Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
Cc1cc(CO)[nH]c(=O)c1CNC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C
InChiKey
CGIAWAKEQRVADP-UHFFFAOYSA-N
Route Signature
29df8dc48ea20d73e65ce2c66d46abd80bd46f5d473e97ec3542ff774a773107
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_f9b95efb52a11472e94c83db",
"signature": "29df8dc48ea20d73e65ce2c66d46abd80bd46f5d473e97ec3542ff774a773107",
"contentHash": "ac9a9d91af5983a85b71c90603627be48b28b9166e87307b755dba6d298d337c",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_d809a0b713c0fafdeee51ead",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-03974",
"moleculeId": "sa_2b1673a732c97689f5279fb1",
"smiles": "Cc1cc(CO)[nH]c(=O)c1CNC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_2b1673a732c97689f5279fb1",
"inchikey": "CGIAWAKEQRVADP-UHFFFAOYSA-N",
"smiles": "Cc1cc(CO)[nH]c(=O)c1CNC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "11124",
"routeId": "sa_f9b95efb52a11472e94c83db",
"moleculeId": "sa_2b1673a732c97689f5279fb1",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_2b1673a732c97689f5279fb1",
"inchikey": "CGIAWAKEQRVADP-UHFFFAOYSA-N",
"smiles": "Cc1cc(CO)[nH]c(=O)c1CNC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C"
},
"smiles": "Cc1cc(CO)[nH]c(=O)c1CNC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C",
"reactionStepId": "sa_195076c2b9209ff4cdc95bd6",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160074394A1;0649;1852070\",\"rsmi\":\"C[O:24][c:23]1[c:15]([CH2:14][NH:13][C:11]([c:10]2[c:9]3[c:2]([CH3:1])[cH:3][n:4]([CH:5]([CH3:6])[CH3:7])[c:8]3[cH:28][c:26]([Br:27])[cH:25]2)=[O:12])[c:16]([CH3:17])[cH:18][c:19]([CH2:20][OH:21])[n:22]1>C1CCOC1.Cl>[CH3:1][c:2]1[cH:3][n:4]([CH:5]([CH3:6])[CH3:7])[c:8]2[c:9]1[c:10]([C:11](=[O:12])[NH:13][CH2:14][c:15]1[c:16]([CH3:17])[cH:18][c:19]([CH2:20][OH:21])[nH:22][c:23]1=[O:24])[cH:25][c:26]([Br:27])[cH:28]2\"},\"mapped_reaction_smiles\":\"C[O:24][c:23]1[c:15]([CH2:14][NH:13][C:11]([c:10]2[c:9]3[c:2]([CH3:1])[cH:3][n:4]([CH:5]([CH3:6])[CH3:7])[c:8]3[cH:28][c:26]([Br:27])[cH:25]2)=[O:12])[c:16]([CH3:17])[cH:18][c:19]([CH2:20][OH:21])[n:22]1>C1CCOC1.Cl>[CH3:1][c:2]1[cH:3][n:4]([CH:5]([CH3:6])[CH3:7])[c:8]2[c:9]1[c:10]([C:11](=[O:12])[NH:13][CH2:14][c:15]1[c:16]([CH3:17])[cH:18][c:19]([CH2:20][OH:21])[nH:22][c:23]1=[O:24])[cH:25][c:26]([Br:27])[cH:28]2\"}",
"reactionStep": {
"id": "sa_195076c2b9209ff4cdc95bd6",
"reactionHash": "e82ab39af91e8d693c8998d58e9005edac999006d1781c78415820e137565b8d"
},
"children": [
{
"id": "11125",
"routeId": "sa_f9b95efb52a11472e94c83db",
"moleculeId": "sa_19f84d019c78544859c914b3",
"parentId": "11124",
"isLeaf": false,
"molecule": {
"id": "sa_19f84d019c78544859c914b3",
"inchikey": "ZWBAGBFKDXZHSK-UHFFFAOYSA-N",
"smiles": "COc1nc(CO)cc(C)c1CNC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C"
},
"smiles": "COc1nc(CO)cc(C)c1CNC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C",
