Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CCOC(=O)C1=CN2C(CC1=O)c1c(cc(OCCCOC)c(F)c1F)CC2C(C)C
InChiKey
VCRAAKGDIKJHKE-UHFFFAOYSA-N
Route Signature
fe6c1f6f12a149936dc78353de0e416859d10a5f13d7dfe23f9687b662aeebc9
Synthesis route with 6 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_904f6d2c18a0890d620eeef1",
"signature": "fe6c1f6f12a149936dc78353de0e416859d10a5f13d7dfe23f9687b662aeebc9",
"contentHash": "fce7345853a6e249a64c9d6e9f0c3e105c38d8f8eef2eb327b5c39c6243383f8",
"length": 6,
"isConvergent": false
},
"target": {
"id": "sa_892d77178b6019aed2d89081",
"benchmarkSetId": "f925e688d731a0ad4e3aa6a505df094f6d3ca64ce3facc312bc5f64731921b33",
"targetId": "n5-00226",
"moleculeId": "sa_d45283462ec2524ec8037799",
"smiles": "CCOC(=O)C1=CN2C(CC1=O)c1c(cc(OCCCOC)c(F)c1F)CC2C(C)C",
"routeLength": 6,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_d45283462ec2524ec8037799",
"inchikey": "VCRAAKGDIKJHKE-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C1=CN2C(CC1=O)c1c(cc(OCCCOC)c(F)c1F)CC2C(C)C"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "3687",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_d45283462ec2524ec8037799",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_d45283462ec2524ec8037799",
"inchikey": "VCRAAKGDIKJHKE-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C1=CN2C(CC1=O)c1c(cc(OCCCOC)c(F)c1F)CC2C(C)C"
},
"smiles": "CCOC(=O)C1=CN2C(CC1=O)c1c(cc(OCCCOC)c(F)c1F)CC2C(C)C",
"reactionStepId": "sa_f53d0451861de16e4fa59a43",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150210682A1;2092;1727239\",\"rsmi\":\"CCO[CH:7]=[C:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[C:11]([CH3:10])=[O:12].[N:8]1=[CH:9][c:13]2[c:14]([cH:15][c:16]([O:17][CH2:18][CH2:19][CH2:20][O:21][CH3:22])[c:23]([F:24])[c:25]2[F:26])[CH2:27][CH:28]1[CH:29]([CH3:30])[CH3:31]>CCO>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C:6]1=[CH:7][N:8]2[CH:9]([CH2:10][C:11]1=[O:12])[c:13]1[c:14]([cH:15][c:16]([O:17][CH2:18][CH2:19][CH2:20][O:21][CH3:22])[c:23]([F:24])[c:25]1[F:26])[CH2:27][CH:28]2[CH:29]([CH3:30])[CH3:31]\"},\"mapped_reaction_smiles\":\"CCO[CH:7]=[C:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[C:11]([CH3:10])=[O:12].[N:8]1=[CH:9][c:13]2[c:14]([cH:15][c:16]([O:17][CH2:18][CH2:19][CH2:20][O:21][CH3:22])[c:23]([F:24])[c:25]2[F:26])[CH2:27][CH:28]1[CH:29]([CH3:30])[CH3:31]>CCO>[CH3:1][CH2:2][O:3][C:4](=[O:5])[C:6]1=[CH:7][N:8]2[CH:9]([CH2:10][C:11]1=[O:12])[c:13]1[c:14]([cH:15][c:16]([O:17][CH2:18][CH2:19][CH2:20][O:21][CH3:22])[c:23]([F:24])[c:25]1[F:26])[CH2:27][CH:28]2[CH:29]([CH3:30])[CH3:31]\"}",
"reactionStep": {
"id": "sa_f53d0451861de16e4fa59a43",
"reactionHash": "fd174ef6016e2c5474c3321a29e1d1e0ac4695da7bc1ee67eb4f63172fc90270"
},
"children": [
{
"id": "3688",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_19c73ddcd82018e856b5dc00",
"parentId": "3687",
"isLeaf": false,
"molecule": {
"id": "sa_19c73ddcd82018e856b5dc00",
"inchikey": "ARJRINJVIPYCKM-UHFFFAOYSA-N",
"smiles": "COCCCOc1cc2c(c(F)c1F)C=NC(C(C)C)C2"
},
"smiles": "COCCCOc1cc2c(c(F)c1F)C=NC(C(C)C)C2",
"reactionStepId": "sa_306ada9026234a7cd8ad5161",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150210682A1;2090;1727238\",\"rsmi\":\"O=[CH:13][NH:14][CH:15]([CH:16]([CH3:17])[CH3:18])[CH2:19][c:20]1[cH:12][c:10]([F:11])[c:8]([F:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:21]1>CC#N.O=P(Cl)(Cl)Cl>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([F:9])[c:10]([F:11])[c:12]2[c:20]([cH:21]1)[CH2:19][CH:15]([CH:16]([CH3:17])[CH3:18])[N:14]=[CH:13]2\"},\"mapped_reaction_smiles\":\"O=[CH:13][NH:14][CH:15]([CH:16]([CH3:17])[CH3:18])[CH2:19][c:20]1[cH:12][c:10]([F:11])[c:8]([F:9])[c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[cH:21]1>CC#N.O=P(Cl)(Cl)Cl>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[c:8]([F:9])[c:10]([F:11])[c:12]2[c:20]([cH:21]1)[CH2:19][CH:15]([CH:16]([CH3:17])[CH3:18])[N:14]=[CH:13]2\"}",
