Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(N)=O)c(F)c3)c2)c(C)c1
InChiKey
DMUAQUAYQJNFRU-UHFFFAOYSA-N
Route Signature
a8eea4185208019851784e844048c0ec3dc7d263c210f2d9fed8f84ee762f3f2
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_3b25003d87883d76866a7317",
"signature": "a8eea4185208019851784e844048c0ec3dc7d263c210f2d9fed8f84ee762f3f2",
"contentHash": "da838cb1646ff96511e0eee9335f8b8bd36782d6b0a2d77c6751e2629b0305b2",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_814d392f7c5fd3b00b4666d2",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00080",
"moleculeId": "sa_90c64e24d14f90ae27dd9765",
"smiles": "CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(N)=O)c(F)c3)c2)c(C)c1",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_90c64e24d14f90ae27dd9765",
"inchikey": "DMUAQUAYQJNFRU-UHFFFAOYSA-N",
"smiles": "CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(N)=O)c(F)c3)c2)c(C)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "53",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_90c64e24d14f90ae27dd9765",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_90c64e24d14f90ae27dd9765",
"inchikey": "DMUAQUAYQJNFRU-UHFFFAOYSA-N",
"smiles": "CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(N)=O)c(F)c3)c2)c(C)c1"
},
"smiles": "CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(N)=O)c(F)c3)c2)c(C)c1",
"reactionStepId": "sa_11e0749e1c1ad756487db0e3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080269220A1;1278;627950\",\"rsmi\":\"O[C:24]([CH2:23][CH2:22][c:21]1[c:19]([F:20])[cH:18][c:17]([NH:16][CH2:15][c:14]2[cH:13][c:12](-[c:11]3[c:9]([CH3:10])[cH:8][c:7]([O:6][CH2:5][CH2:4][O:3][CH2:2][CH3:1])[cH:34][c:32]3[CH3:33])[cH:31][cH:30][cH:29]2)[cH:28][cH:27]1)=[O:26].[NH3:25]>C1CCC2=NCCCN2CC1.CC#N.CCN(CC)CC.CCN=C=NCCCN.CO.Cl.O=C(O)O.On1nnc2ccccc21.[Na+]>[CH3:1][CH2:2][O:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH2:15][NH:16][c:17]3[cH:18][c:19]([F:20])[c:21]([CH2:22][CH2:23][C:24]([NH2:25])=[O:26])[cH:27][cH:28]3)[cH:29][cH:30][cH:31]2)[c:32]([CH3:33])[cH:34]1\"},\"mapped_reaction_smiles\":\"O[C:24]([CH2:23][CH2:22][c:21]1[c:19]([F:20])[cH:18][c:17]([NH:16][CH2:15][c:14]2[cH:13][c:12](-[c:11]3[c:9]([CH3:10])[cH:8][c:7]([O:6][CH2:5][CH2:4][O:3][CH2:2][CH3:1])[cH:34][c:32]3[CH3:33])[cH:31][cH:30][cH:29]2)[cH:28][cH:27]1)=[O:26].[NH3:25]>C1CCC2=NCCCN2CC1.CC#N.CCN(CC)CC.CCN=C=NCCCN.CO.Cl.O=C(O)O.On1nnc2ccccc21.[Na+]>[CH3:1][CH2:2][O:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH2:15][NH:16][c:17]3[cH:18][c:19]([F:20])[c:21]([CH2:22][CH2:23][C:24]([NH2:25])=[O:26])[cH:27][cH:28]3)[cH:29][cH:30][cH:31]2)[c:32]([CH3:33])[cH:34]1\"}",
"reactionStep": {
"id": "sa_11e0749e1c1ad756487db0e3",
