Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COC1(c2ccc(Cl)c(Cc3ccc(COC4CC4)cc3)c2)O[C@H](CO)[C@@H](O)[C@H](O)[C@H]1O
InChiKey
FWUHXNCUBPFYPQ-MLYSRARTSA-N
Route Signature
1675b1aa858f48551be9798a9e9bbd3b7c376b162cf12e493cc8216975a9f61f
Synthesis route with 7 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_55eacda9dfbed0ecc1476886",
"signature": "1675b1aa858f48551be9798a9e9bbd3b7c376b162cf12e493cc8216975a9f61f",
"contentHash": "cc860c44fa0295181dae8372fb35de3cdc8643d8fc7b2431071af14f46aac60a",
"length": 7,
"isConvergent": false
},
"target": {
"id": "sa_127767f6c3c7b2e3c0cd756a",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00057",
"moleculeId": "sa_9c052462bb64e4ff37b38445",
"smiles": "COC1(c2ccc(Cl)c(Cc3ccc(COC4CC4)cc3)c2)O[C@H](CO)[C@@H](O)[C@H](O)[C@H]1O",
"routeLength": 7,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_9c052462bb64e4ff37b38445",
"inchikey": "FWUHXNCUBPFYPQ-MLYSRARTSA-N",
"smiles": "COC1(c2ccc(Cl)c(Cc3ccc(COC4CC4)cc3)c2)O[C@H](CO)[C@@H](O)[C@H](O)[C@H]1O"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "12263",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_9c052462bb64e4ff37b38445",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_9c052462bb64e4ff37b38445",
"inchikey": "FWUHXNCUBPFYPQ-MLYSRARTSA-N",
"smiles": "COC1(c2ccc(Cl)c(Cc3ccc(COC4CC4)cc3)c2)O[C@H](CO)[C@@H](O)[C@H](O)[C@H]1O"
},
"smiles": "COC1(c2ccc(Cl)c(Cc3ccc(COC4CC4)cc3)c2)O[C@H](CO)[C@@H](O)[C@H](O)[C@H]1O",
"reactionStepId": "sa_a40cae7ca49448423e7432a0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140031300A1;0371;1479416\",\"rsmi\":\"Br[c:4]1[cH:5][c:6]([CH2:7][c:8]2[cH:9][cH:10][c:11]([CH2:12][O:13][CH:14]3[CH2:15][CH2:16]3)[cH:17][cH:18]2)[c:19]([Cl:20])[cH:21][cH:22]1.C[Si](C)(C)[O:26][CH2:25][C@H:24]1[O:23][C:3](=O)[C@H:31]([O:32][Si](C)(C)C)[C@@H:29]([O:30][Si](C)(C)C)[C@@H:27]1[O:28][Si](C)(C)C.[CH3:1][OH:2]>C1CCOC1.CS(=O)(=O)O.Cc1ccccc1.Cc1ccccc1.[Li]CCCC>[CH3:1][O:2][C:3]1([c:4]2[cH:5][c:6]([CH2:7][c:8]3[cH:9][cH:10][c:11]([CH2:12][O:13][CH:14]4[CH2:15][CH2:16]4)[cH:17][cH:18]3)[c:19]([Cl:20])[cH:21][cH:22]2)[O:23][C@H:24]([CH2:25][OH:26])[C@@H:27]([OH:28])[C@H:29]([OH:30])[C@H:31]1[OH:32]\"},\"mapped_reaction_smiles\":\"Br[c:4]1[cH:5][c:6]([CH2:7][c:8]2[cH:9][cH:10][c:11]([CH2:12][O:13][CH:14]3[CH2:15][CH2:16]3)[cH:17][cH:18]2)[c:19]([Cl:20])[cH:21][cH:22]1.C[Si](C)(C)[O:26][CH2:25][C@H:24]1[O:23][C:3](=O)[C@H:31]([O:32][Si](C)(C)C)[C@@H:29]([O:30][Si](C)(C)C)[C@@H:27]1[O:28][Si](C)(C)C.[CH3:1][OH:2]>C1CCOC1.CS(=O)(=O)O.Cc1ccccc1.Cc1ccccc1.[Li]CCCC>[CH3:1][O:2][C:3]1([c:4]2[cH:5][c:6]([CH2:7][c:8]3[cH:9][cH:10][c:11]([CH2:12][O:13][CH:14]4[CH2:15][CH2:16]4)[cH:17][cH:18]3)[c:19]([Cl:20])[cH:21][cH:22]2)[O:23][C@H:24]([CH2:25][OH:26])[C@@H:27]([OH:28])[C@H:29]([OH:30])[C@H:31]1[OH:32]\"}",
