Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](c3nnco3)C[C@H]2CS1
InChiKey
VBXCGICXNVLUFX-XABDRZNLSA-N
Route Signature
68c3229ed97f1d47a715960627651d94ce9294b10e2d14b27c8326507347473e
Synthesis route with 14 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_e5ad3b91e041d189d3baa718",
"signature": "68c3229ed97f1d47a715960627651d94ce9294b10e2d14b27c8326507347473e",
"contentHash": "f92cfc47cce33f49b18719764997cb64dc3e127714d9522116bacf94c92be834",
"length": 14,
"isConvergent": false
},
"target": {
"id": "sa_ab47ba0585fe2eaf5c68e0e7",
"benchmarkSetId": "019173c85ab67300a20aafbd44174d6551ca67a41e948a511372ae5dca775a80",
"targetId": "USPTO-005/190",
"moleculeId": "sa_15777df5f3dd84fbe7416435",
"smiles": "NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](c3nnco3)C[C@H]2CS1",
"routeLength": 14,
"isConvergent": false,
"metadata": "{\"source\":\"retro-pickle\"}",
"molecule": {
"id": "sa_15777df5f3dd84fbe7416435",
"inchikey": "VBXCGICXNVLUFX-XABDRZNLSA-N",
"smiles": "NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](c3nnco3)C[C@H]2CS1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "18106",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_15777df5f3dd84fbe7416435",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_15777df5f3dd84fbe7416435",
"inchikey": "VBXCGICXNVLUFX-XABDRZNLSA-N",
"smiles": "NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](c3nnco3)C[C@H]2CS1"
},
"smiles": "NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](c3nnco3)C[C@H]2CS1",
"reactionStepId": "sa_5aaf5620c2ece1a508c75ada",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_5aaf5620c2ece1a508c75ada",
"reactionHash": "e5cca99baeed2231c207acb7e7ab5a5a3ad89a8e5e5e0c92abaeb6d7b4c184ff"
},
"children": [
{
"id": "18107",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_ae4d7bb5577b8762a5a1fc9e",
"parentId": "18106",
"isLeaf": false,
"molecule": {
"id": "sa_ae4d7bb5577b8762a5a1fc9e",
"inchikey": "WDNRDBJXDFVQNN-OHOGDBNVSA-N",
"smiles": "O=C(NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](c3nnco3)C[C@H]2CS1)c1ccccc1"
},
"smiles": "O=C(NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](c3nnco3)C[C@H]2CS1)c1ccccc1",
"reactionStepId": "sa_778550adc39df084db6c4d95",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_778550adc39df084db6c4d95",
"reactionHash": "2a3646e2cde443b07516cd1a95df4a006018a2823f56d614d6fbe0485f3fa132"
},
"children": [
{
"id": "18108",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_31c6f8924dae0b520a148660",
"parentId": "18107",
"isLeaf": false,
"molecule": {
"id": "sa_31c6f8924dae0b520a148660",
"inchikey": "BMVFEJSGQHXPLC-IFCGJNOESA-N",
"smiles": "NNC(=O)[C@H]1C[C@H]2CSC(NC(=O)c3ccccc3)=N[C@@]2(c2ccc(F)cc2F)CO1"
},
"smiles": "NNC(=O)[C@H]1C[C@H]2CSC(NC(=O)c3ccccc3)=N[C@@]2(c2ccc(F)cc2F)CO1",
"reactionStepId": "sa_a28d14a44d68c968a7dbb625",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_a28d14a44d68c968a7dbb625",
"reactionHash": "e6b93ee77dd29fdf2a4966c1a5c0f0d5dae92e23b8c11563d0e7116c11c70ad5"
},
"children": [
{
"id": "18109",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_6b1bb7d0f020e6cdf1c80da7",
"parentId": "18108",
"isLeaf": false,
"molecule": {
"id": "sa_6b1bb7d0f020e6cdf1c80da7",
