Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COC(OC)C(C)(O)c1cnc(-c2ccc(C(CC3CCOCC3)c3ccc(S(=O)(=O)C4CC4)cc3)[nH]2)s1
InChiKey
XCVAQWAQXNCPHK-UHFFFAOYSA-N
Route Signature
e4f72a8e37cf11481020f38d0a18abc171f7a49b69364d4521021def2e71866a
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_1afbe6c36b45d54307d5db46",
"signature": "e4f72a8e37cf11481020f38d0a18abc171f7a49b69364d4521021def2e71866a",
"contentHash": "505ece2a6999cd9d0839a28fc1d71741531b6999a7d3dec323dac333496ce7db",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_aa93b59158c49d0657935d64",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-01303",
"moleculeId": "sa_1cd42d4b1418aaae3a935eef",
"smiles": "COC(OC)C(C)(O)c1cnc(-c2ccc(C(CC3CCOCC3)c3ccc(S(=O)(=O)C4CC4)cc3)[nH]2)s1",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_1cd42d4b1418aaae3a935eef",
"inchikey": "XCVAQWAQXNCPHK-UHFFFAOYSA-N",
"smiles": "COC(OC)C(C)(O)c1cnc(-c2ccc(C(CC3CCOCC3)c3ccc(S(=O)(=O)C4CC4)cc3)[nH]2)s1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "10076",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_1cd42d4b1418aaae3a935eef",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_1cd42d4b1418aaae3a935eef",
"inchikey": "XCVAQWAQXNCPHK-UHFFFAOYSA-N",
"smiles": "COC(OC)C(C)(O)c1cnc(-c2ccc(C(CC3CCOCC3)c3ccc(S(=O)(=O)C4CC4)cc3)[nH]2)s1"
},
"smiles": "COC(OC)C(C)(O)c1cnc(-c2ccc(C(CC3CCOCC3)c3ccc(S(=O)(=O)C4CC4)cc3)[nH]2)s1",
"reactionStepId": "sa_8d8e0bc4f8ca19f71396497b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100130446A1;1726;885305\",\"rsmi\":\"O=[C:13]([c:12]1[n:11][cH:10][c:9]([C:6]([CH:3]([O:2][CH3:1])[O:4][CH3:5])([CH3:7])[OH:8])[s:38]1)[CH2:14][CH2:15][C:16](=O)[CH:17]([CH2:18][CH:19]1[CH2:20][CH2:21][O:22][CH2:23][CH2:24]1)[c:25]1[cH:26][cH:27][c:28]([S:29](=[O:30])(=[O:31])[CH:32]2[CH2:33][CH2:34]2)[cH:35][cH:36]1.[NH3:37]>CC(=O)O.CC(=O)O.[Na+].O>[CH3:1][O:2][CH:3]([O:4][CH3:5])[C:6]([CH3:7])([OH:8])[c:9]1[cH:10][n:11][c:12](-[c:13]2[cH:14][cH:15][c:16]([CH:17]([CH2:18][CH:19]3[CH2:20][CH2:21][O:22][CH2:23][CH2:24]3)[c:25]3[cH:26][cH:27][c:28]([S:29](=[O:30])(=[O:31])[CH:32]4[CH2:33][CH2:34]4)[cH:35][cH:36]3)[nH:37]2)[s:38]1\"},\"mapped_reaction_smiles\":\"O=[C:13]([c:12]1[n:11][cH:10][c:9]([C:6]([CH:3]([O:2][CH3:1])[O:4][CH3:5])([CH3:7])[OH:8])[s:38]1)[CH2:14][CH2:15][C:16](=O)[CH:17]([CH2:18][CH:19]1[CH2:20][CH2:21][O:22][CH2:23][CH2:24]1)[c:25]1[cH:26][cH:27][c:28]([S:29](=[O:30])(=[O:31])[CH:32]2[CH2:33][CH2:34]2)[cH:35][cH:36]1.[NH3:37]>CC(=O)O.CC(=O)O.[Na+].O>[CH3:1][O:2][CH:3]([O:4][CH3:5])[C:6]([CH3:7])([OH:8])[c:9]1[cH:10][n:11][c:12](-[c:13]2[cH:14][cH:15][c:16]([CH:17]([CH2:18][CH:19]3[CH2:20][CH2:21][O:22][CH2:23][CH2:24]3)[c:25]3[cH:26][cH:27][c:28]([S:29](=[O:30])(=[O:31])[CH:32]4[CH2:33][CH2:34]4)[cH:35][cH:36]3)[nH:37]2)[s:38]1\"}",
