Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCS(C)(=O)=O
InChiKey
VYPGBCXDVXAJPJ-UHFFFAOYSA-N
Route Signature
38cc6f12f06c2992a20a2b02c11f9ebc9d7d51421a42382da8ae3e31baaf2d53
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_695d78b1d924b71e7ea8cf37",
"signature": "38cc6f12f06c2992a20a2b02c11f9ebc9d7d51421a42382da8ae3e31baaf2d53",
"contentHash": "b134256781df103c4ba2c9d8cd631b08d0ffaa49f296cc4fed95ae198b2612e2",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_4295e645a78409ed3e361a52",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00735",
"moleculeId": "sa_07d189db4e838db0cea1e6fc",
"smiles": "CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCS(C)(=O)=O",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_07d189db4e838db0cea1e6fc",
"inchikey": "VYPGBCXDVXAJPJ-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCS(C)(=O)=O"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "1148",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_07d189db4e838db0cea1e6fc",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_07d189db4e838db0cea1e6fc",
"inchikey": "VYPGBCXDVXAJPJ-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCS(C)(=O)=O"
},
"smiles": "CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCS(C)(=O)=O",
"reactionStepId": "sa_614a509847b6f01866352848",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090281023A9;0332;788966\",\"rsmi\":\"Cl[S:29]([CH3:30])(=[O:31])=[O:32].O[CH2:28][CH2:27][O:26][CH2:25][CH2:24][O:23][CH2:22][CH2:21][O:20][CH2:19][CH2:18][O:17][CH2:16][CH2:15][O:14][CH2:13][CH2:12][O:11][CH2:10][CH2:9][CH2:8][CH2:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5]>CCN(CC)CC.ClCCl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][O:11][CH2:12][CH2:13][O:14][CH2:15][CH2:16][O:17][CH2:18][CH2:19][O:20][CH2:21][CH2:22][O:23][CH2:24][CH2:25][O:26][CH2:27][CH2:28][S:29]([CH3:30])(=[O:31])=[O:32]\"},\"mapped_reaction_smiles\":\"Cl[S:29]([CH3:30])(=[O:31])=[O:32].O[CH2:28][CH2:27][O:26][CH2:25][CH2:24][O:23][CH2:22][CH2:21][O:20][CH2:19][CH2:18][O:17][CH2:16][CH2:15][O:14][CH2:13][CH2:12][O:11][CH2:10][CH2:9][CH2:8][CH2:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5]>CCN(CC)CC.ClCCl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][O:11][CH2:12][CH2:13][O:14][CH2:15][CH2:16][O:17][CH2:18][CH2:19][O:20][CH2:21][CH2:22][O:23][CH2:24][CH2:25][O:26][CH2:27][CH2:28][S:29]([CH3:30])(=[O:31])=[O:32]\"}",
"reactionStep": {
"id": "sa_614a509847b6f01866352848",
"reactionHash": "5ddcbf10f3fcccb9098134ddfd6cc8482ea6c9701b3ebd1c6c631a6abf287076"
},
"children": [
{
"id": "1149",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_ab48e24e0fe3cc1456aca881",
"parentId": "1148",
"isLeaf": false,
"molecule": {
"id": "sa_ab48e24e0fe3cc1456aca881",
"inchikey": "DZLHYBZOQWFEJS-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCO"
},
"smiles": "CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCO",