"reactionStep": {
"id": "sa_a40cae7ca49448423e7432a0",
"reactionHash": "eea085f39169228f0649289202ffdf06f9e62a40265334f15d101e1896e80029"
},
"children": [
{
"id": "12264",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "12263",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12265",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_6c38d31c71c9f5cf0475df0e",
"parentId": "12263",
"isLeaf": false,
"molecule": {
"id": "sa_6c38d31c71c9f5cf0475df0e",
"inchikey": "PLTAUXPFLRNJFK-UHFFFAOYSA-N",
"smiles": "Clc1ccc(Br)cc1Cc1ccc(COC2CC2)cc1"
},
"smiles": "Clc1ccc(Br)cc1Cc1ccc(COC2CC2)cc1",
"reactionStepId": "sa_5262f4e0d1baf384b1b0cad0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140031300A1;0369;1479415\",\"rsmi\":\"I[CH2:12]I.[Cl:1][c:2]1[c:3]([CH2:4][c:5]2[cH:6][cH:7][c:8]([CH2:9][O:10][CH:11]=[CH2:13])[cH:14][cH:15]2)[cH:16][c:17]([Br:18])[cH:19][cH:20]1>CCOCC.CC[Zn]CC>[Cl:1][c:2]1[c:3]([CH2:4][c:5]2[cH:6][cH:7][c:8]([CH2:9][O:10][CH:11]3[CH2:12][CH2:13]3)[cH:14][cH:15]2)[cH:16][c:17]([Br:18])[cH:19][cH:20]1\"},\"mapped_reaction_smiles\":\"I[CH2:12]I.[Cl:1][c:2]1[c:3]([CH2:4][c:5]2[cH:6][cH:7][c:8]([CH2:9][O:10][CH:11]=[CH2:13])[cH:14][cH:15]2)[cH:16][c:17]([Br:18])[cH:19][cH:20]1>CCOCC.CC[Zn]CC>[Cl:1][c:2]1[c:3]([CH2:4][c:5]2[cH:6][cH:7][c:8]([CH2:9][O:10][CH:11]3[CH2:12][CH2:13]3)[cH:14][cH:15]2)[cH:16][c:17]([Br:18])[cH:19][cH:20]1\"}",
"reactionStep": {
"id": "sa_5262f4e0d1baf384b1b0cad0",
"reactionHash": "abe4e7f8e950454a043afeeb565c175ffd5da9b75a630ba46a41ada843679a39"
},
"children": [
{
"id": "12266",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_6fcd0200ac748b1e9b1b102a",
"parentId": "12265",
"isLeaf": false,
"molecule": {
"id": "sa_6fcd0200ac748b1e9b1b102a",
"inchikey": "IAKQVAPGQSWMQZ-UHFFFAOYSA-N",
"smiles": "C=COCc1ccc(Cc2cc(Br)ccc2Cl)cc1"
},
"smiles": "C=COCc1ccc(Cc2cc(Br)ccc2Cl)cc1",
"reactionStepId": "sa_d046812ff29163fe90a6dd00",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140031300A1;0367;1479414\",\"rsmi\":\"CC(=O)O[CH:2]=[CH2:1].[OH:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([CH2:9][c:10]2[c:11]([Cl:12])[cH:13][cH:14][c:15]([Br:16])[cH:17]2)[cH:18][cH:19]1>CCOC(C)=O.Cc1ccccc1.O=C(O)O.[Na+].[Na+]>[CH2:1]=[CH:2][O:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([CH2:9][c:10]2[c:11]([Cl:12])[cH:13][cH:14][c:15]([Br:16])[cH:17]2)[cH:18][cH:19]1\"},\"mapped_reaction_smiles\":\"CC(=O)O[CH:2]=[CH2:1].