Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COC1=C(OC)C(=O)C(Cc2cccc(C(=O)O)c2O)=C(C)C1=O
InChiKey
VGQIDQJWDAJEBV-UHFFFAOYSA-N
Route Signature
cb6d642d4d35a6456b55b68f906511a633fcf9d5145b93bcccfafa06bf97c4d8
Synthesis route with 7 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_f2fde93d7243d9964b836cf8",
"signature": "cb6d642d4d35a6456b55b68f906511a633fcf9d5145b93bcccfafa06bf97c4d8",
"contentHash": "9e11d42bec9b47fb02a0f9f5e59edcbc0e487ae5b8492e9c10e0276da327991f",
"length": 7,
"isConvergent": false
},
"target": {
"id": "sa_c0df6194b7bf92b662ff7c3c",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00054",
"moleculeId": "sa_1ff8c2c1424a7beffe22eabb",
"smiles": "COC1=C(OC)C(=O)C(Cc2cccc(C(=O)O)c2O)=C(C)C1=O",
"routeLength": 7,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_1ff8c2c1424a7beffe22eabb",
"inchikey": "VGQIDQJWDAJEBV-UHFFFAOYSA-N",
"smiles": "COC1=C(OC)C(=O)C(Cc2cccc(C(=O)O)c2O)=C(C)C1=O"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "12239",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_1ff8c2c1424a7beffe22eabb",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_1ff8c2c1424a7beffe22eabb",
"inchikey": "VGQIDQJWDAJEBV-UHFFFAOYSA-N",
"smiles": "COC1=C(OC)C(=O)C(Cc2cccc(C(=O)O)c2O)=C(C)C1=O"
},
"smiles": "COC1=C(OC)C(=O)C(Cc2cccc(C(=O)O)c2O)=C(C)C1=O",
"reactionStepId": "sa_a8850e0e5dccad89fda5588e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07064124B2;0395;727847\",\"rsmi\":\"CC(=O)[O:20][c:19]1[c:11]([CH2:10][C:9]2=[C:21]([CH3:22])[C:23](=[O:24])[C:3]([O:2][CH3:1])=[C:4]([O:5][CH3:6])[C:7]2=[O:8])[cH:12][cH:13][cH:14][c:15]1[C:16](=[O:17])[OH:18]>CO.O.O=C(O)O.[Na+]>[CH3:1][O:2][C:3]1=[C:4]([O:5][CH3:6])[C:7](=[O:8])[C:9]([CH2:10][c:11]2[cH:12][cH:13][cH:14][c:15]([C:16](=[O:17])[OH:18])[c:19]2[OH:20])=[C:21]([CH3:22])[C:23]1=[O:24]\"},\"mapped_reaction_smiles\":\"CC(=O)[O:20][c:19]1[c:11]([CH2:10][C:9]2=[C:21]([CH3:22])[C:23](=[O:24])[C:3]([O:2][CH3:1])=[C:4]([O:5][CH3:6])[C:7]2=[O:8])[cH:12][cH:13][cH:14][c:15]1[C:16](=[O:17])[OH:18]>CO.O.O=C(O)O.[Na+]>[CH3:1][O:2][C:3]1=[C:4]([O:5][CH3:6])[C:7](=[O:8])[C:9]([CH2:10][c:11]2[cH:12][cH:13][cH:14][c:15]([C:16](=[O:17])[OH:18])[c:19]2[OH:20])=[C:21]([CH3:22])[C:23]1=[O:24]\"}",
"reactionStep": {
"id": "sa_a8850e0e5dccad89fda5588e",
"reactionHash": "073c386dc55695e9884944c24575f6cef1774c8bef4ef3cd2c877865d50f0f75"
},
"children": [
{
"id": "12240",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_bba0f8c037dbd655935ed1f7",
"parentId": "12239",
"isLeaf": false,
"molecule": {
"id": "sa_bba0f8c037dbd655935ed1f7",
"inchikey": "AUDRGYNEUBEJOU-UHFFFAOYSA-N",
"smiles": "COC1=C(OC)C(=O)C(Cc2cccc(C(=O)O)c2OC(C)=O)=C(C)C1=O"
},
"smiles": "COC1=C(OC)C(=O)C(Cc2cccc(C(=O)O)c2OC(C)=O)=C(C)C1=O",