"reactionStepId": "sa_32f55897981a51ef258b4431",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090281023A9;0331;788965\",\"rsmi\":\"c1ccc(C[O:29][CH2:28][CH2:27][O:26][CH2:25][CH2:24][O:23][CH2:22][CH2:21][O:20][CH2:19][CH2:18][O:17][CH2:16][CH2:15][O:14][CH2:13][CH2:12][O:11][CH2:10][CH2:9][CH2:8][CH2:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])cc1>CCO.[Pd]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][O:11][CH2:12][CH2:13][O:14][CH2:15][CH2:16][O:17][CH2:18][CH2:19][O:20][CH2:21][CH2:22][O:23][CH2:24][CH2:25][O:26][CH2:27][CH2:28][OH:29]\"},\"mapped_reaction_smiles\":\"c1ccc(C[O:29][CH2:28][CH2:27][O:26][CH2:25][CH2:24][O:23][CH2:22][CH2:21][O:20][CH2:19][CH2:18][O:17][CH2:16][CH2:15][O:14][CH2:13][CH2:12][O:11][CH2:10][CH2:9][CH2:8][CH2:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])cc1>CCO.[Pd]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][O:11][CH2:12][CH2:13][O:14][CH2:15][CH2:16][O:17][CH2:18][CH2:19][O:20][CH2:21][CH2:22][O:23][CH2:24][CH2:25][O:26][CH2:27][CH2:28][OH:29]\"}",
"reactionStep": {
"id": "sa_32f55897981a51ef258b4431",
"reactionHash": "86ddb9e9d2f7ce9d075a9bf01780fc2e25dd7b475eb3a953a54ca187ea7f9c10"
},
"children": [
{
"id": "1150",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_4b8b0a275c1270b4f0cbf56b",
"parentId": "1149",
"isLeaf": false,
"molecule": {
"id": "sa_4b8b0a275c1270b4f0cbf56b",
"inchikey": "RTWKDLQHBWDKNP-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCOCc1ccccc1"
},
"smiles": "CCOC(=O)CCCCCOCCOCCOCCOCCOCCOCCOCc1ccccc1",
"reactionStepId": "sa_c2eea960e1459ea9ad567a6a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090281023A9;0330;788964\",\"rsmi\":\"CS(=O)(=O)O[CH2:10][CH2:9][CH2:8][CH2:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:11][CH2:12][CH2:13][O:14][CH2:15][CH2:16][O:17][CH2:18][CH2:19][O:20][CH2:21][CH2:22][O:23][CH2:24][CH2:25][O:26][CH2:27][CH2:28][O:29][CH2:30][c:31]1[cH:32][cH:33][cH:34][cH:35][cH:36]1>Cc1ccccc1.[HH].[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][O:11][CH2:12][CH2:13][O:14][CH2:15][CH2:16][O:17][CH2:18][CH2:19][O:20][CH2:21][CH2:22][O:23][CH2:24][CH2:25][O:26][CH2:27][CH2:28][O:29][CH2:30][c:31]1[cH:32][cH:33][cH:34][cH:35][cH:36]1\"},\"mapped_reaction_smiles\":\"CS(=O)(=O)O[CH2:10][CH2:9][CH2:8][CH2:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:11][CH2:12][CH2:13][O:14][CH2:15][CH2:16][O:17][CH2:18][CH2:19][O:20][CH2:21][CH2:22][O:23][CH2:24][CH2:25][O:26][CH2:27][CH2:28][O:29][CH2:30][c:31]1[cH:32][cH:33][cH:34][cH:35][cH:36]1>Cc1ccccc1.[HH].[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][O:11][CH2:12][CH2:13][O:14][CH2:15][CH2:16][O:17][CH2:18][CH2:19][O:20][CH2:21][CH2:22][O:23][CH2:24][CH2:25][O:26][CH2:27][CH2:28][O:29][CH2:30][c:31]1[cH:32][cH:33][cH:34][cH:35][cH:36]1\"}",
"reactionStep": {
"id": "sa_c2eea960e1459ea9ad567a6a",
"reactionHash": "79263760bcae1b21b95d3d5b3d07c2e3eefa9dab15757d3188cf13bd5460f083"
},
"children": [
{
"id": "1151",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_1c044dcd4214c05021043ecc",
"parentId": "1150",
"isLeaf": false,
"molecule": {
"id": "sa_1c044dcd4214c05021043ecc",
"inchikey": "CHMCRBDGDXQXQU-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCCCCOS(C)(=O)=O"
},
"smiles": "CCOC(=O)CCCCCOS(C)(=O)=O",
"reactionStepId": "sa_3414f7699d02a2161970c8ec",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090281023A9;0329;788963\",\"rsmi\":\"Cl[S:12]([CH3:13])(=[O:14])=[O:15].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][OH:11]>CCN(CC)CC.ClCCl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][O:11][S:12]([CH3:13])(=[O:14])=[O:15]\"},\"mapped_reaction_smiles\":\"Cl[S:12]([CH3:13])(=[O:14])=[O:15].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][OH:11]>CCN(CC)CC.ClCCl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][CH2:8][CH2:9][CH2:10][O:11][S:12]([CH3:13])(=[O:14])=[O:15]\"}",
