Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1cc(F)c(CS(C)(=O)=O)cc1-c1cn(C)c(=O)c2ccc(-c3cnn(C)c3)cc12
InChiKey
CBBUGDYXGFLQCM-UHFFFAOYSA-N
Route Signature
c82ada258dedf31e5ee99c0cb90e29fa4ab47799aebafa5351f526ae4ac95fcd
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_53d3b36fa22777cd345367e4",
"signature": "c82ada258dedf31e5ee99c0cb90e29fa4ab47799aebafa5351f526ae4ac95fcd",
"contentHash": "957bede0d1e9bd4168b05dc64f3d763b22c0371ecdbe4ecd543088e7f38fda32",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_c03b9ffa84eaff597d527e29",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00205",
"moleculeId": "sa_ebc9accda06f208815eb935a",
"smiles": "COc1cc(F)c(CS(C)(=O)=O)cc1-c1cn(C)c(=O)c2ccc(-c3cnn(C)c3)cc12",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_ebc9accda06f208815eb935a",
"inchikey": "CBBUGDYXGFLQCM-UHFFFAOYSA-N",
"smiles": "COc1cc(F)c(CS(C)(=O)=O)cc1-c1cn(C)c(=O)c2ccc(-c3cnn(C)c3)cc12"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9252",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_ebc9accda06f208815eb935a",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_ebc9accda06f208815eb935a",
"inchikey": "CBBUGDYXGFLQCM-UHFFFAOYSA-N",
"smiles": "COc1cc(F)c(CS(C)(=O)=O)cc1-c1cn(C)c(=O)c2ccc(-c3cnn(C)c3)cc12"
},
"smiles": "COc1cc(F)c(CS(C)(=O)=O)cc1-c1cn(C)c(=O)c2ccc(-c3cnn(C)c3)cc12",
"reactionStepId": "sa_de4aae971d69d85ff7030001",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150111885A1;0539;1681423\",\"rsmi\":\"Br[c:4]1[c:3]([O:2][CH3:1])[cH:32][c:30]([F:31])[c:24]([CH2:25][S:26]([CH3:27])(=[O:28])=[O:29])[cH:23]1.CC1(C)OB([c:5]2[cH:6][n:7]([CH3:8])[c:9](=[O:10])[c:11]3[cH:12][cH:13][c:14](-[c:15]4[cH:16][n:17]([CH3:18])[n:19][cH:20]4)[cH:21][c:22]23)OC1(C)C>C1COCCO1.Cl[Pd]Cl.O=P(O)(O)O.[Fe+2].[K+].[K+].[K+]>[CH3:1][O:2][c:3]1[c:4](-[c:5]2[cH:6][n:7]([CH3:8])[c:9](=[O:10])[c:11]3[cH:12][cH:13][c:14](-[c:15]4[cH:16][n:17]([CH3:18])[n:19][cH:20]4)[cH:21][c:22]23)[cH:23][c:24]([CH2:25][S:26]([CH3:27])(=[O:28])=[O:29])[c:30]([F:31])[cH:32]1\"},\"mapped_reaction_smiles\":\"Br[c:4]1[c:3]([O:2][CH3:1])[cH:32][c:30]([F:31])[c:24]([CH2:25][S:26]([CH3:27])(=[O:28])=[O:29])[cH:23]1.CC1(C)OB([c:5]2[cH:6][n:7]([CH3:8])[c:9](=[O:10])[c:11]3[cH:12][cH:13][c:14](-[c:15]4[cH:16][n:17]([CH3:18])[n:19][cH:20]4)[cH:21][c:22]23)OC1(C)C>C1COCCO1.Cl[Pd]Cl.O=P(O)(O)O.[Fe+2].[K+].[K+].[K+]>[CH3:1][O:2][c:3]1[c:4](-[c:5]2[cH:6][n:7]([CH3:8])[c:9](=[O:10])[c:11]3[cH:12][cH:13][c:14](-[c:15]4[cH:16][n:17]([CH3:18])[n:19][cH:20]4)[cH:21][c:22]23)[cH:23][c:24]([CH2:25][S:26]([CH3:27])(=[O:28])=[O:29])[c:30]([F:31])[cH:32]1\"}",