"reactionStepId": "sa_c30203db817ed7d79ac3600a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160074394A1;0647;1852069\",\"rsmi\":\"O[C:14](=[O:15])[c:16]1[cH:17][c:18]([Br:19])[cH:20][c:21]2[c:22]1[c:23]([CH3:24])[cH:25][n:26]2[CH:27]([CH3:28])[CH3:29].[CH3:1][O:2][c:3]1[n:4][c:5]([CH2:6][OH:7])[cH:8][c:9]([CH3:10])[c:11]1[CH2:12][NH2:13]>CCOC(C)=O.CN(C)C=O.ClCCCl.ClCCl.On1nnc2cccnc21>[CH3:1][O:2][c:3]1[n:4][c:5]([CH2:6][OH:7])[cH:8][c:9]([CH3:10])[c:11]1[CH2:12][NH:13][C:14](=[O:15])[c:16]1[cH:17][c:18]([Br:19])[cH:20][c:21]2[c:22]1[c:23]([CH3:24])[cH:25][n:26]2[CH:27]([CH3:28])[CH3:29]\"},\"mapped_reaction_smiles\":\"O[C:14](=[O:15])[c:16]1[cH:17][c:18]([Br:19])[cH:20][c:21]2[c:22]1[c:23]([CH3:24])[cH:25][n:26]2[CH:27]([CH3:28])[CH3:29].[CH3:1][O:2][c:3]1[n:4][c:5]([CH2:6][OH:7])[cH:8][c:9]([CH3:10])[c:11]1[CH2:12][NH2:13]>CCOC(C)=O.CN(C)C=O.ClCCCl.ClCCl.On1nnc2cccnc21>[CH3:1][O:2][c:3]1[n:4][c:5]([CH2:6][OH:7])[cH:8][c:9]([CH3:10])[c:11]1[CH2:12][NH:13][C:14](=[O:15])[c:16]1[cH:17][c:18]([Br:19])[cH:20][c:21]2[c:22]1[c:23]([CH3:24])[cH:25][n:26]2[CH:27]([CH3:28])[CH3:29]\"}",
"reactionStep": {
"id": "sa_c30203db817ed7d79ac3600a",
"reactionHash": "bd1da6ef30426a742b196bafdf9cc286e2dda0df988db9bc65af07617d812c22"
},
"children": [
{
"id": "11126",
"routeId": "sa_f9b95efb52a11472e94c83db",
"moleculeId": "sa_7186e5ce3b71dd7d217aa4ff",
"parentId": "11125",
"isLeaf": false,
"molecule": {
"id": "sa_7186e5ce3b71dd7d217aa4ff",
"inchikey": "HNMDJRSGZVKODO-UHFFFAOYSA-N",
"smiles": "Cc1cn(C(C)C)c2cc(Br)cc(C(=O)O)c12"
},
"smiles": "Cc1cn(C(C)C)c2cc(Br)cc(C(=O)O)c12",
"reactionStepId": "sa_0312f5502a9a7042c141f5ce",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160074394A1;0841;1852142\",\"rsmi\":\"C[O:13][C:11]([c:10]1[c:9]2[c:2]([CH3:1])[cH:3][n:4]([CH:5]([CH3:6])[CH3:7])[c:8]2[cH:17][c:15]([Br:16])[cH:14]1)=[O:12]>CCO.O.[Na+].O>[CH3:1][c:2]1[cH:3][n:4]([CH:5]([CH3:6])[CH3:7])[c:8]2[c:9]1[c:10]([C:11](=[O:12])[OH:13])[cH:14][c:15]([Br:16])[cH:17]2\"},\"mapped_reaction_smiles\":\"C[O:13][C:11]([c:10]1[c:9]2[c:2]([CH3:1])[cH:3][n:4]([CH:5]([CH3:6])[CH3:7])[c:8]2[cH:17][c:15]([Br:16])[cH:14]1)=[O:12]>CCO.O.[Na+].O>[CH3:1][c:2]1[cH:3][n:4]([CH:5]([CH3:6])[CH3:7])[c:8]2[c:9]1[c:10]([C:11](=[O:12])[OH:13])[cH:14][c:15]([Br:16])[cH:17]2\"}",
"reactionStep": {
"id": "sa_0312f5502a9a7042c141f5ce",
"reactionHash": "4328b1b8b4ce6472630275201d6ae03deee1d631a46d86478bd8ba2cea73f1f4"
},
"children": [
{
"id": "11127",
"routeId": "sa_f9b95efb52a11472e94c83db",
"moleculeId": "sa_0d64e3816f4a3d510c3baf2b",
"parentId": "11126",
"isLeaf": false,
"molecule": {
"id": "sa_0d64e3816f4a3d510c3baf2b",
"inchikey": "VZPCQSDKWBZZDS-UHFFFAOYSA-N",
"smiles": "COC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C"
},
"smiles": "COC(=O)c1cc(Br)cc2c1c(C)cn2C(C)C",
"reactionStepId": "sa_f2354bfb7286ba64ab501804",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160074394A1;0839;1852141\",\"rsmi\":\"O=[CH:13][c:12]1[c:11]2[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:6][c:7]([Br:8])[cH:9][c:10]2[n:15]([CH:16]([CH3:17])[CH3:18])[cH:14]1>CN(C)C=O.Cc1ccc([SH](=O)=O)cc1.O.O=S1(=O)CCCC1.BC#N.[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([Br:8])[cH:9][c:10]2[c:11]1[c:12]([CH3:13])[cH:14][n:15]2[CH:16]([CH3:17])[CH3:18]\"},\"mapped_reaction_smiles\":\"O=[CH:13][c:12]1[c:11]2[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:6][c:7]([Br:8])[cH:9][c:10]2[n:15]([CH:16]([CH3:17])[CH3:18])[cH:14]1>CN(C)C=O.Cc1ccc([SH](=O)=O)cc1.O.O=S1(=O)CCCC1.BC#N.[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([Br:8])[cH:9][c:10]2[c:11]1[c:12]([CH3:13])[cH:14][n:15]2[CH:16]([CH3:17])[CH3:18]\"}",
