Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CCCCc1ccc(Sc2ccc(C(O)CC(CO)(CO)NC(C)=O)cc2)cc1
InChiKey
NHXDTSRQIOWWMR-UHFFFAOYSA-N
Route Signature
121bbb1a7df3ce54690fcc6006a77494ddaa1fa96f2cf6f04204ea9aa0fd08f1
Synthesis route with 5 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_48113eb16490bcc8851a0f17",
"signature": "121bbb1a7df3ce54690fcc6006a77494ddaa1fa96f2cf6f04204ea9aa0fd08f1",
"contentHash": "414cbece463f7d9d3df87e067eee2d37570e2ece2e0dc319296768bb585af01f",
"length": 5,
"isConvergent": false
},
"target": {
"id": "sa_ce9ffa6498ed00277efed6df",
"benchmarkSetId": "f925e688d731a0ad4e3aa6a505df094f6d3ca64ce3facc312bc5f64731921b33",
"targetId": "n5-01827",
"moleculeId": "sa_b38b8f22091fac4e62eeb58e",
"smiles": "CCCCc1ccc(Sc2ccc(C(O)CC(CO)(CO)NC(C)=O)cc2)cc1",
"routeLength": 5,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_b38b8f22091fac4e62eeb58e",
"inchikey": "NHXDTSRQIOWWMR-UHFFFAOYSA-N",
"smiles": "CCCCc1ccc(Sc2ccc(C(O)CC(CO)(CO)NC(C)=O)cc2)cc1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "6058",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_b38b8f22091fac4e62eeb58e",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_b38b8f22091fac4e62eeb58e",
"inchikey": "NHXDTSRQIOWWMR-UHFFFAOYSA-N",
"smiles": "CCCCc1ccc(Sc2ccc(C(O)CC(CO)(CO)NC(C)=O)cc2)cc1"
},
"smiles": "CCCCc1ccc(Sc2ccc(C(O)CC(CO)(CO)NC(C)=O)cc2)cc1",
"reactionStepId": "sa_53c18b1e508541aad3763c3e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140323501A1;0457;1606043\",\"rsmi\":\"CCO[C:18]([C:17]([CH2:16][C:14]([c:13]1[cH:12][cH:11][c:10]([S:9][c:8]2[cH:7][cH:6][c:5]([CH2:4][CH2:3][CH2:2][CH3:1])[cH:29][cH:28]2)[cH:27][cH:26]1)=[O:15])([C:20](OCC)=[O:21])[NH:22][C:23]([CH3:24])=[O:25])=[O:19]>CCO.O.O=P(O)(O)O.B.[K+].[K+].[Na+].[Na+].O>[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][c:13]([CH:14]([OH:15])[CH2:16][C:17]([CH2:18][OH:19])([CH2:20][OH:21])[NH:22][C:23]([CH3:24])=[O:25])[cH:26][cH:27]2)[cH:28][cH:29]1\"},\"mapped_reaction_smiles\":\"CCO[C:18]([C:17]([CH2:16][C:14]([c:13]1[cH:12][cH:11][c:10]([S:9][c:8]2[cH:7][cH:6][c:5]([CH2:4][CH2:3][CH2:2][CH3:1])[cH:29][cH:28]2)[cH:27][cH:26]1)=[O:15])([C:20](OCC)=[O:21])[NH:22][C:23]([CH3:24])=[O:25])=[O:19]>CCO.O.O=P(O)(O)O.B.[K+].[K+].[Na+].[Na+].O>[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][c:13]([CH:14]([OH:15])[CH2:16][C:17]([CH2:18][OH:19])([CH2:20][OH:21])[NH:22][C:23]([CH3:24])=[O:25])[cH:26][cH:27]2)[cH:28][cH:29]1\"}",
"reactionStep": {
"id": "sa_53c18b1e508541aad3763c3e",
"reactionHash": "df89cdfa666ee130282c1e9e4150dc510724328057aa571ca178709ceeb121f2"
},
"children": [
{
"id": "6059",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_9f744ca7e105e6007259d436",
"parentId": "6058",
"isLeaf": false,
"molecule": {
"id": "sa_9f744ca7e105e6007259d436",
"inchikey": "QFNHZOBQUORZBD-UHFFFAOYSA-N",
"smiles": "CCCCc1ccc(Sc2ccc(C(=O)CC(NC(C)=O)(C(=O)OCC)C(=O)OCC)cc2)cc1"
},
"smiles": "CCCCc1ccc(Sc2ccc(C(=O)CC(NC(C)=O)(C(=O)OCC)C(=O)OCC)cc2)cc1",