"reactionStep": {
"id": "sa_de4aae971d69d85ff7030001",
"reactionHash": "379d48c278c87b38f3a21fc703a0cdb5674294aee2890b40b3306a147dd073d8"
},
"children": [
{
"id": "9253",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_b12993c74dedddfe7f85c969",
"parentId": "9252",
"isLeaf": false,
"molecule": {
"id": "sa_b12993c74dedddfe7f85c969",
"inchikey": "IPNQOPZIYAVHHI-UHFFFAOYSA-N",
"smiles": "COc1cc(F)c(CS(C)(=O)=O)cc1Br"
},
"smiles": "COc1cc(F)c(CS(C)(=O)=O)cc1Br",
"reactionStepId": "sa_19279f1936cc3b9056515a7e",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150111885A1;0537;1681422\",\"rsmi\":\"[CH3:1][O:2][c:3]1[c:4]([Br:5])[cH:6][c:7]([CH2:8][S:9][CH3:10])[c:13]([F:14])[cH:15]1.OS(O[OH:12])=[O:11]>CO.O.[K+]>[CH3:1][O:2][c:3]1[c:4]([Br:5])[cH:6][c:7]([CH2:8][S:9]([CH3:10])(=[O:11])=[O:12])[c:13]([F:14])[cH:15]1\"},\"mapped_reaction_smiles\":\"[CH3:1][O:2][c:3]1[c:4]([Br:5])[cH:6][c:7]([CH2:8][S:9][CH3:10])[c:13]([F:14])[cH:15]1.OS(O[OH:12])=[O:11]>CO.O.[K+]>[CH3:1][O:2][c:3]1[c:4]([Br:5])[cH:6][c:7]([CH2:8][S:9]([CH3:10])(=[O:11])=[O:12])[c:13]([F:14])[cH:15]1\"}",
"reactionStep": {
"id": "sa_19279f1936cc3b9056515a7e",
"reactionHash": "74b977cb463ef1e8a431bf115193d10b3e035ba99e34e3c65833f482584ca508"
},
"children": [
{
"id": "9254",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_772e3d6f4278e1cff6cf430d",
"parentId": "9253",
"isLeaf": true,
"molecule": {
"id": "sa_772e3d6f4278e1cff6cf430d",
"inchikey": "AYSIGUCDFZQVQT-UHFFFAOYSA-N",
"smiles": "O=S(O)OO"
},
"smiles": "O=S(O)OO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9255",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_ba8597a53c5b0740894da922",
"parentId": "9253",
"isLeaf": false,
"molecule": {
"id": "sa_ba8597a53c5b0740894da922",
"inchikey": "UWUVRDHSNBVOJK-UHFFFAOYSA-N",
"smiles": "COc1cc(F)c(CSC)cc1Br"
},
"smiles": "COc1cc(F)c(CSC)cc1Br",
"reactionStepId": "sa_4e35cbe11d84c5aacbbed156",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150111885A1;0535;1681421\",\"rsmi\":\"Br[CH2:8][c:7]1[cH:6][c:4]([Br:5])[c:3]([O:2][CH3:1])[cH:13][c:11]1[F:12].[SH:9][CH3:10]>CCOC(C)=O.CN(C)C=O.O>[CH3:1][O:2][c:3]1[c:4]([Br:5])[cH:6][c:7]([CH2:8][S:9][CH3:10])[c:11]([F:12])[cH:13]1\"},\"mapped_reaction_smiles\":\"Br[CH2:8][c:7]1[cH:6][c:4]([Br:5])[c:3]([O:2][CH3:1])[cH:13][c:11]1[F:12].[SH:9][CH3:10]>CCOC(C)=O.CN(C)C=O.O>[CH3:1][O:2][c:3]1[c:4]([Br:5])[cH:6][c:7]([CH2:8][S:9][CH3:10])[c:11]([F:12])[cH:13]1\"}",
