Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)NOC1CCCCO1)CC(C)C
InChiKey
YYRSQNXFTZXXGE-ZDOMSUIMSA-N
Route Signature
366d140d6818d6d07f1a96b5629c54ef725c7dfc8437a24efc8828233e2aa2a8
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_c07cc7b1eeb8aa7326553fb9",
"signature": "366d140d6818d6d07f1a96b5629c54ef725c7dfc8437a24efc8828233e2aa2a8",
"contentHash": "cfe97967800cbcbfe0b15c0e044dfe029ed51026ee03530f4aefa4f2abc0ef5f",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_c8a4e176abfa11a6af929b38",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00354",
"moleculeId": "sa_d08522bb05529e3469db3bc6",
"smiles": "CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)NOC1CCCCO1)CC(C)C",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_d08522bb05529e3469db3bc6",
"inchikey": "YYRSQNXFTZXXGE-ZDOMSUIMSA-N",
"smiles": "CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)NOC1CCCCO1)CC(C)C"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9427",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_d08522bb05529e3469db3bc6",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_d08522bb05529e3469db3bc6",
"inchikey": "YYRSQNXFTZXXGE-ZDOMSUIMSA-N",
"smiles": "CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)NOC1CCCCO1)CC(C)C"
},
"smiles": "CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)NOC1CCCCO1)CC(C)C",
"reactionStepId": "sa_5f5e859564d359a237226a9b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070049518A1;0151;435294\",\"rsmi\":\"O[C:19]([CH2:18][C@@H:17]([C:15]([NH:14][C@H:5]([C:3]([NH:2][CH3:1])=[O:4])[CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)=[O:16])[CH2:29][CH:30]([CH3:31])[CH3:32])=[O:20].[NH2:21][O:22][CH:23]1[CH2:24][CH2:25][CH2:26][CH2:27][O:28]1>C1CCOC1.CCN(CC)CC.ClCCCl.On1nnc2ccccc21>[CH3:1][NH:2][C:3](=[O:4])[C@H:5]([CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)[NH:14][C:15](=[O:16])[C@H:17]([CH2:18][C:19](=[O:20])[NH:21][O:22][CH:23]1[CH2:24][CH2:25][CH2:26][CH2:27][O:28]1)[CH2:29][CH:30]([CH3:31])[CH3:32]\"},\"mapped_reaction_smiles\":\"O[C:19]([CH2:18][C@@H:17]([C:15]([NH:14][C@H:5]([C:3]([NH:2][CH3:1])=[O:4])[CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)=[O:16])[CH2:29][CH:30]([CH3:31])[CH3:32])=[O:20].[NH2:21][O:22][CH:23]1[CH2:24][CH2:25][CH2:26][CH2:27][O:28]1>C1CCOC1.CCN(CC)CC.ClCCCl.On1nnc2ccccc21>[CH3:1][NH:2][C:3](=[O:4])[C@H:5]([CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)[NH:14][C:15](=[O:16])[C@H:17]([CH2:18][C:19](=[O:20])[NH:21][O:22][CH:23]1[CH2:24][CH2:25][CH2:26][CH2:27][O:28]1)[CH2:29][CH:30]([CH3:31])[CH3:32]\"}",
"reactionStep": {
"id": "sa_5f5e859564d359a237226a9b",
"reactionHash": "9480bd57fb77d213fbc5b11784e247a2328a5bad5d4d380fbf16b03045a2eb5a"
},
"children": [
{
"id": "9428",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_be55ebe390d60a6d6bfad752",
"parentId": "9427",
"isLeaf": true,
"molecule": {
"id": "sa_be55ebe390d60a6d6bfad752",
"inchikey": "NLXXVSKHVGDQAT-UHFFFAOYSA-N",
"smiles": "NOC1CCCCO1"
},
"smiles": "NOC1CCCCO1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9429",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_6846a5e755ef18aa09ba4b84",
