Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CCCCCN(Cc1ccc(OCC(=O)O)c(C)c1)c1cccc(-c2ccc(C(F)(F)F)cc2)c1
InChiKey
PEAWRZYPKVFBPF-UHFFFAOYSA-N
Route Signature
e7809116ba67e7536877d710b859cc8a02e398155d65e56ad58c3aeb244d4695
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_2a55e552b1ecc5d7656ee8db",
"signature": "e7809116ba67e7536877d710b859cc8a02e398155d65e56ad58c3aeb244d4695",
"contentHash": "87a512c6f365eb8efb2efca8440b7a26d8138e77b3a839673cbd52f1cd86939d",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_a891c1e4bde67e17a1325fa5",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00369",
"moleculeId": "sa_1a4e75d7110aefe27bf3ddea",
"smiles": "CCCCCN(Cc1ccc(OCC(=O)O)c(C)c1)c1cccc(-c2ccc(C(F)(F)F)cc2)c1",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_1a4e75d7110aefe27bf3ddea",
"inchikey": "PEAWRZYPKVFBPF-UHFFFAOYSA-N",
"smiles": "CCCCCN(Cc1ccc(OCC(=O)O)c(C)c1)c1cccc(-c2ccc(C(F)(F)F)cc2)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "651",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_1a4e75d7110aefe27bf3ddea",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_1a4e75d7110aefe27bf3ddea",
"inchikey": "PEAWRZYPKVFBPF-UHFFFAOYSA-N",
"smiles": "CCCCCN(Cc1ccc(OCC(=O)O)c(C)c1)c1cccc(-c2ccc(C(F)(F)F)cc2)c1"
},
"smiles": "CCCCCN(Cc1ccc(OCC(=O)O)c(C)c1)c1cccc(-c2ccc(C(F)(F)F)cc2)c1",
"reactionStepId": "sa_5d55fcacd776d35480979f84",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060074111A1;0479;338742\",\"rsmi\":\"CC[O:17][C:15]([CH2:14][O:13][c:12]1[c:10]([CH3:11])[cH:9][c:8]([CH2:7][N:6]([CH2:5][CH2:4][CH2:3][CH2:2][CH3:1])[c:20]2[cH:21][cH:22][cH:23][c:24](-[c:25]3[cH:26][cH:27][c:28]([C:29]([F:30])([F:31])[F:32])[cH:33][cH:34]3)[cH:35]2)[cH:19][cH:18]1)=[O:16]>C1CCOC1.CO.[Na+].O>[CH3:1][CH2:2][CH2:3][CH2:4][CH2:5][N:6]([CH2:7][c:8]1[cH:9][c:10]([CH3:11])[c:12]([O:13][CH2:14][C:15](=[O:16])[OH:17])[cH:18][cH:19]1)[c:20]1[cH:21][cH:22][cH:23][c:24](-[c:25]2[cH:26][cH:27][c:28]([C:29]([F:30])([F:31])[F:32])[cH:33][cH:34]2)[cH:35]1\"},\"mapped_reaction_smiles\":\"CC[O:17][C:15]([CH2:14][O:13][c:12]1[c:10]([CH3:11])[cH:9][c:8]([CH2:7][N:6]([CH2:5][CH2:4][CH2:3][CH2:2][CH3:1])[c:20]2[cH:21][cH:22][cH:23][c:24](-[c:25]3[cH:26][cH:27][c:28]([C:29]([F:30])([F:31])[F:32])[cH:33][cH:34]3)[cH:35]2)[cH:19][cH:18]1)=[O:16]>C1CCOC1.CO.[Na+].O>[CH3:1][CH2:2][CH2:3][CH2:4][CH2:5][N:6]([CH2:7][c:8]1[cH:9][c:10]([CH3:11])[c:12]([O:13][CH2:14][C:15](=[O:16])[OH:17])[cH:18][cH:19]1)[c:20]1[cH:21][cH:22][cH:23][c:24](-[c:25]2[cH:26][cH:27][c:28]([C:29]([F:30])([F:31])[F:32])[cH:33][cH:34]2)[cH:35]1\"}",
"reactionStep": {
"id": "sa_5d55fcacd776d35480979f84",
"reactionHash": "98d10cc87e564b1fe94151eb3c80ee8acd8ccc983937853996b0e549ddb58d02"
},
"children": [
{
"id": "652",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_fb4314008c605937692ee0ae",
"parentId": "651",
"isLeaf": false,
"molecule": {
"id": "sa_fb4314008c605937692ee0ae",
"inchikey": "OZZCTIIDZSKGRP-UHFFFAOYSA-N",
"smiles": "CCCCCN(Cc1ccc(OCC(=O)OCC)c(C)c1)c1cccc(-c2ccc(C(F)(F)F)cc2)c1"
},
"smiles": "CCCCCN(Cc1ccc(OCC(=O)OCC)c(C)c1)c1cccc(-c2ccc(C(F)(F)F)cc2)c1",
