Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CN(c1ccc(/C=C/C[C@H](NC(=O)c2c(Cl)cccc2Cl)C(=O)O)cc1)c1ncccn1
InChiKey
ZKQVWGWBOWLLFL-XUYKHGSPSA-N
Route Signature
3e8529bd12c82d4a28840bf25f267ec3a356b2cad306b5b90cd649134e68201d
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_62fbf98346716775d39472fd",
"signature": "3e8529bd12c82d4a28840bf25f267ec3a356b2cad306b5b90cd649134e68201d",
"contentHash": "2f724abe56ae5696115ec80a7de746151c78263673af466e5c92677af7315256",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_2f5d9608cd8e31840890d198",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00109",
"moleculeId": "sa_3fc5f42e237ff9bab7800e2d",
"smiles": "CN(c1ccc(/C=C/C[C@H](NC(=O)c2c(Cl)cccc2Cl)C(=O)O)cc1)c1ncccn1",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_3fc5f42e237ff9bab7800e2d",
"inchikey": "ZKQVWGWBOWLLFL-XUYKHGSPSA-N",
"smiles": "CN(c1ccc(/C=C/C[C@H](NC(=O)c2c(Cl)cccc2Cl)C(=O)O)cc1)c1ncccn1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9171",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_3fc5f42e237ff9bab7800e2d",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_3fc5f42e237ff9bab7800e2d",
"inchikey": "ZKQVWGWBOWLLFL-XUYKHGSPSA-N",
"smiles": "CN(c1ccc(/C=C/C[C@H](NC(=O)c2c(Cl)cccc2Cl)C(=O)O)cc1)c1ncccn1"
},
"smiles": "CN(c1ccc(/C=C/C[C@H](NC(=O)c2c(Cl)cccc2Cl)C(=O)O)cc1)c1ncccn1",
"reactionStepId": "sa_8738c6c4835301b4438ee82a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07879837B2;0394;1047028\",\"rsmi\":\"C[O:24][C:22]([C@H:10]([CH2:9]/[CH:8]=[CH:7]/[c:6]1[cH:5][cH:4][c:3]([N:2]([CH3:1])[c:27]2[n:28][cH:29][cH:30][cH:31][n:32]2)[cH:26][cH:25]1)[NH:11][C:12](=[O:13])[c:14]1[c:15]([Cl:16])[cH:17][cH:18][cH:19][c:20]1[Cl:21])=[O:23]>C1CCOC1.O.[Li+].O>[CH3:1][N:2]([c:3]1[cH:4][cH:5][c:6](/[CH:7]=[CH:8]/[CH2:9][C@H:10]([NH:11][C:12](=[O:13])[c:14]2[c:15]([Cl:16])[cH:17][cH:18][cH:19][c:20]2[Cl:21])[C:22](=[O:23])[OH:24])[cH:25][cH:26]1)[c:27]1[n:28][cH:29][cH:30][cH:31][n:32]1\"},\"mapped_reaction_smiles\":\"C[O:24][C:22]([C@H:10]([CH2:9]/[CH:8]=[CH:7]/[c:6]1[cH:5][cH:4][c:3]([N:2]([CH3:1])[c:27]2[n:28][cH:29][cH:30][cH:31][n:32]2)[cH:26][cH:25]1)[NH:11][C:12](=[O:13])[c:14]1[c:15]([Cl:16])[cH:17][cH:18][cH:19][c:20]1[Cl:21])=[O:23]>C1CCOC1.O.[Li+].O>[CH3:1][N:2]([c:3]1[cH:4][cH:5][c:6](/[CH:7]=[CH:8]/[CH2:9][C@H:10]([NH:11][C:12](=[O:13])[c:14]2[c:15]([Cl:16])[cH:17][cH:18][cH:19][c:20]2[Cl:21])[C:22](=[O:23])[OH:24])[cH:25][cH:26]1)[c:27]1[n:28][cH:29][cH:30][cH:31][n:32]1\"}",
"reactionStep": {
"id": "sa_8738c6c4835301b4438ee82a",
"reactionHash": "51cec2c1024de11d5a727100db74e964ee5f537c1f1088c076ca42fa8f32e03c"
},
"children": [
{
