Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
Cc1ccc(NC(=O)c2ccccc2)cc1OCc1csc2c(C(=O)NCCO)cnc(N)c12
InChiKey
IPQWTWQLYANNDA-UHFFFAOYSA-N
Route Signature
e6e19fbdec16da3364e3cee219566e7bea132fbf8f9b94b0e61ecb4487333157
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_a72b85327b07cc67a500e979",
"signature": "e6e19fbdec16da3364e3cee219566e7bea132fbf8f9b94b0e61ecb4487333157",
"contentHash": "1a9a35b784d377facc2632c6693332e8573319307f271fe8ecb190a87858ed81",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_46a366f9bcd256370ee489d3",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-04734",
"moleculeId": "sa_d5aeed845498937be46a84b6",
"smiles": "Cc1ccc(NC(=O)c2ccccc2)cc1OCc1csc2c(C(=O)NCCO)cnc(N)c12",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_d5aeed845498937be46a84b6",
"inchikey": "IPQWTWQLYANNDA-UHFFFAOYSA-N",
"smiles": "Cc1ccc(NC(=O)c2ccccc2)cc1OCc1csc2c(C(=O)NCCO)cnc(N)c12"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "11273",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_d5aeed845498937be46a84b6",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_d5aeed845498937be46a84b6",
"inchikey": "IPQWTWQLYANNDA-UHFFFAOYSA-N",
"smiles": "Cc1ccc(NC(=O)c2ccccc2)cc1OCc1csc2c(C(=O)NCCO)cnc(N)c12"
},
"smiles": "Cc1ccc(NC(=O)c2ccccc2)cc1OCc1csc2c(C(=O)NCCO)cnc(N)c12",
"reactionStepId": "sa_199ceedeea618ed962334de5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070060607A1;0704;440936\",\"rsmi\":\"CCO[C:16]([c:15]1[c:9]2[s:8][cH:7][c:6]([CH2:5][O:4][c:3]3[c:2]([CH3:1])[cH:34][cH:33][c:23]([NH:24][C:25](=[O:26])[c:27]4[cH:28][cH:29][cH:30][cH:31][cH:32]4)[cH:22]3)[c:10]2[c:11]([NH2:12])[n:13][cH:14]1)=[O:17].[NH2:18][CH2:19][CH2:20][OH:21]>CS(C)=O>[CH3:1][c:2]1[c:3]([O:4][CH2:5][c:6]2[cH:7][s:8][c:9]3[c:10]2[c:11]([NH2:12])[n:13][cH:14][c:15]3[C:16](=[O:17])[NH:18][CH2:19][CH2:20][OH:21])[cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]2[cH:28][cH:29][cH:30][cH:31][cH:32]2)[cH:33][cH:34]1\"},\"mapped_reaction_smiles\":\"CCO[C:16]([c:15]1[c:9]2[s:8][cH:7][c:6]([CH2:5][O:4][c:3]3[c:2]([CH3:1])[cH:34][cH:33][c:23]([NH:24][C:25](=[O:26])[c:27]4[cH:28][cH:29][cH:30][cH:31][cH:32]4)[cH:22]3)[c:10]2[c:11]([NH2:12])[n:13][cH:14]1)=[O:17].[NH2:18][CH2:19][CH2:20][OH:21]>CS(C)=O>[CH3:1][c:2]1[c:3]([O:4][CH2:5][c:6]2[cH:7][s:8][c:9]3[c:10]2[c:11]([NH2:12])[n:13][cH:14][c:15]3[C:16](=[O:17])[NH:18][CH2:19][CH2:20][OH:21])[cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]2[cH:28][cH:29][cH:30][cH:31][cH:32]2)[cH:33][cH:34]1\"}",
"reactionStep": {
"id": "sa_199ceedeea618ed962334de5",
"reactionHash": "c4b873161e440f4e7c9876484db52c85b64f44d20ee9104989bd4f7ec42643d5"
},
"children": [
{
"id": "11274",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_465b8a07686da20bd4f5a4c0",
"parentId": "11273",
"isLeaf": true,
"molecule": {
"id": "sa_465b8a07686da20bd4f5a4c0",
"inchikey": "HZAXFHJVJLSVMW-UHFFFAOYSA-N",
"smiles": "NCCO"
},
"smiles": "NCCO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11275",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_f0c482f8bff7c22b844ac02b",
