Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
OC(COc1cccc(-c2ccc3ncn(Cc4ccccc4)c3c2)c1)CN1CCc2ccccc2C1
InChiKey
QRPLRPXUJNDKKA-UHFFFAOYSA-N
Route Signature
5fc6ee3789fd3bf046609ad89eec39f59a10560cd73435bc1ab4cf34b478fff4
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_d7f606fbd032d278d0c44a15",
"signature": "5fc6ee3789fd3bf046609ad89eec39f59a10560cd73435bc1ab4cf34b478fff4",
"contentHash": "e147e36491b2aeed1b71d90d4621bb0b2b8f275ee1e27ab454e7c46009e3659f",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_cb6ccc3331bee6cac8de700d",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00045",
"moleculeId": "sa_785bfbad117e68284e569ca9",
"smiles": "OC(COc1cccc(-c2ccc3ncn(Cc4ccccc4)c3c2)c1)CN1CCc2ccccc2C1",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_785bfbad117e68284e569ca9",
"inchikey": "QRPLRPXUJNDKKA-UHFFFAOYSA-N",
"smiles": "OC(COc1cccc(-c2ccc3ncn(Cc4ccccc4)c3c2)c1)CN1CCc2ccccc2C1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "1",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_785bfbad117e68284e569ca9",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_785bfbad117e68284e569ca9",
"inchikey": "QRPLRPXUJNDKKA-UHFFFAOYSA-N",
"smiles": "OC(COc1cccc(-c2ccc3ncn(Cc4ccccc4)c3c2)c1)CN1CCc2ccccc2C1"
},
"smiles": "OC(COc1cccc(-c2ccc3ncn(Cc4ccccc4)c3c2)c1)CN1CCc2ccccc2C1",
"reactionStepId": "sa_3ce5fefac146fbcfb877a61b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160214985A1;0457;1911654\",\"rsmi\":\"Br[c:8]1[cH:9][c:10]2[c:11]([cH:12][cH:13]1)[n:14][cH:15][n:16]2[CH2:17][c:18]1[cH:19][cH:20][cH:21][cH:22][cH:23]1.CC1(C)OB([c:7]2[cH:6][c:5]([O:4][CH2:3][CH:2]([OH:1])[CH2:27][N:28]3[CH2:29][CH2:30][c:31]4[cH:32][cH:33][cH:34][cH:35][c:36]4[CH2:37]3)[cH:26][cH:25][cH:24]2)OC1(C)C>C1COCCO1.Cl[Pd]Cl.O.O=C(O)O.[Fe+2].[K+].[K+]>[OH:1][CH:2]([CH2:3][O:4][c:5]1[cH:6][c:7](-[c:8]2[cH:9][c:10]3[c:11]([cH:12][cH:13]2)[n:14][cH:15][n:16]3[CH2:17][c:18]2[cH:19][cH:20][cH:21][cH:22][cH:23]2)[cH:24][cH:25][cH:26]1)[CH2:27][N:28]1[CH2:29][CH2:30][c:31]2[cH:32][cH:33][cH:34][cH:35][c:36]2[CH2:37]1\"},\"mapped_reaction_smiles\":\"Br[c:8]1[cH:9][c:10]2[c:11]([cH:12][cH:13]1)[n:14][cH:15][n:16]2[CH2:17][c:18]1[cH:19][cH:20][cH:21][cH:22][cH:23]1.CC1(C)OB([c:7]2[cH:6][c:5]([O:4][CH2:3][CH:2]([OH:1])[CH2:27][N:28]3[CH2:29][CH2:30][c:31]4[cH:32][cH:33][cH:34][cH:35][c:36]4[CH2:37]3)[cH:26][cH:25][cH:24]2)OC1(C)C>C1COCCO1.Cl[Pd]Cl.O.O=C(O)O.[Fe+2].[K+].[K+]>[OH:1][CH:2]([CH2:3][O:4][c:5]1[cH:6][c:7](-[c:8]2[cH:9][c:10]3[c:11]([cH:12][cH:13]2)[n:14][cH:15][n:16]3[CH2:17][c:18]2[cH:19][cH:20][cH:21][cH:22][cH:23]2)[cH:24][cH:25][cH:26]1)[CH2:27][N:28]1[CH2:29][CH2:30][c:31]2[cH:32][cH:33][cH:34][cH:35][c:36]2[CH2:37]1\"}",
