Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
O=C(NCCOc1ccc(CC(Oc2ccccc2)C(=O)O)cc1)c1ccc(-c2ccccc2)cc1
InChiKey
PHHILQDWMIGNKB-UHFFFAOYSA-N
Route Signature
8af80b798276297b72195038b5a16af37f70e3fe2d3acf0034a6c2209e4ddd29
Synthesis route with 7 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_29969af344befd38fb5eddc5",
"signature": "8af80b798276297b72195038b5a16af37f70e3fe2d3acf0034a6c2209e4ddd29",
"contentHash": "7d9a19f4d99d7978308b9577a83d7b9c07904c0be1a4c8c3dd32b675271b8396",
"length": 7,
"isConvergent": false
},
"target": {
"id": "sa_70928c2f4a513d9d753b838e",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00420",
"moleculeId": "sa_eb2af33d728d55ebe5823ffa",
"smiles": "O=C(NCCOc1ccc(CC(Oc2ccccc2)C(=O)O)cc1)c1ccc(-c2ccccc2)cc1",
"routeLength": 7,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_eb2af33d728d55ebe5823ffa",
"inchikey": "PHHILQDWMIGNKB-UHFFFAOYSA-N",
"smiles": "O=C(NCCOc1ccc(CC(Oc2ccccc2)C(=O)O)cc1)c1ccc(-c2ccccc2)cc1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "13241",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_eb2af33d728d55ebe5823ffa",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_eb2af33d728d55ebe5823ffa",
"inchikey": "PHHILQDWMIGNKB-UHFFFAOYSA-N",
"smiles": "O=C(NCCOc1ccc(CC(Oc2ccccc2)C(=O)O)cc1)c1ccc(-c2ccccc2)cc1"
},
"smiles": "O=C(NCCOc1ccc(CC(Oc2ccccc2)C(=O)O)cc1)c1ccc(-c2ccccc2)cc1",
"reactionStepId": "sa_6188ad4232abbaba7aa3829d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040006141A1;0966;123376\",\"rsmi\":\"CC[O:22][C:20]([CH:12]([CH2:11][c:10]1[cH:9][cH:8][c:7]([O:6][CH2:5][CH2:4][NH:3][C:2](=[O:1])[c:25]2[cH:26][cH:27][c:28](-[c:29]3[cH:30][cH:31][cH:32][cH:33][cH:34]3)[cH:35][cH:36]2)[cH:24][cH:23]1)[O:13][c:14]1[cH:15][cH:16][cH:17][cH:18][cH:19]1)=[O:21]>[Na+].O>[O:1]=[C:2]([NH:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][cH:9][c:10]([CH2:11][CH:12]([O:13][c:14]2[cH:15][cH:16][cH:17][cH:18][cH:19]2)[C:20](=[O:21])[OH:22])[cH:23][cH:24]1)[c:25]1[cH:26][cH:27][c:28](-[c:29]2[cH:30][cH:31][cH:32][cH:33][cH:34]2)[cH:35][cH:36]1\"},\"mapped_reaction_smiles\":\"CC[O:22][C:20]([CH:12]([CH2:11][c:10]1[cH:9][cH:8][c:7]([O:6][CH2:5][CH2:4][NH:3][C:2](=[O:1])[c:25]2[cH:26][cH:27][c:28](-[c:29]3[cH:30][cH:31][cH:32][cH:33][cH:34]3)[cH:35][cH:36]2)[cH:24][cH:23]1)[O:13][c:14]1[cH:15][cH:16][cH:17][cH:18][cH:19]1)=[O:21]>[Na+].O>[O:1]=[C:2]([NH:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][cH:9][c:10]([CH2:11][CH:12]([O:13][c:14]2[cH:15][cH:16][cH:17][cH:18][cH:19]2)[C:20](=[O:21])[OH:22])[cH:23][cH:24]1)[c:25]1[cH:26][cH:27][c:28](-[c:29]2[cH:30][cH:31][cH:32][cH:33][cH:34]2)[cH:35][cH:36]1\"}",
"reactionStep": {
"id": "sa_6188ad4232abbaba7aa3829d",
"reactionHash": "62059a31a5f82d7b37dd20011e0bcc4188c4aee547d6703fcb2c63b4ab1e273d"
},
"children": [
{
"id": "13242",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_1daa7f4895b415ae24f3b247",
"parentId": "13241",
"isLeaf": false,
"molecule": {
"id": "sa_1daa7f4895b415ae24f3b247",
"inchikey": "KWODDLWLHOFIRV-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(Cc1ccc(OCCNC(=O)c2ccc(-c3ccccc3)cc2)cc1)Oc1ccccc1"
},
"smiles": "CCOC(=O)C(Cc1ccc(OCCNC(=O)c2ccc(-c3ccccc3)cc2)cc1)Oc1ccccc1",
