Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1cc(F)cc(CC(=O)c2cc(OC)ccc2OC)c1
InChiKey
MAKDBHJPYNPJII-UHFFFAOYSA-N
Route Signature
f2b25d4d714db2f06ef49fabb3928714eeeae771a55a0f861cb9671152fb6d0c
Synthesis route with 6 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_8c749fb8a84ed9db26af90d5",
"signature": "f2b25d4d714db2f06ef49fabb3928714eeeae771a55a0f861cb9671152fb6d0c",
"contentHash": "66da554faaf486ea670bb7dd3195997e6c1366141a680deddcaf7994bb824896",
"length": 6,
"isConvergent": false
},
"target": {
"id": "sa_21c722f0a7409eedb8cd4fd6",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00838",
"moleculeId": "sa_6a470d01877a2d7879871f13",
"smiles": "COc1cc(F)cc(CC(=O)c2cc(OC)ccc2OC)c1",
"routeLength": 6,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_6a470d01877a2d7879871f13",
"inchikey": "MAKDBHJPYNPJII-UHFFFAOYSA-N",
"smiles": "COc1cc(F)cc(CC(=O)c2cc(OC)ccc2OC)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "13821",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_6a470d01877a2d7879871f13",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_6a470d01877a2d7879871f13",
"inchikey": "MAKDBHJPYNPJII-UHFFFAOYSA-N",
"smiles": "COc1cc(F)cc(CC(=O)c2cc(OC)ccc2OC)c1"
},
"smiles": "COc1cc(F)cc(CC(=O)c2cc(OC)ccc2OC)c1",
"reactionStepId": "sa_bf74cc66c0d897b7c156129b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140107095A1;0622;1513045\",\"rsmi\":\"O[C:7]([CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:22][c:20]([F:21])[cH:19]1)=[O:8].[cH:9]1[c:10]([O:11][CH3:12])[cH:13][cH:14][c:15]([O:16][CH3:17])[cH:18]1>O>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[c:9]2[c:10]([O:11][CH3:12])[cH:13][cH:14][c:15]([O:16][CH3:17])[cH:18]2)[cH:19][c:20]([F:21])[cH:22]1\"},\"mapped_reaction_smiles\":\"O[C:7]([CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:22][c:20]([F:21])[cH:19]1)=[O:8].[cH:9]1[c:10]([O:11][CH3:12])[cH:13][cH:14][c:15]([O:16][CH3:17])[cH:18]1>O>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[c:9]2[c:10]([O:11][CH3:12])[cH:13][cH:14][c:15]([O:16][CH3:17])[cH:18]2)[cH:19][c:20]([F:21])[cH:22]1\"}",
"reactionStep": {
"id": "sa_bf74cc66c0d897b7c156129b",
"reactionHash": "ebcec9df9dfa266a4eb229b30781af95c18cc86f4550c5f4f82657b2bf70680e"
},
"children": [
{
"id": "13822",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_3417d9f68bcbb2cc8652ff11",
"parentId": "13821",
"isLeaf": true,
"molecule": {
"id": "sa_3417d9f68bcbb2cc8652ff11",
"inchikey": "OHBQPCCCRFSCAX-UHFFFAOYSA-N",
"smiles": "COc1ccc(OC)cc1"
},
"smiles": "COc1ccc(OC)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13823",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_d92c2d0b372b006f43f51a0b",
"parentId": "13821",
"isLeaf": false,
"molecule": {
"id": "sa_d92c2d0b372b006f43f51a0b",
"inchikey": "VMMVVQRJJWQGKE-UHFFFAOYSA-N",
"smiles": "COc1cc(F)cc(CC(=O)O)c1"
},
"smiles": "COc1cc(F)cc(CC(=O)O)c1",
"reactionStepId": "sa_5773d1176ba270860fb14c12",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140107095A1;0620;1513044\",\"rsmi\":\"C[OH:9].N#[C:7][CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:13][c:11]([F:12])[cH:10]1.[OH2:8]>Cl.O.[Na+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[OH:9])[cH:10][c:11]([F:12])[cH:13]1\"},\"mapped_reaction_smiles\":\"C[OH:9].N#[C:7][CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:13][c:11]([F:12])[cH:10]1.[OH2:8]>Cl.O.[Na+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[OH:9])[cH:10][c:11]([F:12])[cH:13]1\"}",
"reactionStep": {
"id": "sa_5773d1176ba270860fb14c12",
"reactionHash": "d7e7464b8a87dcbf338830ed8d7fc9e99f15e86e4e60b2ba74022732b4be8845"
},
"children": [
{
"id": "13824",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "13823",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13825",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_c86b853633a46745b1d02b0f",
"parentId": "13823",
"isLeaf": false,
"molecule": {
"id": "sa_c86b853633a46745b1d02b0f",
"inchikey": "VWYCYRCMXIAREJ-UHFFFAOYSA-N",
"smiles": "COc1cc(F)cc(CC#N)c1"
},
"smiles": "COc1cc(F)cc(CC#N)c1",
"reactionStepId": "sa_2a23dea64a6369bd91251d66",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140107095A1;0618;1513043\",\"rsmi\":\"Cl[CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:12][c:10]([F:11])[cH:9]1.[CH:7]#[N:8]>CS(C)=O.O.[K+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7]#[N:8])[cH:9][c:10]([F:11])[cH:12]1\"},\"mapped_reaction_smiles\":\"Cl[CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:12][c:10]([F:11])[cH:9]1.[CH:7]#[N:8]>CS(C)=O.O.[K+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7]#[N:8])[cH:9][c:10]([F:11])[cH:12]1\"}",