"inchikey": "QEKBJGKLTSUYTG-FTVBGQFJSA-N",
"smiles": "CC(C)(C)OC(=O)NNC(=O)[C@H]1C[C@H]2CSC(NC(=O)c3ccccc3)=N[C@@]2(c2ccc(F)cc2F)CO1"
},
"smiles": "CC(C)(C)OC(=O)NNC(=O)[C@H]1C[C@H]2CSC(NC(=O)c3ccccc3)=N[C@@]2(c2ccc(F)cc2F)CO1",
"reactionStepId": "sa_0daef745d97bff2b0faaf017",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_0daef745d97bff2b0faaf017",
"reactionHash": "d03a5641f5fcfbea3f630a5826f5131528b255c1565b9dea7bdf6ffa4508d735"
},
"children": [
{
"id": "18110",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_20ede000ec9e23fc9f225a17",
"parentId": "18109",
"isLeaf": false,
"molecule": {
"id": "sa_20ede000ec9e23fc9f225a17",
"inchikey": "ASRRGXFQSHGLJU-ZCPGDWHISA-N",
"smiles": "COC(CNC(=O)[C@H]1C[C@H]2CSC(NC(=O)c3ccccc3)=N[C@@]2(c2ccc(F)cc2F)CO1)OC"
},
"smiles": "COC(CNC(=O)[C@H]1C[C@H]2CSC(NC(=O)c3ccccc3)=N[C@@]2(c2ccc(F)cc2F)CO1)OC",
"reactionStepId": "sa_a42687f093eba44ad64e7f24",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_a42687f093eba44ad64e7f24",
"reactionHash": "e0beb58f737197c5822924b7cdefc236bf71e4194969ff42fb15dc6ce85ce279"
},
"children": [
{
"id": "18111",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_15914eaa733d1b15635e3949",
"parentId": "18110",
"isLeaf": false,
"molecule": {
"id": "sa_15914eaa733d1b15635e3949",
"inchikey": "IOLXZWKHKCWGDB-IFCGJNOESA-N",
"smiles": "O=C(NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](C(=O)O)C[C@H]2CS1)c1ccccc1"
},
"smiles": "O=C(NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](C(=O)O)C[C@H]2CS1)c1ccccc1",
"reactionStepId": "sa_0fbf0c338ab3be975c5af1a8",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_0fbf0c338ab3be975c5af1a8",
"reactionHash": "bd6c559011c335e6fcb2329ec182024d8b0399f464a8521d99e99c4880081320"
},
"children": [
{
"id": "18112",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_98c52c9702022ac96b8fd43d",
"parentId": "18111",
"isLeaf": true,
"molecule": {
"id": "sa_98c52c9702022ac96b8fd43d",
"inchikey": "LFTLOKWAGJYHHR-UHFFFAOYSA-N",
"smiles": "C[N+]1([O-])CCOCC1"
},
"smiles": "C[N+]1([O-])CCOCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "18113",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_651a348ec98875c62e9b0581",
"parentId": "18111",
"isLeaf": false,
"molecule": {
"id": "sa_651a348ec98875c62e9b0581",
"inchikey": "OQQJVXBPMZWLIC-PXARDIRTSA-N",
"smiles": "O=C(NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](CO)C[C@H]2CS1)c1ccccc1"
},
"smiles": "O=C(NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](CO)C[C@H]2CS1)c1ccccc1",
"reactionStepId": "sa_d518ca99a5753b1bf89d39b7",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_d518ca99a5753b1bf89d39b7",
"reactionHash": "c82660033d419138b6574e2b4ecc0962bc532c1e1373e68761567e9c5bb42d91"
},
"children": [
{
"id": "18114",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_90fe3b7efb5d10ab47911a54",
"parentId": "18113",
"isLeaf": false,
"molecule": {
"id": "sa_90fe3b7efb5d10ab47911a54",
"inchikey": "CCTKGRVGOFCNQO-ZCUZBQTDSA-N",
"smiles": "O=C(NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](COCc3ccccc3)C[C@H]2CS1)c1ccccc1"
},
"smiles": "O=C(NC1=N[C@@]2(c3ccc(F)cc3F)CO[C@@H](COCc3ccccc3)C[C@H]2CS1)c1ccccc1",
