Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CSc1sc(C(=N)N)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2COCCC(=O)O)c1
InChiKey
BXXWGDVILXKVHL-UHFFFAOYSA-N
Route Signature
9c8e91382372adcbc0d87ef89bca71dc57cd63e4547e604b00a58fa22f2d6649
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_dced53ea1c52984a4de80e36",
"signature": "9c8e91382372adcbc0d87ef89bca71dc57cd63e4547e604b00a58fa22f2d6649",
"contentHash": "127e83283b91e83497d777f94305d317ea9742cf8b2be5a5b43c18ba964d3231",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_8fa78d78608afa3bbf50dff8",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00617",
"moleculeId": "sa_b9e9ab493f6f68a976e2da85",
"smiles": "CSc1sc(C(=N)N)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2COCCC(=O)O)c1",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_b9e9ab493f6f68a976e2da85",
"inchikey": "BXXWGDVILXKVHL-UHFFFAOYSA-N",
"smiles": "CSc1sc(C(=N)N)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2COCCC(=O)O)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9611",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_b9e9ab493f6f68a976e2da85",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_b9e9ab493f6f68a976e2da85",
"inchikey": "BXXWGDVILXKVHL-UHFFFAOYSA-N",
"smiles": "CSc1sc(C(=N)N)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2COCCC(=O)O)c1"
},
"smiles": "CSc1sc(C(=N)N)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2COCCC(=O)O)c1",
"reactionStepId": "sa_84a2c73dec5c2bde91a2c783",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07109354B2;0732;745400\",\"rsmi\":\"CC(C)(C)OC(=O)[NH:32][C:30]([c:29]1[cH:28][c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][cH:10][cH:11][c:12](-[c:13]3[c:14]([CH2:15][O:16][CH2:17][CH2:18][C:19](=[O:20])[OH:21])[cH:22][cH:23][cH:24][c:25]3[CH3:26])[cH:27]2)[c:3]([S:2][CH3:1])[s:33]1)=[NH:31]>ClCCl.O=C(O)C(F)(F)F>[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][cH:10][cH:11][c:12](-[c:13]3[c:14]([CH2:15][O:16][CH2:17][CH2:18][C:19](=[O:20])[OH:21])[cH:22][cH:23][cH:24][c:25]3[CH3:26])[cH:27]2)[cH:28][c:29]([C:30](=[NH:31])[NH2:32])[s:33]1\"},\"mapped_reaction_smiles\":\"CC(C)(C)OC(=O)[NH:32][C:30]([c:29]1[cH:28][c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][cH:10][cH:11][c:12](-[c:13]3[c:14]([CH2:15][O:16][CH2:17][CH2:18][C:19](=[O:20])[OH:21])[cH:22][cH:23][cH:24][c:25]3[CH3:26])[cH:27]2)[c:3]([S:2][CH3:1])[s:33]1)=[NH:31]>ClCCl.O=C(O)C(F)(F)F>[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][cH:10][cH:11][c:12](-[c:13]3[c:14]([CH2:15][O:16][CH2:17][CH2:18][C:19](=[O:20])[OH:21])[cH:22][cH:23][cH:24][c:25]3[CH3:26])[cH:27]2)[cH:28][c:29]([C:30](=[NH:31])[NH2:32])[s:33]1\"}",
"reactionStep": {
"id": "sa_84a2c73dec5c2bde91a2c783",
"reactionHash": "84c831cc841a45db5152bd65b69a87bf1cbe2cfc5a044964ac6d77936a174b40"
},
"children": [
{
"id": "9612",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_b01658532a14edcf7154a5cc",
"parentId": "9611",
"isLeaf": false,
"molecule": {
"id": "sa_b01658532a14edcf7154a5cc",
"inchikey": "UDRSXMAKWIUEAG-UHFFFAOYSA-N",
"smiles": "CSc1sc(C(=N)NC(=O)OC(C)(C)C)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2COCCC(=O)O)c1"
},
