Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
O=C(O)c1c[nH]c2cc(Cl)c(-c3ccc(OCCN4CCOCC4)cc3)cc12
InChiKey
BBIFWVXFXWEFGJ-UHFFFAOYSA-N
Route Signature
e4fe0b93bff2dfa4826d5d5128bc699ea11bf8dd95aa1c498a9a5349aadd8863
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_a442d664f4aa2f9cb6863f10",
"signature": "e4fe0b93bff2dfa4826d5d5128bc699ea11bf8dd95aa1c498a9a5349aadd8863",
"contentHash": "748d5599849da4178c2bbcb96537a571ec97eccfa68980fcd3586bc1cbaf879a",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_36a9b822de770675f1caaedd",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-04271",
"moleculeId": "sa_d3e930cd4998117f37951dbc",
"smiles": "O=C(O)c1c[nH]c2cc(Cl)c(-c3ccc(OCCN4CCOCC4)cc3)cc12",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_d3e930cd4998117f37951dbc",
"inchikey": "BBIFWVXFXWEFGJ-UHFFFAOYSA-N",
"smiles": "O=C(O)c1c[nH]c2cc(Cl)c(-c3ccc(OCCN4CCOCC4)cc3)cc12"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "11200",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_d3e930cd4998117f37951dbc",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_d3e930cd4998117f37951dbc",
"inchikey": "BBIFWVXFXWEFGJ-UHFFFAOYSA-N",
"smiles": "O=C(O)c1c[nH]c2cc(Cl)c(-c3ccc(OCCN4CCOCC4)cc3)cc12"
},
"smiles": "O=C(O)c1c[nH]c2cc(Cl)c(-c3ccc(OCCN4CCOCC4)cc3)cc12",
"reactionStepId": "sa_b7d9c9dd6f6d0c1476c69bb4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160016940A1;0796;1821853\",\"rsmi\":\"O[Cl+][O-:3].[O:1]=[CH:2][c:4]1[cH:5][nH:6][c:7]2[cH:8][c:9]([Cl:10])[c:11](-[c:12]3[cH:13][cH:14][c:15]([O:16][CH2:17][CH2:18][N:19]4[CH2:20][CH2:21][O:22][CH2:23][CH2:24]4)[cH:25][cH:26]3)[cH:27][c:28]12>CC#N.CC(C)(C)O.CC=C(C)C.O.O=P(O)(O)O.[Na+].[Na+]>[O:1]=[C:2]([OH:3])[c:4]1[cH:5][nH:6][c:7]2[cH:8][c:9]([Cl:10])[c:11](-[c:12]3[cH:13][cH:14][c:15]([O:16][CH2:17][CH2:18][N:19]4[CH2:20][CH2:21][O:22][CH2:23][CH2:24]4)[cH:25][cH:26]3)[cH:27][c:28]12\"},\"mapped_reaction_smiles\":\"O[Cl+][O-:3].[O:1]=[CH:2][c:4]1[cH:5][nH:6][c:7]2[cH:8][c:9]([Cl:10])[c:11](-[c:12]3[cH:13][cH:14][c:15]([O:16][CH2:17][CH2:18][N:19]4[CH2:20][CH2:21][O:22][CH2:23][CH2:24]4)[cH:25][cH:26]3)[cH:27][c:28]12>CC#N.CC(C)(C)O.CC=C(C)C.O.O=P(O)(O)O.[Na+].[Na+]>[O:1]=[C:2]([OH:3])[c:4]1[cH:5][nH:6][c:7]2[cH:8][c:9]([Cl:10])[c:11](-[c:12]3[cH:13][cH:14][c:15]([O:16][CH2:17][CH2:18][N:19]4[CH2:20][CH2:21][O:22][CH2:23][CH2:24]4)[cH:25][cH:26]3)[cH:27][c:28]12\"}",
"reactionStep": {
"id": "sa_b7d9c9dd6f6d0c1476c69bb4",
"reactionHash": "58feaf4dca71ae9e8225fd0e88b444349d8089e9c2a28c73bc93d03991a8cb49"