"reactionStepId": "sa_b37106914827e73e9a076d3a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040006141A1;0963;123375\",\"rsmi\":\"O[C:16](=[O:17])[c:18]1[cH:19][cH:20][c:21](-[c:22]2[cH:23][cH:24][cH:25][cH:26][cH:27]2)[cH:28][cH:29]1.[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][NH2:15])[cH:30][cH:31]1)[O:32][c:33]1[cH:34][cH:35][cH:36][cH:37][cH:38]1>O=C(n1ccnc1)n1ccnc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][NH:15][C:16](=[O:17])[c:18]2[cH:19][cH:20][c:21](-[c:22]3[cH:23][cH:24][cH:25][cH:26][cH:27]3)[cH:28][cH:29]2)[cH:30][cH:31]1)[O:32][c:33]1[cH:34][cH:35][cH:36][cH:37][cH:38]1\"},\"mapped_reaction_smiles\":\"O[C:16](=[O:17])[c:18]1[cH:19][cH:20][c:21](-[c:22]2[cH:23][cH:24][cH:25][cH:26][cH:27]2)[cH:28][cH:29]1.[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][NH2:15])[cH:30][cH:31]1)[O:32][c:33]1[cH:34][cH:35][cH:36][cH:37][cH:38]1>O=C(n1ccnc1)n1ccnc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][NH:15][C:16](=[O:17])[c:18]2[cH:19][cH:20][c:21](-[c:22]3[cH:23][cH:24][cH:25][cH:26][cH:27]3)[cH:28][cH:29]2)[cH:30][cH:31]1)[O:32][c:33]1[cH:34][cH:35][cH:36][cH:37][cH:38]1\"}",
"reactionStep": {
"id": "sa_b37106914827e73e9a076d3a",
"reactionHash": "b2d5e7cb189fdb027cb0ef9b1b28e40b8e18ef7e2a625a0a3bf6c173e3dc5dd1"
},
"children": [
{
"id": "13243",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_d8c48f3954264bcf3ae55ada",
"parentId": "13242",
"isLeaf": true,
"molecule": {
"id": "sa_d8c48f3954264bcf3ae55ada",
"inchikey": "NNJMFJSKMRYHSR-UHFFFAOYSA-N",
"smiles": "O=C(O)c1ccc(-c2ccccc2)cc1"
},
"smiles": "O=C(O)c1ccc(-c2ccccc2)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13244",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_4fc4937e6def4d0d7a3d6ac2",
"parentId": "13242",
"isLeaf": false,
"molecule": {
"id": "sa_4fc4937e6def4d0d7a3d6ac2",
"inchikey": "OGNIEBPUSZRWFE-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(Cc1ccc(OCCN)cc1)Oc1ccccc1"
},
"smiles": "CCOC(=O)C(Cc1ccc(OCCN)cc1)Oc1ccccc1",
"reactionStepId": "sa_a025a7a51b5a74ed68efbf77",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040006141A1;1339;123453\",\"rsmi\":\"[N-]=[N+]=[N:15][CH2:14][CH2:13][O:12][c:11]1[cH:10][cH:9][c:8]([CH2:7][CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[O:18][c:19]2[cH:20][cH:21][cH:22][cH:23][cH:24]2)[cH:17][cH:16]1>[Pd]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][NH2:15])[cH:16][cH:17]1)[O:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1\"},\"mapped_reaction_smiles\":\"[N-]=[N+]=[N:15][CH2:14][CH2:13][O:12][c:11]1[cH:10][cH:9][c:8]([CH2:7][CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[O:18][c:19]2[cH:20][cH:21][cH:22][cH:23][cH:24]2)[cH:17][cH:16]1>[Pd]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][NH2:15])[cH:16][cH:17]1)[O:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1\"}",
"reactionStep": {
"id": "sa_a025a7a51b5a74ed68efbf77",
"reactionHash": "bd6b3621cb6813fb6df1a63342f3cdc9d9df17a9c4f665fd21d8574c25e7fbb6"
},
"children": [
{
"id": "13245",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_3453ad7d3d94f54f1bd4696b",
"parentId": "13244",
"isLeaf": false,
"molecule": {
"id": "sa_3453ad7d3d94f54f1bd4696b",
"inchikey": "IVTBVBQWUNXMQJ-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(Cc1ccc(OCCN=[N+]=[N-])cc1)Oc1ccccc1"
},
"smiles": "CCOC(=O)C(Cc1ccc(OCCN=[N+]=[N-])cc1)Oc1ccccc1",
