Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
O=C(COc1ccccc1N1CCOCC1)NCC(O)CN1CCc2ccccc2C1
InChiKey
GDSFAPAOBYYWAC-UHFFFAOYSA-N
Route Signature
57e779a20b65e2419fab8830a6f576fe4f93d95e4f47c1673f6507865b7625f6
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_d6f83db18baed84df32e6136",
"signature": "57e779a20b65e2419fab8830a6f576fe4f93d95e4f47c1673f6507865b7625f6",
"contentHash": "c51cb6552640c9b16e17caed790742045d22f3f5452fa71da1592ea7c6ac51f4",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_58674756fd218d8d6269a98a",
"benchmarkSetId": "7390a9c2522b1c81605e80a42a8de7c7ad9a5797d028633b54904bc78f091bb8",
"targetId": "n5-02980",
"moleculeId": "sa_f5e261162d53bfd9827ae38c",
"smiles": "O=C(COc1ccccc1N1CCOCC1)NCC(O)CN1CCc2ccccc2C1",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_f5e261162d53bfd9827ae38c",
"inchikey": "GDSFAPAOBYYWAC-UHFFFAOYSA-N",
"smiles": "O=C(COc1ccccc1N1CCOCC1)NCC(O)CN1CCc2ccccc2C1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 3
},
"rootNode": {
"id": "2067",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_f5e261162d53bfd9827ae38c",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_f5e261162d53bfd9827ae38c",
"inchikey": "GDSFAPAOBYYWAC-UHFFFAOYSA-N",
"smiles": "O=C(COc1ccccc1N1CCOCC1)NCC(O)CN1CCc2ccccc2C1"
},
"smiles": "O=C(COc1ccccc1N1CCOCC1)NCC(O)CN1CCc2ccccc2C1",
"reactionStepId": "sa_8283a79edb63d16a7aa10c87",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140221345A1;0377;1560257\",\"rsmi\":\"CCO[C:2](=[O:1])[CH2:3][O:4][c:5]1[c:6]([N:7]2[CH2:8][CH2:9][O:10][CH2:11][CH2:12]2)[cH:13][cH:14][cH:15][cH:16]1.[NH2:17][CH2:18][CH:19]([OH:20])[CH2:21][N:22]1[CH2:23][CH2:24][c:25]2[cH:26][cH:27][cH:28][cH:29][c:30]2[CH2:31]1>CCO>[O:1]=[C:2]([CH2:3][O:4][c:5]1[c:6]([N:7]2[CH2:8][CH2:9][O:10][CH2:11][CH2:12]2)[cH:13][cH:14][cH:15][cH:16]1)[NH:17][CH2:18][CH:19]([OH:20])[CH2:21][N:22]1[CH2:23][CH2:24][c:25]2[cH:26][cH:27][cH:28][cH:29][c:30]2[CH2:31]1\"},\"mapped_reaction_smiles\":\"CCO[C:2](=[O:1])[CH2:3][O:4][c:5]1[c:6]([N:7]2[CH2:8][CH2:9][O:10][CH2:11][CH2:12]2)[cH:13][cH:14][cH:15][cH:16]1.[NH2:17][CH2:18][CH:19]([OH:20])[CH2:21][N:22]1[CH2:23][CH2:24][c:25]2[cH:26][cH:27][cH:28][cH:29][c:30]2[CH2:31]1>CCO>[O:1]=[C:2]([CH2:3][O:4][c:5]1[c:6]([N:7]2[CH2:8][CH2:9][O:10][CH2:11][CH2:12]2)[cH:13][cH:14][cH:15][cH:16]1)[NH:17][CH2:18][CH:19]([OH:20])[CH2:21][N:22]1[CH2:23][CH2:24][c:25]2[cH:26][cH:27][cH:28][cH:29][c:30]2[CH2:31]1\"}",
"reactionStep": {
"id": "sa_8283a79edb63d16a7aa10c87",
"reactionHash": "d6edb0ed1b1e915da46945996fe3a1705d62a2c0f02a546b4e2f8a6b876c80d6"
},
"children": [
{
"id": "2068",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_9ba14974a9a662b284a2613d",
"parentId": "2067",
"isLeaf": false,
"molecule": {
"id": "sa_9ba14974a9a662b284a2613d",
"inchikey": "BYWDGTKESWRSML-UHFFFAOYSA-N",
"smiles": "NCC(O)CN1CCc2ccccc2C1"
},
"smiles": "NCC(O)CN1CCc2ccccc2C1",