},
"children": [
{
"id": "11201",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_c47c6987d35056f0921ddb02",
"parentId": "11200",
"isLeaf": false,
"molecule": {
"id": "sa_c47c6987d35056f0921ddb02",
"inchikey": "CHHKQWPKVKQWJW-UHFFFAOYSA-N",
"smiles": "O=Cc1c[nH]c2cc(Cl)c(-c3ccc(OCCN4CCOCC4)cc3)cc12"
},
"smiles": "O=Cc1c[nH]c2cc(Cl)c(-c3ccc(OCCN4CCOCC4)cc3)cc12",
"reactionStepId": "sa_619b8a39aa1ac3393d7121b3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160016940A1;0795;1821852\",\"rsmi\":\"Br[c:10]1[c:8]([Cl:9])[cH:7][c:6]2[nH:5][cH:4][c:3]([CH:2]=[O:1])[c:27]2[cH:26]1.CC1(C)COB([c:11]2[cH:12][cH:13][c:14]([O:15][CH2:16][CH2:17][N:18]3[CH2:19][CH2:20][O:21][CH2:22][CH2:23]3)[cH:24][cH:25]2)OC1>CCO.CCOC(C)=O.Cc1ccccc1.Cl[Pd]Cl.O=C(O)O.[Fe+2].[K+].[K+]>[O:1]=[CH:2][c:3]1[cH:4][nH:5][c:6]2[cH:7][c:8]([Cl:9])[c:10](-[c:11]3[cH:12][cH:13][c:14]([O:15][CH2:16][CH2:17][N:18]4[CH2:19][CH2:20][O:21][CH2:22][CH2:23]4)[cH:24][cH:25]3)[cH:26][c:27]12\"},\"mapped_reaction_smiles\":\"Br[c:10]1[c:8]([Cl:9])[cH:7][c:6]2[nH:5][cH:4][c:3]([CH:2]=[O:1])[c:27]2[cH:26]1.CC1(C)COB([c:11]2[cH:12][cH:13][c:14]([O:15][CH2:16][CH2:17][N:18]3[CH2:19][CH2:20][O:21][CH2:22][CH2:23]3)[cH:24][cH:25]2)OC1>CCO.CCOC(C)=O.Cc1ccccc1.Cl[Pd]Cl.O=C(O)O.[Fe+2].[K+].[K+]>[O:1]=[CH:2][c:3]1[cH:4][nH:5][c:6]2[cH:7][c:8]([Cl:9])[c:10](-[c:11]3[cH:12][cH:13][c:14]([O:15][CH2:16][CH2:17][N:18]4[CH2:19][CH2:20][O:21][CH2:22][CH2:23]4)[cH:24][cH:25]3)[cH:26][c:27]12\"}",
"reactionStep": {
"id": "sa_619b8a39aa1ac3393d7121b3",
"reactionHash": "77b4b6d2aa0e827cac546a770eaba5256381ec231efff766f3e0c4e0a8361538"
},
"children": [
{
"id": "11202",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_97fd698712fb4eee0016bfe2",
"parentId": "11201",
"isLeaf": false,
"molecule": {
"id": "sa_97fd698712fb4eee0016bfe2",
"inchikey": "ISNMSGBNFQGRLG-UHFFFAOYSA-N",
"smiles": "O=Cc1c[nH]c2cc(Cl)c(Br)cc12"
},
"smiles": "O=Cc1c[nH]c2cc(Cl)c(Br)cc12",
"reactionStepId": "sa_3f630ab48ae66d0ba2198d75",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160016940A1;0687;1821783\",\"rsmi\":\"CN(C)[CH:2]=[O:1].[cH:3]1[cH:4][nH:5][c:6]2[cH:7][c:8]([Cl:9])[c:10]([Br:11])[cH:12][c:13]12>O.O=P(Cl)(Cl)Cl.[Na+].O>[O:1]=[CH:2][c:3]1[cH:4][nH:5][c:6]2[cH:7][c:8]([Cl:9])[c:10]([Br:11])[cH:12][c:13]12\"},\"mapped_reaction_smiles\":\"CN(C)[CH:2]=[O:1].[cH:3]1[cH:4][nH:5][c:6]2[cH:7][c:8]([Cl:9])[c:10]([Br:11])[cH:12][c:13]12>O.O=P(Cl)(Cl)Cl.[Na+].O>[O:1]=[CH:2][c:3]1[cH:4][nH:5][c:6]2[cH:7][c:8]([Cl:9])[c:10]([Br:11])[cH:12][c:13]12\"}",
