Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
Clc1ccnc2c(I)cccc12
InChiKey
JMDRQEKDXIQUBD-UHFFFAOYSA-N
Route Signature
dbdc6f6bdc79f5283c99a7fb6c475cc7701dddf0ee11181d4398ebaeda8014ff
Synthesis route with 5 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_2ed91c711828ee9a1fd59c28",
"signature": "dbdc6f6bdc79f5283c99a7fb6c475cc7701dddf0ee11181d4398ebaeda8014ff",
"contentHash": "f96238c81f7de54df61d806f5998658ac36466e4004d760b53498b12d2b38727",
"length": 5,
"isConvergent": false
},
"target": {
"id": "sa_dc1d997d764b245d39fbb59c",
"benchmarkSetId": "f925e688d731a0ad4e3aa6a505df094f6d3ca64ce3facc312bc5f64731921b33",
"targetId": "n5-02355",
"moleculeId": "sa_2011c8deed99e05e564e0d1d",
"smiles": "Clc1ccnc2c(I)cccc12",
"routeLength": 5,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_2011c8deed99e05e564e0d1d",
"inchikey": "JMDRQEKDXIQUBD-UHFFFAOYSA-N",
"smiles": "Clc1ccnc2c(I)cccc12"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 4
},
"rootNode": {
"id": "6319",
"routeId": "sa_2ed91c711828ee9a1fd59c28",
"moleculeId": "sa_2011c8deed99e05e564e0d1d",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_2011c8deed99e05e564e0d1d",
"inchikey": "JMDRQEKDXIQUBD-UHFFFAOYSA-N",
"smiles": "Clc1ccnc2c(I)cccc12"
},
"smiles": "Clc1ccnc2c(I)cccc12",
"reactionStepId": "sa_6a85d7a3586fdf405a717d74",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100093761A1;0999;863255\",\"rsmi\":\"O=P(Cl)(Cl)[Cl:1].O=[c:2]1[cH:3][cH:4][nH:5][c:6]2[c:7]([I:8])[cH:9][cH:10][cH:11][c:12]12>CN(C)C=O>[Cl:1][c:2]1[cH:3][cH:4][n:5][c:6]2[c:7]([I:8])[cH:9][cH:10][cH:11][c:12]12\"},\"mapped_reaction_smiles\":\"O=P(Cl)(Cl)[Cl:1].O=[c:2]1[cH:3][cH:4][nH:5][c:6]2[c:7]([I:8])[cH:9][cH:10][cH:11][c:12]12>CN(C)C=O>[Cl:1][c:2]1[cH:3][cH:4][n:5][c:6]2[c:7]([I:8])[cH:9][cH:10][cH:11][c:12]12\"}",
"reactionStep": {
"id": "sa_6a85d7a3586fdf405a717d74",
"reactionHash": "4093741c4087a7193d6ceb44b3367d42c25596af7a2900ed43fb24edb022d1ca"
},
"children": [
{
"id": "6320",
"routeId": "sa_2ed91c711828ee9a1fd59c28",
"moleculeId": "sa_1cff06dd45122fd8a86b7536",
"parentId": "6319",
"isLeaf": false,
"molecule": {
"id": "sa_1cff06dd45122fd8a86b7536",
"inchikey": "WTZKVPWLTHDRNQ-UHFFFAOYSA-N",
"smiles": "Oc1ccnc2c(I)cccc12"
},
"smiles": "O=c1cc[nH]c2c(I)cccc12",
"reactionStepId": "sa_faa7f5e1a9f39225da6d2c5a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100093761A1;0998;863254\",\"rsmi\":\"O=C(O)[c:3]1[c:2](=[O:1])[c:12]2[c:6]([nH:5][cH:4]1)[c:7]([I:8])[cH:9][cH:10][cH:11]2>c1ccc(Oc2ccccc2)cc1>[O:1]=[c:2]1[cH:3][cH:4][nH:5][c:6]2[c:7]([I:8])[cH:9][cH:10][cH:11][c:12]12\"},\"mapped_reaction_smiles\":\"O=C(O)[c:3]1[c:2](=[O:1])[c:12]2[c:6]([nH:5][cH:4]1)[c:7]([I:8])[cH:9][cH:10][cH:11]2>c1ccc(Oc2ccccc2)cc1>[O:1]=[c:2]1[cH:3][cH:4][nH:5][c:6]2[c:7]([I:8])[cH:9][cH:10][cH:11][c:12]12\"}",
