Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1ccc([C@@H]2C[C@H]2NC(=O)CCC[C@H](NC(=O)c2ccc(F)cc2)C(=O)N2CCN(C)CC2)cc1
InChiKey
ZXHTWBBJIBBTTM-CCDWMCETSA-N
Route Signature
2cfe63deb68d58bf1b7cf9437f1243678d10106e38afab6b913e607dc89e5a0b
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_ca9172b4ed9f48e2f9e9a154",
"signature": "2cfe63deb68d58bf1b7cf9437f1243678d10106e38afab6b913e607dc89e5a0b",
"contentHash": "2f285df59264d63a66edfaac23248d6addc2baa9fd15285c91a9fbb926389265",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_2f6bd69f29d6bf6834e012d2",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00797",
"moleculeId": "sa_471876e8bc1b85960deb6a1d",
"smiles": "COc1ccc([C@@H]2C[C@H]2NC(=O)CCC[C@H](NC(=O)c2ccc(F)cc2)C(=O)N2CCN(C)CC2)cc1",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_471876e8bc1b85960deb6a1d",
"inchikey": "ZXHTWBBJIBBTTM-CCDWMCETSA-N",
"smiles": "COc1ccc([C@@H]2C[C@H]2NC(=O)CCC[C@H](NC(=O)c2ccc(F)cc2)C(=O)N2CCN(C)CC2)cc1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9756",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_471876e8bc1b85960deb6a1d",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_471876e8bc1b85960deb6a1d",
"inchikey": "ZXHTWBBJIBBTTM-CCDWMCETSA-N",
"smiles": "COc1ccc([C@@H]2C[C@H]2NC(=O)CCC[C@H](NC(=O)c2ccc(F)cc2)C(=O)N2CCN(C)CC2)cc1"
},
"smiles": "COc1ccc([C@@H]2C[C@H]2NC(=O)CCC[C@H](NC(=O)c2ccc(F)cc2)C(=O)N2CCN(C)CC2)cc1",
"reactionStepId": "sa_7d29ae15432ea0de82594476",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160257662A1;0326;1931223\",\"rsmi\":\"O[C:11](=[O:12])[CH2:13][CH2:14][CH2:15][C@H:16]([NH:17][C:18](=[O:19])[c:20]1[cH:21][cH:22][c:23]([F:24])[cH:25][cH:26]1)[C:27](=[O:28])[N:29]1[CH2:30][CH2:31][N:32]([CH3:33])[CH2:34][CH2:35]1.[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]2[CH2:8][C@H:9]2[NH2:10])[cH:36][cH:37]1>CCN(C(C)C)C(C)C.CN(C)C(On1nnc2cccnc21)=[N+](C)C.CN(C)C=O.F[PH](F)(F)(F)(F)F>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]2[CH2:8][C@H:9]2[NH:10][C:11](=[O:12])[CH2:13][CH2:14][CH2:15][C@H:16]([NH:17][C:18](=[O:19])[c:20]2[cH:21][cH:22][c:23]([F:24])[cH:25][cH:26]2)[C:27](=[O:28])[N:29]2[CH2:30][CH2:31][N:32]([CH3:33])[CH2:34][CH2:35]2)[cH:36][cH:37]1\"},\"mapped_reaction_smiles\":\"O[C:11](=[O:12])[CH2:13][CH2:14][CH2:15][C@H:16]([NH:17][C:18](=[O:19])[c:20]1[cH:21][cH:22][c:23]([F:24])[cH:25][cH:26]1)[C:27](=[O:28])[N:29]1[CH2:30][CH2:31][N:32]([CH3:33])[CH2:34][CH2:35]1.[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]2[CH2:8][C@H:9]2[NH2:10])[cH:36][cH:37]1>CCN(C(C)C)C(C)C.CN(C)C(On1nnc2cccnc21)=[N+](C)C.CN(C)C=O.F[PH](F)(F)(F)(F)F>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]2[CH2:8][C@H:9]2[NH:10][C:11](=[O:12])[CH2:13][CH2:14][CH2:15][C@H:16]([NH:17][C:18](=[O:19])[c:20]2[cH:21][cH:22][c:23]([F:24])[cH:25][cH:26]2)[C:27](=[O:28])[N:29]2[CH2:30][CH2:31][N:32]([CH3:33])[CH2:34][CH2:35]2)[cH:36][cH:37]1\"}",