"reactionStep": {
"id": "sa_306ada9026234a7cd8ad5161",
"reactionHash": "1d656980fc0cbbeadb7d08fd92d719a17f833fc30f4f360cc06f3acd7056aa2f"
},
"children": [
{
"id": "3689",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_d934d330b9256fc6b3878d9a",
"parentId": "3688",
"isLeaf": false,
"molecule": {
"id": "sa_d934d330b9256fc6b3878d9a",
"inchikey": "UJMSMULUAHXSNO-UHFFFAOYSA-N",
"smiles": "COCCCOc1cc(CC(NC=O)C(C)C)cc(F)c1F"
},
"smiles": "COCCCOc1cc(CC(NC=O)C(C)C)cc(F)c1F",
"reactionStepId": "sa_24f7f84a2a3df828a5c680dd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150210682A1;2088;1727237\",\"rsmi\":\"O[CH:13]=[O:14].[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH2:10][CH:11]([NH2:12])[CH:15]([CH3:16])[CH3:17])[cH:18][c:19]([F:20])[c:21]1[F:22]>C1COCCO1>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH2:10][CH:11]([NH:12][CH:13]=[O:14])[CH:15]([CH3:16])[CH3:17])[cH:18][c:19]([F:20])[c:21]1[F:22]\"},\"mapped_reaction_smiles\":\"O[CH:13]=[O:14].[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH2:10][CH:11]([NH2:12])[CH:15]([CH3:16])[CH3:17])[cH:18][c:19]([F:20])[c:21]1[F:22]>C1COCCO1>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH2:10][CH:11]([NH:12][CH:13]=[O:14])[CH:15]([CH3:16])[CH3:17])[cH:18][c:19]([F:20])[c:21]1[F:22]\"}",
"reactionStep": {
"id": "sa_24f7f84a2a3df828a5c680dd",
"reactionHash": "088dc97f19b689485265bf8b5532bca2fd829b643b99176745023285f960a953"
},
"children": [
{
"id": "3690",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_3bff5ea8042027b95a7e61c6",
"parentId": "3689",
"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": "3691",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_d25a8db17550be5aed81bedc",
"parentId": "3689",
"isLeaf": false,
"molecule": {
"id": "sa_d25a8db17550be5aed81bedc",
"inchikey": "NAUFRKPVOQSIJF-UHFFFAOYSA-N",
"smiles": "COCCCOc1cc(CC(N)C(C)C)cc(F)c1F"
},
"smiles": "COCCCOc1cc(CC(N)C(C)C)cc(F)c1F",
"reactionStepId": "sa_9f0cecebbef281e451e4e84e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150210682A1;2086;1727236\",\"rsmi\":\"O=[C:11]([CH2:10][c:9]1[cH:8][c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[c:19]([F:20])[c:17]([F:18])[cH:16]1)[CH:13]([CH3:14])[CH3:15].[NH3:12]>CC(=O)O.CO.BC#N.[Na+]>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH2:10][CH:11]([NH2:12])[CH:13]([CH3:14])[CH3:15])[cH:16][c:17]([F:18])[c:19]1[F:20]\"},\"mapped_reaction_smiles\":\"O=[C:11]([CH2:10][c:9]1[cH:8][c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[c:19]([F:20])[c:17]([F:18])[cH:16]1)[CH:13]([CH3:14])[CH3:15].[NH3:12]>CC(=O)O.CO.BC#N.[Na+]>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH2:10][CH:11]([NH2:12])[CH:13]([CH3:14])[CH3:15])[cH:16][c:17]([F:18])[c:19]1[F:20]\"}",
"reactionStep": {
"id": "sa_9f0cecebbef281e451e4e84e",
"reactionHash": "e9bec1a6b5dfe919572da9ded6b6b23265029eb45d51430191b830678d9b9845"
},
"children": [
{
"id": "3692",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_c9679fdd876f32f86b77fb69",
"parentId": "3691",
"isLeaf": true,
"molecule": {
"id": "sa_c9679fdd876f32f86b77fb69",
"inchikey": "QGZKDVFQNNGYKY-UHFFFAOYSA-N",
"smiles": "N"
},
"smiles": "N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "3693",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_08490df6d90ec59e0af662d4",
"parentId": "3691",
"isLeaf": false,
"molecule": {
"id": "sa_08490df6d90ec59e0af662d4",
"inchikey": "YZUQVNSBDPCUCQ-UHFFFAOYSA-N",
"smiles": "COCCCOc1cc(CC(=O)C(C)C)cc(F)c1F"
},