"smiles": "CSc1sc(C(=N)NC(=O)OC(C)(C)C)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2COCCC(=O)O)c1",
"reactionStepId": "sa_c53e05be36f7e7d4b17a347f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07109354B2;0730;745399\",\"rsmi\":\"CC[O:21][C:19]([CH2:18][CH2:17][O:16][CH2:15][c:14]1[c:13](-[c:12]2[cH:11][cH:10][cH:9][c:8]([S:5]([c:4]3[c:3]([S:2][CH3:1])[s:40][c:29]([C:30](=[NH:31])[NH:32][C:33](=[O:34])[O:35][C:36]([CH3:37])([CH3:38])[CH3:39])[cH:28]3)(=[O:6])=[O:7])[cH:27]2)[c:25]([CH3:26])[cH:24][cH:23][cH:22]1)=[O:20]>C1CCOC1.CO.Cl.O.O.[Li+].O>[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][cH:10][cH:11][c:12](-[c:13]3[c:14]([CH2:15][O:16][CH2:17][CH2:18][C:19](=[O:20])[OH:21])[cH:22][cH:23][cH:24][c:25]3[CH3:26])[cH:27]2)[cH:28][c:29]([C:30](=[NH:31])[NH:32][C:33](=[O:34])[O:35][C:36]([CH3:37])([CH3:38])[CH3:39])[s:40]1\"},\"mapped_reaction_smiles\":\"CC[O:21][C:19]([CH2:18][CH2:17][O:16][CH2:15][c:14]1[c:13](-[c:12]2[cH:11][cH:10][cH:9][c:8]([S:5]([c:4]3[c:3]([S:2][CH3:1])[s:40][c:29]([C:30](=[NH:31])[NH:32][C:33](=[O:34])[O:35][C:36]([CH3:37])([CH3:38])[CH3:39])[cH:28]3)(=[O:6])=[O:7])[cH:27]2)[c:25]([CH3:26])[cH:24][cH:23][cH:22]1)=[O:20]>C1CCOC1.CO.Cl.O.O.[Li+].O>[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][cH:10][cH:11][c:12](-[c:13]3[c:14]([CH2:15][O:16][CH2:17][CH2:18][C:19](=[O:20])[OH:21])[cH:22][cH:23][cH:24][c:25]3[CH3:26])[cH:27]2)[cH:28][c:29]([C:30](=[NH:31])[NH:32][C:33](=[O:34])[O:35][C:36]([CH3:37])([CH3:38])[CH3:39])[s:40]1\"}",
"reactionStep": {
"id": "sa_c53e05be36f7e7d4b17a347f",
"reactionHash": "8000969d0b36fec28c0da45fce2f8d8fce1b88eca82fe13c2ed23cedaeff05fa"
},
"children": [
{
"id": "9613",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_94f2dfc80f4f3e16c1bf1b7d",
"parentId": "9612",
"isLeaf": false,
"molecule": {
"id": "sa_94f2dfc80f4f3e16c1bf1b7d",
"inchikey": "QNSKPFPQNKHHBK-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCOCc1cccc(C)c1-c1cccc(S(=O)(=O)c2cc(C(=N)NC(=O)OC(C)(C)C)sc2SC)c1"
},
"smiles": "CCOC(=O)CCOCc1cccc(C)c1-c1cccc(S(=O)(=O)c2cc(C(=N)NC(=O)OC(C)(C)C)sc2SC)c1",
"reactionStepId": "sa_ec433170ebbc64e0e28f4e1b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07109354B2;0728;745398\",\"rsmi\":\"Br[CH2:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:8][CH2:9][c:10]1[c:11](-[c:12]2[cH:13][c:14]([S:15](=[O:16])(=[O:17])[c:18]3[c:19]([S:20][CH3:21])[s:22][c:23]([C:24](=[NH:25])[NH:26][C:27](=[O:28])[O:29][C:30]([CH3:31])([CH3:32])[CH3:33])[cH:34]3)[cH:35][cH:36][cH:37]2)[c:38]([CH3:39])[cH:40][cH:41][cH:42]1>CN(C)C=O.[HH].[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][O:8][CH2:9][c:10]1[c:11](-[c:12]2[cH:13][c:14]([S:15](=[O:16])(=[O:17])[c:18]3[c:19]([S:20][CH3:21])[s:22][c:23]([C:24](=[NH:25])[NH:26][C:27](=[O:28])[O:29][C:30]([CH3:31])([CH3:32])[CH3:33])[cH:34]3)[cH:35][cH:36][cH:37]2)[c:38]([CH3:39])[cH:40][cH:41][cH:42]1\"},\"mapped_reaction_smiles\":\"Br[CH2:7][CH2:6][C:4]([O:3][CH2:2][CH3:1])=[O:5].[OH:8][CH2:9][c:10]1[c:11](-[c:12]2[cH:13][c:14]([S:15](=[O:16])(=[O:17])[c:18]3[c:19]([S:20][CH3:21])[s:22][c:23]([C:24](=[NH:25])[NH:26][C:27](=[O:28])[O:29][C:30]([CH3:31])([CH3:32])[CH3:33])[cH:34]3)[cH:35][cH:36][cH:37]2)[c:38]([CH3:39])[cH:40][cH:41][cH:42]1>CN(C)C=O.[HH].[Na+]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][O:8][CH2:9][c:10]1[c:11](-[c:12]2[cH:13][c:14]([S:15](=[O:16])(=[O:17])[c:18]3[c:19]([S:20][CH3:21])[s:22][c:23]([C:24](=[NH:25])[NH:26][C:27](=[O:28])[O:29][C:30]([CH3:31])([CH3:32])[CH3:33])[cH:34]3)[cH:35][cH:36][cH:37]2)[c:38]([CH3:39])[cH:40][cH:41][cH:42]1\"}",