[OH:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([CH2:9][c:10]2[c:11]([Cl:12])[cH:13][cH:14][c:15]([Br:16])[cH:17]2)[cH:18][cH:19]1>CCOC(C)=O.Cc1ccccc1.O=C(O)O.[Na+].[Na+]>[CH2:1]=[CH:2][O:3][CH2:4][c:5]1[cH:6][cH:7][c:8]([CH2:9][c:10]2[c:11]([Cl:12])[cH:13][cH:14][c:15]([Br:16])[cH:17]2)[cH:18][cH:19]1\"}",
"reactionStep": {
"id": "sa_d046812ff29163fe90a6dd00",
"reactionHash": "28f481b1f415f7975da6c549fe69122dd746aa9d4973d3428831c5bcfc9250e0"
},
"children": [
{
"id": "12267",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_2f97ec7f452f261237ba824b",
"parentId": "12266",
"isLeaf": false,
"molecule": {
"id": "sa_2f97ec7f452f261237ba824b",
"inchikey": "CEILEQXJIXIBCC-UHFFFAOYSA-N",
"smiles": "OCc1ccc(Cc2cc(Br)ccc2Cl)cc1"
},
"smiles": "OCc1ccc(Cc2cc(Br)ccc2Cl)cc1",
"reactionStepId": "sa_282896082604eed669b52329",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140031300A1;0230;1479370\",\"rsmi\":\"CC(=O)[O:1][CH2:2][c:3]1[cH:4][cH:5][c:6]([CH2:7][c:8]2[c:9]([Cl:10])[cH:11][cH:12][c:13]([Br:14])[cH:15]2)[cH:16][cH:17]1>C1CCOC1.CCOC(C)=O.CO.O.O.[Li]O>[OH:1][CH2:2][c:3]1[cH:4][cH:5][c:6]([CH2:7][c:8]2[c:9]([Cl:10])[cH:11][cH:12][c:13]([Br:14])[cH:15]2)[cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"CC(=O)[O:1][CH2:2][c:3]1[cH:4][cH:5][c:6]([CH2:7][c:8]2[c:9]([Cl:10])[cH:11][cH:12][c:13]([Br:14])[cH:15]2)[cH:16][cH:17]1>C1CCOC1.CCOC(C)=O.CO.O.O.[Li]O>[OH:1][CH2:2][c:3]1[cH:4][cH:5][c:6]([CH2:7][c:8]2[c:9]([Cl:10])[cH:11][cH:12][c:13]([Br:14])[cH:15]2)[cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_282896082604eed669b52329",
"reactionHash": "4216444cd52c3ed4de5ae0b1cf12a5af7303fd869c878654ed57405a9cb7137c"
},
"children": [
{
"id": "12268",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_ab72e2fd74d29cc59d2c0433",
"parentId": "12267",
"isLeaf": false,
"molecule": {
"id": "sa_ab72e2fd74d29cc59d2c0433",
"inchikey": "GKTIUWIWKSDQKE-UHFFFAOYSA-N",
"smiles": "CC(=O)OCc1ccc(Cc2cc(Br)ccc2Cl)cc1"
},
"smiles": "CC(=O)OCc1ccc(Cc2cc(Br)ccc2Cl)cc1",
"reactionStepId": "sa_9c1e186f4c5245ad87826756",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140031300A1;0228;1479369\",\"rsmi\":\"Br[CH2:5][c:6]1[cH:7][cH:8][c:9]([CH2:10][c:11]2[c:12]([Cl:13])[cH:14][cH:15][c:16]([Br:17])[cH:18]2)[cH:19][cH:20]1.[CH3:1][C:2](=[O:3])[OH:4]>CCOC(C)=O.O.[Na+]>[CH3:1][C:2](=[O:3])[O:4][CH2:5][c:6]1[cH:7][cH:8][c:9]([CH2:10][c:11]2[c:12]([Cl:13])[cH:14][cH:15][c:16]([Br:17])[cH:18]2)[cH:19][cH:20]1\"},\"mapped_reaction_smiles\":\"Br[CH2:5][c:6]1[cH:7][cH:8][c:9]([CH2:10][c:11]2[c:12]([Cl:13])[cH:14][cH:15][c:16]([Br:17])[cH:18]2)[cH:19][cH:20]1.[CH3:1][C:2](=[O:3])[OH:4]>CCOC(C)=O.O.[Na+]>[CH3:1][C:2](=[O:3])[O:4][CH2:5][c:6]1[cH:7][cH:8][c:9]([CH2:10][c:11]2[c:12]([Cl:13])[cH:14][cH:15][c:16]([Br:17])[cH:18]2)[cH:19][cH:20]1\"}",