"reactionStepId": "sa_b30970860d560d20be321da6",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_b30970860d560d20be321da6",
"reactionHash": "ac75945e46d52fe61617ed89099a92c769761fe8e2354ffb3bec9d78fab746a6"
},
"children": [
{
"id": "18115",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_c8af6316d7817e522deb9eee",
"parentId": "18114",
"isLeaf": false,
"molecule": {
"id": "sa_c8af6316d7817e522deb9eee",
"inchikey": "JUOMBAJDGJCNRU-ZCUZBQTDSA-N",
"smiles": "O=C(NC(=S)N[C@@]1(c2ccc(F)cc2F)CO[C@@H](COCc2ccccc2)C[C@H]1CO)c1ccccc1"
},
"smiles": "O=C(NC(=S)N[C@@]1(c2ccc(F)cc2F)CO[C@@H](COCc2ccccc2)C[C@H]1CO)c1ccccc1",
"reactionStepId": "sa_a2cc17cae03582d1585cfdea",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_a2cc17cae03582d1585cfdea",
"reactionHash": "0e328026af2d2802e0b98f04c80d15439e061c0287ec4fddf84adda68647491c"
},
"children": [
{
"id": "18116",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_da820465b0365eb32fb2a64a",
"parentId": "18115",
"isLeaf": true,
"molecule": {
"id": "sa_da820465b0365eb32fb2a64a",
"inchikey": "CPEKAXYCDKETEN-UHFFFAOYSA-N",
"smiles": "O=C(N=C=S)c1ccccc1"
},
"smiles": "O=C(N=C=S)c1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "18117",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_e13f86dc261cca206c0c64f6",
"parentId": "18115",
"isLeaf": false,
"molecule": {
"id": "sa_e13f86dc261cca206c0c64f6",
"inchikey": "SDFLUNRFKYHXHG-VPWXQRGCSA-N",
"smiles": "N[C@@]1(c2ccc(F)cc2F)CO[C@@H](COCc2ccccc2)C[C@H]1CO"
},
"smiles": "N[C@@]1(c2ccc(F)cc2F)CO[C@@H](COCc2ccccc2)C[C@H]1CO",
"reactionStepId": "sa_0165fdcafee158a63a791e24",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_0165fdcafee158a63a791e24",
"reactionHash": "cbbfe51fa8b918c7f5bc73327548578a85a4c1d02f56f044c3693109349fb88c"
},
"children": [
{
"id": "18118",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_3fa20f006ce1e3f3c1adb4c4",
"parentId": "18117",
"isLeaf": false,
"molecule": {
"id": "sa_3fa20f006ce1e3f3c1adb4c4",
"inchikey": "SPERJVBJQROOBN-VPWXQRGCSA-N",
"smiles": "Fc1ccc([C@]23CO[C@@H](COCc4ccccc4)C[C@H]2CON3)c(F)c1"
},
"smiles": "Fc1ccc([C@]23CO[C@@H](COCc4ccccc4)C[C@H]2CON3)c(F)c1",
"reactionStepId": "sa_9f63d3148e5bb7d107cb41a2",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_9f63d3148e5bb7d107cb41a2",
"reactionHash": "aa9d11a47021273e8ef90f805597341ed8d6048ce41e076b108c1cfcaa574d42"
},
"children": [
{
"id": "18119",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_d2c225ce58322f4b4c8b9d9e",
"parentId": "18118",
"isLeaf": false,
"molecule": {
"id": "sa_d2c225ce58322f4b4c8b9d9e",
"inchikey": "LXYBKZVFHKHLSR-QWHCGFSZSA-N",
"smiles": "c1ccc(COC[C@H]2C[C@H]3CON=C3CO2)cc1"
},
"smiles": "c1ccc(COC[C@H]2C[C@H]3CON=C3CO2)cc1",
"reactionStepId": "sa_ef77c2d1640290719e1367a8",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_ef77c2d1640290719e1367a8",
"reactionHash": "33545f79b6675c78e8080987247f636374d657c46f145159fa79ac8acbec70ca"
},
"children": [
{
"id": "18120",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_a078457739bf336cc8cd1409",
"parentId": "18119",
"isLeaf": false,
"molecule": {
"id": "sa_a078457739bf336cc8cd1409",
"inchikey": "RFIODJCRBOZUOP-CQSZACIVSA-N",
"smiles": "C=CC[C@H](COCc1ccccc1)OCC=NO"
