Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
C[C@H](O)CONC(=O)c1ccc2cncn2c1Nc1ccc(I)cc1F
InChiKey
ZYWKPZACNZQFED-JTQLQIEISA-N
Route Signature
ab8827b90322fec45e1dbc80b6bc21ba38593712abfd6f7d9d45a5c56edd2d36
Synthesis route with 8 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_43b88c4c002b30330fc026f4",
"signature": "ab8827b90322fec45e1dbc80b6bc21ba38593712abfd6f7d9d45a5c56edd2d36",
"contentHash": "563dd1694078824e3f601eb5fcb9ca6d5e392d175811f9f3f72a392fb41b369f",
"length": 8,
"isConvergent": false
},
"target": {
"id": "sa_69f00e92e38b82da2acb6205",
"benchmarkSetId": "a82783729b577c36f2e09a2b6fdd55ae9542aed5546571d67ef9cb74dc21f70a",
"targetId": "n1-00506",
"moleculeId": "sa_35bb7ba10781a5d280e6f95e",
"smiles": "C[C@H](O)CONC(=O)c1ccc2cncn2c1Nc1ccc(I)cc1F",
"routeLength": 8,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_35bb7ba10781a5d280e6f95e",
"inchikey": "ZYWKPZACNZQFED-JTQLQIEISA-N",
"smiles": "C[C@H](O)CONC(=O)c1ccc2cncn2c1Nc1ccc(I)cc1F"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "17142",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_35bb7ba10781a5d280e6f95e",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_35bb7ba10781a5d280e6f95e",
"inchikey": "ZYWKPZACNZQFED-JTQLQIEISA-N",
"smiles": "C[C@H](O)CONC(=O)c1ccc2cncn2c1Nc1ccc(I)cc1F"
},
"smiles": "C[C@H](O)CONC(=O)c1ccc2cncn2c1Nc1ccc(I)cc1F",
"reactionStepId": "sa_9a4867303ad153e619c91a8a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07923456B2;0405;1067368\",\"rsmi\":\"O[C:7](=[O:8])[c:9]1[c:10]([NH:11][c:12]2[c:13]([F:14])[cH:15][c:16]([I:17])[cH:18][cH:19]2)[n:20]2[cH:21][n:22][cH:23][c:24]2[cH:25][cH:26]1.[CH3:1][C@H:2]([OH:3])[CH2:4][O:5][NH2:6]>C1CCOC1.CCN(C(C)C)C(C)C.CCN=C=NCCCN(C)C.Cl.On1nnc2ccccc21>[CH3:1][C@H:2]([OH:3])[CH2:4][O:5][NH:6][C:7](=[O:8])[c:9]1[c:10]([NH:11][c:12]2[c:13]([F:14])[cH:15][c:16]([I:17])[cH:18][cH:19]2)[n:20]2[cH:21][n:22][cH:23][c:24]2[cH:25][cH:26]1\"},\"mapped_reaction_smiles\":\"O[C:7](=[O:8])[c:9]1[c:10]([NH:11][c:12]2[c:13]([F:14])[cH:15][c:16]([I:17])[cH:18][cH:19]2)[n:20]2[cH:21][n:22][cH:23][c:24]2[cH:25][cH:26]1.[CH3:1][C@H:2]([OH:3])[CH2:4][O:5][NH2:6]>C1CCOC1.CCN(C(C)C)C(C)C.CCN=C=NCCCN(C)C.Cl.On1nnc2ccccc21>[CH3:1][C@H:2]([OH:3])[CH2:4][O:5][NH:6][C:7](=[O:8])[c:9]1[c:10]([NH:11][c:12]2[c:13]([F:14])[cH:15][c:16]([I:17])[cH:18][cH:19]2)[n:20]2[cH:21][n:22][cH:23][c:24]2[cH:25][cH:26]1\"}",
"reactionStep": {
"id": "sa_9a4867303ad153e619c91a8a",
"reactionHash": "121b95628ce89dd6060421d2e188a54c1199c816f393828a8db6a1972fcbe624"
},
"children": [
{
"id": "17143",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_cd22ea93c9320580dd474302",
"parentId": "17142",
"isLeaf": true,
"molecule": {
"id": "sa_cd22ea93c9320580dd474302",
"inchikey": "NDJYVTLJWDGQGL-VKHMYHEASA-N",
"smiles": "C[C@H](O)CON"
},
"smiles": "C[C@H](O)CON",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "17144",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_ed13c597bff370a91fc480ba",
"parentId": "17142",
"isLeaf": false,
"molecule": {
"id": "sa_ed13c597bff370a91fc480ba",
"inchikey": "YFTJHXMDVHEEMS-UHFFFAOYSA-N",
