Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
CNC(=O)c1ccc(Nc2nc(NC3CCCC3)c3c(-c4ccc(O)cc4)cn(COCC[Si](C)(C)C)c3n2)c(OC)c1
InChiKey
ZDMARYSNAPKRSQ-UHFFFAOYSA-N
Route Signature
b646f7cbee35074a6ff65c93fe1b35c30f5ca8fb51d06dbd532d58fed7e77e62
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_8d47dfc19bc4e641bf8626b2",
"signature": "b646f7cbee35074a6ff65c93fe1b35c30f5ca8fb51d06dbd532d58fed7e77e62",
"contentHash": "53c63ba4e5bd228d4400b87e5b68fba1a690d535b0607a801c2c7bab502120d8",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_774033f4082265f96b007fc9",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-01014",
"moleculeId": "sa_c19649f1bff9f2a8e20901a5",
"smiles": "CNC(=O)c1ccc(Nc2nc(NC3CCCC3)c3c(-c4ccc(O)cc4)cn(COCC[Si](C)(C)C)c3n2)c(OC)c1",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_c19649f1bff9f2a8e20901a5",
"inchikey": "ZDMARYSNAPKRSQ-UHFFFAOYSA-N",
"smiles": "CNC(=O)c1ccc(Nc2nc(NC3CCCC3)c3c(-c4ccc(O)cc4)cn(COCC[Si](C)(C)C)c3n2)c(OC)c1"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9895",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_c19649f1bff9f2a8e20901a5",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_c19649f1bff9f2a8e20901a5",
"inchikey": "ZDMARYSNAPKRSQ-UHFFFAOYSA-N",
"smiles": "CNC(=O)c1ccc(Nc2nc(NC3CCCC3)c3c(-c4ccc(O)cc4)cn(COCC[Si](C)(C)C)c3n2)c(OC)c1"
},
"smiles": "CNC(=O)c1ccc(Nc2nc(NC3CCCC3)c3c(-c4ccc(O)cc4)cn(COCC[Si](C)(C)C)c3n2)c(OC)c1",
"reactionStepId": "sa_7ed988b9ef8589f59ab83c5b",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140200207A1;0176;1551159\",\"rsmi\":\"Cl[c:12]1[n:13][c:14]2[c:15]([c:16](-[c:17]3[cH:18][cH:19][c:20]([OH:21])[cH:22][cH:23]3)[cH:24][n:25]2[CH2:26][O:27][CH2:28][CH2:29][Si:30]([CH3:31])([CH3:32])[CH3:33])[c:34]([NH:35][CH:36]2[CH2:37][CH2:38][CH2:39][CH2:40]2)[n:41]1.[CH3:1][NH:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([O:8][CH3:9])[c:10]([NH2:11])[cH:42][cH:43]1>C1COCCO1.CC1(C)c2cccc(P(c3ccccc3)c3ccccc3)c2Oc2c(P(c3ccccc3)c3ccccc3)cccc21.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(O)O.[K+].[K+].[Pd].[Pd]>[CH3:1][NH:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([O:8][CH3:9])[c:10]([NH:11][c:12]2[n:13][c:14]3[c:15]([c:16](-[c:17]4[cH:18][cH:19][c:20]([OH:21])[cH:22][cH:23]4)[cH:24][n:25]3[CH2:26][O:27][CH2:28][CH2:29][Si:30]([CH3:31])([CH3:32])[CH3:33])[c:34]([NH:35][CH:36]3[CH2:37][CH2:38][CH2:39][CH2:40]3)[n:41]2)[cH:42][cH:43]1\"},\"mapped_reaction_smiles\":\"Cl[c:12]1[n:13][c:14]2[c:15]([c:16](-[c:17]3[cH:18][cH:19][c:20]([OH:21])[cH:22][cH:23]3)[cH:24][n:25]2[CH2:26][O:27][CH2:28][CH2:29][Si:30]([CH3:31])([CH3:32])[CH3:33])[c:34]([NH:35][CH:36]2[CH2:37][CH2:38][CH2:39][CH2:40]2)[n:41]1.