"reactionStep": {
"id": "sa_8d8e0bc4f8ca19f71396497b",
"reactionHash": "428dbe1ef1ceadd5312755a742652f896824edc0ac7a3a8ce90b607fa1f07e0d"
},
"children": [
{
"id": "10077",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_ccbdc01c9b15ce9ee1cc1803",
"parentId": "10076",
"isLeaf": false,
"molecule": {
"id": "sa_ccbdc01c9b15ce9ee1cc1803",
"inchikey": "KCKOOVXYZKQMJF-UHFFFAOYSA-N",
"smiles": "COC(OC)C(C)(O)c1cnc(C(=O)CCC(=O)C(CC2CCOCC2)c2ccc(S(=O)(=O)C3CC3)cc2)s1"
},
"smiles": "COC(OC)C(C)(O)c1cnc(C(=O)CCC(=O)C(CC2CCOCC2)c2ccc(S(=O)(=O)C3CC3)cc2)s1",
"reactionStepId": "sa_9d75a21e433d02ab1a06522e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100130446A1;1096;885127\",\"rsmi\":\"[CH2:15]=[CH:16][C:17](=[O:18])[CH:19]([CH2:20][CH:21]1[CH2:22][CH2:23][O:24][CH2:25][CH2:26]1)[c:27]1[cH:28][cH:29][c:30]([S:31](=[O:32])(=[O:33])[CH:34]2[CH2:35][CH2:36]2)[cH:37][cH:38]1.[CH3:1][O:2][CH:3]([O:4][CH3:5])[C:6]([CH3:7])([OH:8])[c:9]1[cH:10][n:11][c:12]([CH:13]=[O:14])[s:39]1>C1CCOC1.CCN(CC)CC.CCO.Cc1c(CCO)sc[n+]1Cc1ccccc1.Cl>[CH3:1][O:2][CH:3]([O:4][CH3:5])[C:6]([CH3:7])([OH:8])[c:9]1[cH:10][n:11][c:12]([C:13](=[O:14])[CH2:15][CH2:16][C:17](=[O:18])[CH:19]([CH2:20][CH:21]2[CH2:22][CH2:23][O:24][CH2:25][CH2:26]2)[c:27]2[cH:28][cH:29][c:30]([S:31](=[O:32])(=[O:33])[CH:34]3[CH2:35][CH2:36]3)[cH:37][cH:38]2)[s:39]1\"},\"mapped_reaction_smiles\":\"[CH2:15]=[CH:16][C:17](=[O:18])[CH:19]([CH2:20][CH:21]1[CH2:22][CH2:23][O:24][CH2:25][CH2:26]1)[c:27]1[cH:28][cH:29][c:30]([S:31](=[O:32])(=[O:33])[CH:34]2[CH2:35][CH2:36]2)[cH:37][cH:38]1.[CH3:1][O:2][CH:3]([O:4][CH3:5])[C:6]([CH3:7])([OH:8])[c:9]1[cH:10][n:11][c:12]([CH:13]=[O:14])[s:39]1>C1CCOC1.CCN(CC)CC.CCO.Cc1c(CCO)sc[n+]1Cc1ccccc1.Cl>[CH3:1][O:2][CH:3]([O:4][CH3:5])[C:6]([CH3:7])([OH:8])[c:9]1[cH:10][n:11][c:12]([C:13](=[O:14])[CH2:15][CH2:16][C:17](=[O:18])[CH:19]([CH2:20][CH:21]2[CH2:22][CH2:23][O:24][CH2:25][CH2:26]2)[c:27]2[cH:28][cH:29][c:30]([S:31](=[O:32])(=[O:33])[CH:34]3[CH2:35][CH2:36]3)[cH:37][cH:38]2)[s:39]1\"}",
"reactionStep": {
"id": "sa_9d75a21e433d02ab1a06522e",
"reactionHash": "9d09b82655ea56165b1cbb6d59c5238539f63f1e870661a33de6ab123760831a"
},
"children": [
{
"id": "10078",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_7030d1eed112632a0ac8a5ec",
"parentId": "10077",
"isLeaf": false,
"molecule": {
"id": "sa_7030d1eed112632a0ac8a5ec",
"inchikey": "VPIPWZOIFLOUCL-UHFFFAOYSA-N",
"smiles": "COC(OC)C(C)(O)c1cnc(C=O)s1"
},
"smiles": "COC(OC)C(C)(O)c1cnc(C=O)s1",