"reactionStep": {
"id": "sa_9c1e186f4c5245ad87826756",
"reactionHash": "c4076bfd8d0ddb5eae0a9bc01043c737219800401caac5d2a8903a089f08aab7"
},
"children": [
{
"id": "12269",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_f1a25cbb2070f020dbe1fb4a",
"parentId": "12268",
"isLeaf": true,
"molecule": {
"id": "sa_f1a25cbb2070f020dbe1fb4a",
"inchikey": "QTBSBXVTEAMEQO-UHFFFAOYSA-N",
"smiles": "CC(=O)O"
},
"smiles": "CC(=O)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12270",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_213e79731d1f2a6ab7f8a28f",
"parentId": "12268",
"isLeaf": false,
"molecule": {
"id": "sa_213e79731d1f2a6ab7f8a28f",
"inchikey": "WBLLWRCPNHANEE-UHFFFAOYSA-N",
"smiles": "Clc1ccc(Br)cc1Cc1ccc(CBr)cc1"
},
"smiles": "Clc1ccc(Br)cc1Cc1ccc(CBr)cc1",
"reactionStepId": "sa_f606b9e5828dfa61a9988245",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140031300A1;0226;1479368\",\"rsmi\":\"O=[C:4]([c:3]1[c:2]([Cl:1])[cH:17][cH:16][c:14]([Br:15])[cH:13]1)[c:5]1[cH:6][cH:7][c:8]([CH2:9][Br:10])[cH:11][cH:12]1>CC[SiH](CC)CC.O=C(O)C(F)(F)F.O=S(=O)(O)C(F)(F)F>[Cl:1][c:2]1[c:3]([CH2:4][c:5]2[cH:6][cH:7][c:8]([CH2:9][Br:10])[cH:11][cH:12]2)[cH:13][c:14]([Br:15])[cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"O=[C:4]([c:3]1[c:2]([Cl:1])[cH:17][cH:16][c:14]([Br:15])[cH:13]1)[c:5]1[cH:6][cH:7][c:8]([CH2:9][Br:10])[cH:11][cH:12]1>CC[SiH](CC)CC.O=C(O)C(F)(F)F.O=S(=O)(O)C(F)(F)F>[Cl:1][c:2]1[c:3]([CH2:4][c:5]2[cH:6][cH:7][c:8]([CH2:9][Br:10])[cH:11][cH:12]2)[cH:13][c:14]([Br:15])[cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_f606b9e5828dfa61a9988245",
"reactionHash": "a1492ff4c6d61a80469f2460f8f97dccca973780eaaa2b79a8882f0907266a25"
},
"children": [
{
"id": "12271",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_60f0936ce07f831ddd8e477c",
"parentId": "12270",
"isLeaf": false,
"molecule": {
"id": "sa_60f0936ce07f831ddd8e477c",
"inchikey": "LBKJCLZQTYERKO-UHFFFAOYSA-N",
"smiles": "O=C(c1ccc(CBr)cc1)c1cc(Br)ccc1Cl"
},
"smiles": "O=C(c1ccc(CBr)cc1)c1cc(Br)ccc1Cl",
