Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1ccc(Br)c(CC(=O)N(C)C)c1
InChiKey
XVSLQGWBQZJQCV-UHFFFAOYSA-N
Route Signature
a80f2b7d3946c9806582ef5bc460399621c5f1246b21e783676a4b07daedab6c
Synthesis route with 6 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_381391caec86d09d9665d463",
"signature": "a80f2b7d3946c9806582ef5bc460399621c5f1246b21e783676a4b07daedab6c",
"contentHash": "25634c03540b689548a034dfdedb5ce4598e9a574044c6e3b8962f3d0d158ad7",
"length": 6,
"isConvergent": false
},
"target": {
"id": "sa_55f9c5fe5ed5d1a47cd2e8bf",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00081",
"moleculeId": "sa_2092a7c63b2fd17c31c24af7",
"smiles": "COc1ccc(Br)c(CC(=O)N(C)C)c1",
"routeLength": 6,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_2092a7c63b2fd17c31c24af7",
"inchikey": "XVSLQGWBQZJQCV-UHFFFAOYSA-N",
"smiles": "COc1ccc(Br)c(CC(=O)N(C)C)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "12352",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_2092a7c63b2fd17c31c24af7",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_2092a7c63b2fd17c31c24af7",
"inchikey": "XVSLQGWBQZJQCV-UHFFFAOYSA-N",
"smiles": "COc1ccc(Br)c(CC(=O)N(C)C)c1"
},
"smiles": "COc1ccc(Br)c(CC(=O)N(C)C)c1",
"reactionStepId": "sa_4105c07d0202fb1a06657d67",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040132769A1;0356;170157\",\"rsmi\":\"Cl[C:7]([CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:15][cH:14][c:12]1[Br:13])=[O:8].[NH:9]([CH3:10])[CH3:11]>CCOCC>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[N:9]([CH3:10])[CH3:11])[c:12]([Br:13])[cH:14][cH:15]1\"},\"mapped_reaction_smiles\":\"Cl[C:7]([CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:15][cH:14][c:12]1[Br:13])=[O:8].[NH:9]([CH3:10])[CH3:11]>CCOCC>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[N:9]([CH3:10])[CH3:11])[c:12]([Br:13])[cH:14][cH:15]1\"}",
"reactionStep": {
"id": "sa_4105c07d0202fb1a06657d67",
"reactionHash": "ada30215e628700c50f46c84039b7373a417d6c1341458fea9115895a25076b1"
},
"children": [
{
"id": "12353",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_e2676e5c7c9d7a020ed1780e",
"parentId": "12352",
"isLeaf": true,
"molecule": {
"id": "sa_e2676e5c7c9d7a020ed1780e",
"inchikey": "ROSDSFDQCJNGOL-UHFFFAOYSA-N",
"smiles": "CNC"
},
"smiles": "CNC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12354",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_bfe189acf8e2168fdb0506a2",
"parentId": "12352",
"isLeaf": false,
"molecule": {
"id": "sa_bfe189acf8e2168fdb0506a2",
"inchikey": "XPIYQESTZPNBFC-UHFFFAOYSA-N",
"smiles": "COc1ccc(Br)c(CC(=O)Cl)c1"
},
"smiles": "COc1ccc(Br)c(CC(=O)Cl)c1",
"reactionStepId": "sa_e2cfcaeeb708ac42cd5934f4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040132769A1;0355;170156\",\"rsmi\":\"O=S(Cl)[Cl:9].O[C:7]([CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:13][cH:12][c:10]1[Br:11])=[O:8]>CN(C)C=O.ClCCl>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[Cl:9])[c:10]([Br:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"O=S(Cl)[Cl:9].O[C:7]([CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:13][cH:12][c:10]1[Br:11])=[O:8]>CN(C)C=O.ClCCl>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[Cl:9])[c:10]([Br:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_e2cfcaeeb708ac42cd5934f4",
"reactionHash": "b7a70069df3aa3f014ea2961ad896b12b79e82a238bd5219599ca71cdcb7eb46"
},
"children": [
{
"id": "12355",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_cd67ce42f230ef1a4063353c",
"parentId": "12354",
"isLeaf": true,
"molecule": {
"id": "sa_cd67ce42f230ef1a4063353c",
"inchikey": "FYSNRJHAOHDILO-UHFFFAOYSA-N",
"smiles": "O=S(Cl)Cl"
},
"smiles": "O=S(Cl)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12356",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_4fde4d6ab81a90f87eee4afe",
"parentId": "12354",
"isLeaf": false,
"molecule": {
"id": "sa_4fde4d6ab81a90f87eee4afe",
"inchikey": "XEXHAKGPISSIIX-UHFFFAOYSA-N",
"smiles": "COc1ccc(Br)c(CC(=O)O)c1"
},
"smiles": "COc1ccc(Br)c(CC(=O)O)c1",
"reactionStepId": "sa_0ba7991e5f184b4013d838bd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040132769A1;0354;170155\",\"rsmi\":\"CC[OH:9].N#[C:7][CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:13][cH:12][c:10]1[Br:11].[OH2:8]>[Na+].O>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[OH:9])[c:10]([Br:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"CC[OH:9].N#[C:7][CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:13][cH:12][c:10]1[Br:11].[OH2:8]>[Na+].O>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7](=[O:8])[OH:9])[c:10]([Br:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_0ba7991e5f184b4013d838bd",