"reactionStepId": "sa_a5a7fdfa8ed04fb341845bf7",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060074111A1;0234;338674\",\"rsmi\":\"Br[CH2:7][c:8]1[cH:9][c:10]([CH3:11])[c:12]([O:13][CH2:14][C:15](=[O:16])[O:17][CH2:18][CH3:19])[cH:20][cH:21]1.[CH3:1][CH2:2][CH2:3][CH2:4][CH2:5][NH:6][c:22]1[cH:23][cH:24][cH:25][c:26](-[c:27]2[cH:28][cH:29][c:30]([C:31]([F:32])([F:33])[F:34])[cH:35][cH:36]2)[cH:37]1>CC#N.CCN(C(C)C)C(C)C>[CH3:1][CH2:2][CH2:3][CH2:4][CH2:5][N:6]([CH2:7][c:8]1[cH:9][c:10]([CH3:11])[c:12]([O:13][CH2:14][C:15](=[O:16])[O:17][CH2:18][CH3:19])[cH:20][cH:21]1)[c:22]1[cH:23][cH:24][cH:25][c:26](-[c:27]2[cH:28][cH:29][c:30]([C:31]([F:32])([F:33])[F:34])[cH:35][cH:36]2)[cH:37]1\"},\"mapped_reaction_smiles\":\"Br[CH2:7][c:8]1[cH:9][c:10]([CH3:11])[c:12]([O:13][CH2:14][C:15](=[O:16])[O:17][CH2:18][CH3:19])[cH:20][cH:21]1.[CH3:1][CH2:2][CH2:3][CH2:4][CH2:5][NH:6][c:22]1[cH:23][cH:24][cH:25][c:26](-[c:27]2[cH:28][cH:29][c:30]([C:31]([F:32])([F:33])[F:34])[cH:35][cH:36]2)[cH:37]1>CC#N.CCN(C(C)C)C(C)C>[CH3:1][CH2:2][CH2:3][CH2:4][CH2:5][N:6]([CH2:7][c:8]1[cH:9][c:10]([CH3:11])[c:12]([O:13][CH2:14][C:15](=[O:16])[O:17][CH2:18][CH3:19])[cH:20][cH:21]1)[c:22]1[cH:23][cH:24][cH:25][c:26](-[c:27]2[cH:28][cH:29][c:30]([C:31]([F:32])([F:33])[F:34])[cH:35][cH:36]2)[cH:37]1\"}",
"reactionStep": {
"id": "sa_a5a7fdfa8ed04fb341845bf7",
"reactionHash": "28df50657fa1f8a69184292a96ffcee0554c6075f1cab4c852d8c440be2f7caf"
},
"children": [
{
"id": "653",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_edae74a35568e48aeb3aff60",
"parentId": "652",
"isLeaf": false,
"molecule": {
"id": "sa_edae74a35568e48aeb3aff60",
"inchikey": "LFQVAPPPNNRBAH-UHFFFAOYSA-N",
"smiles": "CCOC(=O)COc1ccc(CBr)cc1C"
},
"smiles": "CCOC(=O)COc1ccc(CBr)cc1C",
"reactionStepId": "sa_c9634f5b8e987de4079d9272",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060074111A1;0203;338664\",\"rsmi\":\"BrC(Br)(Br)[Br:14].O[CH2:13][c:12]1[cH:11][c:9]([CH3:10])[c:8]([O:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])[cH:16][cH:15]1>ClCCl.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[c:9]([CH3:10])[cH:11][c:12]([CH2:13][Br:14])[cH:15][cH:16]1\"},\"mapped_reaction_smiles\":\"BrC(Br)(Br)[Br:14].O[CH2:13][c:12]1[cH:11][c:9]([CH3:10])[c:8]([O:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5])[cH:16][cH:15]1>ClCCl.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[c:9]([CH3:10])[cH:11][c:12]([CH2:13][Br:14])[cH:15][cH:16]1\"}",
"reactionStep": {
"id": "sa_c9634f5b8e987de4079d9272",
"reactionHash": "4938995dade2649494f3e8ceceec5f7d2cc8245f3770240dbf121a529a3eff83"
},
"children": [
{
"id": "654",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_58b67f497826131e21b7cfb1",
"parentId": "653",
"isLeaf": false,
"molecule": {
"id": "sa_58b67f497826131e21b7cfb1",
"inchikey": "AFFKOLQGRWKEBK-UHFFFAOYSA-N",
"smiles": "CCOC(=O)COc1ccc(CO)cc1C"
},
"smiles": "CCOC(=O)COc1ccc(CO)cc1C",
