Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COCOc1cc(C)c(-c2cccc(COc3ccc4c(c3)-c3ccccc3C4=O)c2C)c(C)c1
InChiKey
RDXIOVDZIDLXAV-UHFFFAOYSA-N
Route Signature
c6a5c9c74eb7b0b5ba46eb810f7cf9a9fac95bad449bd369936c2b6c1cecae12
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_8f1798050358fcdfd643382d",
"signature": "c6a5c9c74eb7b0b5ba46eb810f7cf9a9fac95bad449bd369936c2b6c1cecae12",
"contentHash": "d06a0db3dbf28e7e9b089615c47611fdaa2ca39abd35160a2b6263fccec33a1a",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_f7e53cc210157ecb6f38452c",
"benchmarkSetId": "7390a9c2522b1c81605e80a42a8de7c7ad9a5797d028633b54904bc78f091bb8",
"targetId": "n5-00241",
"moleculeId": "sa_802a24c7a4c221f2b3b37862",
"smiles": "COCOc1cc(C)c(-c2cccc(COc3ccc4c(c3)-c3ccccc3C4=O)c2C)c(C)c1",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_802a24c7a4c221f2b3b37862",
"inchikey": "RDXIOVDZIDLXAV-UHFFFAOYSA-N",
"smiles": "COCOc1cc(C)c(-c2cccc(COc3ccc4c(c3)-c3ccccc3C4=O)c2C)c(C)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 4
},
"rootNode": {
"id": "493",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_802a24c7a4c221f2b3b37862",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_802a24c7a4c221f2b3b37862",
"inchikey": "RDXIOVDZIDLXAV-UHFFFAOYSA-N",
"smiles": "COCOc1cc(C)c(-c2cccc(COc3ccc4c(c3)-c3ccccc3C4=O)c2C)c(C)c1"
},
"smiles": "COCOc1cc(C)c(-c2cccc(COc3ccc4c(c3)-c3ccccc3C4=O)c2C)c(C)c1",
"reactionStepId": "sa_c4f0958ed05d86839d6ec2b3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120035196A1;0393;1178076\",\"rsmi\":\"F[c:16]1[cH:17][c:18]2[c:19]([cH:20][cH:21]1)[C:22](=[O:23])[c:24]1[cH:25][cH:26][cH:27][cH:28][c:29]1-2.[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9](-[c:10]2[c:11]([CH3:12])[c:13]([CH2:14][OH:15])[cH:30][cH:31][cH:32]2)[c:33]([CH3:34])[cH:35]1>CN(C)C=O.O.[HH].[Na+]>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9](-[c:10]2[c:11]([CH3:12])[c:13]([CH2:14][O:15][c:16]3[cH:17][c:18]4[c:19]([cH:20][cH:21]3)[C:22](=[O:23])[c:24]3[cH:25][cH:26][cH:27][cH:28][c:29]3-4)[cH:30][cH:31][cH:32]2)[c:33]([CH3:34])[cH:35]1\"},\"mapped_reaction_smiles\":\"F[c:16]1[cH:17][c:18]2[c:19]([cH:20][cH:21]1)[C:22](=[O:23])[c:24]1[cH:25][cH:26][cH:27][cH:28][c:29]1-2.[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9](-[c:10]2[c:11]([CH3:12])[c:13]([CH2:14][OH:15])[cH:30][cH:31][cH:32]2)[c:33]([CH3:34])[cH:35]1>CN(C)C=O.O.[HH].[Na+]>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9](-[c:10]2[c:11]([CH3:12])[c:13]([CH2:14][O:15][c:16]3[cH:17][c:18]4[c:19]([cH:20][cH:21]3)[C:22](=[O:23])[c:24]3[cH:25][cH:26][cH:27][cH:28][c:29]3-4)[cH:30][cH:31][cH:32]2)[c:33]([CH3:34])[cH:35]1\"}",
"reactionStep": {