"reactionStep": {
"id": "sa_7d29ae15432ea0de82594476",
"reactionHash": "9cc788814cddb116bed03ce44258a64aa6b3e55c1eaffbcc2e102ddf8cae29e7"
},
"children": [
{
"id": "9757",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_646f5453d73e6723cd5a2d9d",
"parentId": "9756",
"isLeaf": false,
"molecule": {
"id": "sa_646f5453d73e6723cd5a2d9d",
"inchikey": "SCLDJNREJBDLHE-VHSXEESVSA-N",
"smiles": "COc1ccc([C@@H]2C[C@H]2N)cc1"
},
"smiles": "COc1ccc([C@@H]2C[C@H]2N)cc1",
"reactionStepId": "sa_70367ba73e2c8cfcb583aae9",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160257662A1;0323;1931221\",\"rsmi\":\"CC(C)(C)OC(=O)[NH:10][C@H:9]1[C@H:7]([c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:12][cH:11]2)[CH2:8]1>CO.Cl>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]2[CH2:8][C@H:9]2[NH2:10])[cH:11][cH:12]1\"},\"mapped_reaction_smiles\":\"CC(C)(C)OC(=O)[NH:10][C@H:9]1[C@H:7]([c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:12][cH:11]2)[CH2:8]1>CO.Cl>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6]([C@@H:7]2[CH2:8][C@H:9]2[NH2:10])[cH:11][cH:12]1\"}",
"reactionStep": {
"id": "sa_70367ba73e2c8cfcb583aae9",
"reactionHash": "aa531c026ee934b9dc8279a7bcc9febf17bbae4361b67bc43bbd679922e9b26e"
},
"children": [
{
"id": "9758",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_239512150815946b066a73ac",
"parentId": "9757",
"isLeaf": true,
"molecule": {
"id": "sa_239512150815946b066a73ac",
"inchikey": "VHWVDHHLVMLLHB-QWHCGFSZSA-N",
"smiles": "COc1ccc([C@@H]2C[C@H]2NC(=O)OC(C)(C)C)cc1"
},
"smiles": "COc1ccc([C@@H]2C[C@H]2NC(=O)OC(C)(C)C)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "9759",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_5626342e1156215c8f518489",
"parentId": "9756",
"isLeaf": false,
"molecule": {
"id": "sa_5626342e1156215c8f518489",
"inchikey": "YJMCCHNSFMDJMR-HNNXBMFYSA-N",
"smiles": "CN1CCN(C(=O)[C@H](CCCC(=O)O)NC(=O)c2ccc(F)cc2)CC1"
},
"smiles": "CN1CCN(C(=O)[C@H](CCCC(=O)O)NC(=O)c2ccc(F)cc2)CC1",
"reactionStepId": "sa_503ceb77dcd904b27b17c520",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160257662A1;0314;1931214\",\"rsmi\":\"C[O:14][C:12]([CH2:11][CH2:10][CH2:9][C@@H:8]([C:6]([N:5]1[CH2:4][CH2:3][N:2]([CH3:1])[CH2:26][CH2:25]1)=[O:7])[NH:15][C:16](=[O:17])[c:18]1[cH:19][cH:20][c:21]([F:22])[cH:23][cH:24]1)=[O:13]>C1CCOC1.O.[Li+].O>[CH3:1][N:2]1[CH2:3][CH2:4][N:5]([C:6](=[O:7])[C@H:8]([CH2:9][CH2:10][CH2:11][C:12](=[O:13])[OH:14])[NH:15][C:16](=[O:17])[c:18]2[cH:19][cH:20][c:21]([F:22])[cH:23][cH:24]2)[CH2:25][CH2:26]1\"},\"mapped_reaction_smiles\":\"C[O:14][C:12]([CH2:11][CH2:10][CH2:9][C@@H:8]([C:6]([N:5]1[CH2:4][CH2:3][N:2]([CH3:1])[CH2:26][CH2:25]1)=[O:7])[NH:15][C:16](=[O:17])[c:18]1[cH:19][cH:20][c:21]([F:22])[cH:23][cH:24]1)=[O:13]>C1CCOC1.O.[Li+].O>[CH3:1][N:2]1[CH2:3][CH2:4][N:5]([C:6](=[O:7])[C@H:8]([CH2:9][CH2:10][CH2:11][C:12](=[O:13])[OH:14])[NH:15][C:16](=[O:17])[c:18]2[cH:19][cH:20][c:21]([F:22])[cH:23][cH:24]2)[CH2:25][CH2:26]1\"}",