"parentId": "9427",
"isLeaf": false,
"molecule": {
"id": "sa_6846a5e755ef18aa09ba4b84",
"inchikey": "VTGLWMUUTZYOEZ-HOTGVXAUSA-N",
"smiles": "CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)O)CC(C)C"
},
"smiles": "CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)O)CC(C)C",
"reactionStepId": "sa_f82930fa132695e4dbd9a5f1",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070049518A1;0149;435293\",\"rsmi\":\"CC(C)(C)[O:21][C:19]([CH2:18][C@@H:17]([C:15]([NH:14][C@H:5]([C:3]([NH:2][CH3:1])=[O:4])[CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)=[O:16])[CH2:22][CH:23]([CH3:24])[CH3:25])=[O:20]>ClCCl.O=C(O)C(F)(F)F>[CH3:1][NH:2][C:3](=[O:4])[C@H:5]([CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)[NH:14][C:15](=[O:16])[C@H:17]([CH2:18][C:19](=[O:20])[OH:21])[CH2:22][CH:23]([CH3:24])[CH3:25]\"},\"mapped_reaction_smiles\":\"CC(C)(C)[O:21][C:19]([CH2:18][C@@H:17]([C:15]([NH:14][C@H:5]([C:3]([NH:2][CH3:1])=[O:4])[CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)=[O:16])[CH2:22][CH:23]([CH3:24])[CH3:25])=[O:20]>ClCCl.O=C(O)C(F)(F)F>[CH3:1][NH:2][C:3](=[O:4])[C@H:5]([CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)[NH:14][C:15](=[O:16])[C@H:17]([CH2:18][C:19](=[O:20])[OH:21])[CH2:22][CH:23]([CH3:24])[CH3:25]\"}",
"reactionStep": {
"id": "sa_f82930fa132695e4dbd9a5f1",
"reactionHash": "b442f58d7b1812cb7610e9797e5ce143f9291a885be14d1ea80f2dbcccebc215"
},
"children": [
{
"id": "9430",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_cbee18ab94cbd9a70804008b",
"parentId": "9429",
"isLeaf": false,
"molecule": {
"id": "sa_cbee18ab94cbd9a70804008b",
"inchikey": "CRMZQZSIOMIXNK-OALUTQOASA-N",
"smiles": "CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)OC(C)(C)C)CC(C)C"
},
"smiles": "CNC(=O)[C@H](CCc1ccccc1)NC(=O)[C@H](CC(=O)OC(C)(C)C)CC(C)C",
"reactionStepId": "sa_82992fbc1b8015e963253eab",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070049518A1;0147;435292\",\"rsmi\":\"O[C:15](=[O:16])[C@H:17]([CH2:18][C:19](=[O:20])[O:21][C:22]([CH3:23])([CH3:24])[CH3:25])[CH2:26][CH:27]([CH3:28])[CH3:29].[CH3:1][NH:2][C:3](=[O:4])[C@H:5]([CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)[NH2:14]>CCN(CC)CC.CN(C)C=O.ClCCCl.On1nnc2ccccc21>[CH3:1][NH:2][C:3](=[O:4])[C@H:5]([CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)[NH:14][C:15](=[O:16])[C@H:17]([CH2:18][C:19](=[O:20])[O:21][C:22]([CH3:23])([CH3:24])[CH3:25])[CH2:26][CH:27]([CH3:28])[CH3:29]\"},\"mapped_reaction_smiles\":\"O[C:15](=[O:16])[C@H:17]([CH2:18][C:19](=[O:20])[O:21][C:22]([CH3:23])([CH3:24])[CH3:25])[CH2:26][CH:27]([CH3:28])[CH3:29].[CH3:1][NH:2][C:3](=[O:4])[C@H:5]([CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)[NH2:14]>CCN(CC)CC.CN(C)C=O.ClCCCl.On1nnc2ccccc21>[CH3:1][NH:2][C:3](=[O:4])[C@H:5]([CH2:6][CH2:7][c:8]1[cH:9][cH:10][cH:11][cH:12][cH:13]1)[NH:14][C:15](=[O:16])[C@H:17]([CH2:18][C:19](=[O:20])[O:21][C:22]([CH3:23])([CH3:24])[CH3:25])[CH2:26][CH:27]([CH3:28])[CH3:29]\"}",
"reactionStep": {
"id": "sa_82992fbc1b8015e963253eab",
