Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1ccc(-c2nc(OC)oc2-c2ccc(OCCNC(N)=O)cc2)cc1
InChiKey
GZUVRVBRBJOEET-UHFFFAOYSA-N
Route Signature
78c03eeee201a3c7b86055a7537bd3ee336883d43954854e1e9b0587fef478a1
Synthesis route with 7 steps
Route tree structure (JSON format)
{
"route": {
"id": "sa_961970954680909f9a617f27",
"signature": "78c03eeee201a3c7b86055a7537bd3ee336883d43954854e1e9b0587fef478a1",
"contentHash": "0c037acfd93884ee6709e67a620763eb76f5214666a6210becb18480306d02e4",
"length": 7,
"isConvergent": false
},
"target": {
"id": "sa_9de53ef09eb79dd372f357d6",
"benchmarkSetId": "61e696668b63e77d7c2a29c0821768e1c383de8313852d6e995224859494442e",
"targetId": "n5-00608",
"moleculeId": "sa_2824584c884f495713ae9604",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCNC(N)=O)cc2)cc1",
"routeLength": 7,
"isConvergent": false,
"metadata": null,
"molecule": {
"id": "sa_2824584c884f495713ae9604",
"inchikey": "GZUVRVBRBJOEET-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCNC(N)=O)cc2)cc1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "13584",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_2824584c884f495713ae9604",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_2824584c884f495713ae9604",
"inchikey": "GZUVRVBRBJOEET-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCNC(N)=O)cc2)cc1"
},
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCNC(N)=O)cc2)cc1",
"reactionStepId": "sa_1f7230446fb1bae966320235",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040157891A1;0754;180000\",\"rsmi\":\"C[Si](C)(C)[N:18]=[C:17]=[O:19].[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][NH2:16])[cH:20][cH:21]3)[o:22][c:23]([O:24][CH3:25])[n:26]2)[cH:27][cH:28]1>CCN(CC)CC.ClCCl>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][NH:16][C:17]([NH2:18])=[O:19])[cH:20][cH:21]3)[o:22][c:23]([O:24][CH3:25])[n:26]2)[cH:27][cH:28]1\"},\"mapped_reaction_smiles\":\"C[Si](C)(C)[N:18]=[C:17]=[O:19].[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][NH2:16])[cH:20][cH:21]3)[o:22][c:23]([O:24][CH3:25])[n:26]2)[cH:27][cH:28]1>CCN(CC)CC.ClCCl>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][NH:16][C:17]([NH2:18])=[O:19])[cH:20][cH:21]3)[o:22][c:23]([O:24][CH3:25])[n:26]2)[cH:27][cH:28]1\"}",
"reactionStep": {
"id": "sa_1f7230446fb1bae966320235",
"reactionHash": "b464b46e98e5f97bbbc377d6d7ba1f5168fd8c52c03f9943cdb7197be80e902d"
},
"children": [
{
"id": "13585",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_52f5cf46492adb227e481690",
"parentId": "13584",
"isLeaf": true,
"molecule": {
"id": "sa_52f5cf46492adb227e481690",
"inchikey": "NIZHERJWXFHGGU-UHFFFAOYSA-N",
"smiles": "C[Si](C)(C)N=C=O"
},
"smiles": "C[Si](C)(C)N=C=O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13586",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_a2838a781b86dcecf08f3d28",
"parentId": "13584",
"isLeaf": false,
"molecule": {
"id": "sa_a2838a781b86dcecf08f3d28",
"inchikey": "UKYQPEGCIMQSHB-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCN)cc2)cc1"
},
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCN)cc2)cc1",