"reactionStep": {
"id": "sa_faa7f5e1a9f39225da6d2c5a",
"reactionHash": "96f3cdc60bb35c5196165efa988e0a2074a1beda1f6e3e0bb7deea944888980b"
},
"children": [
{
"id": "6321",
"routeId": "sa_2ed91c711828ee9a1fd59c28",
"moleculeId": "sa_cae322504f21975509abecd6",
"parentId": "6320",
"isLeaf": false,
"molecule": {
"id": "sa_cae322504f21975509abecd6",
"inchikey": "LWJIHHQENNRCSH-UHFFFAOYSA-N",
"smiles": "O=C(O)c1c[nH]c2c(I)cccc2c1=O"
},
"smiles": "O=C(O)c1c[nH]c2c(I)cccc2c1=O",
"reactionStepId": "sa_0ba82e2155d1a1a0babdc0a9",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100093761A1;0997;863253\",\"rsmi\":\"CC[O:3][C:2](=[O:1])[c:4]1[cH:5][nH:6][c:7]2[c:8]([I:9])[cH:10][cH:11][cH:12][c:13]2[c:14]1=[O:15]>Cl.O.[Na+].O>[O:1]=[C:2]([OH:3])[c:4]1[cH:5][nH:6][c:7]2[c:8]([I:9])[cH:10][cH:11][cH:12][c:13]2[c:14]1=[O:15]\"},\"mapped_reaction_smiles\":\"CC[O:3][C:2](=[O:1])[c:4]1[cH:5][nH:6][c:7]2[c:8]([I:9])[cH:10][cH:11][cH:12][c:13]2[c:14]1=[O:15]>Cl.O.[Na+].O>[O:1]=[C:2]([OH:3])[c:4]1[cH:5][nH:6][c:7]2[c:8]([I:9])[cH:10][cH:11][cH:12][c:13]2[c:14]1=[O:15]\"}",
"reactionStep": {
"id": "sa_0ba82e2155d1a1a0babdc0a9",
"reactionHash": "79f0eaec526ecb308b8ab30a1fae7a91c9efc6e2207e5b3f9d3dced506c80ac0"
},
"children": [
{
"id": "6322",
"routeId": "sa_2ed91c711828ee9a1fd59c28",
"moleculeId": "sa_85b9ee0cdc5e397f5efc839b",
"parentId": "6321",
"isLeaf": false,
"molecule": {
"id": "sa_85b9ee0cdc5e397f5efc839b",
"inchikey": "HQRQWIBERSITPY-UHFFFAOYSA-N",
"smiles": "CCOC(=O)c1c[nH]c2c(I)cccc2c1=O"
},
"smiles": "CCOC(=O)c1c[nH]c2c(I)cccc2c1=O",
"reactionStepId": "sa_e444edf60554eac9147cf2c9",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100093761A1;0996;863252\",\"rsmi\":\"CCO[C:16]([C:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])=[CH:7][NH:8][c:9]1[c:10]([I:11])[cH:12][cH:13][cH:14][cH:15]1)=[O:17]>Cc1ccc(S(=O)(=O)O)cc1.c1ccc(Oc2ccccc2)cc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][nH:8][c:9]2[c:10]([I:11])[cH:12][cH:13][cH:14][c:15]2[c:16]1=[O:17]\"},\"mapped_reaction_smiles\":\"CCO[C:16]([C:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])=[CH:7][NH:8][c:9]1[c:10]([I:11])[cH:12][cH:13][cH:14][cH:15]1)=[O:17]>Cc1ccc(S(=O)(=O)O)cc1.c1ccc(Oc2ccccc2)cc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][nH:8][c:9]2[c:10]([I:11])[cH:12][cH:13][cH:14][c:15]2[c:16]1=[O:17]\"}",