"reactionStep": {
"id": "sa_ec433170ebbc64e0e28f4e1b",
"reactionHash": "33911f9f25e8ab95bc1bb012db97f47d98a59123049d374b73c23e56f930eb8f"
},
"children": [
{
"id": "9614",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_fed7d95c2487764fd7cb99b1",
"parentId": "9613",
"isLeaf": false,
"molecule": {
"id": "sa_fed7d95c2487764fd7cb99b1",
"inchikey": "BJKXZAQMQFTFFD-UHFFFAOYSA-N",
"smiles": "CSc1sc(C(=N)NC(=O)OC(C)(C)C)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2CO)c1"
},
"smiles": "CSc1sc(C(=N)NC(=O)OC(C)(C)C)cc1S(=O)(=O)c1cccc(-c2c(C)cccc2CO)c1",
"reactionStepId": "sa_9fbb18ae216b2a572c67b54b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07109354B2;0866;745446\",\"rsmi\":\"Br[c:12]1[cH:11][cH:10][cH:9][c:8]([S:5]([c:4]2[c:3]([S:2][CH3:1])[s:35][c:24]([C:25](=[NH:26])[NH:27][C:28](=[O:29])[O:30][C:31]([CH3:32])([CH3:33])[CH3:34])[cH:23]2)(=[O:6])=[O:7])[cH:22]1.I[c:13]1[c:14]([CH2:15][OH:16])[cH:17][cH:18][cH:19][c:20]1[CH3:21]>CCOC(C)=O.CCOCC.COB(OC)OC.O=C(O)O.[Li]CCCC.[Na+].[Na+].[Pd].c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][cH:10][cH:11][c:12](-[c:13]3[c:14]([CH2:15][OH:16])[cH:17][cH:18][cH:19][c:20]3[CH3:21])[cH:22]2)[cH:23][c:24]([C:25](=[NH:26])[NH:27][C:28](=[O:29])[O:30][C:31]([CH3:32])([CH3:33])[CH3:34])[s:35]1\"},\"mapped_reaction_smiles\":\"Br[c:12]1[cH:11][cH:10][cH:9][c:8]([S:5]([c:4]2[c:3]([S:2][CH3:1])[s:35][c:24]([C:25](=[NH:26])[NH:27][C:28](=[O:29])[O:30][C:31]([CH3:32])([CH3:33])[CH3:34])[cH:23]2)(=[O:6])=[O:7])[cH:22]1.I[c:13]1[c:14]([CH2:15][OH:16])[cH:17][cH:18][cH:19][c:20]1[CH3:21]>CCOC(C)=O.CCOCC.COB(OC)OC.O=C(O)O.[Li]CCCC.[Na+].[Na+].[Pd].c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1.c1ccc(P(c2ccccc2)c2ccccc2)cc1>[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][cH:10][cH:11][c:12](-[c:13]3[c:14]([CH2:15][OH:16])[cH:17][cH:18][cH:19][c:20]3[CH3:21])[cH:22]2)[cH:23][c:24]([C:25](=[NH:26])[NH:27][C:28](=[O:29])[O:30][C:31]([CH3:32])([CH3:33])[CH3:34])[s:35]1\"}",
"reactionStep": {
"id": "sa_9fbb18ae216b2a572c67b54b",
"reactionHash": "97ccde76bee50633c7de527b58f626f2e14665dfcd8a35cbc4c99a1cda1250c9"
},
"children": [
{
"id": "9615",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_666afc204f219989127d08cf",
"parentId": "9614",
"isLeaf": false,
"molecule": {
"id": "sa_666afc204f219989127d08cf",
"inchikey": "AOUMAODPLMTFCM-UHFFFAOYSA-N",
"smiles": "CSc1sc(C(=N)NC(=O)OC(C)(C)C)cc1S(=O)(=O)c1cccc(Br)c1"
},
"smiles": "CSc1sc(C(=N)NC(=O)OC(C)(C)C)cc1S(=O)(=O)c1cccc(Br)c1",