},
"smiles": "C=CC[C@H](COCc1ccccc1)OCC=NO",
"reactionStepId": "sa_da0b280e4428a7d3cbefa017",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_da0b280e4428a7d3cbefa017",
"reactionHash": "35011d3a3d5520ce912498d91dc8edae9dbcf8da9272c5e877d734cecfa48313"
},
"children": [
{
"id": "18121",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_04a18e3f07bde82ca29399ee",
"parentId": "18120",
"isLeaf": true,
"molecule": {
"id": "sa_04a18e3f07bde82ca29399ee",
"inchikey": "AVXURJPOCDRRFD-UHFFFAOYSA-N",
"smiles": "NO"
},
"smiles": "NO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "18122",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_7cae59d5b02a6ba12ed3033a",
"parentId": "18120",
"isLeaf": false,
"molecule": {
"id": "sa_7cae59d5b02a6ba12ed3033a",
"inchikey": "PZAUSXWSVPODJP-QGZVFWFLSA-N",
"smiles": "C=CC[C@H](COCc1ccccc1)OCC(OCC)OCC"
},
"smiles": "C=CC[C@H](COCc1ccccc1)OCC(OCC)OCC",
"reactionStepId": "sa_11dc4a77dd5baac1e674b3f7",
"template": null,
"metadata": null,
"reactionStep": {
"id": "sa_11dc4a77dd5baac1e674b3f7",
"reactionHash": "3169c9cec5438908cd75a22850c1603edef27ddb5b425b1efb67062ff0c1f300"
},
"children": [
{
"id": "18123",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_acc3c42951a0807679f571ef",
"parentId": "18122",
"isLeaf": true,
"molecule": {
"id": "sa_acc3c42951a0807679f571ef",
"inchikey": "KTFVKQQUQQYFPB-GFCCVEGCSA-N",
"smiles": "C=CC[C@@H](O)COCc1ccccc1"
},
"smiles": "C=CC[C@@H](O)COCc1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "18124",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_a03c80f6959de11dcab3c476",
"parentId": "18122",
"isLeaf": true,
"molecule": {
"id": "sa_a03c80f6959de11dcab3c476",
"inchikey": "LILXDMFJXYAKMK-UHFFFAOYSA-N",
"smiles": "CCOC(CBr)OCC"
},
"smiles": "CCOC(CBr)OCC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "18125",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_89513fc23e2ad9f1eb192304",
"parentId": "18118",
"isLeaf": true,
"molecule": {
"id": "sa_89513fc23e2ad9f1eb192304",
"inchikey": "YKLDMAPEGQYZRT-UHFFFAOYSA-N",
"smiles": "Fc1ccc(I)c(F)c1"
},
"smiles": "Fc1ccc(I)c(F)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
]
}
]
},
{
"id": "18126",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_b8573c1cdd0f1c6b81849d15",
"parentId": "18110",
"isLeaf": true,
"molecule": {
"id": "sa_b8573c1cdd0f1c6b81849d15",
"inchikey": "QKWWDTYDYOFRJL-UHFFFAOYSA-N",
"smiles": "COC(CN)OC"
},
"smiles": "COC(CN)OC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "18127",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_153bc9a741c3fecd816c6a49",
"parentId": "18109",
"isLeaf": true,
"molecule": {
"id": "sa_153bc9a741c3fecd816c6a49",
"inchikey": "DKACXUFSLUYRFU-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(O)=NN"
},
"smiles": "CC(C)(C)OC(=O)NN",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "18128",
"routeId": "sa_e5ad3b91e041d189d3baa718",
"moleculeId": "sa_0c16e531f8a4d1359a305a70",
"parentId": "18107",
"isLeaf": true,
"molecule": {
"id": "sa_0c16e531f8a4d1359a305a70",
"inchikey": "JOXIMZWYDAKGHI-UHFFFAOYSA-N",
"smiles": "Cc1ccc(S(=O)(=O)O)cc1"
},
"smiles": "Cc1ccc(S(=O)(=O)O)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}