Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CC[C@H](Nc1nc(NCc2cccnc2)c2ncn(C(C)C)c2n1)C(O)C(C)C
InChiKey
AGGGWZCOULSEER-ATNAJCNCSA-N
Route Signature
808e97bfa4aea35cb76e1f01579b83d76e576999b4f954c016f6cd3522ac34eb
Synthesis route with 3 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_8966bd2fceec75157d839bc4",
"signature": "808e97bfa4aea35cb76e1f01579b83d76e576999b4f954c016f6cd3522ac34eb",
"contentHash": "33985dba3de309c589a4d799dda70ba2a78e78711edbe9de2c215355f2f03c63",
"length": 3,
"isConvergent": true
},
"target": {
"id": "sa_ad59cc25d4938a735f316688",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-04550",
"moleculeId": "sa_999f9d979345a0c032d24591",
"smiles": "CC[C@H](Nc1nc(NCc2cccnc2)c2ncn(C(C)C)c2n1)C(O)C(C)C",
"routeLength": 3,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_999f9d979345a0c032d24591",
"inchikey": "AGGGWZCOULSEER-ATNAJCNCSA-N",
"smiles": "CC[C@H](Nc1nc(NCc2cccnc2)c2ncn(C(C)C)c2n1)C(O)C(C)C"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "11238",
"routeId": "sa_8966bd2fceec75157d839bc4",
"moleculeId": "sa_999f9d979345a0c032d24591",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_999f9d979345a0c032d24591",
"inchikey": "AGGGWZCOULSEER-ATNAJCNCSA-N",
"smiles": "CC[C@H](Nc1nc(NCc2cccnc2)c2ncn(C(C)C)c2n1)C(O)C(C)C"
},
"smiles": "CC[C@H](Nc1nc(NCc2cccnc2)c2ncn(C(C)C)c2n1)C(O)C(C)C",
"reactionStepId": "sa_f4a7f5bf3c8ba96f7b0bc5ef",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08846696B2;0315;1518547\",\"rsmi\":\"F[c:5]1[n:6][c:7]([NH:8][CH2:9][c:10]2[cH:11][cH:12][cH:13][n:14][cH:15]2)[c:16]2[n:17][cH:18][n:19]([CH:20]([CH3:21])[CH3:22])[c:23]2[n:24]1.[CH3:1][CH2:2][C@H:3]([NH2:4])[CH:25]([OH:26])[CH:27]([CH3:28])[CH3:29]>CCCCO.CCN(C(C)C)C(C)C.CS(C)=O>[CH3:1][CH2:2][C@H:3]([NH:4][c:5]1[n:6][c:7]([NH:8][CH2:9][c:10]2[cH:11][cH:12][cH:13][n:14][cH:15]2)[c:16]2[n:17][cH:18][n:19]([CH:20]([CH3:21])[CH3:22])[c:23]2[n:24]1)[CH:25]([OH:26])[CH:27]([CH3:28])[CH3:29]\"},\"mapped_reaction_smiles\":\"F[c:5]1[n:6][c:7]([NH:8][CH2:9][c:10]2[cH:11][cH:12][cH:13][n:14][cH:15]2)[c:16]2[n:17][cH:18][n:19]([CH:20]([CH3:21])[CH3:22])[c:23]2[n:24]1.[CH3:1][CH2:2][C@H:3]([NH2:4])[CH:25]([OH:26])[CH:27]([CH3:28])[CH3:29]>CCCCO.CCN(C(C)C)C(C)C.CS(C)=O>[CH3:1][CH2:2][C@H:3]([NH:4][c:5]1[n:6][c:7]([NH:8][CH2:9][c:10]2[cH:11][cH:12][cH:13][n:14][cH:15]2)[c:16]2[n:17][cH:18][n:19]([CH:20]([CH3:21])[CH3:22])[c:23]2[n:24]1)[CH:25]([OH:26])[CH:27]([CH3:28])[CH3:29]\"}",
"reactionStep": {
"id": "sa_f4a7f5bf3c8ba96f7b0bc5ef",