"id": "sa_c4f0958ed05d86839d6ec2b3",
"reactionHash": "f803c15fb4e305d774c6aca704972a96cb11917528f8e6cba19ebc039ba4cbbd"
},
"children": [
{
"id": "494",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_40e3323cfe9991cb782401e8",
"parentId": "493",
"isLeaf": false,
"molecule": {
"id": "sa_40e3323cfe9991cb782401e8",
"inchikey": "IIMZVUVYRKMUPE-UHFFFAOYSA-N",
"smiles": "COCOc1cc(C)c(-c2cccc(CO)c2C)c(C)c1"
},
"smiles": "COCOc1cc(C)c(-c2cccc(CO)c2C)c(C)c1",
"reactionStepId": "sa_131cbf52cca52b80dbc7c413",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120035196A1;0391;1178075\",\"rsmi\":\"CO[C:14]([c:13]1[c:11]([CH3:12])[c:10](-[c:9]2[c:7]([CH3:8])[cH:6][c:5]([O:4][CH2:3][O:2][CH3:1])[cH:21][c:19]2[CH3:20])[cH:18][cH:17][cH:16]1)=[O:15]>C1CCOC1.[Al+3].[HH].[HH].[HH].[HH].[Li+]>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9](-[c:10]2[c:11]([CH3:12])[c:13]([CH2:14][OH:15])[cH:16][cH:17][cH:18]2)[c:19]([CH3:20])[cH:21]1\"},\"mapped_reaction_smiles\":\"CO[C:14]([c:13]1[c:11]([CH3:12])[c:10](-[c:9]2[c:7]([CH3:8])[cH:6][c:5]([O:4][CH2:3][O:2][CH3:1])[cH:21][c:19]2[CH3:20])[cH:18][cH:17][cH:16]1)=[O:15]>C1CCOC1.[Al+3].[HH].[HH].[HH].[HH].[Li+]>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9](-[c:10]2[c:11]([CH3:12])[c:13]([CH2:14][OH:15])[cH:16][cH:17][cH:18]2)[c:19]([CH3:20])[cH:21]1\"}",
"reactionStep": {
"id": "sa_131cbf52cca52b80dbc7c413",
"reactionHash": "a270d5cb0df5da4368f2666304b981161cdac0eae3a4f55fc9b71a2e3356e3f2"
},
"children": [
{
"id": "495",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_97a3e2508d51334012817636",
"parentId": "494",
"isLeaf": false,
"molecule": {
"id": "sa_97a3e2508d51334012817636",
"inchikey": "KRDBNULPUSCGRT-UHFFFAOYSA-N",
"smiles": "COCOc1cc(C)c(-c2cccc(C(=O)OC)c2C)c(C)c1"
},
"smiles": "COCOc1cc(C)c(-c2cccc(C(=O)OC)c2C)c(C)c1",
"reactionStepId": "sa_364369728c40586fd6be7ba4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120035196A1;0387;1178073\",\"rsmi\":\"Br[c:10]1[c:11]([CH3:12])[c:13]([C:14](=[O:15])[O:16][CH3:17])[cH:18][cH:19][cH:20]1.OB(O)[c:9]1[c:7]([CH3:8])[cH:6][c:5]([O:4][CH2:3][O:2][CH3:1])[cH:23][c:21]1[CH3:22]>CC(=O)O.CC(=O)O.COc1cccc(OC)c1-c1ccccc1P(C1CCCCC1)C1CCCCC1.Cc1ccccc1.O.O=P(O)(O)O.[K+].[K+].[K+].[Pd+2]>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9](-[c:10]2[c:11]([CH3:12])[c:13]([C:14](=[O:15])[O:16][CH3:17])[cH:18][cH:19][cH:20]2)[c:21]([CH3:22])[cH:23]1\"},\"mapped_reaction_smiles\":\"Br[c:10]1[c:11]([CH3:12])[c:13]([C:14](=[O:15])[O:16][CH3:17])[cH:18][cH:19][cH:20]1.OB(O)[c:9]1[c:7]([CH3:8])[cH:6][c:5]([O:4][CH2:3][O:2][CH3:1])[cH:23][c:21]1[CH3:22]>CC(=O)O.CC(=O)O.COc1cccc(OC)c1-c1ccccc1P(C1CCCCC1)C1CCCCC1.Cc1ccccc1.O.O=P(O)(O)O.[K+].[K+].[K+].[Pd+2]>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9](-[c:10]2[c:11]([CH3:12])[c:13]([C:14](=[O:15])[O:16][CH3:17])[cH:18][cH:19][cH:20]2)[c:21]([CH3:22])[cH:23]1\"}",