"reactionStepId": "sa_84f6bb69a0df03053b7356e5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07064124B2;0392;727844\",\"rsmi\":\"C[O:8][c:7]1[c:4]([O:5][CH3:6])[c:3]([O:2][CH3:1])[c:26]([O:27]C)[c:24]([CH3:25])[c:9]1[CH2:10][c:11]1[cH:12][cH:13][cH:14][c:15]([C:16](=[O:17])[OH:18])[c:19]1[O:20][C:21]([CH3:22])=[O:23]>CC#N.O.O=[N+]([O-])O.O=[N+]([O-])O.O=[N+]([O-])O.O=[N+]([O-])O.O=[N+]([O-])O.O=[N+]([O-])O.[Ce+4].N.N>[CH3:1][O:2][C:3]1=[C:4]([O:5][CH3:6])[C:7](=[O:8])[C:9]([CH2:10][c:11]2[cH:12][cH:13][cH:14][c:15]([C:16](=[O:17])[OH:18])[c:19]2[O:20][C:21]([CH3:22])=[O:23])=[C:24]([CH3:25])[C:26]1=[O:27]\"},\"mapped_reaction_smiles\":\"C[O:8][c:7]1[c:4]([O:5][CH3:6])[c:3]([O:2][CH3:1])[c:26]([O:27]C)[c:24]([CH3:25])[c:9]1[CH2:10][c:11]1[cH:12][cH:13][cH:14][c:15]([C:16](=[O:17])[OH:18])[c:19]1[O:20][C:21]([CH3:22])=[O:23]>CC#N.O.O=[N+]([O-])O.O=[N+]([O-])O.O=[N+]([O-])O.O=[N+]([O-])O.O=[N+]([O-])O.O=[N+]([O-])O.[Ce+4].N.N>[CH3:1][O:2][C:3]1=[C:4]([O:5][CH3:6])[C:7](=[O:8])[C:9]([CH2:10][c:11]2[cH:12][cH:13][cH:14][c:15]([C:16](=[O:17])[OH:18])[c:19]2[O:20][C:21]([CH3:22])=[O:23])=[C:24]([CH3:25])[C:26]1=[O:27]\"}",
"reactionStep": {
"id": "sa_84f6bb69a0df03053b7356e5",
"reactionHash": "b2bc82103c6727a2b8afd226bd1b0cd62445911877f34cac2f41799fd1ea8785"
},
"children": [
{
"id": "12241",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_7237e05bda1dcc52cc8b5b92",
"parentId": "12240",
"isLeaf": false,
"molecule": {
"id": "sa_7237e05bda1dcc52cc8b5b92",
"inchikey": "USUBYUSHEMVKEM-UHFFFAOYSA-N",
"smiles": "COc1c(C)c(Cc2cccc(C(=O)O)c2OC(C)=O)c(OC)c(OC)c1OC"
},
"smiles": "COc1c(C)c(Cc2cccc(C(=O)O)c2OC(C)=O)c(OC)c(OC)c1OC",
"reactionStepId": "sa_0761bc5863f3aded5a1e1c99",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07064124B2;0359;727813\",\"rsmi\":\"CC(=O)O[C:25]([CH3:26])=[O:27].[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]2[OH:24])[c:28]1[CH3:29]>O>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]2[O:24][C:25]([CH3:26])=[O:27])[c:28]1[CH3:29]\"},\"mapped_reaction_smiles\":\"CC(=O)O[C:25]([CH3:26])=[O:27].[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]2[OH:24])[c:28]1[CH3:29]>O>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]2[O:24][C:25]([CH3:26])=[O:27])[c:28]1[CH3:29]\"}",
"reactionStep": {
"id": "sa_0761bc5863f3aded5a1e1c99",
"reactionHash": "c16d4b2ea460e843875cbec2959e479d244606624548b995f36100a01e245fef"
},
"children": [
{
"id": "12242",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_0da2db4b6ab79ac61cd79c37",
"parentId": "12241",
"isLeaf": false,
"molecule": {
"id": "sa_0da2db4b6ab79ac61cd79c37",
"inchikey": "MZKNYUAXIANRGS-UHFFFAOYSA-N",
"smiles": "COc1c(C)c(Cc2cccc(C(=O)O)c2O)c(OC)c(OC)c1OC"
},
"smiles": "COc1c(C)c(Cc2cccc(C(=O)O)c2O)c(OC)c(OC)c1OC",
"reactionStepId": "sa_b5aa8dfaced668ecf58f0654",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07064124B2;0356;727810\",\"rsmi\":\"c1ccc(C[O:24][c:23]2[c:15]([CH2:14][c:13]3[c:10]([O:11][CH3:12])[c:7]([O:8][CH3:9])[c:4]([O:5][CH3:6])[c:3]([O:2][CH3:1])[c:25]3[CH3:26])[cH:16][cH:17][cH:18][c:19]2[C:20](=[O:21])[OH:22])cc1>CCO.[H][H].[Pd]>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]2[OH:24])[c:25]1[CH3:26]\"},\"mapped_reaction_smiles\":\"c1ccc(C[O:24][c:23]2[c:15]([CH2:14][c:13]3[c:10]([O:11][CH3:12])[c:7]([O:8][CH3:9])[c:4]([O:5][CH3:6])[c:3]([O:2][CH3:1])[c:25]3[CH3:26])[cH:16][cH:17][cH:18][c:19]2[C:20](=[O:21])[OH:22])cc1>CCO.[H][H].[Pd]>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]2[OH:24])[c:25]1[CH3:26]\"}",
