXLUPJ-UHFFFAOYSA-N",
"smiles": "Fc1cc(CCl)cc2c1OCO2"
},
"smiles": "Fc1cc(CCl)cc2c1OCO2",
"reactionStepId": "sa_6b673feef472ad66fbd1a212",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160271105A1;0433;1934872\",\"rsmi\":\"O=S(Cl)[Cl:6].O[CH2:5][c:4]1[cH:3][c:2]([F:1])[c:9]2[c:8]([cH:7]1)[O:12][CH2:11][O:10]2>O=C(O)O.[Na+]>[F:1][c:2]1[cH:3][c:4]([CH2:5][Cl:6])[cH:7][c:8]2[c:9]1[O:10][CH2:11][O:12]2\"},\"mapped_reaction_smiles\":\"O=S(Cl)[Cl:6].O[CH2:5][c:4]1[cH:3][c:2]([F:1])[c:9]2[c:8]([cH:7]1)[O:12][CH2:11][O:10]2>O=C(O)O.[Na+]>[F:1][c:2]1[cH:3][c:4]([CH2:5][Cl:6])[cH:7][c:8]2[c:9]1[O:10][CH2:11][O:12]2\"}",
"reactionStep": {
"id": "sa_6b673feef472ad66fbd1a212",
"reactionHash": "d3d113362be2c252f2a1b680a49a5aec69b88d99bec8a1aaec74ff9255049dd9"
},
"children": [
{
"id": "8103",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_cd67ce42f230ef1a4063353c",
"parentId": "8102",
"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": "8104",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_4d5ba6173bcfc315ce78d890",
"parentId": "8102",
"isLeaf": false,
"molecule": {
"id": "sa_4d5ba6173bcfc315ce78d890",
"inchikey": "NRLUSHXBTPUYEM-UHFFFAOYSA-N",
"smiles": "OCc1cc(F)c2c(c1)OCO2"
},
"smiles": "OCc1cc(F)c2c(c1)OCO2",
"reactionStepId": "sa_a0aa69c84feea83db523751a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160271105A1;0432;1934871\",\"rsmi\":\"[O:1]=[CH:2][c:3]1[cH:4][c:5]2[c:6]([c:10]([F:11])[cH:12]1)[O:7][CH2:8][O:9]2>CO.B.[Na+]>[OH:1][CH2:2][c:3]1[cH:4][c:5]2[c:6]([c:10]([F:11])[cH:12]1)[O:7][CH2:8][O:9]2\"},\"mapped_reaction_smiles\":\"[O:1]=[CH:2][c:3]1[cH:4][c:5]2[c:6]([c:10]([F:11])[cH:12]1)[O:7][CH2:8][O:9]2>CO.B.[Na+]>[OH:1][CH2:2][c:3]1[cH:4][c:5]2[c:6]([c:10]([F:11])[cH:12]1)[O:7][CH2:8][O:9]2\"}",
"reactionStep": {
"id": "sa_a0aa69c84feea83db523751a",
"reactionHash": "a4318a61ff0706084d4dc0fcc9251324787ec0a7a37807a9140c771ed098e05f"
},
"children": [
{
"id": "8105",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_f364b97ba007975df21c3367",
"parentId": "8104",
"isLeaf": false,
"molecule": {
"id": "sa_f364b97ba007975df21c3367",
"inchikey": "NDIFBXNJTOFFAX-UHFFFAOYSA-N",
"smiles": "O=Cc1cc(F)c2c(c1)OCO2"
},
"smiles": "O=Cc1cc(F)c2c(c1)OCO2",
"reactionStepId": "sa_3ce44913ff4597a1ad66ea5f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160271105A1;0431;1934870\",\"rsmi\":\"CN(C)[CH:8]=O.[O:1]=[CH:2][c:3]1[cH:4][c:5]([OH:9])[c:6]([OH:7])[c:10]([F:11])[cH:12]1>O.O=C(O)O.[Cs+].[Cs+]>[O:1]=[CH:2][c:3]1[cH:4][c:5]2[c:6]([c:10]([F:11])[cH:12]1)[O:7][CH2:8][O:9]2\"},\"mapped_reaction_smiles\":\"CN(C)[CH:8]=O.[O:1]=[CH:2][c:3]1[cH:4][c:5]([OH:9])[c:6]([OH:7])[c:10]([F:11])[cH:12]1>O.O=C(O)O.[Cs+].[Cs+]>[O:1]=[CH:2][c:3]1[cH:4][c:5]2[c:6]([c:10]([F:11])[cH:12]1)[O:7][CH2:8][O:9]2\"}",
"reactionStep": {
"id": "sa_3ce44913ff4597a1ad66ea5f",
"reactionHash": "8d1f9d7726d70da033d8f51c7e30248f8ede4ab86a118fe68dd6db3a8d61f9ab"
},
"children": [
{
"id": "8106",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_48e3063c66773bbcae0bec10",
"parentId": "8105",
"isLeaf": false,
"molecule": {
"id": "sa_48e3063c66773bbcae0bec10",
"inchikey": "AFSUIFYFQDSKPC-UHFFFAOYSA-N",
"smiles": "O=Cc1cc(O)c(O)c(F)c1"
},
"smiles": "O=Cc1cc(O)c(O)c(F)c1",
"reactionStepId": "sa_985da72b0a944c766611543e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160271105A1;0430;1934869\",\"rsmi\":\"C[O:10][c:9]1[c:7]([OH:8])[c:5]([F:6])[cH:4][c:3]([CH:2]=[O:1])[cH:11]1>BrB(Br)Br.ClCCl>[O:1]=[CH:2][c:3]1[cH:4][c:5]([F:6])[c:7]([OH:8])[c:9]([OH:10])[cH:11]1\"},\"mapped_reaction_smiles\":\"C[O:10][c:9]1[c:7]([OH:8])[c:5]([F:6])[cH:4][c:3]([CH:2]=[O:1])[cH:11]1>BrB(Br)Br.ClCCl>[O:1]=[CH:2][c:3]1[cH:4][c:5]([F:6])[c:7]([OH:8])[c:9]([OH:10])[cH:11]1\"}",
"reactionStep": {
"id": "sa_985da72b0a944c766611543e",
"reactionHash": "34749d1d7e6ef22e3e7bb5e3b546b108ab2eb2b20d611f15651ce326144a5ba0"
},
"children": [
{
"id": "8107",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_377b1a2c396eec64f7d320b1",
"parentId": "8106",
"isLeaf": true,
"molecule": {
"id": "sa_377b1a2c396eec64f7d320b1",
"inchikey": "OOGOFUKAJDPHDJ-UHFFFAOYSA-N",
"smiles": "COc1cc(C=O)cc(F)c1O"
},
"smiles": "COc1cc(C=O)cc(F)c1O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "8108",
"routeId": "sa_8951393394296d8c1b66ef8c",
"moleculeId": "sa_e0b5e93d36242e79e81ef68c",
"parentId": "8105",
"isLeaf": true,
"molecule": {
"id": "sa_e0b5e93d36242e79e81ef68c",
"inchikey": "ZMXDDKWLCZADIW-UHFFFAOYSA-N",
"smiles": "CN(C)C=O"
},
"smiles": "CN(C)C=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}