"reactionStep": {
"id": "sa_3414f7699d02a2161970c8ec",
"reactionHash": "150e75639e7bea132041f3deada973f26f8d3f80ae7a16c77b6a309c0d2e6cc5"
},
"children": [
{
"id": "1152",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_7585376ef271538676f8e37a",
"parentId": "1151",
"isLeaf": true,
"molecule": {
"id": "sa_7585376ef271538676f8e37a",
"inchikey": "HYXRUZUPCFVWAH-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCCCCO"
},
"smiles": "CCOC(=O)CCCCCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "1153",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "1151",
"isLeaf": true,
"molecule": {
"id": "sa_d2a31ea58046b00856f61ca5",
"inchikey": "QARBMVPHQWIHKH-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)Cl"
},
"smiles": "CS(=O)(=O)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "1154",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_185b162eb1fdff9d8684bb0a",
"parentId": "1150",
"isLeaf": false,
"molecule": {
"id": "sa_185b162eb1fdff9d8684bb0a",
"inchikey": "VVBQKDDPSXBMMZ-UHFFFAOYSA-N",
"smiles": "OCCOCCOCCOCCOCCOCCOCc1ccccc1"
},
"smiles": "OCCOCCOCCOCCOCCOCCOCc1ccccc1",
"reactionStepId": "sa_1f6c0284bc6e56a89a631ea5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20090281023A9;0328;788962\",\"rsmi\":\"Cl[CH2:20][c:21]1[cH:22][cH:23][cH:24][cH:25][cH:26]1.[OH:1][CH2:2][CH2:3][O:4][CH2:5][CH2:6][O:7][CH2:8][CH2:9][O:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][OH:19]>O.O.Cl.[Na+].[Na+].O>[OH:1][CH2:2][CH2:3][O:4][CH2:5][CH2:6][O:7][CH2:8][CH2:9][O:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][O:19][CH2:20][c:21]1[cH:22][cH:23][cH:24][cH:25][cH:26]1\"},\"mapped_reaction_smiles\":\"Cl[CH2:20][c:21]1[cH:22][cH:23][cH:24][cH:25][cH:26]1.[OH:1][CH2:2][CH2:3][O:4][CH2:5][CH2:6][O:7][CH2:8][CH2:9][O:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][OH:19]>O.O.Cl.[Na+].[Na+].O>[OH:1][CH2:2][CH2:3][O:4][CH2:5][CH2:6][O:7][CH2:8][CH2:9][O:10][CH2:11][CH2:12][O:13][CH2:14][CH2:15][O:16][CH2:17][CH2:18][O:19][CH2:20][c:21]1[cH:22][cH:23][cH:24][cH:25][cH:26]1\"}",
"reactionStep": {
"id": "sa_1f6c0284bc6e56a89a631ea5",
"reactionHash": "80a98d85ad8530d1aa3e3ee762d7740e07f2446dd07c092892401b740594ef84"
},
"children": [
{
"id": "1155",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_894289bb85e79e382742ed7c",
"parentId": "1154",
"isLeaf": true,
"molecule": {
"id": "sa_894289bb85e79e382742ed7c",
"inchikey": "IIRDTKBZINWQAW-UHFFFAOYSA-N",
"smiles": "OCCOCCOCCOCCOCCOCCO"
},
"smiles": "OCCOCCOCCOCCOCCOCCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "1156",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_bf52d13f96cd56b211e02b92",
"parentId": "1154",
"isLeaf": true,
"molecule": {
"id": "sa_bf52d13f96cd56b211e02b92",
"inchikey": "KCXMKQUNVWSEMD-UHFFFAOYSA-N",
"smiles": "ClCc1ccccc1"
},
"smiles": "ClCc1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "1157",
"routeId": "sa_695d78b1d924b71e7ea8cf37",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "1148",
"isLeaf": true,
"molecule": {
"id": "sa_d2a31ea58046b00856f61ca5",
"inchikey": "QARBMVPHQWIHKH-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)Cl"
},
"smiles": "CS(=O)(=O)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}