[CH3:1][NH:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([O:8][CH3:9])[c:10]([NH2:11])[cH:42][cH:43]1>C1COCCO1.CC1(C)c2cccc(P(c3ccccc3)c3ccccc3)c2Oc2c(P(c3ccccc3)c3ccccc3)cccc21.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(/C=C/c1ccccc1)/C=C/c1ccccc1.O=C(O)O.[K+].[K+].[Pd].[Pd]>[CH3:1][NH:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([O:8][CH3:9])[c:10]([NH:11][c:12]2[n:13][c:14]3[c:15]([c:16](-[c:17]4[cH:18][cH:19][c:20]([OH:21])[cH:22][cH:23]4)[cH:24][n:25]3[CH2:26][O:27][CH2:28][CH2:29][Si:30]([CH3:31])([CH3:32])[CH3:33])[c:34]([NH:35][CH:36]3[CH2:37][CH2:38][CH2:39][CH2:40]3)[n:41]2)[cH:42][cH:43]1\"}",
"reactionStep": {
"id": "sa_7ed988b9ef8589f59ab83c5b",
"reactionHash": "3a131b2543fd6f62e3b81a96de325b93f9e3f7f7289b7f0088a158b2effd3250"
},
"children": [
{
"id": "9896",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_6567734c933bc8359224376e",
"parentId": "9895",
"isLeaf": false,
"molecule": {
"id": "sa_6567734c933bc8359224376e",
"inchikey": "DCGJHLWCPSSASD-UHFFFAOYSA-N",
"smiles": "C[Si](C)(C)CCOCn1cc(-c2ccc(O)cc2)c2c(NC3CCCC3)nc(Cl)nc21"
},
"smiles": "C[Si](C)(C)CCOCn1cc(-c2ccc(O)cc2)c2c(NC3CCCC3)nc(Cl)nc21",
"reactionStepId": "sa_846464e12f620fbe22a57eb3",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140200207A1;0175;1551158\",\"rsmi\":\"I[c:11]1[cH:10][n:9]([CH2:8][O:7][CH2:6][CH2:5][Si:2]([CH3:1])([CH3:3])[CH3:4])[c:20]2[c:19]1[c:25]([NH:26][CH:27]1[CH2:28][CH2:29][CH2:30][CH2:31]1)[n:24][c:22]([Cl:23])[n:21]2.OB(O)[c:12]1[cH:13][cH:14][c:15]([OH:16])[cH:17][cH:18]1>C1COCCO1.O.O=C(O)O.[K+].[K+].c1ccc([PH](c2ccccc2)(c2ccccc2)[Pd]([PH](c2ccccc2)(c2ccccc2)c2ccccc2)([PH](c2ccccc2)(c2ccccc2)c2ccccc2)[PH](c2ccccc2)(c2ccccc2)c2ccccc2)cc1>[CH3:1][Si:2]([CH3:3])([CH3:4])[CH2:5][CH2:6][O:7][CH2:8][n:9]1[cH:10][c:11](-[c:12]2[cH:13][cH:14][c:15]([OH:16])[cH:17][cH:18]2)[c:19]2[c:20]1[n:21][c:22]([Cl:23])[n:24][c:25]2[NH:26][CH:27]1[CH2:28][CH2:29][CH2:30][CH2:31]1\"},\"mapped_reaction_smiles\":\"I[c:11]1[cH:10][n:9]([CH2:8][O:7][CH2:6][CH2:5][Si:2]([CH3:1])([CH3:3])[CH3:4])[c:20]2[c:19]1[c:25]([NH:26][CH:27]1[CH2:28][CH2:29][CH2:30][CH2:31]1)[n:24][c:22]([Cl:23])[n:21]2.OB(O)[c:12]1[cH:13][cH:14][c:15]([OH:16])[cH:17][cH:18]1>C1COCCO1.O.O=C(O)O.[K+].[K+].c1ccc([PH](c2ccccc2)(c2ccccc2)[Pd]([PH](c2ccccc2)(c2ccccc2)c2ccccc2)([PH](c2ccccc2)(c2ccccc2)c2ccccc2)[PH](c2ccccc2)(c2ccccc2)c2ccccc2)cc1>[CH3:1][Si:2]([CH3:3])([CH3:4])[CH2:5][CH2:6][O:7][CH2:8][n:9]1[cH:10][c:11](-[c:12]2[cH:13][cH:14][c:15]([OH:16])[cH:17][cH:18]2)[c:19]2[c:20]1[n:21][c:22]([Cl:23])[n:24][c:25]2[NH:26][CH:27]1[CH2:28][CH2:29][CH2:30][CH2:31]1\"}",