"smiles": "O=C(O)c1ccc2cncn2c1Nc1ccc(I)cc1F"
},
"smiles": "O=C(O)c1ccc2cncn2c1Nc1ccc(I)cc1F",
"reactionStepId": "sa_aa15305b58d96305f98e86e6",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07923456B2;0312;1067327\",\"rsmi\":\"C[O:3][C:2](=[O:1])[c:4]1[c:5]([NH:6][c:7]2[c:8]([F:9])[cH:10][c:11]([I:12])[cH:13][cH:14]2)[n:15]2[cH:16][n:17][cH:18][c:19]2[cH:20][cH:21]1>[Na+].O>[O:1]=[C:2]([OH:3])[c:4]1[c:5]([NH:6][c:7]2[c:8]([F:9])[cH:10][c:11]([I:12])[cH:13][cH:14]2)[n:15]2[cH:16][n:17][cH:18][c:19]2[cH:20][cH:21]1\"},\"mapped_reaction_smiles\":\"C[O:3][C:2](=[O:1])[c:4]1[c:5]([NH:6][c:7]2[c:8]([F:9])[cH:10][c:11]([I:12])[cH:13][cH:14]2)[n:15]2[cH:16][n:17][cH:18][c:19]2[cH:20][cH:21]1>[Na+].O>[O:1]=[C:2]([OH:3])[c:4]1[c:5]([NH:6][c:7]2[c:8]([F:9])[cH:10][c:11]([I:12])[cH:13][cH:14]2)[n:15]2[cH:16][n:17][cH:18][c:19]2[cH:20][cH:21]1\"}",
"reactionStep": {
"id": "sa_aa15305b58d96305f98e86e6",
"reactionHash": "b814f6600f7c85c7b43e8f955c56cc85cf6ad0377f851f733615fb63809d4598"
},
"children": [
{
"id": "17145",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_5991b826cb4bfc4e20c284db",
"parentId": "17144",
"isLeaf": false,
"molecule": {
"id": "sa_5991b826cb4bfc4e20c284db",
"inchikey": "SMXVQFKNWBMQJL-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc2cncn2c1Nc1ccc(I)cc1F"
},
"smiles": "COC(=O)c1ccc2cncn2c1Nc1ccc(I)cc1F",
"reactionStepId": "sa_2d039ba5a71c542b7d873163",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07923456B2;0315;1067328\",\"rsmi\":\"Cl[c:6]1[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:22][cH:21][c:20]2[n:16]1[cH:17][n:18][cH:19]2.[NH2:7][c:8]1[c:9]([F:10])[cH:11][c:12]([I:13])[cH:14][cH:15]1>C1CCOC1.C[Si](C)(C)N[Si](C)(C)C.[Li+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([NH:7][c:8]2[c:9]([F:10])[cH:11][c:12]([I:13])[cH:14][cH:15]2)[n:16]2[cH:17][n:18][cH:19][c:20]2[cH:21][cH:22]1\"},\"mapped_reaction_smiles\":\"Cl[c:6]1[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:22][cH:21][c:20]2[n:16]1[cH:17][n:18][cH:19]2.[NH2:7][c:8]1[c:9]([F:10])[cH:11][c:12]([I:13])[cH:14][cH:15]1>C1CCOC1.C[Si](C)(C)N[Si](C)(C)C.[Li+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([NH:7][c:8]2[c:9]([F:10])[cH:11][c:12]([I:13])[cH:14][cH:15]2)[n:16]2[cH:17][n:18][cH:19][c:20]2[cH:21][cH:22]1\"}",
"reactionStep": {
"id": "sa_2d039ba5a71c542b7d873163",
"reactionHash": "89a4b6e6e193d65b0db7523ec175be443477cb89b3aca07b23d0a758b8ddb90d"
},
"children": [
{
"id": "17146",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_3cd0c14d967fa04960ac1db1",
"parentId": "17145",
"isLeaf": true,
"molecule": {
"id": "sa_3cd0c14d967fa04960ac1db1",
"inchikey": "CUMTUBVTKOYYOU-UHFFFAOYSA-N",
"smiles": "Nc1ccc(I)cc1F"
},
"smiles": "Nc1ccc(I)cc1F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "17147",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_e6fb2e648bb6d70b14536680",
"parentId": "17145",
"isLeaf": false,
"molecule": {
"id": "sa_e6fb2e648bb6d70b14536680",
"inchikey": "LHXRTDJUZZEEQH-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc2cncn2c1Cl"
},
"smiles": "COC(=O)c1ccc2cncn2c1Cl",