"parentId": "11273",
"isLeaf": false,
"molecule": {
"id": "sa_f0c482f8bff7c22b844ac02b",
"inchikey": "QUPMNDRYZNHRFO-UHFFFAOYSA-N",
"smiles": "CCOC(=O)c1cnc(N)c2c(COc3cc(NC(=O)c4ccccc4)ccc3C)csc12"
},
"smiles": "CCOC(=O)c1cnc(N)c2c(COc3cc(NC(=O)c4ccccc4)ccc3C)csc12",
"reactionStepId": "sa_21431e843c7b7cfcf90c4270",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070060607A1;0701;440935\",\"rsmi\":\"Cl[c:9]1[n:8][cH:7][c:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[c:12]2[c:11]1[c:15]([CH2:16][O:17][c:18]1[c:19]([CH3:20])[cH:21][cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]3[cH:28][cH:29][cH:30][cH:31][cH:32]3)[cH:33]1)[cH:14][s:13]2.[NH3:10]>CC(C)O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([NH2:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH2:16][O:17][c:18]1[c:19]([CH3:20])[cH:21][cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]2[cH:28][cH:29][cH:30][cH:31][cH:32]2)[cH:33]1\"},\"mapped_reaction_smiles\":\"Cl[c:9]1[n:8][cH:7][c:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[c:12]2[c:11]1[c:15]([CH2:16][O:17][c:18]1[c:19]([CH3:20])[cH:21][cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]3[cH:28][cH:29][cH:30][cH:31][cH:32]3)[cH:33]1)[cH:14][s:13]2.[NH3:10]>CC(C)O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([NH2:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH2:16][O:17][c:18]1[c:19]([CH3:20])[cH:21][cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]2[cH:28][cH:29][cH:30][cH:31][cH:32]2)[cH:33]1\"}",
"reactionStep": {
"id": "sa_21431e843c7b7cfcf90c4270",
"reactionHash": "2ed5f254fd8237663b5aa4a17ae56e8154b73d8b3b57101a1f1c36b92afd6177"
},
"children": [
{
"id": "11276",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_ceae4752e00940bd2b2eb037",
"parentId": "11275",
"isLeaf": false,
"molecule": {
"id": "sa_ceae4752e00940bd2b2eb037",
"inchikey": "LAOXBQCEPBGZME-UHFFFAOYSA-N",
"smiles": "CCOC(=O)c1cnc(Cl)c2c(COc3cc(NC(=O)c4ccccc4)ccc3C)csc12"
},
"smiles": "CCOC(=O)c1cnc(Cl)c2c(COc3cc(NC(=O)c4ccccc4)ccc3C)csc12",
"reactionStepId": "sa_058f77aaf0c22e3298145fac",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070060607A1;0700;440934\",\"rsmi\":\"Br[CH2:16][c:15]1[c:11]2[c:9]([Cl:10])[n:8][cH:7][c:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[c:12]2[s:13][cH:14]1.[OH:17][c:18]1[c:19]([CH3:20])[cH:21][cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]2[cH:28][cH:29][cH:30][cH:31][cH:32]2)[cH:33]1>C1CCOC1.CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([Cl:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH2:16][O:17][c:18]1[c:19]([CH3:20])[cH:21][cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]2[cH:28][cH:29][cH:30][cH:31][cH:32]2)[cH:33]1\"},\"mapped_reaction_smiles\":\"Br[CH2:16][c:15]1[c:11]2[c:9]([Cl:10])[n:8][cH:7][c:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[c:12]2[s:13][cH:14]1.[OH:17][c:18]1[c:19]([CH3:20])[cH:21][cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]2[cH:28][cH:29][cH:30][cH:31][cH:32]2)[cH:33]1>C1CCOC1.CN(C)C=O.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([Cl:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH2:16][O:17][c:18]1[c:19]([CH3:20])[cH:21][cH:22][c:23]([NH:24][C:25](=[O:26])[c:27]2[cH:28][cH:29][cH:30][cH:31][cH:32]2)[cH:33]1\"}",