"reactionHash": "ea7dc70ee48c8fc1d70090ac35ad00a7c57945d0597109eca4c4502dd7308938"
},
"children": [
{
"id": "9431",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_a208c9abfd9dcdeccfb08820",
"parentId": "9430",
"isLeaf": false,
"molecule": {
"id": "sa_a208c9abfd9dcdeccfb08820",
"inchikey": "NPIMKSLXCPUXPD-VIFPVBQESA-N",
"smiles": "CC(C)C[C@@H](CC(=O)OC(C)(C)C)C(=O)O"
},
"smiles": "CC(C)C[C@@H](CC(=O)OC(C)(C)C)C(=O)O",
"reactionStepId": "sa_e0d9f7768a27a56c40303229",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070049518A1;0146;435291\",\"rsmi\":\"C[O:16][C:14]([C@@H:5]([CH2:4][CH:2]([CH3:1])[CH3:3])[CH2:6][C:7](=[O:8])[O:9][C:10]([CH3:11])([CH3:12])[CH3:13])=[O:15]>CO.O.O=C(O)O.[K+].[K+]>[CH3:1][CH:2]([CH3:3])[CH2:4][C@@H:5]([CH2:6][C:7](=[O:8])[O:9][C:10]([CH3:11])([CH3:12])[CH3:13])[C:14](=[O:15])[OH:16]\"},\"mapped_reaction_smiles\":\"C[O:16][C:14]([C@@H:5]([CH2:4][CH:2]([CH3:1])[CH3:3])[CH2:6][C:7](=[O:8])[O:9][C:10]([CH3:11])([CH3:12])[CH3:13])=[O:15]>CO.O.O=C(O)O.[K+].[K+]>[CH3:1][CH:2]([CH3:3])[CH2:4][C@@H:5]([CH2:6][C:7](=[O:8])[O:9][C:10]([CH3:11])([CH3:12])[CH3:13])[C:14](=[O:15])[OH:16]\"}",
"reactionStep": {
"id": "sa_e0d9f7768a27a56c40303229",
"reactionHash": "57e643bb1c5a7d7df4cc5011a8d7e32c61372acc6f534dd597669558d920c48f"
},
"children": [
{
"id": "9432",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_83c0aa48c9bcd491ad3db987",
"parentId": "9431",
"isLeaf": false,
"molecule": {
"id": "sa_83c0aa48c9bcd491ad3db987",
"inchikey": "FHXGVGJIGPALII-JTQLQIEISA-N",
"smiles": "COC(=O)[C@H](CC(=O)OC(C)(C)C)CC(C)C"
},
"smiles": "COC(=O)[C@H](CC(=O)OC(C)(C)C)CC(C)C",
"reactionStepId": "sa_51f40b1c3c9501254aa145a2",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070049518A1;0144;435290\",\"rsmi\":\"CC(C)(C)OC(=O)OC(=O)O[C:10]([CH3:11])([CH3:12])[CH3:13].[CH3:1][O:2][C:3](=[O:4])[C@H:5]([CH2:6][C:7](=[O:8])[OH:9])[CH2:14][CH:15]([CH3:16])[CH3:17]>CC(C)(C)O.CN(C)c1ccncc1>[CH3:1][O:2][C:3](=[O:4])[C@H:5]([CH2:6][C:7](=[O:8])[O:9][C:10]([CH3:11])([CH3:12])[CH3:13])[CH2:14][CH:15]([CH3:16])[CH3:17]\"},\"mapped_reaction_smiles\":\"CC(C)(C)OC(=O)OC(=O)O[C:10]([CH3:11])([CH3:12])[CH3:13].[CH3:1][O:2][C:3](=[O:4])[C@H:5]([CH2:6][C:7](=[O:8])[OH:9])[CH2:14][CH:15]([CH3:16])[CH3:17]>CC(C)(C)O.CN(C)c1ccncc1>[CH3:1][O:2][C:3](=[O:4])[C@H:5]([CH2:6][C:7](=[O:8])[O:9][C:10]([CH3:11])([CH3:12])[CH3:13])[CH2:14][CH:15]([CH3:16])[CH3:17]\"}",
"reactionStep": {
"id": "sa_51f40b1c3c9501254aa145a2",
"reactionHash": "db5e9fe9a1b88d329028d66bccd1f6c999692c693b053e704a1362aa4e6f581b"
},
"children": [
{
"id": "9433",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_524422860939622592e9fd1b",
"parentId": "9432",
"isLeaf": true,
"molecule": {
"id": "sa_524422860939622592e9fd1b",
"inchikey": "AJNNFMRCMKGYHA-ZETCQYMHSA-N",
"smiles": "COC(=O)[C@H](CC(=O)O)CC(C)C"
},
"smiles": "COC(=O)[C@H](CC(=O)O)CC(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9434",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_b273d4d4546165bca2b249b5",
"parentId": "9432",
"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": "9435",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_26c87b8af78436b212809e15",