"reactionStep": {
"id": "sa_e444edf60554eac9147cf2c9",
"reactionHash": "b2b52f397430bafc91361c96df9048231cc6d827e81a60eede6bba1bde7f5973"
},
"children": [
{
"id": "6323",
"routeId": "sa_2ed91c711828ee9a1fd59c28",
"moleculeId": "sa_9de76c0fc98f50f1ae001541",
"parentId": "6322",
"isLeaf": false,
"molecule": {
"id": "sa_9de76c0fc98f50f1ae001541",
"inchikey": "HBYYKZHGTVOZGZ-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(=CNc1ccccc1I)C(=O)OCC"
},
"smiles": "CCOC(=O)C(=CNc1ccccc1I)C(=O)OCC",
"reactionStepId": "sa_d6d2a91eee00aad5908959ce",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100093761A1;0995;863251\",\"rsmi\":\"CCO[C:4](=[O:5])[C:6](=[CH:7][O:3][CH2:2][CH3:1])[C:16](=[O:17])[O:18][CH2:19][CH3:20].[NH2:8][c:9]1[c:10]([I:11])[cH:12][cH:13][cH:14][cH:15]1>ClCCl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C:6](=[CH:7][NH:8][c:9]1[c:10]([I:11])[cH:12][cH:13][cH:14][cH:15]1)[C:16](=[O:17])[O:18][CH2:19][CH3:20]\"},\"mapped_reaction_smiles\":\"CCO[C:4](=[O:5])[C:6](=[CH:7][O:3][CH2:2][CH3:1])[C:16](=[O:17])[O:18][CH2:19][CH3:20].[NH2:8][c:9]1[c:10]([I:11])[cH:12][cH:13][cH:14][cH:15]1>ClCCl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C:6](=[CH:7][NH:8][c:9]1[c:10]([I:11])[cH:12][cH:13][cH:14][cH:15]1)[C:16](=[O:17])[O:18][CH2:19][CH3:20]\"}",
"reactionStep": {
"id": "sa_d6d2a91eee00aad5908959ce",
"reactionHash": "ae05ef607769cbff27efdd1fe69fca433617ce192769ff0fc024177ba3c95c47"
},
"children": [
{
"id": "6324",
"routeId": "sa_2ed91c711828ee9a1fd59c28",
"moleculeId": "sa_0553be87bb49fb4dc53aa354",
"parentId": "6323",
"isLeaf": true,
"molecule": {
"id": "sa_0553be87bb49fb4dc53aa354",
"inchikey": "LTMHNWPUDSTBKD-UHFFFAOYSA-N",
"smiles": "CCOC=C(C(=O)OCC)C(=O)OCC"
},
"smiles": "CCOC=C(C(=O)OCC)C(=O)OCC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "6325",
"routeId": "sa_2ed91c711828ee9a1fd59c28",
"moleculeId": "sa_ccb8160d1fccf60f36b3d78b",
"parentId": "6323",
"isLeaf": true,
"molecule": {
"id": "sa_ccb8160d1fccf60f36b3d78b",
"inchikey": "UBPDKIDWEADHPP-UHFFFAOYSA-N",
"smiles": "Nc1ccccc1I"
},
"smiles": "Nc1ccccc1I",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
},
{
"id": "6326",
"routeId": "sa_2ed91c711828ee9a1fd59c28",
"moleculeId": "sa_312a7cd3d48a055e9bc98180",
"parentId": "6319",
"isLeaf": true,
"molecule": {
"id": "sa_312a7cd3d48a055e9bc98180",
"inchikey": "XHXFXVLFKHQFAL-UHFFFAOYSA-N",
"smiles": "O=P(Cl)(Cl)Cl"
},
"smiles": "O=P(Cl)(Cl)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}