"reactionStepId": "sa_2891cfda5e2d8e7186ccf641",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07109354B2;0450;745313\",\"rsmi\":\"CC(C)(C)OC(=O)O[C:20](=[O:21])[O:22][C:23]([CH3:24])([CH3:25])[CH3:26].[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][c:10]([Br:11])[cH:12][cH:13][cH:14]2)[cH:15][c:16]([C:17](=[NH:18])[NH2:19])[s:27]1>CCN(C(C)C)C(C)C.CCOC(C)=O.CN(C)C=O.O=C(O)C(F)(F)F>[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][c:10]([Br:11])[cH:12][cH:13][cH:14]2)[cH:15][c:16]([C:17](=[NH:18])[NH:19][C:20](=[O:21])[O:22][C:23]([CH3:24])([CH3:25])[CH3:26])[s:27]1\"},\"mapped_reaction_smiles\":\"CC(C)(C)OC(=O)O[C:20](=[O:21])[O:22][C:23]([CH3:24])([CH3:25])[CH3:26].[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][c:10]([Br:11])[cH:12][cH:13][cH:14]2)[cH:15][c:16]([C:17](=[NH:18])[NH2:19])[s:27]1>CCN(C(C)C)C(C)C.CCOC(C)=O.CN(C)C=O.O=C(O)C(F)(F)F>[CH3:1][S:2][c:3]1[c:4]([S:5](=[O:6])(=[O:7])[c:8]2[cH:9][c:10]([Br:11])[cH:12][cH:13][cH:14]2)[cH:15][c:16]([C:17](=[NH:18])[NH:19][C:20](=[O:21])[O:22][C:23]([CH3:24])([CH3:25])[CH3:26])[s:27]1\"}",
"reactionStep": {
"id": "sa_2891cfda5e2d8e7186ccf641",
"reactionHash": "5145cca0ff1cccbd69ed47412f5117ff3fd8b45c79d7f35ef47bad2bf882671e"
},
"children": [
{
"id": "9616",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_b273d4d4546165bca2b249b5",
"parentId": "9615",
"isLeaf": true,
"molecule": {
"id": "sa_b273d4d4546165bca2b249b5",
"inchikey": "DYHSDKLCOJIUFX-UHFFFAOYSA-N",
"smiles": "CC(C)(C)OC(=O)OC(=O)OC(C)(C)C"
},
"smiles": "CC(C)(C)OC(=O)OC(=O)OC(C)(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9617",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_871704b64a6d5f676e2d5799",
"parentId": "9615",
"isLeaf": true,
"molecule": {
"id": "sa_871704b64a6d5f676e2d5799",
"inchikey": "ZNRJWLLKRMWGGV-UHFFFAOYSA-N",
"smiles": "CSc1sc(C(=N)N)cc1S(=O)(=O)c1cccc(Br)c1"
},
"smiles": "CSc1sc(C(=N)N)cc1S(=O)(=O)c1cccc(Br)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "9618",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_82399071ef3f30da2522ec6a",
"parentId": "9614",
"isLeaf": false,
"molecule": {
"id": "sa_82399071ef3f30da2522ec6a",
"inchikey": "NVDGNIBWPJTMDL-UHFFFAOYSA-N",
"smiles": "Cc1cccc(CO)c1I"
},
"smiles": "Cc1cccc(CO)c1I",
"reactionStepId": "sa_6bae603cce69cdb01d8124e5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07109354B2;0369;745284\",\"rsmi\":\"O=[C:7]([c:6]1[cH:5][cH:4][cH:3][c:2]([CH3:1])[c:9]1[I:10])[OH:8]>ClCCl.O=S(Cl)Cl.[Al+3].B.[HH].[HH].[HH].[HH].[Li+].[Na+]>[CH3:1][c:2]1[cH:3][cH:4][cH:5][c:6]([CH2:7][OH:8])[c:9]1[I:10]\"},\"mapped_reaction_smiles\":\"O=[C:7]([c:6]1[cH:5][cH:4][cH:3][c:2]([CH3:1])[c:9]1[I:10])[OH:8]>ClCCl.O=S(Cl)Cl.[Al+3].B.[HH].[HH].[HH].[HH].[Li+].[Na+]>[CH3:1][c:2]1[cH:3][cH:4][cH:5][c:6]([CH2:7][OH:8])[c:9]1[I:10]\"}",
"reactionStep": {
"id": "sa_6bae603cce69cdb01d8124e5",
"reactionHash": "cdacb235605b6b175b40894b6202093fc795ee4780f1e5619eef50e7d79771cc"
},
"children": [
{
"id": "9619",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_b342498ccf1dac9f099f93fa",
"parentId": "9618",
"isLeaf": true,
"molecule": {
"id": "sa_b342498ccf1dac9f099f93fa",
"inchikey": "PZUXUOZSSYKAMX-UHFFFAOYSA-N",
"smiles": "Cc1cccc(C(=O)O)c1I"
},
"smiles": "Cc1cccc(C(=O)O)c1I",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "9620",
"routeId": "sa_dced53ea1c52984a4de80e36",
"moleculeId": "sa_da00719dfec119cdda649b7c",
"parentId": "9613",
"isLeaf": true,
"molecule": {
"id": "sa_da00719dfec119cdda649b7c",
"inchikey": "FQTIYMRSUOADDK-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCBr"
},
"smiles": "CCOC(=O)CCBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}