Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CC(C)c1onc(CCc2c(Cl)cccc2Cl)c1COc1ccc(-c2ccc3cccc(C(=O)O)c3c2)cc1
InChiKey
YEOXFVQGKAJALY-UHFFFAOYSA-N
Route Signature
3826b8bb1080e98d2464ec21176327661d9c5a96fe4bd8a45c0bc988b738794b
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_427e4ca0a7fec020dd4223c3",
"signature": "3826b8bb1080e98d2464ec21176327661d9c5a96fe4bd8a45c0bc988b738794b",
"contentHash": "799a0c8e25c6cee7bb1d2378b47ea4d590391b95a8bded0af295d429145d0e36",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_5768cb2b2e79df65d206b07c",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-01322",
"moleculeId": "sa_b276f288f305835dc1a6609b",
"smiles": "CC(C)c1onc(CCc2c(Cl)cccc2Cl)c1COc1ccc(-c2ccc3cccc(C(=O)O)c3c2)cc1",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_b276f288f305835dc1a6609b",
"inchikey": "YEOXFVQGKAJALY-UHFFFAOYSA-N",
"smiles": "CC(C)c1onc(CCc2c(Cl)cccc2Cl)c1COc1ccc(-c2ccc3cccc(C(=O)O)c3c2)cc1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "10086",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_b276f288f305835dc1a6609b",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_b276f288f305835dc1a6609b",
"inchikey": "YEOXFVQGKAJALY-UHFFFAOYSA-N",
"smiles": "CC(C)c1onc(CCc2c(Cl)cccc2Cl)c1COc1ccc(-c2ccc3cccc(C(=O)O)c3c2)cc1"
},
"smiles": "CC(C)c1onc(CCc2c(Cl)cccc2Cl)c1COc1ccc(-c2ccc3cccc(C(=O)O)c3c2)cc1",
"reactionStepId": "sa_3d24a6aa3d40da63f8950523",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100160398A1;0334;903342\",\"rsmi\":\"C[O:22][C:20]([c:19]1[cH:18][cH:17][cH:16][c:15]2[cH:14][cH:13][c:12](-[c:11]3[cH:10][cH:9][c:8]([O:7][CH2:6][c:5]4[c:4]([CH:2]([CH3:1])[CH3:3])[o:39][n:38][c:27]4[CH2:28][CH2:29][c:30]4[c:31]([Cl:32])[cH:33][cH:34][cH:35][c:36]4[Cl:37])[cH:26][cH:25]3)[cH:24][c:23]21)=[O:21]>C1CCOC1.CO.[Na+].O>[CH3:1][CH:2]([CH3:3])[c:4]1[c:5]([CH2:6][O:7][c:8]2[cH:9][cH:10][c:11](-[c:12]3[cH:13][cH:14][c:15]4[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]4[cH:24]3)[cH:25][cH:26]2)[c:27]([CH2:28][CH2:29][c:30]2[c:31]([Cl:32])[cH:33][cH:34][cH:35][c:36]2[Cl:37])[n:38][o:39]1\"},\"mapped_reaction_smiles\":\"C[O:22][C:20]([c:19]1[cH:18][cH:17][cH:16][c:15]2[cH:14][cH:13][c:12](-[c:11]3[cH:10][cH:9][c:8]([O:7][CH2:6][c:5]4[c:4]([CH:2]([CH3:1])[CH3:3])[o:39][n:38][c:27]4[CH2:28][CH2:29][c:30]4[c:31]([Cl:32])[cH:33][cH:34][cH:35][c:36]4[Cl:37])[cH:26][cH:25]3)[cH:24][c:23]21)=[O:21]>C1CCOC1.CO.[Na+].O>[CH3:1][CH:2]([CH3:3])[c:4]1[c:5]([CH2:6][O:7][c:8]2[cH:9][cH:10][c:11](-[c:12]3[cH:13][cH:14][c:15]4[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]4[cH:24]3)[cH:25][cH:26]2)[c:27]([CH2:28][CH2:29][c:30]2[c:31]([Cl:32])[cH:33][cH:34][cH:35][c:36]2[Cl:37])[n:38][o:39]1\"}",
"reactionStep": {