"reactionStepId": "sa_4d1bcef3ab976b4b2d9b8cde",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040157891A1;0751;179999\",\"rsmi\":\"O=C1c2ccccc2C(=O)[N:16]1[CH2:15][CH2:14][O:13][c:12]1[cH:11][cH:10][c:9](-[c:8]2[c:7](-[c:6]3[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:25][cH:24]3)[n:23][c:20]([O:21][CH3:22])[o:19]2)[cH:18][cH:17]1>CCO.NN.O>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][NH2:16])[cH:17][cH:18]3)[o:19][c:20]([O:21][CH3:22])[n:23]2)[cH:24][cH:25]1\"},\"mapped_reaction_smiles\":\"O=C1c2ccccc2C(=O)[N:16]1[CH2:15][CH2:14][O:13][c:12]1[cH:11][cH:10][c:9](-[c:8]2[c:7](-[c:6]3[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:25][cH:24]3)[n:23][c:20]([O:21][CH3:22])[o:19]2)[cH:18][cH:17]1>CCO.NN.O>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][NH2:16])[cH:17][cH:18]3)[o:19][c:20]([O:21][CH3:22])[n:23]2)[cH:24][cH:25]1\"}",
"reactionStep": {
"id": "sa_4d1bcef3ab976b4b2d9b8cde",
"reactionHash": "de611f85d8d3171aa34be402122a6536b090ea227f7d9f1a657a26f693c83ec8"
},
"children": [
{
"id": "13587",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_bc54e3334ef850b872f1789f",
"parentId": "13586",
"isLeaf": false,
"molecule": {
"id": "sa_bc54e3334ef850b872f1789f",
"inchikey": "YDDZVFQZQHUYBM-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCN3C(=O)c4ccccc4C3=O)cc2)cc1"
},
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCN3C(=O)c4ccccc4C3=O)cc2)cc1",
"reactionStepId": "sa_cd2a2f99da2360a74e8e1385",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040157891A1;0748;179998\",\"rsmi\":\"CS(=O)(=O)O[CH2:15][CH2:14][O:13][c:12]1[cH:11][cH:10][c:9](-[c:8]2[c:7](-[c:6]3[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:35][cH:34]3)[n:33][c:30]([O:31][CH3:32])[o:29]2)[cH:28][cH:27]1.[NH:16]1[C:17](=[O:18])[c:19]2[cH:20][cH:21][cH:22][cH:23][c:24]2[C:25]1=[O:26]>CN(C)C=O.[K]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][N:16]4[C:17](=[O:18])[c:19]5[cH:20][cH:21][cH:22][cH:23][c:24]5[C:25]4=[O:26])[cH:27][cH:28]3)[o:29][c:30]([O:31][CH3:32])[n:33]2)[cH:34][cH:35]1\"},\"mapped_reaction_smiles\":\"CS(=O)(=O)O[CH2:15][CH2:14][O:13][c:12]1[cH:11][cH:10][c:9](-[c:8]2[c:7](-[c:6]3[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:35][cH:34]3)[n:33][c:30]([O:31][CH3:32])[o:29]2)[cH:28][cH:27]1.[NH:16]1[C:17](=[O:18])[c:19]2[cH:20][cH:21][cH:22][cH:23][c:24]2[C:25]1=[O:26]>CN(C)C=O.[K]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][N:16]4[C:17](=[O:18])[c:19]5[cH:20][cH:21][cH:22][cH:23][c:24]5[C:25]4=[O:26])[cH:27][cH:28]3)[o:29][c:30]([O:31][CH3:32])[n:33]2)[cH:34][cH:35]1\"}",
"reactionStep": {
"id": "sa_cd2a2f99da2360a74e8e1385",
"reactionHash": "7802b05cac9af0ae09964775726d13ebd6a27153921233cb1a20ec1e8b9b8fff"
},
"children": [
{
"id": "13588",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_000834deac22c1de0dd8dcbd",
"parentId": "13587",
"isLeaf": false,
"molecule": {
"id": "sa_000834deac22c1de0dd8dcbd",
"inchikey": "AHSGFZNZYLBDND-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCOS(C)(=O)=O)cc2)cc1"
},
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCOS(C)(=O)=O)cc2)cc1",