"reactionStep": {
"id": "sa_058f77aaf0c22e3298145fac",
"reactionHash": "6ecc012e80a55d6084aa1507c4d5e094a408386c4e56c5723d8ebb33b9ce87a4"
},
"children": [
{
"id": "11277",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_df041ec9b3caee1d5a17ffe1",
"parentId": "11276",
"isLeaf": false,
"molecule": {
"id": "sa_df041ec9b3caee1d5a17ffe1",
"inchikey": "HOWNDUOBCWJDQY-UHFFFAOYSA-N",
"smiles": "Cc1ccc(NC(=O)c2ccccc2)cc1O"
},
"smiles": "Cc1ccc(NC(=O)c2ccccc2)cc1O",
"reactionStepId": "sa_37437aa2a329a6587978915f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070060607A1;0699;440933\",\"rsmi\":\"Cl[C:8](=[O:9])[c:10]1[cH:11][cH:12][cH:13][cH:14][cH:15]1.[CH3:1][c:2]1[c:3]([OH:4])[cH:5][c:6]([NH2:7])[cH:16][cH:17]1>C1CCOC1.CCN(CC)CC.CO.O.[Na+].O>[CH3:1][c:2]1[c:3]([OH:4])[cH:5][c:6]([NH:7][C:8](=[O:9])[c:10]2[cH:11][cH:12][cH:13][cH:14][cH:15]2)[cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"Cl[C:8](=[O:9])[c:10]1[cH:11][cH:12][cH:13][cH:14][cH:15]1.[CH3:1][c:2]1[c:3]([OH:4])[cH:5][c:6]([NH2:7])[cH:16][cH:17]1>C1CCOC1.CCN(CC)CC.CO.O.[Na+].O>[CH3:1][c:2]1[c:3]([OH:4])[cH:5][c:6]([NH:7][C:8](=[O:9])[c:10]2[cH:11][cH:12][cH:13][cH:14][cH:15]2)[cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_37437aa2a329a6587978915f",
"reactionHash": "998004eb39ae14e9bd9f5b091ca8a3c94b7bf84a3d17b85f283e5196cb25a957"
},
"children": [
{
"id": "11278",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_b131fd2d7e407143e967c956",
"parentId": "11277",
"isLeaf": true,
"molecule": {
"id": "sa_b131fd2d7e407143e967c956",
"inchikey": "DBFYESDCPWWCHN-UHFFFAOYSA-N",
"smiles": "Cc1ccc(N)cc1O"
},
"smiles": "Cc1ccc(N)cc1O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11279",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_ece938eaaf00d311129c8f06",
"parentId": "11277",
"isLeaf": true,
"molecule": {
"id": "sa_ece938eaaf00d311129c8f06",
"inchikey": "PASDCCFISLVPSO-UHFFFAOYSA-N",
"smiles": "O=C(Cl)c1ccccc1"
},
"smiles": "O=C(Cl)c1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "11280",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_40337abd21ee1ea9418f20df",
"parentId": "11276",
"isLeaf": false,
"molecule": {
"id": "sa_40337abd21ee1ea9418f20df",
"inchikey": "LXLXFZVZXDUUSO-UHFFFAOYSA-N",
"smiles": "CCOC(=O)c1cnc(Cl)c2c(CBr)csc12"
},
"smiles": "CCOC(=O)c1cnc(Cl)c2c(CBr)csc12",