"reactionStepId": "sa_bc51c4e61278cc54b5bdc2b9",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140221345A1;0218;1560195\",\"rsmi\":\"[CH2:2]1[CH:3]([CH2:5][N:6]2[CH2:7][CH2:8][c:9]3[cH:10][cH:11][cH:12][cH:13][c:14]3[CH2:15]2)[O:4]1.[NH3:1]>CCO>[NH2:1][CH2:2][CH:3]([OH:4])[CH2:5][N:6]1[CH2:7][CH2:8][c:9]2[cH:10][cH:11][cH:12][cH:13][c:14]2[CH2:15]1\"},\"mapped_reaction_smiles\":\"[CH2:2]1[CH:3]([CH2:5][N:6]2[CH2:7][CH2:8][c:9]3[cH:10][cH:11][cH:12][cH:13][c:14]3[CH2:15]2)[O:4]1.[NH3:1]>CCO>[NH2:1][CH2:2][CH:3]([OH:4])[CH2:5][N:6]1[CH2:7][CH2:8][c:9]2[cH:10][cH:11][cH:12][cH:13][c:14]2[CH2:15]1\"}",
"reactionStep": {
"id": "sa_bc51c4e61278cc54b5bdc2b9",
"reactionHash": "4d5d76842856a005936db531ed5f6c6ea628f5fa3ebed7fde0c150a722507f4b"
},
"children": [
{
"id": "2069",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_10168cfbb03a1050daed4302",
"parentId": "2068",
"isLeaf": true,
"molecule": {
"id": "sa_10168cfbb03a1050daed4302",
"inchikey": "OBDIDGKANKNXDV-UHFFFAOYSA-N",
"smiles": "c1ccc2c(c1)CCN(CC1CO1)C2"
},
"smiles": "c1ccc2c(c1)CCN(CC1CO1)C2",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "2070",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_c9679fdd876f32f86b77fb69",
"parentId": "2068",
"isLeaf": true,
"molecule": {
"id": "sa_c9679fdd876f32f86b77fb69",
"inchikey": "QGZKDVFQNNGYKY-UHFFFAOYSA-N",
"smiles": "N"
},
"smiles": "N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "2071",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_108be4160b06d1be5e53a744",
"parentId": "2067",
"isLeaf": false,
"molecule": {
"id": "sa_108be4160b06d1be5e53a744",
"inchikey": "VJVVFTDFAGAARR-UHFFFAOYSA-N",
"smiles": "CCOC(=O)COc1ccccc1N1CCOCC1"
},
"smiles": "CCOC(=O)COc1ccccc1N1CCOCC1",
"reactionStepId": "sa_d336458acd232faef949abec",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140221345A1;0375;1560256\",\"rsmi\":\"Br[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:7][c:8]1[c:9]([N:10]2[CH2:11][CH2:12][O:13][CH2:14][CH2:15]2)[cH:16][cH:17][cH:18][cH:19]1>CC#N.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[c:9]([N:10]2[CH2:11][CH2:12][O:13][CH2:14][CH2:15]2)[cH:16][cH:17][cH:18][cH:19]1\"},\"mapped_reaction_smiles\":\"Br[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:7][c:8]1[c:9]([N:10]2[CH2:11][CH2:12][O:13][CH2:14][CH2:15]2)[cH:16][cH:17][cH:18][cH:19]1>CC#N.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[c:9]([N:10]2[CH2:11][CH2:12][O:13][CH2:14][CH2:15]2)[cH:16][cH:17][cH:18][cH:19]1\"}",
"reactionStep": {
"id": "sa_d336458acd232faef949abec",
"reactionHash": "deca316435f93814b2037c52c89c7aeb67ac6c37c093d361f03af2c64ce9406e"
},
"children": [
{
"id": "2072",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_6170bddd2f4a4137325c4a17",
"parentId": "2071",
"isLeaf": true,
"molecule": {
"id": "sa_6170bddd2f4a4137325c4a17",
"inchikey": "PQJJJMRNHATNKG-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CBr"
},