"reactionHash": "135c7bea7e75131ac7500656ad256495883d1f73a89c8476e6e9774f126ed6e3"
},
"children": [
{
"id": "12357",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_afaca116b303dc7d01346819",
"parentId": "12356",
"isLeaf": true,
"molecule": {
"id": "sa_afaca116b303dc7d01346819",
"inchikey": "LFQSCWFLJHTTHZ-UHFFFAOYSA-N",
"smiles": "CCO"
},
"smiles": "CCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12358",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_519fcf60462bb5af8543cec1",
"parentId": "12356",
"isLeaf": false,
"molecule": {
"id": "sa_519fcf60462bb5af8543cec1",
"inchikey": "VSSZEBGUCILFSV-UHFFFAOYSA-N",
"smiles": "COc1ccc(Br)c(CC#N)c1"
},
"smiles": "COc1ccc(Br)c(CC#N)c1",
"reactionStepId": "sa_c93e258c67492c4cddc7c7cb",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040132769A1;0353;170154\",\"rsmi\":\"Br[CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:12][cH:11][c:9]1[Br:10].[CH:7]#[N:8]>CCO.O.Br.[Na+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7]#[N:8])[c:9]([Br:10])[cH:11][cH:12]1\"},\"mapped_reaction_smiles\":\"Br[CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:12][cH:11][c:9]1[Br:10].[CH:7]#[N:8]>CCO.O.Br.[Na+]>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][C:7]#[N:8])[c:9]([Br:10])[cH:11][cH:12]1\"}",
"reactionStep": {
"id": "sa_c93e258c67492c4cddc7c7cb",
"reactionHash": "75e9fb366f652d8492d9a060985111c1f79d2106f25f470d2a7a680be826c062"
},
"children": [
{
"id": "12359",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_5995aff3aeff665a1f3e984d",
"parentId": "12358",
"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": "12360",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_b1b83031a5ee481c4ea84343",
"parentId": "12358",
"isLeaf": false,
"molecule": {
"id": "sa_b1b83031a5ee481c4ea84343",
"inchikey": "MURVUTUZSUEIGI-UHFFFAOYSA-N",
"smiles": "COc1ccc(Br)c(CBr)c1"
},
"smiles": "COc1ccc(Br)c(CBr)c1",
"reactionStepId": "sa_fe819ad4742608bf5e65e91e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040132769A1;0352;170153\",\"rsmi\":\"O[CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:11][cH:10][c:8]1[Br:9].[BrH:7]>O>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][Br:7])[c:8]([Br:9])[cH:10][cH:11]1\"},\"mapped_reaction_smiles\":\"O[CH2:6][c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:11][cH:10][c:8]1[Br:9].[BrH:7]>O>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][Br:7])[c:8]([Br:9])[cH:10][cH:11]1\"}",
"reactionStep": {
"id": "sa_fe819ad4742608bf5e65e91e",
"reactionHash": "39b166612320e3ac96b2e54f943637750bb1fd60ac502cb972bffae91edede0e"
},
"children": [
{
"id": "12361",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_70f4de2e51ba34b93e025a04",
"parentId": "12360",
"isLeaf": true,
"molecule": {
"id": "sa_70f4de2e51ba34b93e025a04",
"inchikey": "CPELXLSAUQHCOX-UHFFFAOYSA-N",
"smiles": "Br"
},
"smiles": "Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12362",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_a706184c8918fedebdc7cb91",
"parentId": "12360",
"isLeaf": false,
"molecule": {
"id": "sa_a706184c8918fedebdc7cb91",
"inchikey": "NRDAKNCVXNJCGB-UHFFFAOYSA-N",
"smiles": "COc1ccc(Br)c(CO)c1"
},
"smiles": "COc1ccc(Br)c(CO)c1",
"reactionStepId": "sa_38a680e2ce2bf1043e2ecad0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040132769A1;0351;170152\",\"rsmi\":\"O=[C:6]([c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:11][cH:10][c:8]1[Br:9])[OH:7]>C1CCOC1.O>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][OH:7])[c:8]([Br:9])[cH:10][cH:11]1\"},\"mapped_reaction_smiles\":\"O=[C:6]([c:5]1[cH:4][c:3]([O:2][CH3:1])[cH:11][cH:10][c:8]1[Br:9])[OH:7]>C1CCOC1.O>[CH3:1][O:2][c:3]1[cH:4][c:5]([CH2:6][OH:7])[c:8]([Br:9])[cH:10][cH:11]1\"}",
"reactionStep": {
"id": "sa_38a680e2ce2bf1043e2ecad0",
"reactionHash": "fdb07a3b6a95e77456a9dab9930f4f2e8d37251646690b6e9bcea1929771a6d9"
},
"children": [
{
"id": "12363",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_6267fbe991dbd0f6c986a461",
"parentId": "12362",
"isLeaf": true,
"molecule": {
"id": "sa_6267fbe991dbd0f6c986a461",
"inchikey": "ODHJOROUCITYNF-UHFFFAOYSA-N",
"smiles": "COc1ccc(Br)c(C(=O)O)c1"
},
"smiles": "COc1ccc(Br)c(C(=O)O)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "12364",
"routeId": "sa_381391caec86d09d9665d463",
"moleculeId": "sa_106b35b8a76bbe73829a0a69",
"parentId": "12356",
"isLeaf": true,
"molecule": {
"id": "sa_106b35b8a76bbe73829a0a69",
"inchikey": "XLYOFNOQVPJJNP-UHFFFAOYSA-N",
"smiles": "O"
},
"smiles": "O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}