"reactionHash": "a5a7170b58f06519b2b1e88f0a90fab0755d5a64952d53672dd94220bc7192ef"
},
"children": [
{
"id": "11239",
"routeId": "sa_8966bd2fceec75157d839bc4",
"moleculeId": "sa_6ee44f5c599691f012dc1b91",
"parentId": "11238",
"isLeaf": false,
"molecule": {
"id": "sa_6ee44f5c599691f012dc1b91",
"inchikey": "CBICPSJSXZLNAC-UHFFFAOYSA-N",
"smiles": "CC(C)n1cnc2c(NCc3cccnc3)nc(F)nc21"
},
"smiles": "CC(C)n1cnc2c(NCc3cccnc3)nc(F)nc21",
"reactionStepId": "sa_de4fbc1a31fd860166ede9fe",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08846696B2;0303;1518541\",\"rsmi\":\"Br[CH:2]([CH3:1])[CH3:3].[nH:4]1[cH:5][n:6][c:7]2[c:8]([NH:9][CH2:10][c:11]3[cH:12][cH:13][cH:14][n:15][cH:16]3)[n:17][c:18]([F:19])[n:20][c:21]12>CC(=O)N(C)C.CO.ClC(Cl)Cl.O=C(O)O.[K+].[K+]>[CH3:1][CH:2]([CH3:3])[n:4]1[cH:5][n:6][c:7]2[c:8]([NH:9][CH2:10][c:11]3[cH:12][cH:13][cH:14][n:15][cH:16]3)[n:17][c:18]([F:19])[n:20][c:21]12\"},\"mapped_reaction_smiles\":\"Br[CH:2]([CH3:1])[CH3:3].[nH:4]1[cH:5][n:6][c:7]2[c:8]([NH:9][CH2:10][c:11]3[cH:12][cH:13][cH:14][n:15][cH:16]3)[n:17][c:18]([F:19])[n:20][c:21]12>CC(=O)N(C)C.CO.ClC(Cl)Cl.O=C(O)O.[K+].[K+]>[CH3:1][CH:2]([CH3:3])[n:4]1[cH:5][n:6][c:7]2[c:8]([NH:9][CH2:10][c:11]3[cH:12][cH:13][cH:14][n:15][cH:16]3)[n:17][c:18]([F:19])[n:20][c:21]12\"}",
"reactionStep": {
"id": "sa_de4fbc1a31fd860166ede9fe",
"reactionHash": "831186148ca467db4ce00ed28eb982f9ab720b99a8e073250bb86bc53f55d889"
},
"children": [
{
"id": "11240",
"routeId": "sa_8966bd2fceec75157d839bc4",
"moleculeId": "sa_511d37ac90c136883bac9fd8",
"parentId": "11239",
"isLeaf": true,
"molecule": {
"id": "sa_511d37ac90c136883bac9fd8",
"inchikey": "NAMYKGVDVNBCFQ-UHFFFAOYSA-N",
"smiles": "CC(C)Br"
},
"smiles": "CC(C)Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11241",
"routeId": "sa_8966bd2fceec75157d839bc4",
"moleculeId": "sa_852e7cab2b345261c8809846",
"parentId": "11239",
"isLeaf": false,
"molecule": {
"id": "sa_852e7cab2b345261c8809846",
"inchikey": "YIDSLZLYPNKFDM-UHFFFAOYSA-N",
"smiles": "Fc1nc(NCc2cccnc2)c2nc[nH]c2n1"
},
"smiles": "Fc1nc(NCc2cccnc2)c2nc[nH]c2n1",
"reactionStepId": "sa_9b609d1af251f9f102b1e87a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08846696B2;0301;1518540\",\"rsmi\":\"Cl[c:4]1[n:3][c:2]([F:1])[n:18][c:17]2[c:13]1[nH:14][cH:15][n:16]2.[NH2:5][CH2:6][c:7]1[cH:8][cH:9][cH:10][n:11][cH:12]1>CCCCO.CCN(C(C)C)C(C)C.CO.ClC(Cl)Cl>[F:1][c:2]1[n:3][c:4]([NH:5][CH2:6][c:7]2[cH:8][cH:9][cH:10][n:11][cH:12]2)[c:13]2[n:14][cH:15][nH:16][c:17]2[n:18]1\"},\"mapped_reaction_smiles\":\"Cl[c:4]1[n:3][c:2]([F:1])[n:18][c:17]2[c:13]1[nH:14][cH:15][n:16]2.[NH2:5][CH2:6][c:7]1[cH:8][cH:9][cH:10][n:11][cH:12]1>CCCCO.CCN(C(C)C)C(C)C.CO.ClC(Cl)Cl>[F:1][c:2]1[n:3][c:4]([NH:5][CH2:6][c:7]2[cH:8][cH:9][cH:10][n:11][cH:12]2)[c:13]2[n:14][cH:15][nH:16][c:17]2[n:18]1\"}",