"reactionStepId": "sa_ddd50c53eea53eae3c6a07a8",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060074111A1;0197;338663\",\"rsmi\":\"Br[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:7][c:8]1[c:9]([CH3:10])[cH:11][c:12]([CH2:13][OH:14])[cH:15][cH:16]1>CC#N.O.O=C(O)O.[Cs+].[Cs+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[c:9]([CH3:10])[cH:11][c:12]([CH2:13][OH:14])[cH:15][cH:16]1\"},\"mapped_reaction_smiles\":\"Br[CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:7][c:8]1[c:9]([CH3:10])[cH:11][c:12]([CH2:13][OH:14])[cH:15][cH:16]1>CC#N.O.O=C(O)O.[Cs+].[Cs+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][O:7][c:8]1[c:9]([CH3:10])[cH:11][c:12]([CH2:13][OH:14])[cH:15][cH:16]1\"}",
"reactionStep": {
"id": "sa_ddd50c53eea53eae3c6a07a8",
"reactionHash": "319db0bc283f516b680c0aa6fd37a146b8b05db04fe7335ae31d50011f2d2607"
},
"children": [
{
"id": "655",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_275a06f193912d6dd7fff734",
"parentId": "654",
"isLeaf": false,
"molecule": {
"id": "sa_275a06f193912d6dd7fff734",
"inchikey": "HSKGHUJMBLYPDO-UHFFFAOYSA-N",
"smiles": "Cc1cc(CO)ccc1O"
},
"smiles": "Cc1cc(CO)ccc1O",
"reactionStepId": "sa_c48b29c89b6609258434ba3d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060074111A1;0194;338662\",\"rsmi\":\"[CH3:1][c:2]1[c:3]([OH:4])[cH:5][cH:6][c:7]([CH:8]=[O:9])[cH:10]1>CCCC[N+](CCCC)(CCCC)CCCC.ClCCl.[B-].Cl.N>[CH3:1][c:2]1[c:3]([OH:4])[cH:5][cH:6][c:7]([CH2:8][OH:9])[cH:10]1\"},\"mapped_reaction_smiles\":\"[CH3:1][c:2]1[c:3]([OH:4])[cH:5][cH:6][c:7]([CH:8]=[O:9])[cH:10]1>CCCC[N+](CCCC)(CCCC)CCCC.ClCCl.[B-].Cl.N>[CH3:1][c:2]1[c:3]([OH:4])[cH:5][cH:6][c:7]([CH2:8][OH:9])[cH:10]1\"}",
"reactionStep": {
"id": "sa_c48b29c89b6609258434ba3d",
"reactionHash": "edd2feee86f3c1380fc16d356b7975eacbdcf85624aa588760fae8044b1ae931"
},
"children": [
{
"id": "656",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_54d48885d9bdcc0f731e6f6a",
"parentId": "655",
"isLeaf": true,
"molecule": {
"id": "sa_54d48885d9bdcc0f731e6f6a",
"inchikey": "BAKYASSDAXQKKY-UHFFFAOYSA-N",
"smiles": "Cc1cc(C=O)ccc1O"
},
"smiles": "Cc1cc(C=O)ccc1O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "657",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_6170bddd2f4a4137325c4a17",
"parentId": "654",
"isLeaf": true,
"molecule": {
"id": "sa_6170bddd2f4a4137325c4a17",
"inchikey": "PQJJJMRNHATNKG-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CBr"
},
"smiles": "CCOC(=O)CBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "658",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_d501d4f8f72e8d66ad5e01cb",
"parentId": "653",
"isLeaf": true,
"molecule": {
"id": "sa_d501d4f8f72e8d66ad5e01cb",
"inchikey": "HJUGFYREWKUQJT-UHFFFAOYSA-N",
"smiles": "BrC(Br)(Br)Br"
},
"smiles": "BrC(Br)(Br)Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "659",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_27caf24f3c3988261157b745",
"parentId": "652",
"isLeaf": false,
"molecule": {
"id": "sa_27caf24f3c3988261157b745",
"inchikey": "YGDDSWMCADDCTP-UHFFFAOYSA-N",
"smiles": "CCCCCNc1cccc(-c2ccc(C(F)(F)F)cc2)c1"
},
"smiles": "CCCCCNc1cccc(-c2ccc(C(F)(F)F)cc2)c1",