"reactionStepId": "sa_7687c2ee9eff0d42f23a9f4e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07923456B2;0306;1067325\",\"rsmi\":\"O=[CH:9][NH:10][CH2:11][c:12]1[n:8][c:6]([Cl:7])[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:14][cH:13]1>CCOC(C)=O.Cc1ccccc1.ClOCl.[Na+].O.[P+5]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8]2[cH:9][n:10][cH:11][c:12]2[cH:13][cH:14]1\"},\"mapped_reaction_smiles\":\"O=[CH:9][NH:10][CH2:11][c:12]1[n:8][c:6]([Cl:7])[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:14][cH:13]1>CCOC(C)=O.Cc1ccccc1.ClOCl.[Na+].O.[P+5]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8]2[cH:9][n:10][cH:11][c:12]2[cH:13][cH:14]1\"}",
"reactionStep": {
"id": "sa_7687c2ee9eff0d42f23a9f4e",
"reactionHash": "011cc042c7968f0b055d8440157af77e0916def49f215543cbc0b3753959ba4b"
},
"children": [
{
"id": "17148",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_6fbd8ecd00ddb102677ea6d1",
"parentId": "17147",
"isLeaf": false,
"molecule": {
"id": "sa_6fbd8ecd00ddb102677ea6d1",
"inchikey": "XTUQHUQSYVMFJA-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(CNC=O)nc1Cl"
},
"smiles": "COC(=O)c1ccc(CNC=O)nc1Cl",
"reactionStepId": "sa_976029f387b64d1667e3db6b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07923456B2;0345;1067337\",\"rsmi\":\"O[CH:12]=[O:13].[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][NH2:11])[cH:14][cH:15]1>CC(=O)OC(C)=O>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][NH:11][CH:12]=[O:13])[cH:14][cH:15]1\"},\"mapped_reaction_smiles\":\"O[CH:12]=[O:13].[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][NH2:11])[cH:14][cH:15]1>CC(=O)OC(C)=O>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][NH:11][CH:12]=[O:13])[cH:14][cH:15]1\"}",
"reactionStep": {
"id": "sa_976029f387b64d1667e3db6b",
"reactionHash": "c501f04ae57db5a2c71ec5e907d41d016891fa036de696c6b0277d25aa55cee3"
},
"children": [
{
"id": "17149",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_3bff5ea8042027b95a7e61c6",
"parentId": "17148",
"isLeaf": true,
"molecule": {
"id": "sa_3bff5ea8042027b95a7e61c6",
"inchikey": "BDAGIHXWWSANSR-UHFFFAOYSA-N",
"smiles": "O=CO"
},
"smiles": "O=CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "17150",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_f287c682110e9757a16f6689",
"parentId": "17148",
"isLeaf": false,
"molecule": {
"id": "sa_f287c682110e9757a16f6689",
"inchikey": "UHJGVTIBZRKJPK-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(CN)nc1Cl"
},
"smiles": "COC(=O)c1ccc(CN)nc1Cl",
"reactionStepId": "sa_8d2d02c062417fe2abcda301",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07923456B2;0343;1067336\",\"rsmi\":\"[N-]=[N+]=[N:11][CH2:10][c:9]1[n:8][c:6]([Cl:7])[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:13][cH:12]1>C1CCOC1.O.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][NH2:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"[N-]=[N+]=[N:11][CH2:10][c:9]1[n:8][c:6]([Cl:7])[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:13][cH:12]1>C1CCOC1.O.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][NH2:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_8d2d02c062417fe2abcda301",