"id": "sa_3d24a6aa3d40da63f8950523",
"reactionHash": "6377a4bd8ac13dfa43339ad22b277b34508629d4528b3f0be0cd0005cefde8ab"
},
"children": [
{
"id": "10087",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_7c37894057b21ea80f6a2f32",
"parentId": "10086",
"isLeaf": false,
"molecule": {
"id": "sa_7c37894057b21ea80f6a2f32",
"inchikey": "MWVUKZDDJIMVCV-UHFFFAOYSA-N",
"smiles": "COC(=O)c1cccc2ccc(-c3ccc(OCc4c(CCc5c(Cl)cccc5Cl)noc4C(C)C)cc3)cc12"
},
"smiles": "COC(=O)c1cccc2ccc(-c3ccc(OCc4c(CCc5c(Cl)cccc5Cl)noc4C(C)C)cc3)cc12",
"reactionStepId": "sa_dcb668fbe8d0fa2d9e88d977",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100160398A1;0332;903341\",\"rsmi\":\"O[c:16]1[cH:15][cH:14][c:13](-[c:12]2[cH:11][cH:10][c:9]3[cH:8][cH:7][cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[c:40]3[cH:39]2)[cH:38][cH:37]1.[OH:17][CH2:18][c:19]1[c:20]([CH:21]([CH3:22])[CH3:23])[o:24][n:25][c:26]1[CH2:27][CH2:28][c:29]1[c:30]([Cl:31])[cH:32][cH:33][cH:34][c:35]1[Cl:36]>CC(C)OC(=O)N=NC(=O)OC(C)C.ClCCl.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][cH:7][cH:8][c:9]2[cH:10][cH:11][c:12](-[c:13]3[cH:14][cH:15][c:16]([O:17][CH2:18][c:19]4[c:20]([CH:21]([CH3:22])[CH3:23])[o:24][n:25][c:26]4[CH2:27][CH2:28][c:29]4[c:30]([Cl:31])[cH:32][cH:33][cH:34][c:35]4[Cl:36])[cH:37][cH:38]3)[cH:39][c:40]12\"},\"mapped_reaction_smiles\":\"O[c:16]1[cH:15][cH:14][c:13](-[c:12]2[cH:11][cH:10][c:9]3[cH:8][cH:7][cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[c:40]3[cH:39]2)[cH:38][cH:37]1.[OH:17][CH2:18][c:19]1[c:20]([CH:21]([CH3:22])[CH3:23])[o:24][n:25][c:26]1[CH2:27][CH2:28][c:29]1[c:30]([Cl:31])[cH:32][cH:33][cH:34][c:35]1[Cl:36]>CC(C)OC(=O)N=NC(=O)OC(C)C.ClCCl.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][cH:7][cH:8][c:9]2[cH:10][cH:11][c:12](-[c:13]3[cH:14][cH:15][c:16]([O:17][CH2:18][c:19]4[c:20]([CH:21]([CH3:22])[CH3:23])[o:24][n:25][c:26]4[CH2:27][CH2:28][c:29]4[c:30]([Cl:31])[cH:32][cH:33][cH:34][c:35]4[Cl:36])[cH:37][cH:38]3)[cH:39][c:40]12\"}",
"reactionStep": {
"id": "sa_dcb668fbe8d0fa2d9e88d977",
"reactionHash": "e27695560c42040d56b23ab74e0a0ab95db06ffe3fe6aa8e5556d7d924b49ad5"
},
"children": [
{
"id": "10088",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_139b65ac15b165c724259936",
"parentId": "10087",
"isLeaf": false,
"molecule": {
"id": "sa_139b65ac15b165c724259936",
"inchikey": "TWVUTYXUWZIARC-UHFFFAOYSA-N",
"smiles": "CC(C)c1onc(CCc2c(Cl)cccc2Cl)c1CO"
},
"smiles": "CC(C)c1onc(CCc2c(Cl)cccc2Cl)c1CO",