"reactionStep": {
"id": "sa_4e35cbe11d84c5aacbbed156",
"reactionHash": "9b46facc3b92cb0814fc8022568fe0122ea6854722db36363b927aaf766026ed"
},
"children": [
{
"id": "9256",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_4ff6ad4ca1f9c12687e811c2",
"parentId": "9255",
"isLeaf": true,
"molecule": {
"id": "sa_4ff6ad4ca1f9c12687e811c2",
"inchikey": "LSDPWZHWYPCBBB-UHFFFAOYSA-N",
"smiles": "CS"
},
"smiles": "CS",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9257",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_f8de66ac902376d7279c9ad9",
"parentId": "9255",
"isLeaf": false,
"molecule": {
"id": "sa_f8de66ac902376d7279c9ad9",
"inchikey": "UTGXJADXRKNETF-UHFFFAOYSA-N",
"smiles": "COc1cc(F)c(CBr)cc1Br"
},
"smiles": "COc1cc(F)c(CBr)cc1Br",
"reactionStepId": "sa_3a5708872e3f305249fe1321",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150111885A1;0533;1681420\",\"rsmi\":\"BrP(Br)[Br:9].O[CH2:8][c:7]1[cH:6][c:4]([Br:5])[c:3]([O:2][CH3:1])[cH:12][c:10]1[F:11]>ClCCl.O=C(O)O.[Na+]>[CH3:1][O:2][c:3]1[c:4]([Br:5])[cH:6][c:7]([CH2:8][Br:9])[c:10]([F:11])[cH:12]1\"},\"mapped_reaction_smiles\":\"BrP(Br)[Br:9].O[CH2:8][c:7]1[cH:6][c:4]([Br:5])[c:3]([O:2][CH3:1])[cH:12][c:10]1[F:11]>ClCCl.O=C(O)O.[Na+]>[CH3:1][O:2][c:3]1[c:4]([Br:5])[cH:6][c:7]([CH2:8][Br:9])[c:10]([F:11])[cH:12]1\"}",
"reactionStep": {
"id": "sa_3a5708872e3f305249fe1321",
"reactionHash": "e6bbd2030d8131f2fead8d1adecc8aea37c5a7450dbfc4f4fffa89cdae67455e"
},
"children": [
{
"id": "9258",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_dffdccbce5a44ffb8b04e1d2",
"parentId": "9257",
"isLeaf": true,
"molecule": {
"id": "sa_dffdccbce5a44ffb8b04e1d2",
"inchikey": "IPNPIHIZVLFAFP-UHFFFAOYSA-N",
"smiles": "BrP(Br)Br"
},
"smiles": "BrP(Br)Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9259",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_697a6484d23e12e8abdb60dd",
"parentId": "9257",
"isLeaf": true,
"molecule": {
"id": "sa_697a6484d23e12e8abdb60dd",
"inchikey": "IWNXTBZHKBZULK-UHFFFAOYSA-N",
"smiles": "COc1cc(F)c(CO)cc1Br"
},
"smiles": "COc1cc(F)c(CO)cc1Br",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "9260",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_08b6e8adef2a324d5204c18f",
"parentId": "9252",
"isLeaf": false,
"molecule": {
"id": "sa_08b6e8adef2a324d5204c18f",
"inchikey": "JOXKQDYTKYIVRY-UHFFFAOYSA-N",
"smiles": "Cn1cc(-c2ccc3c(=O)n(C)cc(B4OC(C)(C)C(C)(C)O4)c3c2)cn1"
},
"smiles": "Cn1cc(-c2ccc3c(=O)n(C)cc(B4OC(C)(C)C(C)(C)O4)c3c2)cn1",