"reactionStep": {
"id": "sa_f2354bfb7286ba64ab501804",
"reactionHash": "1e6c1dcc48550322d7fadc2f9a949a968cf8796aa96d4729090d1a17e01b5050"
},
"children": [
{
"id": "11128",
"routeId": "sa_f9b95efb52a11472e94c83db",
"moleculeId": "sa_5394534eaf4248e2c71283d8",
"parentId": "11127",
"isLeaf": true,
"molecule": {
"id": "sa_5394534eaf4248e2c71283d8",
"inchikey": "TWCUCUFAHMRUFA-UHFFFAOYSA-N",
"smiles": "COC(=O)c1cc(Br)cc2c1c(C=O)cn2C(C)C"
},
"smiles": "COC(=O)c1cc(Br)cc2c1c(C=O)cn2C(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "11129",
"routeId": "sa_f9b95efb52a11472e94c83db",
"moleculeId": "sa_da316898d4b9f39d5ae8ba05",
"parentId": "11125",
"isLeaf": false,
"molecule": {
"id": "sa_da316898d4b9f39d5ae8ba05",
"inchikey": "SXRHRRRVAWPEDP-UHFFFAOYSA-N",
"smiles": "COc1nc(CO)cc(C)c1CN"
},
"smiles": "COc1nc(CO)cc(C)c1CN",
"reactionStepId": "sa_93ac06e29a2e8f5f599b85b4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160074394A1;0818;1852132\",\"rsmi\":\"[CH3:1][O:2][c:3]1[c:4]([C:5]#[N:6])[c:7]([CH3:8])[cH:9][c:10]([CH2:11][OH:12])[n:13]1>CC(=O)O.CCO.[Ni]>[CH3:1][O:2][c:3]1[c:4]([CH2:5][NH2:6])[c:7]([CH3:8])[cH:9][c:10]([CH2:11][OH:12])[n:13]1\"},\"mapped_reaction_smiles\":\"[CH3:1][O:2][c:3]1[c:4]([C:5]#[N:6])[c:7]([CH3:8])[cH:9][c:10]([CH2:11][OH:12])[n:13]1>CC(=O)O.CCO.[Ni]>[CH3:1][O:2][c:3]1[c:4]([CH2:5][NH2:6])[c:7]([CH3:8])[cH:9][c:10]([CH2:11][OH:12])[n:13]1\"}",
"reactionStep": {
"id": "sa_93ac06e29a2e8f5f599b85b4",
"reactionHash": "dcfa41498e0dec2d9ec70fab64fb88016560eb94a3bb61b7fb8e05309b34f444"
},
"children": [
{
"id": "11130",
"routeId": "sa_f9b95efb52a11472e94c83db",
"moleculeId": "sa_9daf6e8255f808a8fc54bd2a",
"parentId": "11129",
"isLeaf": false,
"molecule": {
"id": "sa_9daf6e8255f808a8fc54bd2a",
"inchikey": "PDPDBMSLNXTORF-UHFFFAOYSA-N",
"smiles": "COc1nc(CO)cc(C)c1C#N"
},
"smiles": "COc1nc(CO)cc(C)c1C#N",
"reactionStepId": "sa_61e4b8b11b3b8f8dc86a93ae",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160074394A1;0817;1852131\",\"rsmi\":\"CCO[C:11]([c:10]1[cH:9][c:7]([CH3:8])[c:4]([C:5]#[N:6])[c:3]([O:2][CH3:1])[n:13]1)=[O:12]>C1CCOC1.CCO.CCOC(C)=O.ClCCl.B.[Ca+2].Cl.Cl.[Na+]>[CH3:1][O:2][c:3]1[c:4]([C:5]#[N:6])[c:7]([CH3:8])[cH:9][c:10]([CH2:11][OH:12])[n:13]1\"},\"mapped_reaction_smiles\":\"CCO[C:11]([c:10]1[cH:9][c:7]([CH3:8])[c:4]([C:5]#[N:6])[c:3]([O:2][CH3:1])[n:13]1)=[O:12]>C1CCOC1.CCO.CCOC(C)=O.ClCCl.B.[Ca+2].Cl.Cl.[Na+]>[CH3:1][O:2][c:3]1[c:4]([C:5]#[N:6])[c:7]([CH3:8])[cH:9][c:10]([CH2:11][OH:12])[n:13]1\"}",
"reactionStep": {
"id": "sa_61e4b8b11b3b8f8dc86a93ae",
"reactionHash": "48401caa8647cc0c86711f8763a20c9f50561edb74caee108c3197602e6d8af7"
},
"children": [
{
"id": "11131",
"routeId": "sa_f9b95efb52a11472e94c83db",
"moleculeId": "sa_0808c133ccac358f1a89f464",
"parentId": "11130",
"isLeaf": true,
"molecule": {
"id": "sa_0808c133ccac358f1a89f464",
"inchikey": "PYXODQXFLFTQNB-UHFFFAOYSA-N",
"smiles": "CCOC(=O)c1cc(C)c(C#N)c(OC)n1"
},
"smiles": "CCOC(=O)c1cc(C)c(C#N)c(OC)n1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}