"reactionStepId": "sa_5272c9ed844361a8ae9c684c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100160398A1;0292;903325\",\"rsmi\":\"C[O:7][C:6](=O)[c:5]1[c:4]([CH:2]([CH3:1])[CH3:3])[o:20][n:19][c:8]1[CH2:9][CH2:10][c:11]1[c:12]([Cl:13])[cH:14][cH:15][cH:16][c:17]1[Cl:18]>C1CCOC1.CC(C)C[Al+]CC(C)C.CO.Cc1ccccc1.O=C(O)[C@H](O)[C@@H](O)C(=O)O.[HH].[K+].[Na+]>[CH3:1][CH:2]([CH3:3])[c:4]1[c:5]([CH2:6][OH:7])[c:8]([CH2:9][CH2:10][c:11]2[c:12]([Cl:13])[cH:14][cH:15][cH:16][c:17]2[Cl:18])[n:19][o:20]1\"},\"mapped_reaction_smiles\":\"C[O:7][C:6](=O)[c:5]1[c:4]([CH:2]([CH3:1])[CH3:3])[o:20][n:19][c:8]1[CH2:9][CH2:10][c:11]1[c:12]([Cl:13])[cH:14][cH:15][cH:16][c:17]1[Cl:18]>C1CCOC1.CC(C)C[Al+]CC(C)C.CO.Cc1ccccc1.O=C(O)[C@H](O)[C@@H](O)C(=O)O.[HH].[K+].[Na+]>[CH3:1][CH:2]([CH3:3])[c:4]1[c:5]([CH2:6][OH:7])[c:8]([CH2:9][CH2:10][c:11]2[c:12]([Cl:13])[cH:14][cH:15][cH:16][c:17]2[Cl:18])[n:19][o:20]1\"}",
"reactionStep": {
"id": "sa_5272c9ed844361a8ae9c684c",
"reactionHash": "32c63d7c51ce26835f709d3e03a4645105862dfa23af92f08367c5a9ba7f3345"
},
"children": [
{
"id": "10089",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_d604f31323900c33574274fd",
"parentId": "10088",
"isLeaf": false,
"molecule": {
"id": "sa_d604f31323900c33574274fd",
"inchikey": "IJKRBDOUONEGBH-UHFFFAOYSA-N",
"smiles": "COC(=O)c1c(CCc2c(Cl)cccc2Cl)noc1C(C)C"
},
"smiles": "COC(=O)c1c(CCc2c(Cl)cccc2Cl)noc1C(C)C",
"reactionStepId": "sa_6bc0652d56c24d58634f901b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100160398A1;0290;903324\",\"rsmi\":\"Cl[C:12](=[N:11][OH:10])[CH2:13][CH2:14][c:15]1[c:16]([Cl:17])[cH:18][cH:19][cH:20][c:21]1[Cl:22].O=[C:6]([CH2:5][C:3]([O:2][CH3:1])=[O:4])[CH:7]([CH3:8])[CH3:9]>C1CCOC1.CO.CO.[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([CH:7]([CH3:8])[CH3:9])[o:10][n:11][c:12]1[CH2:13][CH2:14][c:15]1[c:16]([Cl:17])[cH:18][cH:19][cH:20][c:21]1[Cl:22]\"},\"mapped_reaction_smiles\":\"Cl[C:12](=[N:11][OH:10])[CH2:13][CH2:14][c:15]1[c:16]([Cl:17])[cH:18][cH:19][cH:20][c:21]1[Cl:22].O=[C:6]([CH2:5][C:3]([O:2][CH3:1])=[O:4])[CH:7]([CH3:8])[CH3:9]>C1CCOC1.CO.CO.[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[c:6]([CH:7]([CH3:8])[CH3:9])[o:10][n:11][c:12]1[CH2:13][CH2:14][c:15]1[c:16]([Cl:17])[cH:18][cH:19][cH:20][c:21]1[Cl:22]\"}",
"reactionStep": {
"id": "sa_6bc0652d56c24d58634f901b",
"reactionHash": "b0f8d01ea9c6dc40a544dc569c4e512fba3a8ee39bcad5091149050adf891e1f"
},
"children": [
{
"id": "10090",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_d31a63864a80ad7e53769c59",
"parentId": "10089",
"isLeaf": true,
"molecule": {
"id": "sa_d31a63864a80ad7e53769c59",
"inchikey": "HNNFDXWDCFCVDM-UHFFFAOYSA-N",
"smiles": "COC(=O)CC(=O)C(C)C"
},
"smiles": "COC(=O)CC(=O)C(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10091",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_eddfbec9d531e2fd00ba24cc",
"parentId": "10089",
"isLeaf": false,
"molecule": {
"id": "sa_eddfbec9d531e2fd00ba24cc",