"reactionStepId": "sa_968c483314e82fdaa08afe2d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040157891A1;0746;179997\",\"rsmi\":\"Cl[S:17]([CH3:18])(=[O:19])=[O:20].[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][OH:16])[cH:21][cH:22]3)[o:23][c:24]([O:25][CH3:26])[n:27]2)[cH:28][cH:29]1>CCN(CC)CC.CCOC(C)=O>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][O:16][S:17]([CH3:18])(=[O:19])=[O:20])[cH:21][cH:22]3)[o:23][c:24]([O:25][CH3:26])[n:27]2)[cH:28][cH:29]1\"},\"mapped_reaction_smiles\":\"Cl[S:17]([CH3:18])(=[O:19])=[O:20].[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][OH:16])[cH:21][cH:22]3)[o:23][c:24]([O:25][CH3:26])[n:27]2)[cH:28][cH:29]1>CCN(CC)CC.CCOC(C)=O>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][O:16][S:17]([CH3:18])(=[O:19])=[O:20])[cH:21][cH:22]3)[o:23][c:24]([O:25][CH3:26])[n:27]2)[cH:28][cH:29]1\"}",
"reactionStep": {
"id": "sa_968c483314e82fdaa08afe2d",
"reactionHash": "213f0b923a0fddfdfffca570ffe12b17889aea7259498a4da3339d6a3038b58b"
},
"children": [
{
"id": "13589",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "13588",
"isLeaf": true,
"molecule": {
"id": "sa_d2a31ea58046b00856f61ca5",
"inchikey": "QARBMVPHQWIHKH-UHFFFAOYSA-N",
"smiles": "CS(=O)(=O)Cl"
},
"smiles": "CS(=O)(=O)Cl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13590",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_c2693bb6a12775e648d31654",
"parentId": "13588",
"isLeaf": false,
"molecule": {
"id": "sa_c2693bb6a12775e648d31654",
"inchikey": "USMSFKOBWYSKHI-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCO)cc2)cc1"
},
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCCO)cc2)cc1",
"reactionStepId": "sa_59b8c012ad691d9fd1a34999",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040157891A1;0742;179996\",\"rsmi\":\"CC(C)(C)[Si](C)(C)[O:16][CH2:15][CH2:14]Br.[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([OH:13])[cH:17][cH:18]3)[o:19][c:20]([O:21][CH3:22])[n:23]2)[cH:24][cH:25]1>CN(C)C=O.O=C(O)O.I.[K+].[K+].[K+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][OH:16])[cH:17][cH:18]3)[o:19][c:20]([O:21][CH3:22])[n:23]2)[cH:24][cH:25]1\"},\"mapped_reaction_smiles\":\"CC(C)(C)[Si](C)(C)[O:16][CH2:15][CH2:14]Br.[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([OH:13])[cH:17][cH:18]3)[o:19][c:20]([O:21][CH3:22])[n:23]2)[cH:24][cH:25]1>CN(C)C=O.O=C(O)O.I.[K+].[K+].[K+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][CH2:15][OH:16])[cH:17][cH:18]3)[o:19][c:20]([O:21][CH3:22])[n:23]2)[cH:24][cH:25]1\"}",
"reactionStep": {
"id": "sa_59b8c012ad691d9fd1a34999",
"reactionHash": "e5656560c68a4949ae734704a60c4c4617f444046cbf8abca3407f30b3defd05"
},
"children": [
{
"id": "13591",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_6a4c99999517f7b3489e7a4b",
"parentId": "13590",
"isLeaf": false,
"molecule": {
"id": "sa_6a4c99999517f7b3489e7a4b",
"inchikey": "IUTFYAWYLRXDOK-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(O)cc2)cc1"
},
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(O)cc2)cc1",
"reactionStepId": "sa_df7da647ec23be8cce4a764a",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040157891A1;0739;179995\",\"rsmi\":\"c1ccc(C[O:13][c:12]2[cH:11][cH:10][c:9](-[c:8]3[c:7](-[c:6]4[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:22][cH:21]4)[n:20][c:17]([O:18][CH3:19])[o:16]3)[cH:15][cH:14]2)cc1>C1=CCCCC1.CCO.O.O.[Pd+2]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([OH:13])[cH:14][cH:15]3)[o:16][c:17]([O:18][CH3:19])[n:20]2)[cH:21][cH:22]1\"},\"mapped_reaction_smiles\":\"c1ccc(C[O:13][c:12]2[cH:11][cH:10][c:9](-[c:8]3[c:7](-[c:6]4[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:22][cH:21]4)[n:20][c:17]([O:18][CH3:19])[o:16]3)[cH:15][cH:14]2)cc1>C1=CCCCC1.CCO.O.O.[Pd+2]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([OH:13])[cH:14][cH:15]3)[o:16][c:17]([O:18][CH3:19])[n:20]2)[cH:21][cH:22]1\"}",
