Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CCOC(=O)/C=C1\CC[C@@H](c2cccc(F)c2F)[C@H](NC(=O)OC(C)(C)C)c2cccnc21
InChiKey
MZUHHJGSWTZUPX-ARSRNARXSA-N
Route Signature
4eafdf848c4ab6fcd8bc250ddb4bc5799d6a691ca5b674c7e3200a2667d20b5e
Synthesis route with 11 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_e84763e75660b2e007029545",
"signature": "4eafdf848c4ab6fcd8bc250ddb4bc5799d6a691ca5b674c7e3200a2667d20b5e",
"contentHash": "e8c2ac9a0c6bd0ce8a150624610deb33bf8aeeb4df6da0f30cb8d2b23ea7047a",
"length": 11,
"isConvergent": false
},
"target": {
"id": "sa_b85b70b3d6261d6af3ccb56b",
"benchmarkSetId": "019173c85ab67300a20aafbd44174d6551ca67a41e948a511372ae5dca775a80",
"targetId": "USPTO-159/190",
"moleculeId": "sa_14f0b3560d21a53285e3fa99",
"smiles": "CCOC(=O)/C=C1\\CC[C@@H](c2cccc(F)c2F)[C@H](NC(=O)OC(C)(C)C)c2cccnc21",
"routeLength": 11,
"isConvergent": false,
"metadata": "{\"source\":\"retro-pickle\"}",
"molecule": {
"id": "sa_14f0b3560d21a53285e3fa99",
"inchikey": "MZUHHJGSWTZUPX-ARSRNARXSA-N",
"smiles": "CCOC(=O)/C=C1\\CC[C@@H](c2cccc(F)c2F)[C@H](NC(=O)OC(C)(C)C)c2cccnc21"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "20035",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_14f0b3560d21a53285e3fa99",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_14f0b3560d21a53285e3fa99",
"inchikey": "MZUHHJGSWTZUPX-ARSRNARXSA-N",
"smiles": "CCOC(=O)/C=C1\\CC[C@@H](c2cccc(F)c2F)[C@H](NC(=O)OC(C)(C)C)c2cccnc21"
},
"smiles": "CCOC(=O)/C=C1\\CC[C@@H](c2cccc(F)c2F)[C@H](NC(=O)OC(C)(C)C)c2cccnc21",
"reactionStepId": "sa_96c774e5389f3d3add374478",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_96c774e5389f3d3add374478",
"reactionHash": "feba7b79c438587da910b41e4285e68b85a0e3347ad6c3f644f2e2ef2888e5ad"
},
"children": [
{
"id": "20036",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_8f470de7af4a17af30176ebd",
"parentId": "20035",
"isLeaf": true,
"molecule": {
"id": "sa_8f470de7af4a17af30176ebd",
"inchikey": "IIHPVYJPDKJYOU-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C=P(c1ccccc1)(c1ccccc1)c1ccccc1"
},
"smiles": "CCOC(=O)C=P(c1ccccc1)(c1ccccc1)c1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "20037",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_c6cefed92f72eca7f48b30eb",
"parentId": "20035",
"isLeaf": false,
"molecule": {
"id": "sa_c6cefed92f72eca7f48b30eb",
"inchikey": "MGTFJAYMAWIDJN-UGSOOPFHSA-N",
"smiles": "CC(C)(C)OC(=O)N[C@@H]1c2cccnc2C(=O)CC[C@H]1c1cccc(F)c1F"
},
"smiles": "CC(C)(C)OC(=O)N[C@@H]1c2cccnc2C(=O)CC[C@H]1c1cccc(F)c1F",
"reactionStepId": "sa_480a763f6719b1dd8f5a985d",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_480a763f6719b1dd8f5a985d",
"reactionHash": "60001bfc6644548e3612ece39b130a45b17354bbae944224a948ac44491e9750"
},
"children": [
{
"id": "20038",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_ee20de34fb4ae6784af3da5a",
"parentId": "20037",
"isLeaf": false,
"molecule": {
"id": "sa_ee20de34fb4ae6784af3da5a",
"inchikey": "YNIAAQHUSABKJA-XCRHUMRWSA-N",
"smiles": "CC(C)(C)OC(=O)N[C@@H]1c2cccnc2[C@H](O)CC[C@H]1c1cccc(F)c1F"
},
"smiles": "CC(C)(C)OC(=O)N[C@@H]1c2cccnc2[C@H](O)CC[C@H]1c1cccc(F)c1F",
"reactionStepId": "sa_9adb0a3c71f1af67fdf10045",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_9adb0a3c71f1af67fdf10045",
"reactionHash": "c8f3c3ce14e1396e874627d4546d7c57d66dcae2198093ddcf91ec6fceead79c"
},
"children": [
{
"id": "20039",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_6006aab6eb1b4e6c0b4cfbd4",
"parentId": "20038",
"isLeaf": false,
"molecule": {
"id": "sa_6006aab6eb1b4e6c0b4cfbd4",
"inchikey": "XYURTOBVZGTANR-RWUBSVTLSA-N",
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@H](NC(=O)OC(C)(C)C)c2cccnc21)(C(C)C)C(C)C"