"reactionHash": "3962896b0f3b2f4ea12695ca1d347bf5d24b614f21b55f305139e5f08787abc2"
},
"children": [
{
"id": "54",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_269d4b354ed48e1c236f8508",
"parentId": "53",
"isLeaf": false,
"molecule": {
"id": "sa_269d4b354ed48e1c236f8508",
"inchikey": "BYYWXHGQMZFTEF-UHFFFAOYSA-N",
"smiles": "CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(=O)O)c(F)c3)c2)c(C)c1"
},
"smiles": "CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(=O)O)c(F)c3)c2)c(C)c1",
"reactionStepId": "sa_b3d6fce936d3a58af7706e9e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080269220A1;1122;627936\",\"rsmi\":\"CC[O:26][C:24]([CH2:23][CH2:22][c:21]1[c:19]([F:20])[cH:18][c:17]([NH:16][CH2:15][c:14]2[cH:13][c:12](-[c:11]3[c:9]([CH3:10])[cH:8][c:7]([O:6][CH2:5][CH2:4][O:3][CH2:2][CH3:1])[cH:34][c:32]3[CH3:33])[cH:31][cH:30][cH:29]2)[cH:28][cH:27]1)=[O:25]>C1CCOC1.CCO.O.O=C(O)CC(O)(CC(=O)O)C(=O)O.[Na+].O>[CH3:1][CH2:2][O:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH2:15][NH:16][c:17]3[cH:18][c:19]([F:20])[c:21]([CH2:22][CH2:23][C:24](=[O:25])[OH:26])[cH:27][cH:28]3)[cH:29][cH:30][cH:31]2)[c:32]([CH3:33])[cH:34]1\"},\"mapped_reaction_smiles\":\"CC[O:26][C:24]([CH2:23][CH2:22][c:21]1[c:19]([F:20])[cH:18][c:17]([NH:16][CH2:15][c:14]2[cH:13][c:12](-[c:11]3[c:9]([CH3:10])[cH:8][c:7]([O:6][CH2:5][CH2:4][O:3][CH2:2][CH3:1])[cH:34][c:32]3[CH3:33])[cH:31][cH:30][cH:29]2)[cH:28][cH:27]1)=[O:25]>C1CCOC1.CCO.O.O=C(O)CC(O)(CC(=O)O)C(=O)O.[Na+].O>[CH3:1][CH2:2][O:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH2:15][NH:16][c:17]3[cH:18][c:19]([F:20])[c:21]([CH2:22][CH2:23][C:24](=[O:25])[OH:26])[cH:27][cH:28]3)[cH:29][cH:30][cH:31]2)[c:32]([CH3:33])[cH:34]1\"}",
"reactionStep": {
"id": "sa_b3d6fce936d3a58af7706e9e",
"reactionHash": "e62449089e13249a8cb4ebbfe607b0b51c738d5d2b6b33f0598cfa84f6d34b42"
},
"children": [
{
"id": "55",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_c41f8fcba653daa2305c15ed",
"parentId": "54",
"isLeaf": false,
"molecule": {
"id": "sa_c41f8fcba653daa2305c15ed",
"inchikey": "BRYPZXPHHHMLFX-UHFFFAOYSA-N",
"smiles": "CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(=O)OCC)c(F)c3)c2)c(C)c1"
},
"smiles": "CCOCCOc1cc(C)c(-c2cccc(CNc3ccc(CCC(=O)OCC)c(F)c3)c2)c(C)c1",
"reactionStepId": "sa_6b8bf1353b227e50537c5397",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080269220A1;1119;627935\",\"rsmi\":\"O=[CH:15][c:14]1[cH:13][c:12](-[c:11]2[c:9]([CH3:10])[cH:8][c:7]([O:6][CH2:5][CH2:4][O:3][CH2:2][CH3:1])[cH:36][c:34]2[CH3:35])[cH:33][cH:32][cH:31]1.