"reactionStepId": "sa_28785a4f063fdef54e162ce2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040006141A1;1336;123452\",\"rsmi\":\"CS(=O)(=O)O[CH2:14][CH2:13][O:12][c:11]1[cH:10][cH:9][c:8]([CH2:7][CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[O:20][c:21]2[cH:22][cH:23][cH:24][cH:25][cH:26]2)[cH:19][cH:18]1.[N-:15]=[N+:16]=[N-:17]>[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][N:15]=[N+:16]=[N-:17])[cH:18][cH:19]1)[O:20][c:21]1[cH:22][cH:23][cH:24][cH:25][cH:26]1\"},\"mapped_reaction_smiles\":\"CS(=O)(=O)O[CH2:14][CH2:13][O:12][c:11]1[cH:10][cH:9][c:8]([CH2:7][CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[O:20][c:21]2[cH:22][cH:23][cH:24][cH:25][cH:26]2)[cH:19][cH:18]1.[N-:15]=[N+:16]=[N-:17]>[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][N:15]=[N+:16]=[N-:17])[cH:18][cH:19]1)[O:20][c:21]1[cH:22][cH:23][cH:24][cH:25][cH:26]1\"}",
"reactionStep": {
"id": "sa_28785a4f063fdef54e162ce2",
"reactionHash": "6e4140e3be68cc51b1319b38229f4f5014df4b34486ef66f8d60fe08179a688e"
},
"children": [
{
"id": "13246",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_d9502e8408c42df12a624eba",
"parentId": "13245",
"isLeaf": false,
"molecule": {
"id": "sa_d9502e8408c42df12a624eba",
"inchikey": "HVYGZIFTTBJYNY-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(Cc1ccc(OCCOS(C)(=O)=O)cc1)Oc1ccccc1"
},
"smiles": "CCOC(=O)C(Cc1ccc(OCCOS(C)(=O)=O)cc1)Oc1ccccc1",
"reactionStepId": "sa_1cd457d6c414a33fd87bfec3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040006141A1;1333;123451\",\"rsmi\":\"Cl[S:16]([CH3:17])(=[O:18])=[O:19].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][OH:15])[cH:20][cH:21]1)[O:22][c:23]1[cH:24][cH:25][cH:26][cH:27][cH:28]1>CCN(CC)CC>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][O:15][S:16]([CH3:17])(=[O:18])=[O:19])[cH:20][cH:21]1)[O:22][c:23]1[cH:24][cH:25][cH:26][cH:27][cH:28]1\"},\"mapped_reaction_smiles\":\"Cl[S:16]([CH3:17])(=[O:18])=[O:19].[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][OH:15])[cH:20][cH:21]1)[O:22][c:23]1[cH:24][cH:25][cH:26][cH:27][cH:28]1>CCN(CC)CC>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][O:15][S:16]([CH3:17])(=[O:18])=[O:19])[cH:20][cH:21]1)[O:22][c:23]1[cH:24][cH:25][cH:26][cH:27][cH:28]1\"}",
"reactionStep": {
"id": "sa_1cd457d6c414a33fd87bfec3",
"reactionHash": "4f7007ea6e82ee05406ceab2b08292ba99456a9acdb822d91c80c94d327d28b0"
},
"children": [
{
"id": "13247",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_3eed840908a2e715f12c900b",
"parentId": "13246",
"isLeaf": false,
"molecule": {
"id": "sa_3eed840908a2e715f12c900b",
"inchikey": "JTYKJGYFFOQAEA-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(Cc1ccc(OCCO)cc1)Oc1ccccc1"
},
"smiles": "CCOC(=O)C(Cc1ccc(OCCO)cc1)Oc1ccccc1",
"reactionStepId": "sa_a18c2ec4a25decfe09b73ad6",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040006141A1;1330;123450\",\"rsmi\":\"C1CCC([O:15][CH2:14][CH2:13][O:12][c:11]2[cH:10][cH:9][c:8]([CH2:7][CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[O:18][c:19]3[cH:20][cH:21][cH:22][cH:23][cH:24]3)[cH:17][cH:16]2)OC1>Cc1ccc(S(=O)(=O)O)cc1.O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][OH:15])[cH:16][cH:17]1)[O:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1\"},\"mapped_reaction_smiles\":\"C1CCC([O:15][CH2:14][CH2:13][O:12][c:11]2[cH:10][cH:9][c:8]([CH2:7][CH:6]([C:4]([O:3][CH2:2][CH3:1])=[O:5])[O:18][c:19]3[cH:20][cH:21][cH:22][cH:23][cH:24]3)[cH:17][cH:16]2)OC1>Cc1ccc(S(=O)(=O)O)cc1.O>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][OH:15])[cH:16][cH:17]1)[O:18][c:19]1[cH:20][cH:21][cH:22][cH:23][cH:24]1\"}",