"reactionStepId": "sa_19efb994dc8f50565fa2cac1",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070060607A1;0209;440821\",\"rsmi\":\"O=C1CCC(=O)N1[Br:17].[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([Cl:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH3:16]>CC(C)(C#N)N=NC(C)(C)C#N.ClC(Cl)(Cl)Cl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([Cl:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH2:16][Br:17]\"},\"mapped_reaction_smiles\":\"O=C1CCC(=O)N1[Br:17].[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([Cl:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH3:16]>CC(C)(C#N)N=NC(C)(C)C#N.ClC(Cl)(Cl)Cl>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([Cl:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH2:16][Br:17]\"}",
"reactionStep": {
"id": "sa_19efb994dc8f50565fa2cac1",
"reactionHash": "49720a21e67e4e192fc1724e93b6f3285ab1086f6db41b5168d0e91489f9c165"
},
"children": [
{
"id": "11281",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_a36f2ce3c2bf4075080caed3",
"parentId": "11280",
"isLeaf": false,
"molecule": {
"id": "sa_a36f2ce3c2bf4075080caed3",
"inchikey": "OGGMPOZTPMKXCG-UHFFFAOYSA-N",
"smiles": "CCOC(=O)c1cnc(Cl)c2c(C)csc12"
},
"smiles": "CCOC(=O)c1cnc(Cl)c2c(C)csc12",
"reactionStepId": "sa_febc8535d593e7b550212b00",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070060607A1;0206;440820\",\"rsmi\":\"O=P(Cl)(Cl)[Cl:10].O=[c:9]1[nH:8][cH:7][c:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[c:12]2[c:11]1[c:15]([CH3:16])[cH:14][s:13]2>CCN(C(C)C)C(C)C.CN(C)C=O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([Cl:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH3:16]\"},\"mapped_reaction_smiles\":\"O=P(Cl)(Cl)[Cl:10].O=[c:9]1[nH:8][cH:7][c:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[c:12]2[c:11]1[c:15]([CH3:16])[cH:14][s:13]2>CCN(C(C)C)C(C)C.CN(C)C=O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[c:6]1[cH:7][n:8][c:9]([Cl:10])[c:11]2[c:12]1[s:13][cH:14][c:15]2[CH3:16]\"}",
"reactionStep": {
"id": "sa_febc8535d593e7b550212b00",
"reactionHash": "5638863c1de4465bd275a4538fd1ccf5d55da0afe5d7981b8f84d67354009b49"
},
"children": [
{
"id": "11282",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_312a7cd3d48a055e9bc98180",
"parentId": "11281",
"isLeaf": true,
"molecule": {
"id": "sa_312a7cd3d48a055e9bc98180",
"inchikey": "XHXFXVLFKHQFAL-UHFFFAOYSA-N",
"smiles": "O=P(Cl)(Cl)Cl"
},
"smiles": "O=P(Cl)(Cl)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "11283",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_1091600c05248bce0cb31cff",
"parentId": "11281",
"isLeaf": true,
"molecule": {
"id": "sa_1091600c05248bce0cb31cff",
"inchikey": "ZQIKCKYDCDCDJE-UHFFFAOYSA-N",
"smiles": "CCOC(=O)c1c[nH]c(=O)c2c(C)csc12"
},
"smiles": "CCOC(=O)c1c[nH]c(=O)c2c(C)csc12",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "11284",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_ccdcf23ac83e7a68bfa4f2e5",
"parentId": "11280",
"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": "11285",
"routeId": "sa_a72b85327b07cc67a500e979",
"moleculeId": "sa_c9679fdd876f32f86b77fb69",
"parentId": "11275",
"isLeaf": true,
"molecule": {
"id": "sa_c9679fdd876f32f86b77fb69",
"inchikey": "QGZKDVFQNNGYKY-UHFFFAOYSA-N",
"smiles": "N"
},
"smiles": "N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}