[NH2:16][c:17]1[cH:18][c:19]([F:20])[c:21]([CH2:22][CH2:23][C:24](=[O:25])[O:26][CH2:27][CH3:28])[cH:29][cH:30]1>Cc1ccccc1>[CH3:1][CH2:2][O:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH2:15][NH:16][c:17]3[cH:18][c:19]([F:20])[c:21]([CH2:22][CH2:23][C:24](=[O:25])[O:26][CH2:27][CH3:28])[cH:29][cH:30]3)[cH:31][cH:32][cH:33]2)[c:34]([CH3:35])[cH:36]1\"},\"mapped_reaction_smiles\":\"O=[CH:15][c:14]1[cH:13][c:12](-[c:11]2[c:9]([CH3:10])[cH:8][c:7]([O:6][CH2:5][CH2:4][O:3][CH2:2][CH3:1])[cH:36][c:34]2[CH3:35])[cH:33][cH:32][cH:31]1.[NH2:16][c:17]1[cH:18][c:19]([F:20])[c:21]([CH2:22][CH2:23][C:24](=[O:25])[O:26][CH2:27][CH3:28])[cH:29][cH:30]1>Cc1ccccc1>[CH3:1][CH2:2][O:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH2:15][NH:16][c:17]3[cH:18][c:19]([F:20])[c:21]([CH2:22][CH2:23][C:24](=[O:25])[O:26][CH2:27][CH3:28])[cH:29][cH:30]3)[cH:31][cH:32][cH:33]2)[c:34]([CH3:35])[cH:36]1\"}",
"reactionStep": {
"id": "sa_6b8bf1353b227e50537c5397",
"reactionHash": "0410e8d3b1bb55c89bc57e24454ff327778c98dbea8033af99117a835a147365"
},
"children": [
{
"id": "56",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_106016e3b4371483e6748322",
"parentId": "55",
"isLeaf": false,
"molecule": {
"id": "sa_106016e3b4371483e6748322",
"inchikey": "BAYWUAWGVDHBDA-UHFFFAOYSA-N",
"smiles": "CCOC(=O)CCc1ccc(N)cc1F"
},
"smiles": "CCOC(=O)CCc1ccc(N)cc1F",
"reactionStepId": "sa_6920c33bc4e6b5e0ff2c42b8",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080269220A1;0451;627815\",\"rsmi\":\"[CH3:1][CH2:2][O:3][C:4](=[O:5])/[CH:6]=[CH:7]/[c:8]1[c:9]([F:10])[cH:11][c:12]([NH2:13])[cH:14][cH:15]1>C.CCO.[Pd]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][c:8]1[c:9]([F:10])[cH:11][c:12]([NH2:13])[cH:14][cH:15]1\"},\"mapped_reaction_smiles\":\"[CH3:1][CH2:2][O:3][C:4](=[O:5])/[CH:6]=[CH:7]/[c:8]1[c:9]([F:10])[cH:11][c:12]([NH2:13])[cH:14][cH:15]1>C.CCO.[Pd]>[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH2:6][CH2:7][c:8]1[c:9]([F:10])[cH:11][c:12]([NH2:13])[cH:14][cH:15]1\"}",
"reactionStep": {
"id": "sa_6920c33bc4e6b5e0ff2c42b8",
"reactionHash": "f9e041b84a954783b7e4b799ad09798f6e1cb2a0b5f8c1d7edd1548dd3ea72e0"
},
"children": [
{
"id": "57",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_f2c18d7f65dcfb053686f5dd",
"parentId": "56",
"isLeaf": false,
"molecule": {
"id": "sa_f2c18d7f65dcfb053686f5dd",
"inchikey": "KCINNDBBSQBCEG-GQCTYLIASA-N",
"smiles": "CCOC(=O)/C=C/c1ccc(N)cc1F"
},
"smiles": "CCOC(=O)/C=C/c1ccc(N)cc1F",