"reactionStep": {
"id": "sa_846464e12f620fbe22a57eb3",
"reactionHash": "3583fd7da10633033c4db8dd3a477270cdf618153b7966f0f746fff94a75def4"
},
"children": [
{
"id": "9897",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_c61789bba57fadeea1a75725",
"parentId": "9896",
"isLeaf": true,
"molecule": {
"id": "sa_c61789bba57fadeea1a75725",
"inchikey": "COIQUVGFTILYGA-UHFFFAOYSA-N",
"smiles": "OB(O)c1ccc(O)cc1"
},
"smiles": "OB(O)c1ccc(O)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9898",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_c7a0088750e1c3f4a0de3e70",
"parentId": "9896",
"isLeaf": false,
"molecule": {
"id": "sa_c7a0088750e1c3f4a0de3e70",
"inchikey": "DPHQQTSDQAJZNZ-UHFFFAOYSA-N",
"smiles": "C[Si](C)(C)CCOCn1cc(I)c2c(NC3CCCC3)nc(Cl)nc21"
},
"smiles": "C[Si](C)(C)CCOCn1cc(I)c2c(NC3CCCC3)nc(Cl)nc21",
"reactionStepId": "sa_d6ee0a084e3239305eb81bc8",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140200207A1;0174;1551157\",\"rsmi\":\"Cl[c:19]1[c:13]2[c:11]([I:12])[cH:10][n:9]([CH2:8][O:7][CH2:6][CH2:5][Si:2]([CH3:1])([CH3:3])[CH3:4])[c:14]2[n:15][c:16]([Cl:17])[n:18]1.[NH2:20][CH:21]1[CH2:22][CH2:23][CH2:24][CH2:25]1>C1COCCO1.CC(C)(C)O.[Na+]>[CH3:1][Si:2]([CH3:3])([CH3:4])[CH2:5][CH2:6][O:7][CH2:8][n:9]1[cH:10][c:11]([I:12])[c:13]2[c:14]1[n:15][c:16]([Cl:17])[n:18][c:19]2[NH:20][CH:21]1[CH2:22][CH2:23][CH2:24][CH2:25]1\"},\"mapped_reaction_smiles\":\"Cl[c:19]1[c:13]2[c:11]([I:12])[cH:10][n:9]([CH2:8][O:7][CH2:6][CH2:5][Si:2]([CH3:1])([CH3:3])[CH3:4])[c:14]2[n:15][c:16]([Cl:17])[n:18]1.[NH2:20][CH:21]1[CH2:22][CH2:23][CH2:24][CH2:25]1>C1COCCO1.CC(C)(C)O.[Na+]>[CH3:1][Si:2]([CH3:3])([CH3:4])[CH2:5][CH2:6][O:7][CH2:8][n:9]1[cH:10][c:11]([I:12])[c:13]2[c:14]1[n:15][c:16]([Cl:17])[n:18][c:19]2[NH:20][CH:21]1[CH2:22][CH2:23][CH2:24][CH2:25]1\"}",
"reactionStep": {
"id": "sa_d6ee0a084e3239305eb81bc8",
"reactionHash": "99ceb5ae6f05de927c2338da022bf26c026feb037bd21325d1714c1d3c35aefd"
},
"children": [
{
"id": "9899",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_1eee1dc8a31bcd8a3de7d497",
"parentId": "9898",
"isLeaf": false,
"molecule": {
"id": "sa_1eee1dc8a31bcd8a3de7d497",
"inchikey": "GOSIUUKDKZGBNS-UHFFFAOYSA-N",
"smiles": "C[Si](C)(C)CCOCn1cc(I)c2c(Cl)nc(Cl)nc21"
},
"smiles": "C[Si](C)(C)CCOCn1cc(I)c2c(Cl)nc(Cl)nc21",
