Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
C=Cc1ccc(Cc2cc(Br)ccc2Cl)cc1
InChiKey
MKJMIXGEKLZMSX-UHFFFAOYSA-N
Route Signature
9d01580758649ca8ea52ec77367820e67ff9dfd9b720abb849136e72733769e8
Synthesis route with 6 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_8925dabc27d8f8ecc0943059",
"signature": "9d01580758649ca8ea52ec77367820e67ff9dfd9b720abb849136e72733769e8",
"contentHash": "fdb9ad9548c19f540eac511578c192d2f23f9d825bea9c3138f0cfa332180c78",
"length": 6,
"isConvergent": false
},
"target": {
"id": "sa_d01358e643eaa2bdc6b0f92f",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-01275",
"moleculeId": "sa_2bbe56181335ea604690950d",
"smiles": "C=Cc1ccc(Cc2cc(Br)ccc2Cl)cc1",
"routeLength": 6,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_2bbe56181335ea604690950d",
"inchikey": "MKJMIXGEKLZMSX-UHFFFAOYSA-N",
"smiles": "C=Cc1ccc(Cc2cc(Br)ccc2Cl)cc1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "14202",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_2bbe56181335ea604690950d",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_2bbe56181335ea604690950d",
"inchikey": "MKJMIXGEKLZMSX-UHFFFAOYSA-N",
"smiles": "C=Cc1ccc(Cc2cc(Br)ccc2Cl)cc1"
},
"smiles": "C=Cc1ccc(Cc2cc(Br)ccc2Cl)cc1",
"reactionStepId": "sa_a5c1c4ec99a8e42efbac7934",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120329732A1;0234;1315477\",\"rsmi\":\"O=[CH: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.c1ccc([CH3:1])cc1>O=C(O)O.[Na+]>[CH2:1]=[CH: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\":\"O=[CH: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.c1ccc([CH3:1])cc1>O=C(O)O.[Na+]>[CH2:1]=[CH: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_a5c1c4ec99a8e42efbac7934",
"reactionHash": "cfd583db82c69ed408ee1a6178caa683559fcfbbd4c2660346a538354badf2b3"
},
"children": [
{
"id": "14203",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_1dc38e074f88595f4c56515b",
"parentId": "14202",
"isLeaf": false,
"molecule": {
"id": "sa_1dc38e074f88595f4c56515b",
"inchikey": "RKODBAQYMOOXOV-UHFFFAOYSA-N",
"smiles": "O=Cc1ccc(Cc2cc(Br)ccc2Cl)cc1"
},
"smiles": "O=Cc1ccc(Cc2cc(Br)ccc2Cl)cc1",
"reactionStepId": "sa_ec84a06930eeffad0bf1aeed",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20120329732A1;0232;1315476\",\"rsmi\":\"[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>CC(=O)OI1(OC(C)=O)(OC(C)=O)OC(=O)c2ccccc21.ClCCl.[Na+].O>[O:1]=[CH: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\":\"[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>CC(=O)OI1(OC(C)=O)(OC(C)=O)OC(=O)c2ccccc21.ClCCl.[Na+].O>[O:1]=[CH: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_ec84a06930eeffad0bf1aeed",
"reactionHash": "0755337c541b0fdd512c3076db79b32224feecb82ad4483f687b1cd6a1b3fa3a"
},
"children": [
{
"id": "14204",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_2f97ec7f452f261237ba824b",
"parentId": "14203",
"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\":\"US20120329732A1;0230;1315475\",\"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": "14205",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_ab72e2fd74d29cc59d2c0433",
"parentId": "14204",
"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\":\"US20120329732A1;0228;1315474\",\"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.CN(C)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.CN(C)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": "14206",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_f1a25cbb2070f020dbe1fb4a",
"parentId": "14205",
"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": "14207",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_213e79731d1f2a6ab7f8a28f",
"parentId": "14205",
"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\":\"US20120329732A1;0226;1315473\",\"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": "14208",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_60f0936ce07f831ddd8e477c",
"parentId": "14207",
"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\":\"US20120329732A1;0224;1315472\",\"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": "14209",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_ccdcf23ac83e7a68bfa4f2e5",
"parentId": "14208",
"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": "14210",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_ea8667d36af2c1a869c6518c",
"parentId": "14208",
"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": "14211",
"routeId": "sa_8925dabc27d8f8ecc0943059",
"moleculeId": "sa_a40312cf6a04aef1a2fafbe9",
"parentId": "14202",
"isLeaf": true,
"molecule": {
"id": "sa_a40312cf6a04aef1a2fafbe9",
"inchikey": "YXFVVABEGXRONW-UHFFFAOYSA-N",
"smiles": "Cc1ccccc1"
},
"smiles": "Cc1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}