"reactionStep": {
"id": "sa_a18c2ec4a25decfe09b73ad6",
"reactionHash": "f686914e6e73a7bddf44b55ae0ad34605a5814bf268d95d5fdddd4f4fec21598"
},
"children": [
{
"id": "13248",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_e2ac2066936f84f0e35c2f1f",
"parentId": "13247",
"isLeaf": false,
"molecule": {
"id": "sa_e2ac2066936f84f0e35c2f1f",
"inchikey": "QREWUSBATUNNDG-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(Cc1ccc(OCCOC2CCCCO2)cc1)Oc1ccccc1"
},
"smiles": "CCOC(=O)C(Cc1ccc(OCCOC2CCCCO2)cc1)Oc1ccccc1",
"reactionStepId": "sa_1024aa72c6dd99652d3e9a42",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040006141A1;1327;123449\",\"rsmi\":\"Br[CH2:13][CH2:14][O:15][CH:16]1[CH2:17][CH2:18][CH2:19][CH2:20][O:21]1.[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([OH:12])[cH:22][cH:23]1)[O:24][c:25]1[cH:26][cH:27][cH:28][cH:29][cH:30]1>CC(=O)N(C)C.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][cH:23]1)[O:24][c:25]1[cH:26][cH:27][cH:28][cH:29][cH:30]1\"},\"mapped_reaction_smiles\":\"Br[CH2:13][CH2:14][O:15][CH:16]1[CH2:17][CH2:18][CH2:19][CH2:20][O:21]1.[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([OH:12])[cH:22][cH:23]1)[O:24][c:25]1[cH:26][cH:27][cH:28][cH:29][cH:30]1>CC(=O)N(C)C.O=C(O)O.[K+].[K+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]([CH2:7][c:8]1[cH:9][cH:10][c:11]([O:12][CH2:13][CH2:14][O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][cH:23]1)[O:24][c:25]1[cH:26][cH:27][cH:28][cH:29][cH:30]1\"}",
"reactionStep": {
"id": "sa_1024aa72c6dd99652d3e9a42",
"reactionHash": "f231179183cccdfb68fd3aa99d818519fd14e77ce1c467da136fffeb6b55de3b"
},
"children": [
{
"id": "13249",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_ab5122491a44b328334a01c5",
"parentId": "13248",
"isLeaf": true,
"molecule": {
"id": "sa_ab5122491a44b328334a01c5",
"inchikey": "GCUOLJOTJRUDIZ-UHFFFAOYSA-N",
"smiles": "BrCCOC1CCCCO1"
},
"smiles": "BrCCOC1CCCCO1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13250",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_87dcdb9657ac8acc06079b3b",
"parentId": "13248",
"isLeaf": true,
"molecule": {
"id": "sa_87dcdb9657ac8acc06079b3b",
"inchikey": "SWORFEYAXCYOMF-UHFFFAOYSA-N",
"smiles": "CCOC(=O)C(Cc1ccc(O)cc1)Oc1ccccc1"
},
"smiles": "CCOC(=O)C(Cc1ccc(O)cc1)Oc1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "13251",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "13246",
"isLeaf": true,
"molecule": {
"id": "sa_d2a31ea58046b00856f61ca5",
"inchikey": "QARBMVPHQWIHKH-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)Cl"
},
"smiles": "CS(=O)(=O)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "13252",
"routeId": "sa_29969af344befd38fb5eddc5",
"moleculeId": "sa_50a8f83dd89c267fbada1205",
"parentId": "13245",
"isLeaf": true,
"molecule": {
"id": "sa_50a8f83dd89c267fbada1205",
"inchikey": "IVRMZWNICZWHMI-UHFFFAOYSA-N",
"smiles": "[N]N=[N-]"
},
"smiles": "[N-]=[N+]=[N-]",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}