"id": "9172",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_fe1f969b28ac7cc3397c65e0",
"parentId": "9171",
"isLeaf": false,
"molecule": {
"id": "sa_fe1f969b28ac7cc3397c65e0",
"inchikey": "RQMXYLRVIGJNAP-QLPSFHHPSA-N",
"smiles": "COC(=O)[C@H](C/C=C/c1ccc(N(C)c2ncccn2)cc1)NC(=O)c1c(Cl)cccc1Cl"
},
"smiles": "COC(=O)[C@H](C/C=C/c1ccc(N(C)c2ncccn2)cc1)NC(=O)c1c(Cl)cccc1Cl",
"reactionStepId": "sa_8662583db68bc21efc3defa7",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07879837B2;0392;1047027\",\"rsmi\":\"I[c:9]1[cH:10][cH:11][c:12]([N:13]([CH3:14])[c:15]2[n:16][cH:17][cH:18][cH:19][n:20]2)[cH:21][cH:22]1.[CH3:1][O:2][C:3](=[O:4])[C@H:5]([CH2:6][CH:7]=[CH2:8])[NH:23][C:24](=[O:25])[c:26]1[c:27]([Cl:28])[cH:29][cH:30][cH:31][c:32]1[Cl:33]>CC(=O)O.CC(=O)O.CCOC(C)=O.CN(C)C=O.Cc1ccccc1P(c1ccccc1C)c1ccccc1C.O=C(O)O.[K+].[K+].[Pd+2]>[CH3:1][O:2][C:3](=[O:4])[C@H:5]([CH2:6]/[CH:7]=[CH:8]/[c:9]1[cH:10][cH:11][c:12]([N:13]([CH3:14])[c:15]2[n:16][cH:17][cH:18][cH:19][n:20]2)[cH:21][cH:22]1)[NH:23][C:24](=[O:25])[c:26]1[c:27]([Cl:28])[cH:29][cH:30][cH:31][c:32]1[Cl:33]\"},\"mapped_reaction_smiles\":\"I[c:9]1[cH:10][cH:11][c:12]([N:13]([CH3:14])[c:15]2[n:16][cH:17][cH:18][cH:19][n:20]2)[cH:21][cH:22]1.[CH3:1][O:2][C:3](=[O:4])[C@H:5]([CH2:6][CH:7]=[CH2:8])[NH:23][C:24](=[O:25])[c:26]1[c:27]([Cl:28])[cH:29][cH:30][cH:31][c:32]1[Cl:33]>CC(=O)O.CC(=O)O.CCOC(C)=O.CN(C)C=O.Cc1ccccc1P(c1ccccc1C)c1ccccc1C.O=C(O)O.[K+].[K+].[Pd+2]>[CH3:1][O:2][C:3](=[O:4])[C@H:5]([CH2:6]/[CH:7]=[CH:8]/[c:9]1[cH:10][cH:11][c:12]([N:13]([CH3:14])[c:15]2[n:16][cH:17][cH:18][cH:19][n:20]2)[cH:21][cH:22]1)[NH:23][C:24](=[O:25])[c:26]1[c:27]([Cl:28])[cH:29][cH:30][cH:31][c:32]1[Cl:33]\"}",
"reactionStep": {
"id": "sa_8662583db68bc21efc3defa7",
"reactionHash": "cb30ffcac09b980592417252de89e90d1a491b315835db28b69537c53dfb976c"
},
"children": [
{
"id": "9173",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_7d15e88f305a07142f35fa89",
"parentId": "9172",
"isLeaf": false,
"molecule": {
"id": "sa_7d15e88f305a07142f35fa89",
"inchikey": "AVQGVKMWEAEAKV-JTQLQIEISA-N",
"smiles": "C=CC[C@H](NC(=O)c1c(Cl)cccc1Cl)C(=O)OC"
},
"smiles": "C=CC[C@H](NC(=O)c1c(Cl)cccc1Cl)C(=O)OC",
"reactionStepId": "sa_822ea238931043ce14021dc4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07879837B2;0234;1047012\",\"rsmi\":\"O[CH3:19].[CH2:1]=[CH:2][CH2:3][C@H:4]([NH:5][C:6](=[O:7])[c:8]1[c:9]([Cl:10])[cH:11][cH:12][cH:13][c:14]1[Cl:15])[C:16](=[O:17])[OH:18]>O.O=C(O)O.O=S(Cl)Cl.[Na+]>[CH2:1]=[CH:2][CH2:3][C@H:4]([NH:5][C:6](=[O:7])[c:8]1[c:9]([Cl:10])[cH:11][cH:12][cH:13][c:14]1[Cl:15])[C:16](=[O:17])[O:18][CH3:19]\"},\"mapped_reaction_smiles\":\"O[CH3:19].[CH2:1]=[CH:2][CH2:3][C@H:4]([NH:5][C:6](=[O:7])[c:8]1[c:9]([Cl:10])[cH:11][cH:12][cH:13][c:14]1[Cl:15])[C:16](=[O:17])[OH:18]>O.O=C(O)O.O=S(Cl)Cl.[Na+]>[CH2:1]=[CH:2][CH2:3][C@H:4]([NH:5][C:6](=[O:7])[c:8]1[c:9]([Cl:10])[cH:11][cH:12][cH:13][c:14]1[Cl:15])[C:16](=[O:17])[O:18][CH3:19]\"}",