"reactionStepId": "sa_a64739205a6d0db00cdfed2f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080269220A1;0448;627814\",\"rsmi\":\"Br[c:8]1[c:9]([F:10])[cH:11][c:12]([NH2:13])[cH:14][cH:15]1.[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]=[CH2:7]>CC(=O)O.CC(=O)O.CCN(C(C)C)C(C)C.CN(C)C=O.Cc1ccccc1P(c1ccccc1C)c1ccccc1C.[Pd+2]>[CH3:1][CH2:2][O:3][C:4](=[O:5])/[CH:6]=[CH:7]/[c:8]1[c:9]([F:10])[cH:11][c:12]([NH2:13])[cH:14][cH:15]1\"},\"mapped_reaction_smiles\":\"Br[c:8]1[c:9]([F:10])[cH:11][c:12]([NH2:13])[cH:14][cH:15]1.[CH3:1][CH2:2][O:3][C:4](=[O:5])[CH:6]=[CH2:7]>CC(=O)O.CC(=O)O.CCN(C(C)C)C(C)C.CN(C)C=O.Cc1ccccc1P(c1ccccc1C)c1ccccc1C.[Pd+2]>[CH3:1][CH2:2][O:3][C:4](=[O:5])/[CH:6]=[CH:7]/[c:8]1[c:9]([F:10])[cH:11][c:12]([NH2:13])[cH:14][cH:15]1\"}",
"reactionStep": {
"id": "sa_a64739205a6d0db00cdfed2f",
"reactionHash": "557e741833704e0c6a8e651a66933a4a4a1d0fde5e1afa299f772fe595a5718c"
},
"children": [
{
"id": "58",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_167a1e4c9d83b5bfc1544756",
"parentId": "57",
"isLeaf": true,
"molecule": {
"id": "sa_167a1e4c9d83b5bfc1544756",
"inchikey": "JIGUQPWFLRLWPJ-UHFFFAOYSA-N",
"smiles": "C=CC(=O)OCC"
},
"smiles": "C=CC(=O)OCC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "59",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_2116c58b0a7aec869380e4c9",
"parentId": "57",
"isLeaf": true,
"molecule": {
"id": "sa_2116c58b0a7aec869380e4c9",
"inchikey": "YTMVYYAKOPIJCZ-UHFFFAOYSA-N",
"smiles": "Nc1ccc(Br)c(F)c1"
},
"smiles": "Nc1ccc(Br)c(F)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "60",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_97fd77491b61d8003f66a3ec",
"parentId": "55",
"isLeaf": false,
"molecule": {
"id": "sa_97fd77491b61d8003f66a3ec",
"inchikey": "CVMSOOLBCASESX-UHFFFAOYSA-N",
"smiles": "CCOCCOc1cc(C)c(-c2cccc(C=O)c2)c(C)c1"
},
"smiles": "CCOCCOc1cc(C)c(-c2cccc(C=O)c2)c(C)c1",
"reactionStepId": "sa_01fa693e8b69caaa7c34c4d3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080269220A1;0442;627812\",\"rsmi\":\"Cl[CH2:5][CH2:4][O:3][CH2:2][CH3:1].[OH:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH:15]=[O:16])[cH:17][cH:18][cH:19]2)[c:20]([CH3:21])[cH:22]1>CN(C)C=O.O.O=C(O)O.I.[K+].[K+].[K+]>[CH3:1][CH2:2][O:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH:15]=[O:16])[cH:17][cH:18][cH:19]2)[c:20]([CH3:21])[cH:22]1\"},\"mapped_reaction_smiles\":\"Cl[CH2:5][CH2:4][O:3][CH2:2][CH3:1].[OH:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH:15]=[O:16])[cH:17][cH:18][cH:19]2)[c:20]([CH3:21])[cH:22]1>CN(C)C=O.O.O=C(O)O.I.[K+].[K+].[K+]>[CH3:1][CH2:2][O:3][CH2:4][CH2:5][O:6][c:7]1[cH:8][c:9]([CH3:10])[c:11](-[c:12]2[cH:13][c:14]([CH:15]=[O:16])[cH:17][cH:18][cH:19]2)[c:20]([CH3:21])[cH:22]1\"}",
"reactionStep": {
"id": "sa_01fa693e8b69caaa7c34c4d3",
"reactionHash": "2c52db572763c5fef28a01c0b9163e961f34f81fbafce9b723df8f63a460d3f2"
},
"children": [
{
"id": "61",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_2e6bd8eeef9f8c4489407b67",
"parentId": "60",
"isLeaf": true,