"reactionStep": {
"id": "sa_503ceb77dcd904b27b17c520",
"reactionHash": "8267ebeb6372f4a8efd1d82fe79ad8e028a96ac8d0294bd4cbc948aab06e1277"
},
"children": [
{
"id": "9760",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_ef5df0840b4f4c8184609a56",
"parentId": "9759",
"isLeaf": false,
"molecule": {
"id": "sa_ef5df0840b4f4c8184609a56",
"inchikey": "YLDBKOHERYEFBK-INIZCTEOSA-N",
"smiles": "COC(=O)CCC[C@H](NC(=O)c1ccc(F)cc1)C(=O)N1CCN(C)CC1"
},
"smiles": "COC(=O)CCC[C@H](NC(=O)c1ccc(F)cc1)C(=O)N1CCN(C)CC1",
"reactionStepId": "sa_af0c36425d6488b128dd5bf9",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160257662A1;0313;1931213\",\"rsmi\":\"O[C:19]([C@H:8]([CH2:7][CH2:6][CH2:5][C:3]([O:2][CH3:1])=[O:4])[NH:9][C:10](=[O:11])[c:12]1[cH:13][cH:14][c:15]([F:16])[cH:17][cH:18]1)=[O:20].[NH:21]1[CH2:22][CH2:23][N:24]([CH3:25])[CH2:26][CH2:27]1>C1CCOC1.CCOP(=O)(OCC)On1nnc2ccccc2c1=O.O=P(O)(O)O.[K+].c1c[nH]cn1>[CH3:1][O:2][C:3](=[O:4])[CH2:5][CH2:6][CH2:7][C@H:8]([NH:9][C:10](=[O:11])[c:12]1[cH:13][cH:14][c:15]([F:16])[cH:17][cH:18]1)[C:19](=[O:20])[N:21]1[CH2:22][CH2:23][N:24]([CH3:25])[CH2:26][CH2:27]1\"},\"mapped_reaction_smiles\":\"O[C:19]([C@H:8]([CH2:7][CH2:6][CH2:5][C:3]([O:2][CH3:1])=[O:4])[NH:9][C:10](=[O:11])[c:12]1[cH:13][cH:14][c:15]([F:16])[cH:17][cH:18]1)=[O:20].[NH:21]1[CH2:22][CH2:23][N:24]([CH3:25])[CH2:26][CH2:27]1>C1CCOC1.CCOP(=O)(OCC)On1nnc2ccccc2c1=O.O=P(O)(O)O.[K+].c1c[nH]cn1>[CH3:1][O:2][C:3](=[O:4])[CH2:5][CH2:6][CH2:7][C@H:8]([NH:9][C:10](=[O:11])[c:12]1[cH:13][cH:14][c:15]([F:16])[cH:17][cH:18]1)[C:19](=[O:20])[N:21]1[CH2:22][CH2:23][N:24]([CH3:25])[CH2:26][CH2:27]1\"}",
"reactionStep": {
"id": "sa_af0c36425d6488b128dd5bf9",
"reactionHash": "cab010ced988023e91a4bb4b2383991fd0df8ced37dd2e3b5e841973202adb48"
},
"children": [
{
"id": "9761",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_b062d42bb85c224c039a43d2",
"parentId": "9760",
"isLeaf": false,
"molecule": {
"id": "sa_b062d42bb85c224c039a43d2",
"inchikey": "PCKMHXIQAXLIGX-NSHDSACASA-N",
"smiles": "COC(=O)CCC[C@H](NC(=O)c1ccc(F)cc1)C(=O)O"
},
"smiles": "COC(=O)CCC[C@H](NC(=O)c1ccc(F)cc1)C(=O)O",
"reactionStepId": "sa_ab0cd4455bbc7e8cec6923bc",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160257662A1;0307;1931209\",\"rsmi\":\"O[CH3:1].[OH:2][C:3](=[O:4])[CH2:5][CH2:6][CH2:7][C@H:8]([NH:9][C:10](=[O:11])[c:12]1[cH:13][cH:14][c:15]([F:16])[cH:17][cH:18]1)[C:19](=[O:20])[OH:21]>CC(=O)Cl.O=C(O)O.[Na+].[Na+]>[CH3:1][O:2][C:3](=[O:4])[CH2:5][CH2:6][CH2:7][C@H:8]([NH:9][C:10](=[O:11])[c:12]1[cH:13][cH:14][c:15]([F:16])[cH:17][cH:18]1)[C:19](=[O:20])[OH:21]\"},\"mapped_reaction_smiles\":\"O[CH3:1].[OH:2][C:3](=[O:4])[CH2:5][CH2:6][CH2:7][C@H:8]([NH:9][C:10](=[O:11])[c:12]1[cH:13][cH:14][c:15]([F:16])[cH:17][cH:18]1)[C:19](=[O:20])[OH:21]>CC(=O)Cl.O=C(O)O.[Na+].[Na+]>[CH3:1][O:2][C:3](=[O:4])[CH2:5][CH2:6][CH2:7][C@H:8]([NH:9][C:10](=[O:11])[c:12]1[cH:13][cH:14][c:15]([F:16])[cH:17][cH:18]1)[C:19](=[O:20])[OH:21]\"}",