"reactionStepId": "sa_9ca62bbd6af936a52849b89d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100130446A1;1094;885126\",\"rsmi\":\"C1C[O:14][CH:13]([c:12]2[n:11][cH:10][c:9]([C:6]([CH:3]([O:2][CH3:1])[O:4][CH3:5])([CH3:7])[OH:8])[s:15]2)O1>CC(C)=O.Cl.O=C(O)O.[Na+]>[CH3:1][O:2][CH:3]([O:4][CH3:5])[C:6]([CH3:7])([OH:8])[c:9]1[cH:10][n:11][c:12]([CH:13]=[O:14])[s:15]1\"},\"mapped_reaction_smiles\":\"C1C[O:14][CH:13]([c:12]2[n:11][cH:10][c:9]([C:6]([CH:3]([O:2][CH3:1])[O:4][CH3:5])([CH3:7])[OH:8])[s:15]2)O1>CC(C)=O.Cl.O=C(O)O.[Na+]>[CH3:1][O:2][CH:3]([O:4][CH3:5])[C:6]([CH3:7])([OH:8])[c:9]1[cH:10][n:11][c:12]([CH:13]=[O:14])[s:15]1\"}",
"reactionStep": {
"id": "sa_9ca62bbd6af936a52849b89d",
"reactionHash": "00239548289e1caf31fa431060cf4bb9bee1624430f40b5ae00c2efdfba67e66"
},
"children": [
{
"id": "10079",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_0e409a56b3320b916b0958a0",
"parentId": "10078",
"isLeaf": true,
"molecule": {
"id": "sa_0e409a56b3320b916b0958a0",
"inchikey": "XZRPQHLFWSOFRK-UHFFFAOYSA-N",
"smiles": "COC(OC)C(C)(O)c1cnc(C2OCCO2)s1"
},
"smiles": "COC(OC)C(C)(O)c1cnc(C2OCCO2)s1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "10080",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_14938e7633b6207e963f0e67",
"parentId": "10077",
"isLeaf": false,
"molecule": {
"id": "sa_14938e7633b6207e963f0e67",
"inchikey": "YBJPUURRFBFIJB-UHFFFAOYSA-N",
"smiles": "C=CC(=O)C(CC1CCOCC1)c1ccc(S(=O)(=O)C2CC2)cc1"
},
"smiles": "C=CC(=O)C(CC1CCOCC1)c1ccc(S(=O)(=O)C2CC2)cc1",
"reactionStepId": "sa_a45c9181647504c0b693d073",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100130446A1;0877;885058\",\"rsmi\":\"Br[Mg][CH:2]=[CH2:1].CON(C)[C:3](=[O:4])[CH:5]([CH2:6][CH:7]1[CH2:8][CH2:9][O:10][CH2:11][CH2:12]1)[c:13]1[cH:14][cH:15][c:16]([S:17](=[O:18])(=[O:19])[CH:20]2[CH2:21][CH2:22]2)[cH:23][cH:24]1>C1CCOC1.Cl>[CH2:1]=[CH:2][C:3](=[O:4])[CH:5]([CH2:6][CH:7]1[CH2:8][CH2:9][O:10][CH2:11][CH2:12]1)[c:13]1[cH:14][cH:15][c:16]([S:17](=[O:18])(=[O:19])[CH:20]2[CH2:21][CH2:22]2)[cH:23][cH:24]1\"},\"mapped_reaction_smiles\":\"Br[Mg][CH:2]=[CH2:1].CON(C)[C:3](=[O:4])[CH:5]([CH2:6][CH:7]1[CH2:8][CH2:9][O:10][CH2:11][CH2:12]1)[c:13]1[cH:14][cH:15][c:16]([S:17](=[O:18])(=[O:19])[CH:20]2[CH2:21][CH2:22]2)[cH:23][cH:24]1>C1CCOC1.Cl>[CH2:1]=[CH:2][C:3](=[O:4])[CH:5]([CH2:6][CH:7]1[CH2:8][CH2:9][O:10][CH2:11][CH2:12]1)[c:13]1[cH:14][cH:15][c:16]([S:17](=[O:18])(=[O:19])[CH:20]2[CH2:21][CH2:22]2)[cH:23][cH:24]1\"}",
"reactionStep": {
"id": "sa_a45c9181647504c0b693d073",
"reactionHash": "aaf0d24d76f06379a4cbf53e47b3c94959e4ed1be7e324efd95328194616510a"
},
"children": [
{
"id": "10081",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_0671db867e4d0b7aa27c846c",
"parentId": "10080",
"isLeaf": false,
"molecule": {
"id": "sa_0671db867e4d0b7aa27c846c",
"inchikey": "VVWJBINUDDXTDJ-UHFFFAOYSA-N",
"smiles": "CON(C)C(=O)C(CC1CCOCC1)c1ccc(S(=O)(=O)C2CC2)cc1"