"reactionStepId": "sa_943996a56b2dc2804dfbfdb9",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140323501A1;0453;1606042\",\"rsmi\":\"Cl[CH2:16][C:14]([c:13]1[cH:12][cH:11][c:10]([S:9][c:8]2[cH:7][cH:6][c:5]([CH2:4][CH2:3][CH2:2][CH3:1])[cH:35][cH:34]2)[cH:33][cH:32]1)=[O:15].[CH:17]([NH:18][C:19]([CH3:20])=[O:21])([C:22](=[O:23])[O:24][CH2:25][CH3:26])[C:27](=[O:28])[O:29][CH2:30][CH3:31]>C1CCOC1.[HH].[Na+]>[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][c:13]([C:14](=[O:15])[CH2:16][C:17]([NH:18][C:19]([CH3:20])=[O:21])([C:22](=[O:23])[O:24][CH2:25][CH3:26])[C:27](=[O:28])[O:29][CH2:30][CH3:31])[cH:32][cH:33]2)[cH:34][cH:35]1\"},\"mapped_reaction_smiles\":\"Cl[CH2:16][C:14]([c:13]1[cH:12][cH:11][c:10]([S:9][c:8]2[cH:7][cH:6][c:5]([CH2:4][CH2:3][CH2:2][CH3:1])[cH:35][cH:34]2)[cH:33][cH:32]1)=[O:15].[CH:17]([NH:18][C:19]([CH3:20])=[O:21])([C:22](=[O:23])[O:24][CH2:25][CH3:26])[C:27](=[O:28])[O:29][CH2:30][CH3:31]>C1CCOC1.[HH].[Na+]>[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][c:13]([C:14](=[O:15])[CH2:16][C:17]([NH:18][C:19]([CH3:20])=[O:21])([C:22](=[O:23])[O:24][CH2:25][CH3:26])[C:27](=[O:28])[O:29][CH2:30][CH3:31])[cH:32][cH:33]2)[cH:34][cH:35]1\"}",
"reactionStep": {
"id": "sa_943996a56b2dc2804dfbfdb9",
"reactionHash": "332d928a9ab4d0f39a3b685009ecfe879341bcaccc81f68c7ac5fc850a726559"
},
"children": [
{
"id": "6060",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_f08b4574ad536b7be445a255",
"parentId": "6059",
"isLeaf": false,
"molecule": {
"id": "sa_f08b4574ad536b7be445a255",
"inchikey": "BOLBVKKULUWVLA-UHFFFAOYSA-N",
"smiles": "CCCCc1ccc(Sc2ccc(C(=O)CCl)cc2)cc1"
},
"smiles": "CCCCc1ccc(Sc2ccc(C(=O)CCl)cc2)cc1",
"reactionStepId": "sa_46dc368ee30ee6fe14b3272b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140323501A1;0451;1606041\",\"rsmi\":\"Cl[C:14](=[O:15])[CH2:16][Cl:17].[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][cH:13][cH:18][cH:19]2)[cH:20][cH:21]1>ClCCl.[Al+3].Cl.Cl.Cl>[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][c:13]([C:14](=[O:15])[CH2:16][Cl:17])[cH:18][cH:19]2)[cH:20][cH:21]1\"},\"mapped_reaction_smiles\":\"Cl[C:14](=[O:15])[CH2:16][Cl:17].[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][cH:13][cH:18][cH:19]2)[cH:20][cH:21]1>ClCCl.[Al+3].Cl.Cl.Cl>[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][c:13]([C:14](=[O:15])[CH2:16][Cl:17])[cH:18][cH:19]2)[cH:20][cH:21]1\"}",
"reactionStep": {
"id": "sa_46dc368ee30ee6fe14b3272b",
"reactionHash": "f092a4dfe406b100626b217e1082e035452a36f48761d822d220bab06858b935"
},
"children": [
{
"id": "6061",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_fdd91e02d23a7280b4c32051",
"parentId": "6060",
"isLeaf": false,
"molecule": {
"id": "sa_fdd91e02d23a7280b4c32051",
"inchikey": "BSVJPYZXRUVBEM-UHFFFAOYSA-N",
"smiles": "CCCCc1ccc(Sc2ccccc2)cc1"
},
"smiles": "CCCCc1ccc(Sc2ccccc2)cc1",