"inchikey": "XLISHUGXFZVICG-UHFFFAOYSA-N",
"smiles": "ON=C(Cl)CCc1c(Cl)cccc1Cl"
},
"smiles": "ON=C(Cl)CCc1c(Cl)cccc1Cl",
"reactionStepId": "sa_e18d174faedb297d4892ca94",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100160398A1;0288;903323\",\"rsmi\":\"O=C1CCC(=O)N1[Cl:4].[OH:1][N:2]=[CH:3][CH2:5][CH2:6][c:7]1[c:8]([Cl:9])[cH:10][cH:11][cH:12][c:13]1[Cl:14]>CN(C)C=O.O>[OH:1][N:2]=[C:3]([Cl:4])[CH2:5][CH2:6][c:7]1[c:8]([Cl:9])[cH:10][cH:11][cH:12][c:13]1[Cl:14]\"},\"mapped_reaction_smiles\":\"O=C1CCC(=O)N1[Cl:4].[OH:1][N:2]=[CH:3][CH2:5][CH2:6][c:7]1[c:8]([Cl:9])[cH:10][cH:11][cH:12][c:13]1[Cl:14]>CN(C)C=O.O>[OH:1][N:2]=[C:3]([Cl:4])[CH2:5][CH2:6][c:7]1[c:8]([Cl:9])[cH:10][cH:11][cH:12][c:13]1[Cl:14]\"}",
"reactionStep": {
"id": "sa_e18d174faedb297d4892ca94",
"reactionHash": "07b2a16d2539edd0bd079418c3e67df4cc4a7dd46168e0e7bb83b9695f873c19"
},
"children": [
{
"id": "10092",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_822ed58f213f43cce9095779",
"parentId": "10091",
"isLeaf": true,
"molecule": {
"id": "sa_822ed58f213f43cce9095779",
"inchikey": "HYPHCDQWKWARLF-UHFFFAOYSA-N",
"smiles": "ON=CCCc1c(Cl)cccc1Cl"
},
"smiles": "ON=CCCc1c(Cl)cccc1Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10093",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_a576f9b9a2caa305053d217d",
"parentId": "10091",
"isLeaf": true,
"molecule": {
"id": "sa_a576f9b9a2caa305053d217d",
"inchikey": "JRNVZBWKYDBUCA-UHFFFAOYSA-N",
"smiles": "O=C1CCC(=O)N1Cl"
},
"smiles": "O=C1CCC(=O)N1Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "10094",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_e7a0eca764d606cfa05b0e03",
"parentId": "10087",
"isLeaf": false,
"molecule": {
"id": "sa_e7a0eca764d606cfa05b0e03",
"inchikey": "YSMOOPZVHMUDTN-UHFFFAOYSA-N",
"smiles": "COC(=O)c1cccc2ccc(-c3ccc(O)cc3)cc12"
},
"smiles": "COC(=O)c1cccc2ccc(-c3ccc(O)cc3)cc12",
"reactionStepId": "sa_94be22083a2ea9ef099a93eb",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100160398A1;0325;903338\",\"rsmi\":\"CC1(C)OB([c:13]2[cH:14][cH:15][c:16]([OH:17])[cH:18][cH:19]2)OC1(C)C.O=S(=O)(O[c:12]1[cH:11][cH:10][c:9]2[cH:8][cH:7][cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[c:21]2[cH:20]1)C(F)(F)F>COCCOC.O=C(O)O.[Na+].[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][cH:7][cH:8][c:9]2[cH:10][cH:11][c:12](-[c:13]3[cH:14][cH:15][c:16]([OH:17])[cH:18][cH:19]3)[cH:20][c:21]12\"},\"mapped_reaction_smiles\":\"CC1(C)OB([c:13]2[cH:14][cH:15][c:16]([OH:17])[cH:18][cH:19]2)OC1(C)C.O=S(=O)(O[c:12]1[cH:11][cH:10][c:9]2[cH:8][cH:7][cH:6][c:5]([C:3]([O:2][CH3:1])=[O:4])[c:21]2[cH:20]1)C(F)(F)F>COCCOC.O=C(O)O.[Na+].[Na+]>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][cH:7][cH:8][c:9]2[cH:10][cH:11][c:12](-[c:13]3[cH:14][cH:15][c:16]([OH:17])[cH:18][cH:19]3)[cH:20][c:21]12\"}",