"reactionStep": {
"id": "sa_3ce5fefac146fbcfb877a61b",
"reactionHash": "9068f3a1e99d2a6e30aa1eec8822174c47e817e7bc94139ab731a2573d2a5eac"
},
"children": [
{
"id": "2",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_b158f79cc50fc674eaeb4752",
"parentId": "1",
"isLeaf": false,
"molecule": {
"id": "sa_b158f79cc50fc674eaeb4752",
"inchikey": "KHRQWUPQXHUGAJ-UHFFFAOYSA-N",
"smiles": "Brc1ccc2ncn(Cc3ccccc3)c2c1"
},
"smiles": "Brc1ccc2ncn(Cc3ccccc3)c2c1",
"reactionStepId": "sa_ae5a9b3048d56f5231314123",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160214985A1;0455;1911653\",\"rsmi\":\"CO[CH:9](OC)OC.[Br:1][c:2]1[cH:3][c:4]([NH:10][CH2:11][c:12]2[cH:13][cH:14][cH:15][cH:16][cH:17]2)[c:5]([NH2:8])[cH:6][cH:7]1>Cc1ccc(S(=O)(=O)O)cc1.O>[Br:1][c:2]1[cH:3][c:4]2[c:5]([cH:6][cH:7]1)[n:8][cH:9][n:10]2[CH2:11][c:12]1[cH:13][cH:14][cH:15][cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"CO[CH:9](OC)OC.[Br:1][c:2]1[cH:3][c:4]([NH:10][CH2:11][c:12]2[cH:13][cH:14][cH:15][cH:16][cH:17]2)[c:5]([NH2:8])[cH:6][cH:7]1>Cc1ccc(S(=O)(=O)O)cc1.O>[Br:1][c:2]1[cH:3][c:4]2[c:5]([cH:6][cH:7]1)[n:8][cH:9][n:10]2[CH2:11][c:12]1[cH:13][cH:14][cH:15][cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_ae5a9b3048d56f5231314123",
"reactionHash": "952977a2f2d1fc26a4fdfcd952f5e287f6144e6ed2fca7c122d7f9db67956eb6"
},
"children": [
{
"id": "3",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_25c60a3c32f5c15b22d4a5b8",
"parentId": "2",
"isLeaf": false,
"molecule": {
"id": "sa_25c60a3c32f5c15b22d4a5b8",
"inchikey": "NWQTUDBTUDGCAJ-UHFFFAOYSA-N",
"smiles": "Nc1ccc(Br)cc1NCc1ccccc1"
},
"smiles": "Nc1ccc(Br)cc1NCc1ccccc1",
"reactionStepId": "sa_c5af56d7610982503f8b6579",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160214985A1;0453;1911652\",\"rsmi\":\"O=[N+:1]([O-])[c:2]1[cH:3][cH:4][c:5]([Br:6])[cH:7][c:8]1[NH:9][CH2:10][c:11]1[cH:12][cH:13][cH:14][cH:15][cH:16]1>CCO.O.Cl.[Fe].N>[NH2:1][c:2]1[cH:3][cH:4][c:5]([Br:6])[cH:7][c:8]1[NH:9][CH2:10][c:11]1[cH:12][cH:13][cH:14][cH:15][cH:16]1\"},\"mapped_reaction_smiles\":\"O=[N+:1]([O-])[c:2]1[cH:3][cH:4][c:5]([Br:6])[cH:7][c:8]1[NH:9][CH2:10][c:11]1[cH:12][cH:13][cH:14][cH:15][cH:16]1>CCO.O.Cl.[Fe].N>[NH2:1][c:2]1[cH:3][cH:4][c:5]([Br:6])[cH:7][c:8]1[NH:9][CH2:10][c:11]1[cH:12][cH:13][cH:14][cH:15][cH:16]1\"}",