"reactionStep": {
"id": "sa_3f630ab48ae66d0ba2198d75",
"reactionHash": "d16e6d7dc766423f7627252c3670ce4ca781f838d42a62ae0938146b38f9959d"
},
"children": [
{
"id": "11203",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_fb41824392d522dc6a273179",
"parentId": "11202",
"isLeaf": true,
"molecule": {
"id": "sa_fb41824392d522dc6a273179",
"inchikey": "SMZUROGBNBCCPT-UHFFFAOYSA-N",
"smiles": "Clc1cc2[nH]ccc2cc1Br"
},
"smiles": "Clc1cc2[nH]ccc2cc1Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11204",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_e0b5e93d36242e79e81ef68c",
"parentId": "11202",
"isLeaf": true,
"molecule": {
"id": "sa_e0b5e93d36242e79e81ef68c",
"inchikey": "ZMXDDKWLCZADIW-UHFFFAOYSA-N",
"smiles": "CN(C)C=O"
},
"smiles": "CN(C)C=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "11205",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_91c9e3b4a64df11cefca05b6",
"parentId": "11201",
"isLeaf": false,
"molecule": {
"id": "sa_91c9e3b4a64df11cefca05b6",
"inchikey": "NKRXUQMSTYXLLS-UHFFFAOYSA-N",
"smiles": "CC1(C)COB(c2ccc(OCCN3CCOCC3)cc2)OC1"
},
"smiles": "CC1(C)COB(c2ccc(OCCN3CCOCC3)cc2)OC1",
"reactionStepId": "sa_1d42059dc0b5b2fade8398a5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160016940A1;0794;1821851\",\"rsmi\":\"Br[c:7]1[cH:8][cH:9][c:10]([O:11][CH2:12][CH2:13][N:14]2[CH2:15][CH2:16][O:17][CH2:18][CH2:19]2)[cH:20][cH:21]1.CC1(C)COB([B:6]2[O:5][CH2:4][C:2]([CH3:1])([CH3:3])[CH2:23][O:22]2)OC1>C1COCCO1.CC(=O)O.CCOC(C)=O.Cl[Pd]Cl.[Fe+2].[K+]>[CH3:1][C:2]1([CH3:3])[CH2:4][O:5][B:6]([c:7]2[cH:8][cH:9][c:10]([O:11][CH2:12][CH2:13][N:14]3[CH2:15][CH2:16][O:17][CH2:18][CH2:19]3)[cH:20][cH:21]2)[O:22][CH2:23]1\"},\"mapped_reaction_smiles\":\"Br[c:7]1[cH:8][cH:9][c:10]([O:11][CH2:12][CH2:13][N:14]2[CH2:15][CH2:16][O:17][CH2:18][CH2:19]2)[cH:20][cH:21]1.CC1(C)COB([B:6]2[O:5][CH2:4][C:2]([CH3:1])([CH3:3])[CH2:23][O:22]2)OC1>C1COCCO1.CC(=O)O.CCOC(C)=O.Cl[Pd]Cl.[Fe+2].[K+]>[CH3:1][C:2]1([CH3:3])[CH2:4][O:5][B:6]([c:7]2[cH:8][cH:9][c:10]([O:11][CH2:12][CH2:13][N:14]3[CH2:15][CH2:16][O:17][CH2:18][CH2:19]3)[cH:20][cH:21]2)[O:22][CH2:23]1\"}",
"reactionStep": {
"id": "sa_1d42059dc0b5b2fade8398a5",
"reactionHash": "dba87941680cb559d5bb039207826cf2a0ca3110be736ce7e43af4b6bca59232"
},
"children": [
{
"id": "11206",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_1127e753c784ae00c70b637a",
"parentId": "11205",
"isLeaf": true,
"molecule": {