"reactionStep": {
"id": "sa_822ea238931043ce14021dc4",
"reactionHash": "a27c9fd6eba701c63a870187117a1e9b541c152269949c44f47daee6a392ebd6"
},
"children": [
{
"id": "9174",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "9173",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9175",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_1bf2d3e5ea8a85d68d3e0953",
"parentId": "9173",
"isLeaf": false,
"molecule": {
"id": "sa_1bf2d3e5ea8a85d68d3e0953",
"inchikey": "ZRZJBAQAKFONSV-VIFPVBQESA-N",
"smiles": "C=CC[C@H](NC(=O)c1c(Cl)cccc1Cl)C(=O)O"
},
"smiles": "C=CC[C@H](NC(=O)c1c(Cl)cccc1Cl)C(=O)O",
"reactionStepId": "sa_a9c1a824806857e7168d4db4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07879837B2;0234;1047011\",\"rsmi\":\"Cl[C:6](=[O:7])[c:8]1[c:9]([Cl:10])[cH:11][cH:12][cH:13][c:14]1[Cl:15].[CH2:1]=[CH:2][CH2:3][C@H:4]([NH2:5])[C:16](=[O:17])[OH:18]>C1CCOC1.[Na+].O>[CH2:1]=[CH:2][CH2:3][C@H:4]([NH:5][C:6](=[O:7])[c:8]1[c:9]([Cl:10])[cH:11][cH:12][cH:13][c:14]1[Cl:15])[C:16](=[O:17])[OH:18]\"},\"mapped_reaction_smiles\":\"Cl[C:6](=[O:7])[c:8]1[c:9]([Cl:10])[cH:11][cH:12][cH:13][c:14]1[Cl:15].[CH2:1]=[CH:2][CH2:3][C@H:4]([NH2:5])[C:16](=[O:17])[OH:18]>C1CCOC1.[Na+].O>[CH2:1]=[CH:2][CH2:3][C@H:4]([NH:5][C:6](=[O:7])[c:8]1[c:9]([Cl:10])[cH:11][cH:12][cH:13][c:14]1[Cl:15])[C:16](=[O:17])[OH:18]\"}",
"reactionStep": {
"id": "sa_a9c1a824806857e7168d4db4",
"reactionHash": "81e8b10d5e297a280f99abcbeb93307a4c48b50a99cac6fcc417bac5460c314d"
},
"children": [
{
"id": "9176",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_b2e418ac9b9da8b5123642f1",
"parentId": "9175",
"isLeaf": true,
"molecule": {
"id": "sa_b2e418ac9b9da8b5123642f1",
"inchikey": "JBLIDPPHFGWTKU-UHFFFAOYSA-N",
"smiles": "O=C(Cl)c1c(Cl)cccc1Cl"
},
"smiles": "O=C(Cl)c1c(Cl)cccc1Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9177",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_d8a0f5ea521229488aeefaf5",
"parentId": "9175",
"isLeaf": true,
"molecule": {
"id": "sa_d8a0f5ea521229488aeefaf5",
"inchikey": "WNNNWFKQCKFSDK-BYPYZUCNSA-N",
"smiles": "C=CC[C@H](N)C(=O)O"
},
"smiles": "C=CC[C@H](N)C(=O)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "9178",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_9a7588bb20892ed1456144f4",
"parentId": "9172",
"isLeaf": false,
"molecule": {
"id": "sa_9a7588bb20892ed1456144f4",
"inchikey": "MLNUQCMBOBZSCO-UHFFFAOYSA-N",
"smiles": "CN(c1ccc(I)cc1)c1ncccn1"