"reactionStep": {
"id": "sa_b5aa8dfaced668ecf58f0654",
"reactionHash": "0731a028aa8e82b06352f597c16e0dd076bbf647ec482155920579d00a9c8088"
},
"children": [
{
"id": "12243",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_f81adbc1ee678aec108c5e71",
"parentId": "12242",
"isLeaf": false,
"molecule": {
"id": "sa_f81adbc1ee678aec108c5e71",
"inchikey": "IPTFKCICXYCCBP-UHFFFAOYSA-N",
"smiles": "COc1c(C)c(Cc2cccc(C(=O)O)c2OCc2ccccc2)c(OC)c(OC)c1OC"
},
"smiles": "COc1c(C)c(Cc2cccc(C(=O)O)c2OCc2ccccc2)c(OC)c(OC)c1OC",
"reactionStepId": "sa_b789e5be2f0c3e2331591bfc",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07064124B2;0349;727803\",\"rsmi\":\"O=P(O)(O)[OH:22].[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([CH:20]=[O:21])[c:23]2[O:24][CH2:25][c:26]2[cH:27][cH:28][cH:29][cH:30][cH:31]2)[c:32]1[CH3:33]>CC#N.O.OO.[Na+].[Na+].[O-][Cl+]O>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]2[O:24][CH2:25][c:26]2[cH:27][cH:28][cH:29][cH:30][cH:31]2)[c:32]1[CH3:33]\"},\"mapped_reaction_smiles\":\"O=P(O)(O)[OH:22].[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([CH:20]=[O:21])[c:23]2[O:24][CH2:25][c:26]2[cH:27][cH:28][cH:29][cH:30][cH:31]2)[c:32]1[CH3:33]>CC#N.O.OO.[Na+].[Na+].[O-][Cl+]O>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([C:20](=[O:21])[OH:22])[c:23]2[O:24][CH2:25][c:26]2[cH:27][cH:28][cH:29][cH:30][cH:31]2)[c:32]1[CH3:33]\"}",
"reactionStep": {
"id": "sa_b789e5be2f0c3e2331591bfc",
"reactionHash": "a71bf316093e831f2aa68a061f36c487f42a37a995ff67a26551cab9a6a05cf4"
},
"children": [
{
"id": "12244",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_b413f4c3493c54f1f450de10",
"parentId": "12243",
"isLeaf": false,
"molecule": {
"id": "sa_b413f4c3493c54f1f450de10",
"inchikey": "DBGNCSNKSPWGQK-UHFFFAOYSA-N",
"smiles": "COc1c(C)c(Cc2cccc(C=O)c2OCc2ccccc2)c(OC)c(OC)c1OC"
},
"smiles": "COc1c(C)c(Cc2cccc(C=O)c2OCc2ccccc2)c(OC)c(OC)c1OC",
"reactionStepId": "sa_82d285f9bf4ff13e990b1604",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07064124B2;0343;727797\",\"rsmi\":\"Br[CH2:24][c:25]1[cH:26][cH:27][cH:28][cH:29][cH:30]1.[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([CH:20]=[O:21])[c:22]2[OH:23])[c:31]1[CH3:32]>CC(C)=O.O=C(O)O.[Na+].[Na+]>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([CH:20]=[O:21])[c:22]2[O:23][CH2:24][c:25]2[cH:26][cH:27][cH:28][cH:29][cH:30]2)[c:31]1[CH3:32]\"},\"mapped_reaction_smiles\":\"Br[CH2:24][c:25]1[cH:26][cH:27][cH:28][cH:29][cH:30]1.[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([CH:20]=[O:21])[c:22]2[OH:23])[c:31]1[CH3:32]>CC(C)=O.O=C(O)O.[Na+].[Na+]>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([CH:20]=[O:21])[c:22]2[O:23][CH2:24][c:25]2[cH:26][cH:27][cH:28][cH:29][cH:30]2)[c:31]1[CH3:32]\"}",
"reactionStep": {
"id": "sa_82d285f9bf4ff13e990b1604",