"parentId": "9430",
"isLeaf": false,
"molecule": {
"id": "sa_26c87b8af78436b212809e15",
"inchikey": "XVBCPGOCLOUCLE-JTQLQIEISA-N",
"smiles": "CNC(=O)[C@@H](N)CCc1ccccc1"
},
"smiles": "CNC(=O)[C@@H](N)CCc1ccccc1",
"reactionStepId": "sa_6365e6016203b326e33b4e4f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070049518A1;0131;435288\",\"rsmi\":\"CO[C:3](=[O:4])[C@@H:5]([NH2:6])[CH2:7][CH2:8][c:9]1[cH:10][cH:11][cH:12][cH:13][cH:14]1.[CH3:1][NH2:2]>CCO.Cl>[CH3:1][NH:2][C:3](=[O:4])[C@@H:5]([NH2:6])[CH2:7][CH2:8][c:9]1[cH:10][cH:11][cH:12][cH:13][cH:14]1\"},\"mapped_reaction_smiles\":\"CO[C:3](=[O:4])[C@@H:5]([NH2:6])[CH2:7][CH2:8][c:9]1[cH:10][cH:11][cH:12][cH:13][cH:14]1.[CH3:1][NH2:2]>CCO.Cl>[CH3:1][NH:2][C:3](=[O:4])[C@@H:5]([NH2:6])[CH2:7][CH2:8][c:9]1[cH:10][cH:11][cH:12][cH:13][cH:14]1\"}",
"reactionStep": {
"id": "sa_6365e6016203b326e33b4e4f",
"reactionHash": "d8d974e2b6638d5c2089a3e22b5bef16ff3f8d05dab3afaf633a7bec6f82c2bf"
},
"children": [
{
"id": "9436",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_e00cdbb7fb9d3ecf114a19d3",
"parentId": "9435",
"isLeaf": true,
"molecule": {
"id": "sa_e00cdbb7fb9d3ecf114a19d3",
"inchikey": "BAVYZALUXZFZLV-UHFFFAOYSA-N",
"smiles": "CN"
},
"smiles": "CN",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9437",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_fd64a34bf50299db9f9cced9",
"parentId": "9435",
"isLeaf": false,
"molecule": {
"id": "sa_fd64a34bf50299db9f9cced9",
"inchikey": "YEPNFOMBMXWUOG-JTQLQIEISA-N",
"smiles": "COC(=O)[C@@H](N)CCc1ccccc1"
},
"smiles": "COC(=O)[C@@H](N)CCc1ccccc1",
"reactionStepId": "sa_50df4f831fe4409cfe52a4cf",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20070049518A1;0129;435287\",\"rsmi\":\"O[C:3](=[O:4])[C@@H:5]([NH2:6])[CH2:7][CH2:8][c:9]1[cH:10][cH:11][cH:12][cH:13][cH:14]1.[CH3:1][OH:2]>O=S(Cl)Cl>[CH3:1][O:2][C:3](=[O:4])[C@@H:5]([NH2:6])[CH2:7][CH2:8][c:9]1[cH:10][cH:11][cH:12][cH:13][cH:14]1\"},\"mapped_reaction_smiles\":\"O[C:3](=[O:4])[C@@H:5]([NH2:6])[CH2:7][CH2:8][c:9]1[cH:10][cH:11][cH:12][cH:13][cH:14]1.[CH3:1][OH:2]>O=S(Cl)Cl>[CH3:1][O:2][C:3](=[O:4])[C@@H:5]([NH2:6])[CH2:7][CH2:8][c:9]1[cH:10][cH:11][cH:12][cH:13][cH:14]1\"}",
"reactionStep": {
"id": "sa_50df4f831fe4409cfe52a4cf",
"reactionHash": "7fab8cfe9fab3dc9ac58c790b2ec531563f28a492ee4ed8edc226ceecc723341"
},
"children": [
{
"id": "9438",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_632e30a48059777505ff94ef",
"parentId": "9437",
"isLeaf": true,
"molecule": {
"id": "sa_632e30a48059777505ff94ef",
"inchikey": "JTTHKOPSMAVJFE-VIFPVBQESA-N",
"smiles": "N[C@@H](CCc1ccccc1)C(=O)O"
},
"smiles": "N[C@@H](CCc1ccccc1)C(=O)O",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9439",
"routeId": "sa_c07cc7b1eeb8aa7326553fb9",
"moleculeId": "sa_061a3efbe4d30c2cc87d48e7",
"parentId": "9437",
"isLeaf": true,
"molecule": {
"id": "sa_061a3efbe4d30c2cc87d48e7",
"inchikey": "OKKJLVBELUTLKV-UHFFFAOYSA-N",
"smiles": "CO"
},
"smiles": "CO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
]
}
}