"molecule": {
"id": "sa_2e6bd8eeef9f8c4489407b67",
"inchikey": "GPTVQTPMFOLLOA-UHFFFAOYSA-N",
"smiles": "CCOCCCl"
},
"smiles": "CCOCCCl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "62",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_06d32ff0b32ca76a0e6e192c",
"parentId": "60",
"isLeaf": false,
"molecule": {
"id": "sa_06d32ff0b32ca76a0e6e192c",
"inchikey": "RGTRSFUXNGBZKU-UHFFFAOYSA-N",
"smiles": "Cc1cc(O)cc(C)c1-c1cccc(C=O)c1"
},
"smiles": "Cc1cc(O)cc(C)c1-c1cccc(C=O)c1",
"reactionStepId": "sa_fb30d539db33234ebe186ffc",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080269220A1;0427;627810\",\"rsmi\":\"Br[c:9]1[c:2]([CH3:1])[cH:3][c:4]([OH:5])[cH:6][c:7]1[CH3:8].OB(O)[c:10]1[cH:11][c:12]([CH:13]=[O:14])[cH:15][cH:16][cH:17]1>CCO.CCOC(C)=O.Cc1ccccc1.O.O=C(O)O.[Na+].[Na+].c1ccc([PH](c2ccccc2)(c2ccccc2)[Pd]([PH](c2ccccc2)(c2ccccc2)c2ccccc2)([PH](c2ccccc2)(c2ccccc2)c2ccccc2)[PH](c2ccccc2)(c2ccccc2)c2ccccc2)cc1>[CH3:1][c:2]1[cH:3][c:4]([OH:5])[cH:6][c:7]([CH3:8])[c:9]1-[c:10]1[cH:11][c:12]([CH:13]=[O:14])[cH:15][cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"Br[c:9]1[c:2]([CH3:1])[cH:3][c:4]([OH:5])[cH:6][c:7]1[CH3:8].OB(O)[c:10]1[cH:11][c:12]([CH:13]=[O:14])[cH:15][cH:16][cH:17]1>CCO.CCOC(C)=O.Cc1ccccc1.O.O=C(O)O.[Na+].[Na+].c1ccc([PH](c2ccccc2)(c2ccccc2)[Pd]([PH](c2ccccc2)(c2ccccc2)c2ccccc2)([PH](c2ccccc2)(c2ccccc2)c2ccccc2)[PH](c2ccccc2)(c2ccccc2)c2ccccc2)cc1>[CH3:1][c:2]1[cH:3][c:4]([OH:5])[cH:6][c:7]([CH3:8])[c:9]1-[c:10]1[cH:11][c:12]([CH:13]=[O:14])[cH:15][cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_fb30d539db33234ebe186ffc",
"reactionHash": "3a889f034f85ba9da208c872ca5a0136f8212911a85b50b3fd82711da6a4e86b"
},
"children": [
{
"id": "63",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_7ac6969c951072006a7b85cf",
"parentId": "62",
"isLeaf": true,
"molecule": {
"id": "sa_7ac6969c951072006a7b85cf",
"inchikey": "HJBGZJMKTOMQRR-UHFFFAOYSA-N",
"smiles": "O=Cc1cccc(B(O)O)c1"
},
"smiles": "O=Cc1cccc(B(O)O)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "64",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_713f26120c6c743dbb3f0714",
"parentId": "62",
"isLeaf": true,
"molecule": {
"id": "sa_713f26120c6c743dbb3f0714",
"inchikey": "WMUWDPLTTLJNPE-UHFFFAOYSA-N",
"smiles": "Cc1cc(O)cc(C)c1Br"
},
"smiles": "Cc1cc(O)cc(C)c1Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
},
{
"id": "65",
"routeId": "sa_3b25003d87883d76866a7317",
"moleculeId": "sa_c9679fdd876f32f86b77fb69",
"parentId": "53",
"isLeaf": true,
"molecule": {
"id": "sa_c9679fdd876f32f86b77fb69",
"inchikey": "QGZKDVFQNNGYKY-UHFFFAOYSA-N",
"smiles": "N"
},
"smiles": "N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
}