"reactionHash": "793060b046d9d60809d78b4e618b5bac0b14ce33360a8443180523b304764d6f"
},
"children": [
{
"id": "12245",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_4ff2e4de9d80150de333c065",
"parentId": "12244",
"isLeaf": true,
"molecule": {
"id": "sa_4ff2e4de9d80150de333c065",
"inchikey": "AGEZXYOZHKGVCM-UHFFFAOYSA-N",
"smiles": "BrCc1ccccc1"
},
"smiles": "BrCc1ccccc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12246",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_2de647dc0fcf39591be87807",
"parentId": "12244",
"isLeaf": false,
"molecule": {
"id": "sa_2de647dc0fcf39591be87807",
"inchikey": "CEIAZCCIZUHNJN-UHFFFAOYSA-N",
"smiles": "COc1c(C)c(Cc2cccc(C=O)c2O)c(OC)c(OC)c1OC"
},
"smiles": "COc1c(C)c(Cc2cccc(C=O)c2O)c(OC)c(OC)c1OC",
"reactionStepId": "sa_24ac0b293405c3549bf5fc49",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US07064124B2;0339;727793\",\"rsmi\":\"O[C:20](C(F)(F)F)=[O:21].[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][cH:19][c:22]2[OH:23])[c:24]1[CH3:25]>C1N2CN3CN1CN(C2)C3>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([CH:20]=[O:21])[c:22]2[OH:23])[c:24]1[CH3:25]\"},\"mapped_reaction_smiles\":\"O[C:20](C(F)(F)F)=[O:21].[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][cH:19][c:22]2[OH:23])[c:24]1[CH3:25]>C1N2CN3CN1CN(C2)C3>[CH3:1][O:2][c:3]1[c:4]([O:5][CH3:6])[c:7]([O:8][CH3:9])[c:10]([O:11][CH3:12])[c:13]([CH2:14][c:15]2[cH:16][cH:17][cH:18][c:19]([CH:20]=[O:21])[c:22]2[OH:23])[c:24]1[CH3:25]\"}",
"reactionStep": {
"id": "sa_24ac0b293405c3549bf5fc49",
"reactionHash": "ca209d26ecc3986deb30e66b5203af51ff3b4a5c2b55500e84cdde161ed93413"
},
"children": [
{
"id": "12247",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_9ee2874235e55f5108d172bc",
"parentId": "12246",
"isLeaf": true,
"molecule": {
"id": "sa_9ee2874235e55f5108d172bc",
"inchikey": "DTQVDTLACAAQTR-UHFFFAOYSA-N",
"smiles": "O=C(O)C(F)(F)F"
},
"smiles": "O=C(O)C(F)(F)F",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "12248",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_caea61c14058bc8b03c75d17",
"parentId": "12246",
"isLeaf": true,
"molecule": {
"id": "sa_caea61c14058bc8b03c75d17",
"inchikey": "OUDHGVRCICVPDG-UHFFFAOYSA-N",
"smiles": "COc1c(C)c(Cc2ccccc2O)c(OC)c(OC)c1OC"
},
"smiles": "COc1c(C)c(Cc2ccccc2O)c(OC)c(OC)c1OC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "12249",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_2727b39ca20bd50996471dcf",
"parentId": "12243",
"isLeaf": true,
"molecule": {
"id": "sa_2727b39ca20bd50996471dcf",
"inchikey": "NBIIXXVUZAFLBC-UHFFFAOYSA-N",
"smiles": "O=P(O)(O)O"
},
"smiles": "O=P(O)(O)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "12250",
"routeId": "sa_f2fde93d7243d9964b836cf8",
"moleculeId": "sa_a7893fcf81826693d9b4bed4",
"parentId": "12241",
"isLeaf": true,
"molecule": {
"id": "sa_a7893fcf81826693d9b4bed4",
"inchikey": "WFDIJRYMOXRFFG-UHFFFAOYSA-N",
"smiles": "CC(=O)OC(C)=O"
},
"smiles": "CC(=O)OC(C)=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}