"id": "sa_1127e753c784ae00c70b637a",
"inchikey": "MDNDJMCSXOXBFZ-UHFFFAOYSA-N",
"smiles": "CC1(C)COB(B2OCC(C)(C)CO2)OC1"
},
"smiles": "CC1(C)COB(B2OCC(C)(C)CO2)OC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11207",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_5b75937d42febdab4bce31f2",
"parentId": "11205",
"isLeaf": false,
"molecule": {
"id": "sa_5b75937d42febdab4bce31f2",
"inchikey": "SWXZUUKQIQPHIC-UHFFFAOYSA-N",
"smiles": "Brc1ccc(OCCN2CCOCC2)cc1"
},
"smiles": "Brc1ccc(OCCN2CCOCC2)cc1",
"reactionStepId": "sa_2602f472dfec01bbaef4358c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160016940A1;0793;1821850\",\"rsmi\":\"O[c:5]1[cH:4][cH:3][c:2]([Br:1])[cH:16][cH:15]1.[OH:6][CH2:7][CH2:8][N:9]1[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1>C1CCOC1.CC(C)OC(=O)/N=N/C(=O)OC(C)C.CCOC(C)=O.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[Br:1][c:2]1[cH:3][cH:4][c:5]([O:6][CH2:7][CH2:8][N:9]2[CH2:10][CH2:11][O:12][CH2:13][CH2:14]2)[cH:15][cH:16]1\"},\"mapped_reaction_smiles\":\"O[c:5]1[cH:4][cH:3][c:2]([Br:1])[cH:16][cH:15]1.[OH:6][CH2:7][CH2:8][N:9]1[CH2:10][CH2:11][O:12][CH2:13][CH2:14]1>C1CCOC1.CC(C)OC(=O)/N=N/C(=O)OC(C)C.CCOC(C)=O.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[Br:1][c:2]1[cH:3][cH:4][c:5]([O:6][CH2:7][CH2:8][N:9]2[CH2:10][CH2:11][O:12][CH2:13][CH2:14]2)[cH:15][cH:16]1\"}",
"reactionStep": {
"id": "sa_2602f472dfec01bbaef4358c",
"reactionHash": "191ba6f4f91402b6654504769fb9a78f6911677e327237ff0040f52d43388d2a"
},
"children": [
{
"id": "11208",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_a39df90fd8de03f4af45b4e1",
"parentId": "11207",
"isLeaf": true,
"molecule": {
"id": "sa_a39df90fd8de03f4af45b4e1",
"inchikey": "GZFGOTFRPZRKDS-UHFFFAOYSA-N",
"smiles": "Oc1ccc(Br)cc1"
},
"smiles": "Oc1ccc(Br)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11209",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_bfd78508eca5c99531e69759",
"parentId": "11207",
"isLeaf": true,
"molecule": {
"id": "sa_bfd78508eca5c99531e69759",
"inchikey": "KKFDCBRMNNSAAW-UHFFFAOYSA-N",
"smiles": "OCCN1CCOCC1"
},
"smiles": "OCCN1CCOCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "11210",
"routeId": "sa_a442d664f4aa2f9cb6863f10",
"moleculeId": "sa_a8aaad1a19a01d46c6a8c07a",
"parentId": "11200",
"isLeaf": true,
"molecule": {
"id": "sa_a8aaad1a19a01d46c6a8c07a",
"inchikey": "NPWPEPVYKMPDKK-UHFFFAOYSA-N",
"smiles": "[O-][Cl+]O"
},
"smiles": "[O-][Cl+]O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}