},
"smiles": "CN(c1ccc(I)cc1)c1ncccn1",
"reactionStepId": "sa_9ec995c5749e6d6d09850468",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07879837B2;0192;1046982\",\"rsmi\":\"I[CH3:1].[NH:2]([c:3]1[cH:4][cH:5][c:6]([I:7])[cH:8][cH:9]1)[c:10]1[n:11][cH:12][cH:13][cH:14][n:15]1>CN(C)C=O.O.[HH].[Na+]>[CH3:1][N:2]([c:3]1[cH:4][cH:5][c:6]([I:7])[cH:8][cH:9]1)[c:10]1[n:11][cH:12][cH:13][cH:14][n:15]1\"},\"mapped_reaction_smiles\":\"I[CH3:1].[NH:2]([c:3]1[cH:4][cH:5][c:6]([I:7])[cH:8][cH:9]1)[c:10]1[n:11][cH:12][cH:13][cH:14][n:15]1>CN(C)C=O.O.[HH].[Na+]>[CH3:1][N:2]([c:3]1[cH:4][cH:5][c:6]([I:7])[cH:8][cH:9]1)[c:10]1[n:11][cH:12][cH:13][cH:14][n:15]1\"}",
"reactionStep": {
"id": "sa_9ec995c5749e6d6d09850468",
"reactionHash": "4bf74d236a7405f1c452b32e7d419bdb0afb97a424d07ed0407d42f71e412243"
},
"children": [
{
"id": "9179",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "9178",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9180",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_08a01fd35449edaa3ab34376",
"parentId": "9178",
"isLeaf": false,
"molecule": {
"id": "sa_08a01fd35449edaa3ab34376",
"inchikey": "IYXLMKGOBQIJGM-UHFFFAOYSA-N",
"smiles": "Ic1ccc(Nc2ncccn2)cc1"
},
"smiles": "Ic1ccc(Nc2ncccn2)cc1",
"reactionStepId": "sa_f53a6bc4115457bd19cac92e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07879837B2;0188;1046980\",\"rsmi\":\"Cl[c:7]1[n:8][cH:9][cH:10][cH:11][n:12]1.[I:1][c:2]1[cH:3][cH:4][c:5]([NH2:6])[cH:13][cH:14]1>C1COCCO1.CC(=O)O.O=C(O)O.[Na+]>[I:1][c:2]1[cH:3][cH:4][c:5]([NH:6][c:7]2[n:8][cH:9][cH:10][cH:11][n:12]2)[cH:13][cH:14]1\"},\"mapped_reaction_smiles\":\"Cl[c:7]1[n:8][cH:9][cH:10][cH:11][n:12]1.[I:1][c:2]1[cH:3][cH:4][c:5]([NH2:6])[cH:13][cH:14]1>C1COCCO1.CC(=O)O.O=C(O)O.[Na+]>[I:1][c:2]1[cH:3][cH:4][c:5]([NH:6][c:7]2[n:8][cH:9][cH:10][cH:11][n:12]2)[cH:13][cH:14]1\"}",
"reactionStep": {
"id": "sa_f53a6bc4115457bd19cac92e",
"reactionHash": "993551822ecc7a7504b94708e4d1ba7d4db7172eeb0d850f590036b57e7073a8"
},
"children": [
{
"id": "9181",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_7150739dcb9903416bee8b24",
"parentId": "9180",
"isLeaf": true,
"molecule": {
"id": "sa_7150739dcb9903416bee8b24",
"inchikey": "UNCQVRBWJWWJBF-UHFFFAOYSA-N",
"smiles": "Clc1ncccn1"
},
"smiles": "Clc1ncccn1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9182",
"routeId": "sa_62fbf98346716775d39472fd",
"moleculeId": "sa_43dfbe049c501e6b2049f94e",
"parentId": "9180",
"isLeaf": true,
"molecule": {
"id": "sa_43dfbe049c501e6b2049f94e",
"inchikey": "VLVCDUSVTXIWGW-UHFFFAOYSA-N",
"smiles": "Nc1ccc(I)cc1"
},
"smiles": "Nc1ccc(I)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}