"reactionStep": {
"id": "sa_2a23dea64a6369bd91251d66",
"reactionHash": "99f9754e22caf2f9a10b2a6abad6182f29e7e8c0c37ceaa37d07d96a1b290f5e"
},
"children": [
{
"id": "13826",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_5995aff3aeff665a1f3e984d",
"parentId": "13825",
"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": "13827",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_5ebf1ead4517eaad33793b61",
"parentId": "13825",
"isLeaf": false,
"molecule": {
"id": "sa_5ebf1ead4517eaad33793b61",
"inchikey": "YXRCCCVFIIMAIP-UHFFFAOYSA-N",
"smiles": "COc1cc(F)cc(CCl)c1"
},
"smiles": "COc1cc(F)cc(CCl)c1",
"reactionStepId": "sa_49798d325d93156c1e7b5c97",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140107095A1;0616;1513042\",\"rsmi\":\"ClC(Cl)(Cl)[Cl:7].O[CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:11][c:9]([F:10])[cH:8]1>ClP(Cl)(Cl)(Cl)Cl.O=C(O)O.[Na+].[Na+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][Cl:7])[cH:8][c:9]([F:10])[cH:11]1\"},\"mapped_reaction_smiles\":\"ClC(Cl)(Cl)[Cl:7].O[CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:11][c:9]([F:10])[cH:8]1>ClP(Cl)(Cl)(Cl)Cl.O=C(O)O.[Na+].[Na+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][Cl:7])[cH:8][c:9]([F:10])[cH:11]1\"}",
"reactionStep": {
"id": "sa_49798d325d93156c1e7b5c97",
"reactionHash": "7b4fdc5b2566019afa36a2322beeb7fa132b72f93bb2d5b081345a08850d81a2"
},
"children": [
{
"id": "13828",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_0236909545aeb4e49bdf2b35",
"parentId": "13827",
"isLeaf": false,
"molecule": {
"id": "sa_0236909545aeb4e49bdf2b35",
"inchikey": "AKNFFYDXPZERQS-UHFFFAOYSA-N",
"smiles": "COc1cc(F)cc(CO)c1"
},
"smiles": "COc1cc(F)cc(CO)c1",
"reactionStepId": "sa_fafb211e5bfe35b7a761f90c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140107095A1;0614;1513041\",\"rsmi\":\"O=[C:6]([c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:11][c:9]([F:10])[cH:8]1)[OH:7]>CCOCC.[Al+3].[HH].[HH].[HH].[HH].[Li+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][OH:7])[cH:8][c:9]([F:10])[cH:11]1\"},\"mapped_reaction_smiles\":\"O=[C:6]([c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:11][c:9]([F:10])[cH:8]1)[OH:7]>CCOCC.[Al+3].[HH].[HH].[HH].[HH].[Li+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][OH:7])[cH:8][c:9]([F:10])[cH:11]1\"}",
"reactionStep": {
"id": "sa_fafb211e5bfe35b7a761f90c",
"reactionHash": "2f08bc4acb1c25e0ef3e735206e2dac58e19d54308ff530f4ba36c51f3b46bc1"
},
"children": [
{
"id": "13829",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_ebe6702bd2d7f96d86833120",
"parentId": "13828",
"isLeaf": false,
"molecule": {
"id": "sa_ebe6702bd2d7f96d86833120",
"inchikey": "WUHJSLPINVJGPW-UHFFFAOYSA-N",
"smiles": "COc1cc(F)cc(C(=O)O)c1"
},
"smiles": "COc1cc(F)cc(C(=O)O)c1",
"reactionStepId": "sa_754820341881ec3322907fdc",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140107095A1;0612;1513040\",\"rsmi\":\"F[c:3]1[cH:4][c:5]([C:6](=[O:7])[OH:8])[cH:9][c:10]([F:11])[cH:12]1.[CH3:1][OH:2]>CN(C)C=O.Cl.O.[Na+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([C:6](=[O:7])[OH:8])[cH:9][c:10]([F:11])[cH:12]1\"},\"mapped_reaction_smiles\":\"F[c:3]1[cH:4][c:5]([C:6](=[O:7])[OH:8])[cH:9][c:10]([F:11])[cH:12]1.[CH3:1][OH:2]>CN(C)C=O.Cl.O.[Na+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([C:6](=[O:7])[OH:8])[cH:9][c:10]([F:11])[cH:12]1\"}",
"reactionStep": {
"id": "sa_754820341881ec3322907fdc",
"reactionHash": "1184b4309589862ca79e6ee377f18a3dd2c566716498a0036ce685e2b03f4c00"
},
"children": [
{
"id": "13830",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_6dd563fdbe1188b9dde0efa9",
"parentId": "13829",
"isLeaf": true,
"molecule": {
"id": "sa_6dd563fdbe1188b9dde0efa9",
"inchikey": "GONAVIHGXFBTOZ-UHFFFAOYSA-N",
"smiles": "O=C(O)c1cc(F)cc(F)c1"
},
"smiles": "O=C(O)c1cc(F)cc(F)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13831",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "13829",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "13832",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_9b14238c7469472a53fc61c6",
"parentId": "13827",
"isLeaf": true,
"molecule": {
"id": "sa_9b14238c7469472a53fc61c6",
"inchikey": "VZGDMQKNWNREIO-UHFFFAOYSA-N",
"smiles": "ClC(Cl)(Cl)Cl"
},
"smiles": "ClC(Cl)(Cl)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "13833",
"routeId": "sa_8c749fb8a84ed9db26af90d5",
"moleculeId": "sa_106b35b8a76bbe73829a0a69",
"parentId": "13823",
"isLeaf": true,
"molecule": {
"id": "sa_106b35b8a76bbe73829a0a69",
"inchikey": "XLYOFNOQVPJJNP-UHFFFAOYSA-N",
"smiles": "O"
},
"smiles": "O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}