"reactionStepId": "sa_6fbd8b302350511425fba131",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140323501A1;0448;1606040\",\"rsmi\":\"O=[C:4]([CH2:3][CH2:2][CH3:1])[c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][cH:13][cH:14][cH:15]2)[cH:16][cH:17]1>C1CCOC1.[Al+3].B.Cl.Cl.Cl.[Na+]>[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][cH:13][cH:14][cH:15]2)[cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"O=[C:4]([CH2:3][CH2:2][CH3:1])[c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][cH:13][cH:14][cH:15]2)[cH:16][cH:17]1>C1CCOC1.[Al+3].B.Cl.Cl.Cl.[Na+]>[CH3:1][CH2:2][CH2:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([S:9][c:10]2[cH:11][cH:12][cH:13][cH:14][cH:15]2)[cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_6fbd8b302350511425fba131",
"reactionHash": "21375100e2dce4938aac2c827c9b169219564150868c3b979b16275a6cead533"
},
"children": [
{
"id": "6062",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_9bdd39d9831cb425bfd97300",
"parentId": "6061",
"isLeaf": false,
"molecule": {
"id": "sa_9bdd39d9831cb425bfd97300",
"inchikey": "PYKHTOHGCVJJMZ-UHFFFAOYSA-N",
"smiles": "CCCC(=O)c1ccc(Sc2ccccc2)cc1"
},
"smiles": "CCCC(=O)c1ccc(Sc2ccccc2)cc1",
"reactionStepId": "sa_c712fa06697e5c88b2fde302",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140323501A1;0444;1606039\",\"rsmi\":\"O[C:4]([CH2:3][CH2:2][CH3:1])=[O:5].[cH:6]1[cH:7][cH:8][c:9]([S:10][c:11]2[cH:12][cH:13][cH:14][cH:15][cH:16]2)[cH:17][cH:18]1>ClP(Cl)Cl.[Al+3].Cl.Cl.Cl>[CH3:1][CH2:2][CH2:3][C:4](=[O:5])[c:6]1[cH:7][cH:8][c:9]([S:10][c:11]2[cH:12][cH:13][cH:14][cH:15][cH:16]2)[cH:17][cH:18]1\"},\"mapped_reaction_smiles\":\"O[C:4]([CH2:3][CH2:2][CH3:1])=[O:5].[cH:6]1[cH:7][cH:8][c:9]([S:10][c:11]2[cH:12][cH:13][cH:14][cH:15][cH:16]2)[cH:17][cH:18]1>ClP(Cl)Cl.[Al+3].Cl.Cl.Cl>[CH3:1][CH2:2][CH2:3][C:4](=[O:5])[c:6]1[cH:7][cH:8][c:9]([S:10][c:11]2[cH:12][cH:13][cH:14][cH:15][cH:16]2)[cH:17][cH:18]1\"}",
"reactionStep": {
"id": "sa_c712fa06697e5c88b2fde302",
"reactionHash": "96e92071448a7b0d1d17c2c33e8c13128f60852dd2d38cf44154d845681742ea"
},
"children": [
{
"id": "6063",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_8951f68a8c1ead7df7af3785",
"parentId": "6062",
"isLeaf": true,
"molecule": {
"id": "sa_8951f68a8c1ead7df7af3785",
"inchikey": "FERIUCNNQQJTOY-UHFFFAOYSA-N",
"smiles": "CCCC(=O)O"
},
"smiles": "CCCC(=O)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "6064",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_5720180bdb91d4fa951c32c2",
"parentId": "6062",
"isLeaf": true,
"molecule": {
"id": "sa_5720180bdb91d4fa951c32c2",
"inchikey": "LTYMSROWYAPPGB-UHFFFAOYSA-N",
"smiles": "c1ccc(Sc2ccccc2)cc1"
},
"smiles": "c1ccc(Sc2ccccc2)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "6065",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_9bcb79a40efded362b9313ac",
"parentId": "6060",
"isLeaf": true,
"molecule": {
"id": "sa_9bcb79a40efded362b9313ac",
"inchikey": "VGCXGMAHQTYDJK-UHFFFAOYSA-N",
"smiles": "O=C(Cl)CCl"
},
"smiles": "O=C(Cl)CCl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "6066",
"routeId": "sa_48113eb16490bcc8851a0f17",
"moleculeId": "sa_3ad1fe7c8fd0e54f74f08491",
"parentId": "6059",
"isLeaf": true,
"molecule": {
"id": "sa_3ad1fe7c8fd0e54f74f08491",
"inchikey": "ISOLMABRZPQKOV-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(NC(C)=O)C(=O)OCC"
},
"smiles": "CCOC(=O)C(NC(C)=O)C(=O)OCC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}