"reactionStep": {
"id": "sa_ab0cd4455bbc7e8cec6923bc",
"reactionHash": "68e8432f5f8ae9628390944b01de44bacbabd3e1aa294c328671226afc1b7dd5"
},
"children": [
{
"id": "9762",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_81b244236a2cccc8797bd2ad",
"parentId": "9761",
"isLeaf": false,
"molecule": {
"id": "sa_81b244236a2cccc8797bd2ad",
"inchikey": "JRYDLSUROLXRNI-JTQLQIEISA-N",
"smiles": "O=C(O)CCC[C@H](NC(=O)c1ccc(F)cc1)C(=O)O"
},
"smiles": "O=C(O)CCC[C@H](NC(=O)c1ccc(F)cc1)C(=O)O",
"reactionStepId": "sa_224d78466074985148ccdccb",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160257662A1;0306;1931208\",\"rsmi\":\"Cl[C:9](=[O:10])[c:11]1[cH:12][cH:13][c:14]([F:15])[cH:16][cH:17]1.[O:1]=[C:2]([OH:3])[CH2:4][CH2:5][CH2:6][C@H:7]([NH2:8])[C:18](=[O:19])[OH:20]>C1COCCO1.Cl.O.O=C(O)O.[Na+].[Na+]>[O:1]=[C:2]([OH:3])[CH2:4][CH2:5][CH2:6][C@H:7]([NH:8][C:9](=[O:10])[c:11]1[cH:12][cH:13][c:14]([F:15])[cH:16][cH:17]1)[C:18](=[O:19])[OH:20]\"},\"mapped_reaction_smiles\":\"Cl[C:9](=[O:10])[c:11]1[cH:12][cH:13][c:14]([F:15])[cH:16][cH:17]1.[O:1]=[C:2]([OH:3])[CH2:4][CH2:5][CH2:6][C@H:7]([NH2:8])[C:18](=[O:19])[OH:20]>C1COCCO1.Cl.O.O=C(O)O.[Na+].[Na+]>[O:1]=[C:2]([OH:3])[CH2:4][CH2:5][CH2:6][C@H:7]([NH:8][C:9](=[O:10])[c:11]1[cH:12][cH:13][c:14]([F:15])[cH:16][cH:17]1)[C:18](=[O:19])[OH:20]\"}",
"reactionStep": {
"id": "sa_224d78466074985148ccdccb",
"reactionHash": "3eea1711f3447387e498453c0fa10922671335d26500730c3573c3c072df8ba1"
},
"children": [
{
"id": "9763",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_e2962f094d8c27c0d938f2cd",
"parentId": "9762",
"isLeaf": true,
"molecule": {
"id": "sa_e2962f094d8c27c0d938f2cd",
"inchikey": "CZKLEJHVLCMVQR-UHFFFAOYSA-N",
"smiles": "O=C(Cl)c1ccc(F)cc1"
},
"smiles": "O=C(Cl)c1ccc(F)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9764",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_0a9556dbe3b0de4c155e2596",
"parentId": "9762",
"isLeaf": true,
"molecule": {
"id": "sa_0a9556dbe3b0de4c155e2596",
"inchikey": "OYIFNHCXNCRBQI-BYPYZUCNSA-N",
"smiles": "N[C@@H](CCCC(=O)O)C(=O)O"
},
"smiles": "N[C@@H](CCCC(=O)O)C(=O)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "9765",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "9761",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "9766",
"routeId": "sa_ca9172b4ed9f48e2f9e9a154",
"moleculeId": "sa_513cbf1b8d13aff0b62eb838",
"parentId": "9760",
"isLeaf": true,
"molecule": {
"id": "sa_513cbf1b8d13aff0b62eb838",
"inchikey": "PVOAHINGSUIXLS-UHFFFAOYSA-N",
"smiles": "CN1CCNCC1"
},
"smiles": "CN1CCNCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}