},
"smiles": "CON(C)C(=O)C(CC1CCOCC1)c1ccc(S(=O)(=O)C2CC2)cc1",
"reactionStepId": "sa_62bb8b0ea6763f1565ae8a62",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100130446A1;0874;885057\",\"rsmi\":\"O[C:5](=[O:6])[CH:7]([CH2:8][CH:9]1[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1)[c:15]1[cH:16][cH:17][c:18]([S:19](=[O:20])(=[O:21])[CH:22]2[CH2:23][CH2:24]2)[cH:25][cH:26]1.[CH3:1][O:2][NH:3][CH3:4]>CCN(CC)CC.CCN=C=NCCCN(C)C.CCOC(C)=O.CN(C)C=O.Cl.Cl.On1nnc2ccccc21>[CH3:1][O:2][N:3]([CH3:4])[C:5](=[O:6])[CH:7]([CH2:8][CH:9]1[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1)[c:15]1[cH:16][cH:17][c:18]([S:19](=[O:20])(=[O:21])[CH:22]2[CH2:23][CH2:24]2)[cH:25][cH:26]1\"},\"mapped_reaction_smiles\":\"O[C:5](=[O:6])[CH:7]([CH2:8][CH:9]1[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1)[c:15]1[cH:16][cH:17][c:18]([S:19](=[O:20])(=[O:21])[CH:22]2[CH2:23][CH2:24]2)[cH:25][cH:26]1.[CH3:1][O:2][NH:3][CH3:4]>CCN(CC)CC.CCN=C=NCCCN(C)C.CCOC(C)=O.CN(C)C=O.Cl.Cl.On1nnc2ccccc21>[CH3:1][O:2][N:3]([CH3:4])[C:5](=[O:6])[CH:7]([CH2:8][CH:9]1[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1)[c:15]1[cH:16][cH:17][c:18]([S:19](=[O:20])(=[O:21])[CH:22]2[CH2:23][CH2:24]2)[cH:25][cH:26]1\"}",
"reactionStep": {
"id": "sa_62bb8b0ea6763f1565ae8a62",
"reactionHash": "b860872ce1e485275fb0cbda54cee5baeb3d6f0b7589bc1fddee37841ceeec8e"
},
"children": [
{
"id": "10082",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_a413108482bdcaac6de4995f",
"parentId": "10081",
"isLeaf": true,
"molecule": {
"id": "sa_a413108482bdcaac6de4995f",
"inchikey": "IMDSBCGXPMSCCM-UHFFFAOYSA-N",
"smiles": "O=C(O)C(CC1CCOCC1)c1ccc(S(=O)(=O)C2CC2)cc1"
},
"smiles": "O=C(O)C(CC1CCOCC1)c1ccc(S(=O)(=O)C2CC2)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10083",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_93e456f7e04541ecb6ebcb69",
"parentId": "10081",
"isLeaf": true,
"molecule": {
"id": "sa_93e456f7e04541ecb6ebcb69",
"inchikey": "KRKPYFLIYNGWTE-UHFFFAOYSA-N",
"smiles": "CNOC"
},
"smiles": "CNOC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "10084",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_8cf6808f0629b06d62310d0a",
"parentId": "10080",
"isLeaf": true,
"molecule": {
"id": "sa_8cf6808f0629b06d62310d0a",
"inchikey": "XHHHAXOHMKAOSL-UHFFFAOYSA-M",
"smiles": "C=[CH][Mg][Br]"
},
"smiles": "C=[CH][Mg][Br]",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "10085",
"routeId": "sa_1afbe6c36b45d54307d5db46",
"moleculeId": "sa_c9679fdd876f32f86b77fb69",
"parentId": "10076",
"isLeaf": true,
"molecule": {
"id": "sa_c9679fdd876f32f86b77fb69",
"inchikey": "QGZKDVFQNNGYKY-UHFFFAOYSA-N",
"smiles": "N"
},
"smiles": "N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}