"reactionStep": {
"id": "sa_c5af56d7610982503f8b6579",
"reactionHash": "cdd6a60b9c7be210bc871866a63fcf6e0b945ce46a3671677268f081a9a32ee1"
},
"children": [
{
"id": "4",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_7d2d590518be850b12411e81",
"parentId": "3",
"isLeaf": false,
"molecule": {
"id": "sa_7d2d590518be850b12411e81",
"inchikey": "UDRFLWCJBHSUQH-UHFFFAOYSA-N",
"smiles": "O=[N+]([O-])c1ccc(Br)cc1NCc1ccccc1"
},
"smiles": "O=[N+]([O-])c1ccc(Br)cc1NCc1ccccc1",
"reactionStepId": "sa_3f694f3499ca9210d350152c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160214985A1;0451;1911651\",\"rsmi\":\"F[c:5]1[c:4]([N+:2](=[O:1])[O-:3])[cH:18][cH:17][c:15]([Br:16])[cH:14]1.[NH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1>CN(C)C=O.O>[O:1]=[N+:2]([O-:3])[c:4]1[c:5]([NH:6][CH2:7][c:8]2[cH:9][cH:10][cH:11][cH:12][cH:13]2)[cH:14][c:15]([Br:16])[cH:17][cH:18]1\"},\"mapped_reaction_smiles\":\"F[c:5]1[c:4]([N+:2](=[O:1])[O-:3])[cH:18][cH:17][c:15]([Br:16])[cH:14]1.[NH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1>CN(C)C=O.O>[O:1]=[N+:2]([O-:3])[c:4]1[c:5]([NH:6][CH2:7][c:8]2[cH:9][cH:10][cH:11][cH:12][cH:13]2)[cH:14][c:15]([Br:16])[cH:17][cH:18]1\"}",
"reactionStep": {
"id": "sa_3f694f3499ca9210d350152c",
"reactionHash": "321b93cc95c1f44df52511d81f6e752b9065ce3742a9396773c90a96fd39cf6c"
},
"children": [
{
"id": "5",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_ecbfba56ef7d1f92e8522f6f",
"parentId": "4",
"isLeaf": true,
"molecule": {
"id": "sa_ecbfba56ef7d1f92e8522f6f",
"inchikey": "VQCWSOYHHXXWSP-UHFFFAOYSA-N",
"smiles": "O=[N+]([O-])c1ccc(Br)cc1F"
},
"smiles": "O=[N+]([O-])c1ccc(Br)cc1F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "6",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_6b16c9b5e9c18df10e07c892",
"parentId": "4",
"isLeaf": true,
"molecule": {
"id": "sa_6b16c9b5e9c18df10e07c892",
"inchikey": "WGQKYBSKWIADBV-UHFFFAOYSA-N",
"smiles": "NCc1ccccc1"
},
"smiles": "NCc1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "7",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_c9fbce0da7a922c8ea07398a",
"parentId": "2",
"isLeaf": true,
"molecule": {
"id": "sa_c9fbce0da7a922c8ea07398a",
"inchikey": "PYOKUURKVVELLB-UHFFFAOYSA-N",
"smiles": "COC(OC)OC"
},
"smiles": "COC(OC)OC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "8",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_80c4a86a8337e343533c97a7",
"parentId": "1",
"isLeaf": false,
"molecule": {
"id": "sa_80c4a86a8337e343533c97a7",