"reactionStep": {
"id": "sa_df7da647ec23be8cce4a764a",
"reactionHash": "a4d4863eaff6d3c9ec8244a4671e395fe695d20ec76b8476066a34730c5ce3a4"
},
"children": [
{
"id": "13592",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_b5543904d31a812bfdda30db",
"parentId": "13591",
"isLeaf": false,
"molecule": {
"id": "sa_b5543904d31a812bfdda30db",
"inchikey": "VEAFRNJOZDOJGN-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCc3ccccc3)cc2)cc1"
},
"smiles": "COc1ccc(-c2nc(OC)oc2-c2ccc(OCc3ccccc3)cc2)cc1",
"reactionStepId": "sa_b7f5ad677ab3c564bc00d3a5",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20040157891A1;0736;179994\",\"rsmi\":\"Cl[c:24]1[o:23][c:8](-[c:9]2[cH:10][cH:11][c:12]([O:13][CH2:14][c:15]3[cH:16][cH:17][cH:18][cH:19][cH:20]3)[cH:21][cH:22]2)[c:7](-[c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:29][cH:28]2)[n:27]1.[OH:25][CH3:26]>CO.[Na+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][c:15]4[cH:16][cH:17][cH:18][cH:19][cH:20]4)[cH:21][cH:22]3)[o:23][c:24]([O:25][CH3:26])[n:27]2)[cH:28][cH:29]1\"},\"mapped_reaction_smiles\":\"Cl[c:24]1[o:23][c:8](-[c:9]2[cH:10][cH:11][c:12]([O:13][CH2:14][c:15]3[cH:16][cH:17][cH:18][cH:19][cH:20]3)[cH:21][cH:22]2)[c:7](-[c:6]2[cH:5][cH:4][c:3]([O:2][CH3:1])[cH:29][cH:28]2)[n:27]1.[OH:25][CH3:26]>CO.[Na+]>[CH3:1][O:2][c:3]1[cH:4][cH:5][c:6](-[c:7]2[c:8](-[c:9]3[cH:10][cH:11][c:12]([O:13][CH2:14][c:15]4[cH:16][cH:17][cH:18][cH:19][cH:20]4)[cH:21][cH:22]3)[o:23][c:24]([O:25][CH3:26])[n:27]2)[cH:28][cH:29]1\"}",
"reactionStep": {
"id": "sa_b7f5ad677ab3c564bc00d3a5",
"reactionHash": "eec552f54e26964b31503bc2647832dd3cb54a3ff914d48bb6cf985695df7c44"
},
"children": [
{
"id": "13593",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "13592",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "13594",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_d7f077568665c935efa5002b",
"parentId": "13592",
"isLeaf": true,
"molecule": {
"id": "sa_d7f077568665c935efa5002b",
"inchikey": "XXYAXPAZXXATNE-UHFFFAOYSA-N",
"smiles": "COc1ccc(-c2nc(Cl)oc2-c2ccc(OCc3ccccc3)cc2)cc1"
},
"smiles": "COc1ccc(-c2nc(Cl)oc2-c2ccc(OCc3ccccc3)cc2)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "13595",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_b434cf8e6af94d706ef0818c",
"parentId": "13590",
"isLeaf": true,
"molecule": {
"id": "sa_b434cf8e6af94d706ef0818c",
"inchikey": "JBKINHFZTVLNEM-UHFFFAOYSA-N",
"smiles": "CC(C)(C)[Si](C)(C)OCCBr"
},
"smiles": "CC(C)(C)[Si](C)(C)OCCBr",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "13596",
"routeId": "sa_961970954680909f9a617f27",
"moleculeId": "sa_55c000779ce0b3d5072b008b",
"parentId": "13587",
"isLeaf": true,
"molecule": {
"id": "sa_55c000779ce0b3d5072b008b",
"inchikey": "XKJCHHZQLQNZHY-UHFFFAOYSA-N",
"smiles": "O=C1N=C(O)c2ccccc21"
},
"smiles": "O=C1NC(=O)c2ccccc21",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
}