"reactionStepId": "sa_abdf9697a0639d6f1cf287e0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140031300A1;0224;1479367\",\"rsmi\":\"O=C1CCC(=O)N1[Br:8].[O:1]=[C:2]([c:3]1[cH:4][cH:5][c:6]([CH3:7])[cH:9][cH:10]1)[c:11]1[c:12]([Cl:13])[cH:14][cH:15][c:16]([Br:17])[cH:18]1>CC(C)(C#N)N=NC(C)(C)C#N.ClC(Cl)(Cl)Cl>[O:1]=[C:2]([c:3]1[cH:4][cH:5][c:6]([CH2:7][Br:8])[cH:9][cH:10]1)[c:11]1[c:12]([Cl:13])[cH:14][cH:15][c:16]([Br:17])[cH:18]1\"},\"mapped_reaction_smiles\":\"O=C1CCC(=O)N1[Br:8].[O:1]=[C:2]([c:3]1[cH:4][cH:5][c:6]([CH3:7])[cH:9][cH:10]1)[c:11]1[c:12]([Cl:13])[cH:14][cH:15][c:16]([Br:17])[cH:18]1>CC(C)(C#N)N=NC(C)(C)C#N.ClC(Cl)(Cl)Cl>[O:1]=[C:2]([c:3]1[cH:4][cH:5][c:6]([CH2:7][Br:8])[cH:9][cH:10]1)[c:11]1[c:12]([Cl:13])[cH:14][cH:15][c:16]([Br:17])[cH:18]1\"}",
"reactionStep": {
"id": "sa_abdf9697a0639d6f1cf287e0",
"reactionHash": "960edc750c77f5b95d5d8c9641e6253a905be54c905d31fe7e0c305fb59eaf17"
},
"children": [
{
"id": "12272",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_ccdcf23ac83e7a68bfa4f2e5",
"parentId": "12271",
"isLeaf": true,
"molecule": {
"id": "sa_ccdcf23ac83e7a68bfa4f2e5",
"inchikey": "PCLIMKBDDGJMGD-UHFFFAOYSA-N",
"smiles": "O=C1CCC(=O)N1Br"
},
"smiles": "O=C1CCC(=O)N1Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12273",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_ea8667d36af2c1a869c6518c",
"parentId": "12271",
"isLeaf": true,
"molecule": {
"id": "sa_ea8667d36af2c1a869c6518c",
"inchikey": "WSFSGMFJQAVADA-UHFFFAOYSA-N",
"smiles": "Cc1ccc(C(=O)c2cc(Br)ccc2Cl)cc1"
},
"smiles": "Cc1ccc(C(=O)c2cc(Br)ccc2Cl)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
},
{
"id": "12274",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_4b69cdb883bc5290934285c2",
"parentId": "12266",
"isLeaf": true,
"molecule": {
"id": "sa_4b69cdb883bc5290934285c2",
"inchikey": "XTXRWKRVRITETP-UHFFFAOYSA-N",
"smiles": "C=COC(C)=O"
},
"smiles": "C=COC(C)=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "12275",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_8fc362ff50a73fbf1de075c8",
"parentId": "12265",
"isLeaf": true,
"molecule": {
"id": "sa_8fc362ff50a73fbf1de075c8",
"inchikey": "NZZFYRREKKOMAT-UHFFFAOYSA-N",
"smiles": "ICI"
},
"smiles": "ICI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "12276",
"routeId": "sa_55eacda9dfbed0ecc1476886",
"moleculeId": "sa_4d61a3a9defd9d44fa24551a",
"parentId": "12263",
"isLeaf": true,
"molecule": {
"id": "sa_4d61a3a9defd9d44fa24551a",
"inchikey": "VNGTZLYNGGLPIZ-WCXIOVBPSA-N",
"smiles": "C[Si](C)(C)OC[C@H]1OC(=O)[C@H](O[Si](C)(C)C)[C@@H](O[Si](C)(C)C)[C@@H]1O[Si](C)(C)C"
},
"smiles": "C[Si](C)(C)OC[C@H]1OC(=O)[C@H](O[Si](C)(C)C)[C@@H](O[Si](C)(C)C)[C@@H]1O[Si](C)(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}