"inchikey": "MUGDETSZFQGZMT-UHFFFAOYSA-N",
"smiles": "CC1(C)OB(c2cccc(OCC(O)CN3CCc4ccccc4C3)c2)OC1(C)C"
},
"smiles": "CC1(C)OB(c2cccc(OCC(O)CN3CCc4ccccc4C3)c2)OC1(C)C",
"reactionStepId": "sa_44c89c300ad0da9212834e30",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160214985A1;0437;1911647\",\"rsmi\":\"Br[c:6]1[cH:7][cH:8][cH:9][c:10]([O:11][CH2:12][CH:13]([OH:14])[CH2:15][N:16]2[CH2:17][CH2:18][c:19]3[cH:20][cH:21][cH:22][cH:23][c:24]3[CH2:25]2)[cH:26]1.CC1(C)OB([B:5]2[O:4][C:2]([CH3:1])([CH3:3])[C:28]([CH3:29])([CH3:30])[O:27]2)OC1(C)C>CC(=O)O.CS(C)=O.O.[K+]>[CH3:1][C:2]1([CH3:3])[O:4][B:5]([c:6]2[cH:7][cH:8][cH:9][c:10]([O:11][CH2:12][CH:13]([OH:14])[CH2:15][N:16]3[CH2:17][CH2:18][c:19]4[cH:20][cH:21][cH:22][cH:23][c:24]4[CH2:25]3)[cH:26]2)[O:27][C:28]1([CH3:29])[CH3:30]\"},\"mapped_reaction_smiles\":\"Br[c:6]1[cH:7][cH:8][cH:9][c:10]([O:11][CH2:12][CH:13]([OH:14])[CH2:15][N:16]2[CH2:17][CH2:18][c:19]3[cH:20][cH:21][cH:22][cH:23][c:24]3[CH2:25]2)[cH:26]1.CC1(C)OB([B:5]2[O:4][C:2]([CH3:1])([CH3:3])[C:28]([CH3:29])([CH3:30])[O:27]2)OC1(C)C>CC(=O)O.CS(C)=O.O.[K+]>[CH3:1][C:2]1([CH3:3])[O:4][B:5]([c:6]2[cH:7][cH:8][cH:9][c:10]([O:11][CH2:12][CH:13]([OH:14])[CH2:15][N:16]3[CH2:17][CH2:18][c:19]4[cH:20][cH:21][cH:22][cH:23][c:24]4[CH2:25]3)[cH:26]2)[O:27][C:28]1([CH3:29])[CH3:30]\"}",
"reactionStep": {
"id": "sa_44c89c300ad0da9212834e30",
"reactionHash": "aa217c05a21b5a764007d7e67b3646314b71c2a7f26e3133c9ca742d87f1fb40"
},
"children": [
{
"id": "9",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_e6c301388ac142801d4af5a2",
"parentId": "8",
"isLeaf": true,
"molecule": {
"id": "sa_e6c301388ac142801d4af5a2",
"inchikey": "IPWKHHSGDUIRAH-UHFFFAOYSA-N",
"smiles": "CC1(C)OB(B2OC(C)(C)C(C)(C)O2)OC1(C)C"
},
"smiles": "CC1(C)OB(B2OC(C)(C)C(C)(C)O2)OC1(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_71a4986ed2238af0156f5a10",
"parentId": "8",
"isLeaf": false,
"molecule": {
"id": "sa_71a4986ed2238af0156f5a10",
"inchikey": "OXYNYMKHUYGHJL-UHFFFAOYSA-N",
"smiles": "OC(COc1cccc(Br)c1)CN1CCc2ccccc2C1"
},
"smiles": "OC(COc1cccc(Br)c1)CN1CCc2ccccc2C1",
"reactionStepId": "sa_7bfb62cdcfe19095300611ad",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160214985A1;0377;1911628\",\"rsmi\":\"[NH:13]1[CH2:14][CH2:15][c:16]2[cH:17][cH:18][cH:19][cH:20][c:21]2[CH2:22]1.[O:1]1[CH:2]([CH2:3][O:4][c:5]2[cH:6][c:7]([Br:8])[cH:9][cH:10][cH:11]2)[CH2:12]1>CCOC(C)=O.CO>[OH:1][CH:2]([CH2:3][O:4][c:5]1[cH:6][c:7]([Br:8])[cH:9][cH:10][cH:11]1)[CH2:12][N:13]1[CH2:14][CH2:15][c:16]2[cH:17][cH:18][cH:19][cH:20][c:21]2[CH2:22]1\"},\"mapped_reaction_smiles\":\"[NH:13]1[CH2:14][CH2:15][c:16]2[cH:17][cH:18][cH:19][cH:20][c:21]2[CH2:22]1.