"reactionStepId": "sa_95d2f926a912e7c7cdb5c4fd",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140200207A1;0172;1551156\",\"rsmi\":\"Cl[CH2:8][O:7][CH2:6][CH2:5][Si:2]([CH3:1])([CH3:3])[CH3:4].[nH:9]1[cH:10][c:11]([I:12])[c:13]2[c:14]1[n:15][c:16]([Cl:17])[n:18][c:19]2[Cl:20]>CN(C)C=O.ClCCl.O.Cl.[HH].N.[Na+]>[CH3:1][Si:2]([CH3:3])([CH3:4])[CH2:5][CH2:6][O:7][CH2:8][n:9]1[cH:10][c:11]([I:12])[c:13]2[c:14]1[n:15][c:16]([Cl:17])[n:18][c:19]2[Cl:20]\"},\"mapped_reaction_smiles\":\"Cl[CH2:8][O:7][CH2:6][CH2:5][Si:2]([CH3:1])([CH3:3])[CH3:4].[nH:9]1[cH:10][c:11]([I:12])[c:13]2[c:14]1[n:15][c:16]([Cl:17])[n:18][c:19]2[Cl:20]>CN(C)C=O.ClCCl.O.Cl.[HH].N.[Na+]>[CH3:1][Si:2]([CH3:3])([CH3:4])[CH2:5][CH2:6][O:7][CH2:8][n:9]1[cH:10][c:11]([I:12])[c:13]2[c:14]1[n:15][c:16]([Cl:17])[n:18][c:19]2[Cl:20]\"}",
"reactionStep": {
"id": "sa_95d2f926a912e7c7cdb5c4fd",
"reactionHash": "8362ff53ac78bc31db667838f54b4e47b45ef9a227484c97a9d04141f1467c93"
},
"children": [
{
"id": "9900",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_57270a1e21fabfe8968ff93f",
"parentId": "9899",
"isLeaf": true,
"molecule": {
"id": "sa_57270a1e21fabfe8968ff93f",
"inchikey": "BPXKZEMBEZGUAH-UHFFFAOYSA-N",
"smiles": "C[Si](C)(C)CCOCCl"
},
"smiles": "C[Si](C)(C)CCOCCl",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9901",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_cd945afa263011d2260ca12b",
"parentId": "9899",
"isLeaf": false,
"molecule": {
"id": "sa_cd945afa263011d2260ca12b",
"inchikey": "RIRSSBIXHXMTLS-UHFFFAOYSA-N",
"smiles": "Clc1nc(Cl)c2c(I)c[nH]c2n1"
},
"smiles": "Clc1nc(Cl)c2c(I)c[nH]c2n1",
"reactionStepId": "sa_4c1cf7014a8f8ee64046eb78",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140200207A1;0171;1551155\",\"rsmi\":\"O=C1CCC(=O)N1[I:7].[Cl:1][c:2]1[n:3][c:4]2[c:5]([cH:6][cH:8][nH:9]2)[c:10]([Cl:11])[n:12]1>ClCCl>[Cl:1][c:2]1[n:3][c:4]2[c:5]([c:6]([I:7])[cH:8][nH:9]2)[c:10]([Cl:11])[n:12]1\"},\"mapped_reaction_smiles\":\"O=C1CCC(=O)N1[I:7].[Cl:1][c:2]1[n:3][c:4]2[c:5]([cH:6][cH:8][nH:9]2)[c:10]([Cl:11])[n:12]1>ClCCl>[Cl:1][c:2]1[n:3][c:4]2[c:5]([c:6]([I:7])[cH:8][nH:9]2)[c:10]([Cl:11])[n:12]1\"}",
"reactionStep": {
"id": "sa_4c1cf7014a8f8ee64046eb78",
"reactionHash": "bce614a86a8cd5e927152850465384e10aa295353a3fb8571af11badad8b8177"
},
"children": [
{
"id": "9902",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_2674bbc3874704f85fca042b",
"parentId": "9901",
"isLeaf": true,
"molecule": {
"id": "sa_2674bbc3874704f85fca042b",
"inchikey": "GHXBPCSSQOKKGB-UHFFFAOYSA-N",
"smiles": "Clc1nc(Cl)c2cc[nH]c2n1"
},