"reactionStepId": "sa_4db67cbb085a716456f3d70d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150111885A1;0450;1681388\",\"rsmi\":\"Br[c:14]1[cH:13][n:11]([CH3:12])[c:9](=[O:10])[c:8]2[cH:7][cH:6][c:5](-[c:4]3[cH:3][n:2]([CH3:1])[n:27][cH:26]3)[cH:25][c:24]21.CC1(C)OB([B:15]2[O:16][C:17]([CH3:18])([CH3:19])[C:20]([CH3:21])([CH3:22])[O:23]2)OC1(C)C>C1COCCO1.CC(=O)O.Cl[Pd]Cl.[Fe+2].[K+]>[CH3:1][n:2]1[cH:3][c:4](-[c:5]2[cH:6][cH:7][c:8]3[c:9](=[O:10])[n:11]([CH3:12])[cH:13][c:14]([B:15]4[O:16][C:17]([CH3:18])([CH3:19])[C:20]([CH3:21])([CH3:22])[O:23]4)[c:24]3[cH:25]2)[cH:26][n:27]1\"},\"mapped_reaction_smiles\":\"Br[c:14]1[cH:13][n:11]([CH3:12])[c:9](=[O:10])[c:8]2[cH:7][cH:6][c:5](-[c:4]3[cH:3][n:2]([CH3:1])[n:27][cH:26]3)[cH:25][c:24]21.CC1(C)OB([B:15]2[O:16][C:17]([CH3:18])([CH3:19])[C:20]([CH3:21])([CH3:22])[O:23]2)OC1(C)C>C1COCCO1.CC(=O)O.Cl[Pd]Cl.[Fe+2].[K+]>[CH3:1][n:2]1[cH:3][c:4](-[c:5]2[cH:6][cH:7][c:8]3[c:9](=[O:10])[n:11]([CH3:12])[cH:13][c:14]([B:15]4[O:16][C:17]([CH3:18])([CH3:19])[C:20]([CH3:21])([CH3:22])[O:23]4)[c:24]3[cH:25]2)[cH:26][n:27]1\"}",
"reactionStep": {
"id": "sa_4db67cbb085a716456f3d70d",
"reactionHash": "e33ed7ffc602b020c413d69e1d6fe53349c3ee9354ebb10c2de0f762749eaf06"
},
"children": [
{
"id": "9261",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_e6c301388ac142801d4af5a2",
"parentId": "9260",
"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": "9262",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_339c527870805df46c08de54",
"parentId": "9260",
"isLeaf": false,
"molecule": {
"id": "sa_339c527870805df46c08de54",
"inchikey": "KORFSROOWWDCQH-UHFFFAOYSA-N",
"smiles": "Cn1cc(-c2ccc3c(=O)n(C)cc(Br)c3c2)cn1"
},
"smiles": "Cn1cc(-c2ccc3c(=O)n(C)cc(Br)c3c2)cn1",
"reactionStepId": "sa_12b530fd572fb4cd9f92aaf4",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150111885A1;0441;1681384\",\"rsmi\":\"Br[Br:15].[CH3:1][n:2]1[cH:3][c:4](-[c:5]2[cH:6][cH:7][c:8]3[c:9](=[O:10])[n:11]([CH3:12])[cH:13][cH:14][c:16]3[cH:17]2)[cH:18][n:19]1>CC(=O)O>[CH3:1][n:2]1[cH:3][c:4](-[c:5]2[cH:6][cH:7][c:8]3[c:9](=[O:10])[n:11]([CH3:12])[cH:13][c:14]([Br:15])[c:16]3[cH:17]2)[cH:18][n:19]1\"},\"mapped_reaction_smiles\":\"Br[Br:15].[CH3:1][n:2]1[cH:3][c:4](-[c:5]2[cH:6][cH:7][c:8]3[c:9](=[O:10])[n:11]([CH3:12])[cH:13][cH:14][c:16]3[cH:17]2)[cH:18][n:19]1>CC(=O)O>[CH3:1][n:2]1[cH:3][c:4](-[c:5]2[cH:6][cH:7][c:8]3[c:9](=[O:10])[n:11]([CH3:12])[cH:13][c:14]([Br:15])[c:16]3[cH:17]2)[cH:18][n:19]1\"}",
"reactionStep": {
"id": "sa_12b530fd572fb4cd9f92aaf4",