"smiles": "CCOC(=O)CBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "2073",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_be29fa18deb89649aafe6390",
"parentId": "2071",
"isLeaf": false,
"molecule": {
"id": "sa_be29fa18deb89649aafe6390",
"inchikey": "VMPYFWTYGZZUMY-UHFFFAOYSA-N",
"smiles": "Oc1ccccc1N1CCOCC1"
},
"smiles": "Oc1ccccc1N1CCOCC1",
"reactionStepId": "sa_f6b09f20db4c650a5e0982f8",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140221345A1;0373;1560255\",\"rsmi\":\"C[O:1][c:2]1[c:3]([N:4]2[CH2:5][CH2:6][O:7][CH2:8][CH2:9]2)[cH:10][cH:11][cH:12][cH:13]1>BrB(Br)Br.ClCCl>[OH:1][c:2]1[c:3]([N:4]2[CH2:5][CH2:6][O:7][CH2:8][CH2:9]2)[cH:10][cH:11][cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"C[O:1][c:2]1[c:3]([N:4]2[CH2:5][CH2:6][O:7][CH2:8][CH2:9]2)[cH:10][cH:11][cH:12][cH:13]1>BrB(Br)Br.ClCCl>[OH:1][c:2]1[c:3]([N:4]2[CH2:5][CH2:6][O:7][CH2:8][CH2:9]2)[cH:10][cH:11][cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_f6b09f20db4c650a5e0982f8",
"reactionHash": "b965c7edd11bf4573078abe416ce5f983022963f073514c6b7b2b37613b2901e"
},
"children": [
{
"id": "2074",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_ec6ff8a84697c41140f12d60",
"parentId": "2073",
"isLeaf": false,
"molecule": {
"id": "sa_ec6ff8a84697c41140f12d60",
"inchikey": "VFLNKDLFYDLRAN-UHFFFAOYSA-N",
"smiles": "COc1ccccc1N1CCOCC1"
},
"smiles": "COc1ccccc1N1CCOCC1",
"reactionStepId": "sa_a7bea6b1b068833ebc553d74",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140221345A1;0371;1560254\",\"rsmi\":\"I[c:4]1[c:3]([O:2][CH3:1])[cH:14][cH:13][cH:12][cH:11]1.[NH:5]1[CH2:6][CH2:7][O:8][CH2:9][CH2:10]1>C1COCCO1.CC(C)(C)O[Na].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.[Pd].[Pd]>[CH3:1][O:2][c:3]1[c:4]([N:5]2[CH2:6][CH2:7][O:8][CH2:9][CH2:10]2)[cH:11][cH:12][cH:13][cH:14]1\"},\"mapped_reaction_smiles\":\"I[c:4]1[c:3]([O:2][CH3:1])[cH:14][cH:13][cH:12][cH:11]1.[NH:5]1[CH2:6][CH2:7][O:8][CH2:9][CH2:10]1>C1COCCO1.CC(C)(C)O[Na].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.[Pd].[Pd]>[CH3:1][O:2][c:3]1[c:4]([N:5]2[CH2:6][CH2:7][O:8][CH2:9][CH2:10]2)[cH:11][cH:12][cH:13][cH:14]1\"}",
"reactionStep": {
"id": "sa_a7bea6b1b068833ebc553d74",
"reactionHash": "af2d7ede97fbe1b55062993104016307caebc36d616767413ae144d5ad793a3a"
},
"children": [
{
"id": "2075",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_040f527651a5670804da8335",
"parentId": "2074",
"isLeaf": true,
"molecule": {
"id": "sa_040f527651a5670804da8335",
"inchikey": "DVQWNQBEUKXONL-UHFFFAOYSA-N",
"smiles": "COc1ccccc1I"
},
"smiles": "COc1ccccc1I",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "2076",
"routeId": "sa_d6f83db18baed84df32e6136",
"moleculeId": "sa_39d71c291f7fdf13918cc969",
"parentId": "2074",
"isLeaf": true,
"molecule": {
"id": "sa_39d71c291f7fdf13918cc969",
"inchikey": "YNAVUWVOSKDBBP-UHFFFAOYSA-N",
"smiles": "C1COCCN1"
},
"smiles": "C1COCCN1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}