},
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@H](NC(=O)OC(C)(C)C)c2cccnc21)(C(C)C)C(C)C",
"reactionStepId": "sa_d9e76ed7016e1dc2376a44d2",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_d9e76ed7016e1dc2376a44d2",
"reactionHash": "dc76812031734b0f7fe69a9c5f298481debc3df4346b3d11ad11984a9f5be9ff"
},
"children": [
{
"id": "20040",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_b273d4d4546165bca2b249b5",
"parentId": "20039",
"isLeaf": true,
"molecule": {
"id": "sa_b273d4d4546165bca2b249b5",
"inchikey": "DYHSDKLCOJIUFX-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)OC(=O)OC(C)(C)C"
},
"smiles": "CC(C)(C)OC(=O)OC(=O)OC(C)(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "20041",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_15d5d3531709c3c9a13b1bf5",
"parentId": "20039",
"isLeaf": false,
"molecule": {
"id": "sa_15d5d3531709c3c9a13b1bf5",
"inchikey": "SNGLNEOTYPIRQO-KWOQKUFVSA-N",
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@H](N)c2cccnc21)(C(C)C)C(C)C"
},
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@H](N)c2cccnc21)(C(C)C)C(C)C",
"reactionStepId": "sa_8c48ee703ae42d14cbef86fb",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_8c48ee703ae42d14cbef86fb",
"reactionHash": "f31a04cdc85914a1f3e51c9d714d967310b0c77db85f4021c50a1086e4964e7f"
},
"children": [
{
"id": "20042",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_2111e622791beae818da110a",
"parentId": "20041",
"isLeaf": false,
"molecule": {
"id": "sa_2111e622791beae818da110a",
"inchikey": "BZSPSYVCLODKAE-KWOQKUFVSA-N",
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@H](N=[N+]=[N-])c2cccnc21)(C(C)C)C(C)C"
},
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@H](N=[N+]=[N-])c2cccnc21)(C(C)C)C(C)C",
"reactionStepId": "sa_3ae1621f42f0209c52c1b128",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_3ae1621f42f0209c52c1b128",
"reactionHash": "d9337421e19db093163fb64787784a6d2486d83240662334177969757f363e8c"
},
"children": [
{
"id": "20043",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_50a8f83dd89c267fbada1205",
"parentId": "20042",
"isLeaf": true,
"molecule": {
"id": "sa_50a8f83dd89c267fbada1205",
"inchikey": "IVRMZWNICZWHMI-UHFFFAOYSA-N",
"smiles": "[N]N=[N-]"
},
"smiles": "[N-]=[N+]=[N-]",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "20044",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_9a6c1174e7e76b90b451629b",
"parentId": "20042",
"isLeaf": false,
"molecule": {
"id": "sa_9a6c1174e7e76b90b451629b",
"inchikey": "NKQVGYIGDJHNMW-CDNPAEQRSA-N",
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@@H](Cl)c2cccnc21)(C(C)C)C(C)C"
},
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@@H](Cl)c2cccnc21)(C(C)C)C(C)C",
"reactionStepId": "sa_75244edce417c87c72446f0e",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_75244edce417c87c72446f0e",
"reactionHash": "c3fc8d243d4f184932404ba9edb8f775dfa0efb3cbc9920bb314d72324b91aaa"
},
"children": [
{
"id": "20045",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_df2226156367e8f049806be4",
"parentId": "20044",
"isLeaf": false,
"molecule": {
"id": "sa_df2226156367e8f049806be4",
"inchikey": "HFAMMJDRXIUNAY-SWHJIRTISA-N",
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@H](O)c2cccnc21)(C(C)C)C(C)C"
},
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)[C@H](O)c2cccnc21)(C(C)C)C(C)C",
"reactionStepId": "sa_00e176a6a79064fc05b92d5d",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_00e176a6a79064fc05b92d5d",
"reactionHash": "e9f3a23a224c29351f26b8eef374383e5180979b97e60ca65cd40ca948fe88d5"
},
"children": [
{
"id": "20046",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_cbe265433fa1bb9d7e96c3fc",