"reactionStep": {
"id": "sa_9b609d1af251f9f102b1e87a",
"reactionHash": "ff95dd91e1c61ee12be160a577b35b66e7e1acc05b271b4a64b300c4e9c69195"
},
"children": [
{
"id": "11242",
"routeId": "sa_8966bd2fceec75157d839bc4",
"moleculeId": "sa_c1440b0d138975d9344b556d",
"parentId": "11241",
"isLeaf": true,
"molecule": {
"id": "sa_c1440b0d138975d9344b556d",
"inchikey": "HDOUGSFASVGDCS-UHFFFAOYSA-N",
"smiles": "NCc1cccnc1"
},
"smiles": "NCc1cccnc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11243",
"routeId": "sa_8966bd2fceec75157d839bc4",
"moleculeId": "sa_c1edc9e60caa8dd844d7f431",
"parentId": "11241",
"isLeaf": true,
"molecule": {
"id": "sa_c1edc9e60caa8dd844d7f431",
"inchikey": "UNRIYCIDCQDGQE-UHFFFAOYSA-N",
"smiles": "Fc1nc(Cl)c2ncnc-2[nH]1"
},
"smiles": "Fc1nc(Cl)c2[nH]cnc2n1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "11244",
"routeId": "sa_8966bd2fceec75157d839bc4",
"moleculeId": "sa_99b54c00b43dacb4d6475fa7",
"parentId": "11238",
"isLeaf": false,
"molecule": {
"id": "sa_99b54c00b43dacb4d6475fa7",
"inchikey": "KHRLRJPSKWLLPI-PKPIPKONSA-N",
"smiles": "CC[C@H](N)C(O)C(C)C"
},
"smiles": "CC[C@H](N)C(O)C(C)C",
"reactionStepId": "sa_d37edd531c754b3505a0f9bc",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US08846696B2;0288;1518537\",\"rsmi\":\"c1ccc(C(c2ccccc2)(c2ccccc2)[NH:4][C@@H:3]([CH2:2][CH3:1])[CH:5]([OH:6])[CH:7]([CH3:8])[CH3:9])cc1>ClCCl.O=C(O)C(F)(F)F>[CH3:1][CH2:2][C@H:3]([NH2:4])[CH:5]([OH:6])[CH:7]([CH3:8])[CH3:9]\"},\"mapped_reaction_smiles\":\"c1ccc(C(c2ccccc2)(c2ccccc2)[NH:4][C@@H:3]([CH2:2][CH3:1])[CH:5]([OH:6])[CH:7]([CH3:8])[CH3:9])cc1>ClCCl.O=C(O)C(F)(F)F>[CH3:1][CH2:2][C@H:3]([NH2:4])[CH:5]([OH:6])[CH:7]([CH3:8])[CH3:9]\"}",
"reactionStep": {
"id": "sa_d37edd531c754b3505a0f9bc",
"reactionHash": "dafaeff1d64b2557814ad8b2f4167e84e802224c434d4649f0bdf31cf98e38bf"
},
"children": [
{
"id": "11245",
"routeId": "sa_8966bd2fceec75157d839bc4",
"moleculeId": "sa_65074ff0c9f4701b4613f1da",
"parentId": "11244",
"isLeaf": true,
"molecule": {
"id": "sa_65074ff0c9f4701b4613f1da",
"inchikey": "RZROWHATYIVXID-SKCDSABHSA-N",
"smiles": "CC[C@H](NC(c1ccccc1)(c1ccccc1)c1ccccc1)C(O)C(C)C"
},
"smiles": "CC[C@H](NC(c1ccccc1)(c1ccccc1)c1ccccc1)C(O)C(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}