"reactionStep": {
"id": "sa_364369728c40586fd6be7ba4",
"reactionHash": "0d43866103177c93708100a30b5ea9becb00ce71f203b2858e51dd7eaf11681d"
},
"children": [
{
"id": "496",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_99d55cbd1cd8e155ecd64a10",
"parentId": "495",
"isLeaf": false,
"molecule": {
"id": "sa_99d55cbd1cd8e155ecd64a10",
"inchikey": "KAAMSKWLTRGLFW-UHFFFAOYSA-N",
"smiles": "COCOc1cc(C)c(B(O)O)c(C)c1"
},
"smiles": "COCOc1cc(C)c(B(O)O)c(C)c1",
"reactionStepId": "sa_c3ee260c7b564ca5e8a8f60c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120035196A1;0384;1178070\",\"rsmi\":\"Br[c:9]1[c:7]([CH3:8])[cH:6][c:5]([O:4][CH2:3][O:2][CH3:1])[cH:15][c:13]1[CH3:14].CC(C)O[B:10]([O:11]C(C)C)[O:12]C(C)C>C1CCOC1.CCCCCC.[Li]CCCC>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9]([B:10]([OH:11])[OH:12])[c:13]([CH3:14])[cH:15]1\"},\"mapped_reaction_smiles\":\"Br[c:9]1[c:7]([CH3:8])[cH:6][c:5]([O:4][CH2:3][O:2][CH3:1])[cH:15][c:13]1[CH3:14].CC(C)O[B:10]([O:11]C(C)C)[O:12]C(C)C>C1CCOC1.CCCCCC.[Li]CCCC>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9]([B:10]([OH:11])[OH:12])[c:13]([CH3:14])[cH:15]1\"}",
"reactionStep": {
"id": "sa_c3ee260c7b564ca5e8a8f60c",
"reactionHash": "aa0642f6a16a03042573cfe297e44de886a99692f5e03f3f722cf1dfa6c71d69"
},
"children": [
{
"id": "497",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_0c3a1c72e8778c8e8b205e29",
"parentId": "496",
"isLeaf": true,
"molecule": {
"id": "sa_0c3a1c72e8778c8e8b205e29",
"inchikey": "NHDIQVFFNDKAQU-UHFFFAOYSA-N",
"smiles": "CC(C)OB(OC(C)C)OC(C)C"
},
"smiles": "CC(C)OB(OC(C)C)OC(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "498",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_c6ab5316c2c612a0ec7f31b2",
"parentId": "496",
"isLeaf": false,
"molecule": {
"id": "sa_c6ab5316c2c612a0ec7f31b2",
"inchikey": "ZGHZNSGBLRLTPQ-UHFFFAOYSA-N",
"smiles": "COCOc1cc(C)c(Br)c(C)c1"
},
"smiles": "COCOc1cc(C)c(Br)c(C)c1",
"reactionStepId": "sa_fdc820a6256b020c33e65f75",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120035196A1;0382;1178069\",\"rsmi\":\"Cl[CH2:3][O:2][CH3:1].[OH:4][c:5]1[cH:6][c:7]([CH3:8])[c:9]([Br:10])[c:11]([CH3:12])[cH:13]1>CC#N.O=C(O)O.[K+].[K+]>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9]([Br:10])[c:11]([CH3:12])[cH:13]1\"},\"mapped_reaction_smiles\":\"Cl[CH2:3][O:2][CH3:1].[OH:4][c:5]1[cH:6][c:7]([CH3:8])[c:9]([Br:10])[c:11]([CH3:12])[cH:13]1>CC#N.O=C(O)O.[K+].[K+]>[CH3:1][O:2][CH2:3][O:4][c:5]1[cH:6][c:7]([CH3:8])[c:9]([Br:10])[c:11]([CH3:12])[cH:13]1\"}",