"reactionHash": "75bc24767ecef82bb93cdc4e6f0056c90b1e58b7227aaf7fd9f1a7faf0e79957"
},
"children": [
{
"id": "17151",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_6103033e813c4490579c566b",
"parentId": "17150",
"isLeaf": false,
"molecule": {
"id": "sa_6103033e813c4490579c566b",
"inchikey": "FIQOIEGQQSMVBQ-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(CN=[N+]=[N-])nc1Cl"
},
"smiles": "COC(=O)c1ccc(CN=[N+]=[N-])nc1Cl",
"reactionStepId": "sa_85c0be7651a3df3b914b1d2a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07923456B2;0341;1067335\",\"rsmi\":\"O[CH2:10][c:9]1[n:8][c:6]([Cl:7])[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:15][cH:14]1.[N-:11]=[N+:12]=[N-:13]>CCOC(C)=O.CS(=O)(=O)Cl.ClCCl.[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][N:11]=[N+:12]=[N-:13])[cH:14][cH:15]1\"},\"mapped_reaction_smiles\":\"O[CH2:10][c:9]1[n:8][c:6]([Cl:7])[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:15][cH:14]1.[N-:11]=[N+:12]=[N-:13]>CCOC(C)=O.CS(=O)(=O)Cl.ClCCl.[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][N:11]=[N+:12]=[N-:13])[cH:14][cH:15]1\"}",
"reactionStep": {
"id": "sa_85c0be7651a3df3b914b1d2a",
"reactionHash": "c7e79bd13c73a82a51db98bfdeb731565a7c4df451683840455d6445e70c8aa4"
},
"children": [
{
"id": "17152",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_50a8f83dd89c267fbada1205",
"parentId": "17151",
"isLeaf": true,
"molecule": {
"id": "sa_50a8f83dd89c267fbada1205",
"inchikey": "IVRMZWNICZWHMI-UHFFFAOYSA-N",
"smiles": "[N]N=[N-]"
},
"smiles": "[N-]=[N+]=[N-]",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "17153",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_424499442b8d142ac3218c78",
"parentId": "17151",
"isLeaf": false,
"molecule": {
"id": "sa_424499442b8d142ac3218c78",
"inchikey": "LBIRLZISQQAOQQ-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(CO)nc1Cl"
},
"smiles": "COC(=O)c1ccc(CO)nc1Cl",
"reactionStepId": "sa_fdfbceff85fc04e13075fb7b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07923456B2;0339;1067334\",\"rsmi\":\"CO[C:10]([c:9]1[n:8][c:6]([Cl:7])[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:13][cH:12]1)=[O:11]>C1CCOC1.CCO.B.[Ca+2].Cl.Cl.[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][OH:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"CO[C:10]([c:9]1[n:8][c:6]([Cl:7])[c:5]([C:3]([O:2][CH3:1])=[O:4])[cH:13][cH:12]1)=[O:11]>C1CCOC1.CCO.B.[Ca+2].Cl.Cl.[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([Cl:7])[n:8][c:9]([CH2:10][OH:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_fdfbceff85fc04e13075fb7b",
"reactionHash": "c30babd0cf435d640ac96620f09a084b1915acc38cacadc8c0f93d4f4d7ef47e"
},
"children": [
{
"id": "17154",
"routeId": "sa_43b88c4c002b30330fc026f4",
"moleculeId": "sa_96124ed818909bb4c62e22e3",
"parentId": "17153",
"isLeaf": true,
"molecule": {
"id": "sa_96124ed818909bb4c62e22e3",
"inchikey": "SYBQUUIWCAKGJS-UHFFFAOYSA-N",
"smiles": "COC(=O)c1ccc(C(=O)OC)c(Cl)n1"
},
"smiles": "COC(=O)c1ccc(C(=O)OC)c(Cl)n1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
]
}
]
}
]
}
]
}
}