"smiles": "Clc1nc(Cl)c2cc[nH]c2n1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9903",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_e0a6dc663dcf837255678d0a",
"parentId": "9901",
"isLeaf": true,
"molecule": {
"id": "sa_e0a6dc663dcf837255678d0a",
"inchikey": "LQZMLBORDGWNPD-UHFFFAOYSA-N",
"smiles": "O=C1CCC(=O)N1I"
},
"smiles": "O=C1CCC(=O)N1I",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "9904",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_882a71327a5153424650c51e",
"parentId": "9898",
"isLeaf": true,
"molecule": {
"id": "sa_882a71327a5153424650c51e",
"inchikey": "NISGSNTVMOOSJQ-UHFFFAOYSA-N",
"smiles": "NC1CCCC1"
},
"smiles": "NC1CCCC1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "9905",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_836c556842c4fb1320227fd5",
"parentId": "9895",
"isLeaf": false,
"molecule": {
"id": "sa_836c556842c4fb1320227fd5",
"inchikey": "WPMXJQCASHLEMI-UHFFFAOYSA-N",
"smiles": "CNC(=O)c1ccc(N)c(OC)c1"
},
"smiles": "CNC(=O)c1ccc(N)c(OC)c1",
"reactionStepId": "sa_d959fca72e381d77b4ff101f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20140200207A1;0180;1551161\",\"rsmi\":\"O[C:3](=[O:4])[c:5]1[cH:6][c:7]([O:8][CH3:9])[c:10]([NH2:11])[cH:12][cH:13]1.[CH3:1][NH2:2]>CN(C)C(On1nnc2cccnc21)=[N+](C)C.Cl.F[PH](F)(F)(F)(F)F.O=C(O)O.[Na+]>[CH3:1][NH:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([O:8][CH3:9])[c:10]([NH2:11])[cH:12][cH:13]1\"},\"mapped_reaction_smiles\":\"O[C:3](=[O:4])[c:5]1[cH:6][c:7]([O:8][CH3:9])[c:10]([NH2:11])[cH:12][cH:13]1.[CH3:1][NH2:2]>CN(C)C(On1nnc2cccnc21)=[N+](C)C.Cl.F[PH](F)(F)(F)(F)F.O=C(O)O.[Na+]>[CH3:1][NH:2][C:3](=[O:4])[c:5]1[cH:6][c:7]([O:8][CH3:9])[c:10]([NH2:11])[cH:12][cH:13]1\"}",
"reactionStep": {
"id": "sa_d959fca72e381d77b4ff101f",
"reactionHash": "05af16ebb22cbcb490823dd3e07372cfe6525c8b72a4bbc949c8daeee67d494b"
},
"children": [
{
"id": "9906",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_e00cdbb7fb9d3ecf114a19d3",
"parentId": "9905",
"isLeaf": true,
"molecule": {
"id": "sa_e00cdbb7fb9d3ecf114a19d3",
"inchikey": "BAVYZALUXZFZLV-UHFFFAOYSA-N",
"smiles": "CN"
},
"smiles": "CN",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9907",
"routeId": "sa_8d47dfc19bc4e641bf8626b2",
"moleculeId": "sa_9df556c4cedf43db961e5bf0",
"parentId": "9905",
"isLeaf": true,
"molecule": {
"id": "sa_9df556c4cedf43db961e5bf0",
"inchikey": "JNFGLYJROFAOQP-UHFFFAOYSA-N",
"smiles": "COc1cc(C(=O)O)ccc1N"
},
"smiles": "COc1cc(C(=O)O)ccc1N",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
}