[O:1]1[CH:2]([CH2:3][O:4][c:5]2[cH:6][c:7]([Br:8])[cH:9][cH:10][cH:11]2)[CH2:12]1>CCOC(C)=O.CO>[OH:1][CH:2]([CH2:3][O:4][c:5]1[cH:6][c:7]([Br:8])[cH:9][cH:10][cH:11]1)[CH2:12][N:13]1[CH2:14][CH2:15][c:16]2[cH:17][cH:18][cH:19][cH:20][c:21]2[CH2:22]1\"}",
"reactionStep": {
"id": "sa_7bfb62cdcfe19095300611ad",
"reactionHash": "bad196dec94cc01c1fe68c8eab9e9a5edd5b5734ed2c107c63a07dd2b2ee5aad"
},
"children": [
{
"id": "11",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_0957ec4ec064083d5aae842e",
"parentId": "10",
"isLeaf": false,
"molecule": {
"id": "sa_0957ec4ec064083d5aae842e",
"inchikey": "MJDGHPATEBXUTI-UHFFFAOYSA-N",
"smiles": "Brc1cccc(OCC2CO2)c1"
},
"smiles": "Brc1cccc(OCC2CO2)c1",
"reactionStepId": "sa_49fae41ca2490d3db8859b22",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20160214985A1;0433;1911645\",\"rsmi\":\"Br[CH2:8][CH:9]1[CH2:10][O:11]1.[Br:1][c:2]1[cH:3][cH:4][cH:5][c:6]([OH:7])[cH:12]1>CN(C)C=O.O.[HH].[Na+]>[Br:1][c:2]1[cH:3][cH:4][cH:5][c:6]([O:7][CH2:8][CH:9]2[CH2:10][O:11]2)[cH:12]1\"},\"mapped_reaction_smiles\":\"Br[CH2:8][CH:9]1[CH2:10][O:11]1.[Br:1][c:2]1[cH:3][cH:4][cH:5][c:6]([OH:7])[cH:12]1>CN(C)C=O.O.[HH].[Na+]>[Br:1][c:2]1[cH:3][cH:4][cH:5][c:6]([O:7][CH2:8][CH:9]2[CH2:10][O:11]2)[cH:12]1\"}",
"reactionStep": {
"id": "sa_49fae41ca2490d3db8859b22",
"reactionHash": "0400ef3cadd4e2a945cb0270818032704780cd8307837928ae97d2397ace4283"
},
"children": [
{
"id": "12",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_deaa43fea342e99a5aa08bc3",
"parentId": "11",
"isLeaf": true,
"molecule": {
"id": "sa_deaa43fea342e99a5aa08bc3",
"inchikey": "GKIPXFAANLTWBM-UHFFFAOYSA-N",
"smiles": "BrCC1CO1"
},
"smiles": "BrCC1CO1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_fdc9afd2d603ee208e361038",
"parentId": "11",
"isLeaf": true,
"molecule": {
"id": "sa_fdc9afd2d603ee208e361038",
"inchikey": "MNOJRWOWILAHAV-UHFFFAOYSA-N",
"smiles": "Oc1cccc(Br)c1"
},
"smiles": "Oc1cccc(Br)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "14",
"routeId": "sa_d7f606fbd032d278d0c44a15",
"moleculeId": "sa_07d0e8ae2030149b1996b525",
"parentId": "10",
"isLeaf": true,
"molecule": {
"id": "sa_07d0e8ae2030149b1996b525",
"inchikey": "UWYZHKAOTLEWKK-UHFFFAOYSA-N",
"smiles": "c1ccc2c(c1)CCNC2"
},
"smiles": "c1ccc2c(c1)CCNC2",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}