"reactionStep": {
"id": "sa_fdc820a6256b020c33e65f75",
"reactionHash": "4046c3970eafc30fd171155ac352865cb9139ff7a271813d6fd529c084dafae6"
},
"children": [
{
"id": "499",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_713f26120c6c743dbb3f0714",
"parentId": "498",
"isLeaf": true,
"molecule": {
"id": "sa_713f26120c6c743dbb3f0714",
"inchikey": "WMUWDPLTTLJNPE-UHFFFAOYSA-N",
"smiles": "Cc1cc(O)cc(C)c1Br"
},
"smiles": "Cc1cc(O)cc(C)c1Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "500",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_3b491e3532b8289adf4ebe71",
"parentId": "498",
"isLeaf": true,
"molecule": {
"id": "sa_3b491e3532b8289adf4ebe71",
"inchikey": "XJUZRXYOEPSWMB-UHFFFAOYSA-N",
"smiles": "COCCl"
},
"smiles": "COCCl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "501",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_09595b099cd633a4ab2edae2",
"parentId": "495",
"isLeaf": false,
"molecule": {
"id": "sa_09595b099cd633a4ab2edae2",
"inchikey": "MKQQTCSBXHAYQL-UHFFFAOYSA-N",
"smiles": "COC(=O)c1cccc(Br)c1C"
},
"smiles": "COC(=O)c1cccc(Br)c1C",
"reactionStepId": "sa_aa2c26e6b1c18cb05f86b32a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120035196A1;0385;1178071\",\"rsmi\":\"O[C:3](=[O:4])[c:5]1[c:6]([CH3:7])[c:8]([Br:9])[cH:10][cH:11][cH:12]1.[CH3:1][OH:2]>O=S(=O)(O)O>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([CH3:7])[c:8]([Br:9])[cH:10][cH:11][cH:12]1\"},\"mapped_reaction_smiles\":\"O[C:3](=[O:4])[c:5]1[c:6]([CH3:7])[c:8]([Br:9])[cH:10][cH:11][cH:12]1.[CH3:1][OH:2]>O=S(=O)(O)O>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([CH3:7])[c:8]([Br:9])[cH:10][cH:11][cH:12]1\"}",
"reactionStep": {
"id": "sa_aa2c26e6b1c18cb05f86b32a",
"reactionHash": "cdff17f0b3b809d11c88854afe337565c8036ccd8654c4cedc531abe6a350995"
},
"children": [
{
"id": "502",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_ff069e176b8a4e2896375c99",
"parentId": "501",
"isLeaf": true,
"molecule": {
"id": "sa_ff069e176b8a4e2896375c99",
"inchikey": "BJGKVCKGUBYULR-UHFFFAOYSA-N",
"smiles": "Cc1c(Br)cccc1C(=O)O"
},
"smiles": "Cc1c(Br)cccc1C(=O)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "503",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "501",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "504",
"routeId": "sa_8f1798050358fcdfd643382d",
"moleculeId": "sa_2be69569c28f5f201d556f93",
"parentId": "493",
"isLeaf": true,
"molecule": {
"id": "sa_2be69569c28f5f201d556f93",
"inchikey": "WNABGBVMUJCYJP-UHFFFAOYSA-N",
"smiles": "O=C1c2ccccc2-c2cc(F)ccc21"
},
"smiles": "O=C1c2ccccc2-c2cc(F)ccc21",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}