"smiles": "COCCCOc1cc(CC(=O)C(C)C)cc(F)c1F",
"reactionStepId": "sa_66a223dbeeae3d54744286a8",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150210682A1;2084;1727235\",\"rsmi\":\"Br[c:9]1[cH:8][c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[c:19]([F:20])[c:17]([F:18])[cH:16]1.[CH3:10][C:11](=[O:12])[CH:13]([CH3:14])[CH3:15]>C1CCOC1.CC(C)(C)O.CC1(C)c2cccc(P(c3ccccc3)c3ccccc3)c2Oc2c(P(c3ccccc3)c3ccccc3)cccc21.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.[Na+].[Pd].[Pd]>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH2:10][C:11](=[O:12])[CH:13]([CH3:14])[CH3:15])[cH:16][c:17]([F:18])[c:19]1[F:20]\"},\"mapped_reaction_smiles\":\"Br[c:9]1[cH:8][c:7]([O:6][CH2:5][CH2:4][CH2:3][O:2][CH3:1])[c:19]([F:20])[c:17]([F:18])[cH:16]1.[CH3:10][C:11](=[O:12])[CH:13]([CH3:14])[CH3:15]>C1CCOC1.CC(C)(C)O.CC1(C)c2cccc(P(c3ccccc3)c3ccccc3)c2Oc2c(P(c3ccccc3)c3ccccc3)cccc21.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.[Na+].[Pd].[Pd]>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH2:10][C:11](=[O:12])[CH:13]([CH3:14])[CH3:15])[cH:16][c:17]([F:18])[c:19]1[F:20]\"}",
"reactionStep": {
"id": "sa_66a223dbeeae3d54744286a8",
"reactionHash": "97a473027d36b7d7bd0e061b3f2c0a8b8f786c4464985c4d956a918241e2ca5a"
},
"children": [
{
"id": "3694",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_95e5ba379cf4bbc0521979aa",
"parentId": "3693",
"isLeaf": false,
"molecule": {
"id": "sa_95e5ba379cf4bbc0521979aa",
"inchikey": "MLIXBEMFYDQMEL-UHFFFAOYSA-N",
"smiles": "COCCCOc1cc(Br)cc(F)c1F"
},
"smiles": "COCCCOc1cc(Br)cc(F)c1F",
"reactionStepId": "sa_eaf89cf96b9a34d65ea5c54e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150210682A1;2082;1727234\",\"rsmi\":\"Br[CH2:5][CH2:4][CH2:3][O:2][CH3:1].[OH:6][c:7]1[cH:8][c:9]([Br:10])[cH:11][c:12]([F:13])[c:14]1[F:15]>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([Br:10])[cH:11][c:12]([F:13])[c:14]1[F:15]\"},\"mapped_reaction_smiles\":\"Br[CH2:5][CH2:4][CH2:3][O:2][CH3:1].[OH:6][c:7]1[cH:8][c:9]([Br:10])[cH:11][c:12]([F:13])[c:14]1[F:15]>CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][O:2][CH2:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([Br:10])[cH:11][c:12]([F:13])[c:14]1[F:15]\"}",
"reactionStep": {
"id": "sa_eaf89cf96b9a34d65ea5c54e",
"reactionHash": "eb69f492d1e82d40d7f640b8b4c227e97326c45308026dc8616e26289c4db223"
},
"children": [
{
"id": "3695",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_53c3ccba6255f13408e7450c",
"parentId": "3694",
"isLeaf": true,
"molecule": {
"id": "sa_53c3ccba6255f13408e7450c",
"inchikey": "CEVMYGZHEJSOHZ-UHFFFAOYSA-N",
"smiles": "COCCCBr"
},
"smiles": "COCCCBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "3696",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_a693d01feb290e4fb7b672a9",
"parentId": "3694",
"isLeaf": true,
"molecule": {
"id": "sa_a693d01feb290e4fb7b672a9",
"inchikey": "QAHCQGXGAYRHHW-UHFFFAOYSA-N",
"smiles": "Oc1cc(Br)cc(F)c1F"
},
"smiles": "Oc1cc(Br)cc(F)c1F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "3697",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_4f1d1952e920fb9d1256940a",
"parentId": "3693",
"isLeaf": true,
"molecule": {
"id": "sa_4f1d1952e920fb9d1256940a",
"inchikey": "SYBYTAAJFKOIEJ-UHFFFAOYSA-N",
"smiles": "CC(=O)C(C)C"
},
"smiles": "CC(=O)C(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
},
{
"id": "3698",
"routeId": "sa_904f6d2c18a0890d620eeef1",
"moleculeId": "sa_2f7e7d0d1f51c7368693e10b",
"parentId": "3687",
"isLeaf": true,
"molecule": {
"id": "sa_2f7e7d0d1f51c7368693e10b",
"inchikey": "FNASCUBBFNCFQO-UHFFFAOYSA-N",
"smiles": "CCOC=C(C(C)=O)C(=O)OCC"
},
"smiles": "CCOC=C(C(C)=O)C(=O)OCC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}