"reactionStep": {
"id": "sa_94be22083a2ea9ef099a93eb",
"reactionHash": "a42994a969103eb228c30867580aae1457fd4dd6b572f8b0011bd00a8b046d9e"
},
"children": [
{
"id": "10095",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_8abfda130f58505f511e73c7",
"parentId": "10094",
"isLeaf": true,
"molecule": {
"id": "sa_8abfda130f58505f511e73c7",
"inchikey": "BICZJRAGTCRORZ-UHFFFAOYSA-N",
"smiles": "CC1(C)OB(c2ccc(O)cc2)OC1(C)C"
},
"smiles": "CC1(C)OB(c2ccc(O)cc2)OC1(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10096",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_07dfd7953f6cf6df434acc9f",
"parentId": "10094",
"isLeaf": false,
"molecule": {
"id": "sa_07dfd7953f6cf6df434acc9f",
"inchikey": "LYASNNFTOHZJTJ-UHFFFAOYSA-N",
"smiles": "COC(=O)c1cccc2ccc(OS(=O)(=O)C(F)(F)F)cc12"
},
"smiles": "COC(=O)c1cccc2ccc(OS(=O)(=O)C(F)(F)F)cc12",
"reactionStepId": "sa_e8df52761842571baf288950",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100160398A1;0323;903337\",\"rsmi\":\"O=S(=O)(O[S:14](=[O:15])(=[O:16])[C:17]([F:18])([F:19])[F:20])C(F)(F)F.[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][cH:7][cH:8][c:9]2[cH:10][cH:11][c:12]([OH:13])[cH:21][c:22]12>ClCCl.c1ccncc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][cH:7][cH:8][c:9]2[cH:10][cH:11][c:12]([O:13][S:14](=[O:15])(=[O:16])[C:17]([F:18])([F:19])[F:20])[cH:21][c:22]12\"},\"mapped_reaction_smiles\":\"O=S(=O)(O[S:14](=[O:15])(=[O:16])[C:17]([F:18])([F:19])[F:20])C(F)(F)F.[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][cH:7][cH:8][c:9]2[cH:10][cH:11][c:12]([OH:13])[cH:21][c:22]12>ClCCl.c1ccncc1>[CH3:1][O:2][C:3](=[O:4])[c:5]1[cH:6][cH:7][cH:8][c:9]2[cH:10][cH:11][c:12]([O:13][S:14](=[O:15])(=[O:16])[C:17]([F:18])([F:19])[F:20])[cH:21][c:22]12\"}",
"reactionStep": {
"id": "sa_e8df52761842571baf288950",
"reactionHash": "d5c6a7b1787fc2654c1563c32368722985cda75aa75104955ac0c0c991158f00"
},
"children": [
{
"id": "10097",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_5a51fe80b077f27aeca9e620",
"parentId": "10096",
"isLeaf": true,
"molecule": {
"id": "sa_5a51fe80b077f27aeca9e620",
"inchikey": "KFDJEXPTZAZSNA-UHFFFAOYSA-N",
"smiles": "COC(=O)c1cccc2ccc(O)cc12"
},
"smiles": "COC(=O)c1cccc2ccc(O)cc12",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10098",
"routeId": "sa_427e4ca0a7fec020dd4223c3",
"moleculeId": "sa_d8869d189c1f39359fac1c8b",
"parentId": "10096",
"isLeaf": true,
"molecule": {
"id": "sa_d8869d189c1f39359fac1c8b",
"inchikey": "WJKHJLXJJJATHN-UHFFFAOYSA-N",
"smiles": "O=S(=O)(OS(=O)(=O)C(F)(F)F)C(F)(F)F"
},
"smiles": "O=S(=O)(OS(=O)(=O)C(F)(F)F)C(F)(F)F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}