"reactionStepId": "sa_54b1988d8ad9114aff23dc58",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060074111A1;0215;338668\",\"rsmi\":\"O=[CH:5][CH2:4][CH2:3][CH2:2][CH3:1].[NH2:6][c:7]1[cH:8][cH:9][cH:10][c:11](-[c:12]2[cH:13][cH:14][c:15]([C:16]([F:17])([F:18])[F:19])[cH:20][cH:21]2)[cH:22]1>CC(=O)O.CC(=O)OB(OC(C)=O)OC(C)=O.ClCCl.[Na+]>[CH3:1][CH2:2][CH2:3][CH2:4][CH2:5][NH:6][c:7]1[cH:8][cH:9][cH:10][c:11](-[c:12]2[cH:13][cH:14][c:15]([C:16]([F:17])([F:18])[F:19])[cH:20][cH:21]2)[cH:22]1\"},\"mapped_reaction_smiles\":\"O=[CH:5][CH2:4][CH2:3][CH2:2][CH3:1].[NH2:6][c:7]1[cH:8][cH:9][cH:10][c:11](-[c:12]2[cH:13][cH:14][c:15]([C:16]([F:17])([F:18])[F:19])[cH:20][cH:21]2)[cH:22]1>CC(=O)O.CC(=O)OB(OC(C)=O)OC(C)=O.ClCCl.[Na+]>[CH3:1][CH2:2][CH2:3][CH2:4][CH2:5][NH:6][c:7]1[cH:8][cH:9][cH:10][c:11](-[c:12]2[cH:13][cH:14][c:15]([C:16]([F:17])([F:18])[F:19])[cH:20][cH:21]2)[cH:22]1\"}",
"reactionStep": {
"id": "sa_54b1988d8ad9114aff23dc58",
"reactionHash": "5ea44f50868a1b77b39d243bbd480730b9ef312e67ccb32b51930898f8829232"
},
"children": [
{
"id": "660",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_d10fb2f06b06f24b0e0d10c2",
"parentId": "659",
"isLeaf": true,
"molecule": {
"id": "sa_d10fb2f06b06f24b0e0d10c2",
"inchikey": "HGBOYTHUEUWSSQ-UHFFFAOYSA-N",
"smiles": "CCCCC=O"
},
"smiles": "CCCCC=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "661",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_fc3de38c48297bf0bfe1d9ae",
"parentId": "659",
"isLeaf": false,
"molecule": {
"id": "sa_fc3de38c48297bf0bfe1d9ae",
"inchikey": "RTSCKIULIJLTHO-UHFFFAOYSA-N",
"smiles": "Nc1cccc(-c2ccc(C(F)(F)F)cc2)c1"
},
"smiles": "Nc1cccc(-c2ccc(C(F)(F)F)cc2)c1",
"reactionStepId": "sa_0b398ac12a3f94e9966d5d9d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20060074111A1;0206;338665\",\"rsmi\":\"I[c:6]1[cH:5][cH:4][cH:3][c:2]([NH2:1])[cH:17]1.OB(O)[c:7]1[cH:8][cH:9][c:10]([C:11]([F:12])([F:13])[F:14])[cH:15][cH:16]1>COCCOC.O.O=C(O)O.[Na+].[Na+].[Pd].c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[NH2:1][c:2]1[cH:3][cH:4][cH:5][c:6](-[c:7]2[cH:8][cH:9][c:10]([C:11]([F:12])([F:13])[F:14])[cH:15][cH:16]2)[cH:17]1\"},\"mapped_reaction_smiles\":\"I[c:6]1[cH:5][cH:4][cH:3][c:2]([NH2:1])[cH:17]1.OB(O)[c:7]1[cH:8][cH:9][c:10]([C:11]([F:12])([F:13])[F:14])[cH:15][cH:16]1>COCCOC.O.O=C(O)O.[Na+].[Na+].[Pd].c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[NH2:1][c:2]1[cH:3][cH:4][cH:5][c:6](-[c:7]2[cH:8][cH:9][c:10]([C:11]([F:12])([F:13])[F:14])[cH:15][cH:16]2)[cH:17]1\"}",
"reactionStep": {
"id": "sa_0b398ac12a3f94e9966d5d9d",
"reactionHash": "cb6dc2d87e7813f5972dd3360128a3bd465f51f0420ac6a9154877db2e98c7cf"
},
"children": [
{
"id": "662",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_43c88ed81039fad4bb07c416",
"parentId": "661",
"isLeaf": true,
"molecule": {
"id": "sa_43c88ed81039fad4bb07c416",
"inchikey": "ALMFIOZYDASRRC-UHFFFAOYSA-N",
"smiles": "OB(O)c1ccc(C(F)(F)F)cc1"
},
"smiles": "OB(O)c1ccc(C(F)(F)F)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "663",
"routeId": "sa_2a55e552b1ecc5d7656ee8db",
"moleculeId": "sa_61e9b164361192225846ec20",
"parentId": "661",
"isLeaf": true,
"molecule": {
"id": "sa_61e9b164361192225846ec20",
"inchikey": "FFCSRWGYGMRBGD-UHFFFAOYSA-N",
"smiles": "Nc1cccc(I)c1"
},
"smiles": "Nc1cccc(I)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}