"parentId": "20045",
"isLeaf": false,
"molecule": {
"id": "sa_cbe265433fa1bb9d7e96c3fc",
"inchikey": "AIVVBBARCYSYDU-SIKLNZKXSA-N",
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)C(=O)c2cccnc21)(C(C)C)C(C)C"
},
"smiles": "CC(C)[Si](O[C@@H]1CC[C@@H](c2cccc(F)c2F)C(=O)c2cccnc21)(C(C)C)C(C)C",
"reactionStepId": "sa_30d47bfb387adb4231d3587d",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_30d47bfb387adb4231d3587d",
"reactionHash": "14a5965af773ae8fe03fef55f24e6afed3a94f097b2b3de0c0ab8ab7ab60fb45"
},
"children": [
{
"id": "20047",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_ce5c5954f17f56cf627fc1c6",
"parentId": "20046",
"isLeaf": false,
"molecule": {
"id": "sa_ce5c5954f17f56cf627fc1c6",
"inchikey": "LZTSMPYESKABAS-GOSISDBHSA-N",
"smiles": "CC(C)[Si](O[C@@H]1CCCC(=O)c2cccnc21)(C(C)C)C(C)C"
},
"smiles": "CC(C)[Si](O[C@@H]1CCCC(=O)c2cccnc21)(C(C)C)C(C)C",
"reactionStepId": "sa_e839a395f4c6eea5051192f2",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_e839a395f4c6eea5051192f2",
"reactionHash": "a88249392c40a62ac1c367cc665efe5bcb9cebb3a4f502ad41bc0914cff8cf16"
},
"children": [
{
"id": "20048",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_3bd16f752671aff63d779054",
"parentId": "20047",
"isLeaf": true,
"molecule": {
"id": "sa_3bd16f752671aff63d779054",
"inchikey": "LHJCZOXMCGQVDQ-UHFFFAOYSA-N",
"smiles": "CC(C)[Si](OS(=O)(=O)C(F)(F)F)(C(C)C)C(C)C"
},
"smiles": "CC(C)[Si](OS(=O)(=O)C(F)(F)F)(C(C)C)C(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "20049",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_c919db3322e6eb3732d8fb7c",
"parentId": "20047",
"isLeaf": false,
"molecule": {
"id": "sa_c919db3322e6eb3732d8fb7c",
"inchikey": "ZZNXHQSAOHUNDA-SECBINFHSA-N",
"smiles": "O=C1CCC[C@@H](O)c2ncccc21"
},
"smiles": "O=C1CCC[C@@H](O)c2ncccc21",
"reactionStepId": "sa_68386a9e6facc86ad618d0a9",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_68386a9e6facc86ad618d0a9",
"reactionHash": "02255926ad4197d4cad36ec6945876a9d9581ee4c9593e17cdec855118541971"
},
"children": [
{
"id": "20050",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_f722ea3c8553f4f05b39b2a6",
"parentId": "20049",
"isLeaf": true,
"molecule": {
"id": "sa_f722ea3c8553f4f05b39b2a6",
"inchikey": "OTLNPYWUJOZPPA-UHFFFAOYSA-N",
"smiles": "O=C(O)c1ccc([N+](=O)[O-])cc1"
},
"smiles": "O=C(O)c1ccc([N+](=O)[O-])cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "20051",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_902302c632b53636210099f6",
"parentId": "20049",
"isLeaf": true,
"molecule": {
"id": "sa_902302c632b53636210099f6",
"inchikey": "RIOQSEWOXXDEQQ-UHFFFAOYSA-N",
"smiles": "c1ccc(P(c2ccccc2)c2ccccc2)cc1"
},
"smiles": "c1ccc(P(c2ccccc2)c2ccccc2)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "20052",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_4e8653c83cde3c60eddaccf8",
"parentId": "20049",
"isLeaf": true,
"molecule": {
"id": "sa_4e8653c83cde3c60eddaccf8",
"inchikey": "VVWRJUBEIPHGQF-UHFFFAOYSA-N",
"smiles": "CC(C)OC(=O)N=NC(=O)OC(C)C"
},
"smiles": "CC(C)OC(=O)N=NC(=O)OC(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "20053",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_9363d59b4840bbc18ea1a10e",
"parentId": "20046",
"isLeaf": true,
"molecule": {
"id": "sa_9363d59b4840bbc18ea1a10e",
"inchikey": "RKWWASUTWAFKHA-UHFFFAOYSA-N",
"smiles": "Fc1cccc(Br)c1F"
},
"smiles": "Fc1cccc(Br)c1F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "20054",
"routeId": "sa_e84763e75660b2e007029545",
"moleculeId": "sa_a576f9b9a2caa305053d217d",
"parentId": "20044",
"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": []
}
]
}
]
}
]
}
]
}
]
}
]
}
]
}
}