"reactionHash": "935d049163d410200ea4fe5f34938f53d54bc34f54f09a5f2d3de7120e32bf38"
},
"children": [
{
"id": "9263",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_8c9c8da39e7654ac159a3547",
"parentId": "9262",
"isLeaf": false,
"molecule": {
"id": "sa_8c9c8da39e7654ac159a3547",
"inchikey": "BYDBHMNCAUGFOF-UHFFFAOYSA-N",
"smiles": "Cn1cc(-c2ccc3c(=O)n(C)ccc3c2)cn1"
},
"smiles": "Cn1cc(-c2ccc3c(=O)n(C)ccc3c2)cn1",
"reactionStepId": "sa_a5a9f1c2c2568f64e31a2fd0",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20150111885A1;0439;1681383\",\"rsmi\":\"Br[c:5]1[cH:6][cH:7][c:8]2[c:9](=[O:10])[n:11]([CH3:12])[cH:13][cH:14][c:15]2[cH:16]1.CC1(C)OB([c:4]2[cH:3][n:2]([CH3:1])[n:18][cH:17]2)OC1(C)C>C1COCCO1.Cl[Pd](Cl)([PH](c1ccccc1)(c1ccccc1)c1ccccc1)[PH](c1ccccc1)(c1ccccc1)c1ccccc1.O.[Cs+].F>[CH3:1][n:2]1[cH:3][c:4](-[c:5]2[cH:6][cH:7][c:8]3[c:9](=[O:10])[n:11]([CH3:12])[cH:13][cH:14][c:15]3[cH:16]2)[cH:17][n:18]1\"},\"mapped_reaction_smiles\":\"Br[c:5]1[cH:6][cH:7][c:8]2[c:9](=[O:10])[n:11]([CH3:12])[cH:13][cH:14][c:15]2[cH:16]1.CC1(C)OB([c:4]2[cH:3][n:2]([CH3:1])[n:18][cH:17]2)OC1(C)C>C1COCCO1.Cl[Pd](Cl)([PH](c1ccccc1)(c1ccccc1)c1ccccc1)[PH](c1ccccc1)(c1ccccc1)c1ccccc1.O.[Cs+].F>[CH3:1][n:2]1[cH:3][c:4](-[c:5]2[cH:6][cH:7][c:8]3[c:9](=[O:10])[n:11]([CH3:12])[cH:13][cH:14][c:15]3[cH:16]2)[cH:17][n:18]1\"}",
"reactionStep": {
"id": "sa_a5a9f1c2c2568f64e31a2fd0",
"reactionHash": "7bf5ccde26d7b2d976c52a73f9fbfd595e523de98a0c3cc4bdcb6f3f6e82cd8c"
},
"children": [
{
"id": "9264",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_8ccec6fc9194e5fbc0d06993",
"parentId": "9263",
"isLeaf": true,
"molecule": {
"id": "sa_8ccec6fc9194e5fbc0d06993",
"inchikey": "UCNGGGYMLHAMJG-UHFFFAOYSA-N",
"smiles": "Cn1cc(B2OC(C)(C)C(C)(C)O2)cn1"
},
"smiles": "Cn1cc(B2OC(C)(C)C(C)(C)O2)cn1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9265",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_a09ea62a485be4118a5eb0e2",
"parentId": "9263",
"isLeaf": true,
"molecule": {
"id": "sa_a09ea62a485be4118a5eb0e2",
"inchikey": "XWALISSRSGMCSU-UHFFFAOYSA-N",
"smiles": "Cn1ccc2cc(Br)ccc2c1=O"
},
"smiles": "Cn1ccc2cc(Br)ccc2c1=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
},
{
"id": "9266",
"routeId": "sa_53d3b36fa22777cd345367e4",
"moleculeId": "sa_24211e89e565c162ea935f73",
"parentId": "9262",
"isLeaf": true,
"molecule": {
"id": "sa_24211e89e565c162ea935f73",
"inchikey": "GDTBXPJZTBHREO-UHFFFAOYSA-N",
"smiles": "BrBr"
},
"smiles": "BrBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}