Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
COc1cc(C#Cc2cncc(C#N)c2)ccc1F
InChiKey
VNZBLRSHSWFLKY-UHFFFAOYSA-N
Route Signature
44e2c6f52aa11a8e62f305079683abcec5b9903912296b4023bb884bdbb001dc
Synthesis route with 4 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_32d9601b99d1a99a8c842010",
"signature": "44e2c6f52aa11a8e62f305079683abcec5b9903912296b4023bb884bdbb001dc",
"contentHash": "73476944c9630795bd74889899b1e5a9e035ee9d4d874a8f05236343d0a3e013",
"length": 4,
"isConvergent": true
},
"target": {
"id": "sa_16655594100a23fc5534b072",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-00502",
"moleculeId": "sa_950d8db977f99ab2a65e5f4a",
"smiles": "COc1cc(C#Cc2cncc(C#N)c2)ccc1F",
"routeLength": 4,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_950d8db977f99ab2a65e5f4a",
"inchikey": "VNZBLRSHSWFLKY-UHFFFAOYSA-N",
"smiles": "COc1cc(C#Cc2cncc(C#N)c2)ccc1F"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "9531",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_950d8db977f99ab2a65e5f4a",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_950d8db977f99ab2a65e5f4a",
"inchikey": "VNZBLRSHSWFLKY-UHFFFAOYSA-N",
"smiles": "COc1cc(C#Cc2cncc(C#N)c2)ccc1F"
},
"smiles": "COc1cc(C#Cc2cncc(C#N)c2)ccc1F",
"reactionStepId": "sa_30953f2cd4436788f4930996",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194647A1;0465;600846\",\"rsmi\":\"I[CH3:1].[OH:2][c:3]1[c:4]([F:5])[cH:6][cH:7][c:8]([C:9]#[C:10][c:11]2[cH:12][c:13]([C:14]#[N:15])[cH:16][n:17][cH:18]2)[cH:19]1>CC#N.O=C(O)O.O=CO.[K+].[K+].[Na+]>[CH3:1][O:2][c:3]1[c:4]([F:5])[cH:6][cH:7][c:8]([C:9]#[C:10][c:11]2[cH:12][c:13]([C:14]#[N:15])[cH:16][n:17][cH:18]2)[cH:19]1\"},\"mapped_reaction_smiles\":\"I[CH3:1].[OH:2][c:3]1[c:4]([F:5])[cH:6][cH:7][c:8]([C:9]#[C:10][c:11]2[cH:12][c:13]([C:14]#[N:15])[cH:16][n:17][cH:18]2)[cH:19]1>CC#N.O=C(O)O.O=CO.[K+].[K+].[Na+]>[CH3:1][O:2][c:3]1[c:4]([F:5])[cH:6][cH:7][c:8]([C:9]#[C:10][c:11]2[cH:12][c:13]([C:14]#[N:15])[cH:16][n:17][cH:18]2)[cH:19]1\"}",
"reactionStep": {
"id": "sa_30953f2cd4436788f4930996",
"reactionHash": "0f68dcce36ea4a365001465f6d6f745e60a7b050b83cb1eec643aa1be26a2806"
},
"children": [
{
"id": "9532",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "9531",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9533",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_8b1f51ef55f24dd21492ad11",
"parentId": "9531",
"isLeaf": false,
"molecule": {
"id": "sa_8b1f51ef55f24dd21492ad11",
"inchikey": "SHLCOYCEVKUIEW-UHFFFAOYSA-N",
"smiles": "N#Cc1cncc(C#Cc2ccc(F)c(O)c2)c1"
},
"smiles": "N#Cc1cncc(C#Cc2ccc(F)c(O)c2)c1",
"reactionStepId": "sa_1e67da51d18301837c4b88ae",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194647A1;0463;600845\",\"rsmi\":\"I[c:10]1[cH:11][c:12]([OH:13])[c:14]([F:15])[cH:16][cH:17]1.[N:1]#[C:2][c:3]1[cH:4][n:5][cH:6][c:7]([C:8]#[CH:9])[cH:18]1>C1COCCO1.CC(C)(C)P(C(C)(C)C)C(C)(C)C.CCNCC.CCOCC.[Cu]I>[N:1]#[C:2][c:3]1[cH:4][n:5][cH:6][c:7]([C:8]#[C:9][c:10]2[cH:11][c:12]([OH:13])[c:14]([F:15])[cH:16][cH:17]2)[cH:18]1\"},\"mapped_reaction_smiles\":\"I[c:10]1[cH:11][c:12]([OH:13])[c:14]([F:15])[cH:16][cH:17]1.[N:1]#[C:2][c:3]1[cH:4][n:5][cH:6][c:7]([C:8]#[CH:9])[cH:18]1>C1COCCO1.CC(C)(C)P(C(C)(C)C)C(C)(C)C.CCNCC.CCOCC.[Cu]I>[N:1]#[C:2][c:3]1[cH:4][n:5][cH:6][c:7]([C:8]#[C:9][c:10]2[cH:11][c:12]([OH:13])[c:14]([F:15])[cH:16][cH:17]2)[cH:18]1\"}",
"reactionStep": {
"id": "sa_1e67da51d18301837c4b88ae",
"reactionHash": "f2acfeac1d129d3b913fdace1658b03ee816860706994cae2172e91817a5ffc6"
},
"children": [
{
"id": "9534",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_c70d443d12a4c4bb8e3b00e2",
"parentId": "9533",
"isLeaf": false,
"molecule": {
"id": "sa_c70d443d12a4c4bb8e3b00e2",
"inchikey": "BHGKLLLDELXBOR-UHFFFAOYSA-N",
"smiles": "C#Cc1cncc(C#N)c1"
},
"smiles": "C#Cc1cncc(C#N)c1",
"reactionStepId": "sa_faf0db42fcf24f7144d03783",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194647A1;0196;600762\",\"rsmi\":\"C[Si](C)(C)[C:1]#[C:2][c:3]1[cH:4][c:5]([C:6]#[N:7])[cH:8][n:9][cH:10]1>C1CCOC1.CCCC[N+](CCCC)(CCCC)CCCC.CCN(CC)CC.CCOC(C)=O.F>[CH:1]#[C:2][c:3]1[cH:4][c:5]([C:6]#[N:7])[cH:8][n:9][cH:10]1\"},\"mapped_reaction_smiles\":\"C[Si](C)(C)[C:1]#[C:2][c:3]1[cH:4][c:5]([C:6]#[N:7])[cH:8][n:9][cH:10]1>C1CCOC1.CCCC[N+](CCCC)(CCCC)CCCC.CCN(CC)CC.CCOC(C)=O.F>[CH:1]#[C:2][c:3]1[cH:4][c:5]([C:6]#[N:7])[cH:8][n:9][cH:10]1\"}",
"reactionStep": {
"id": "sa_faf0db42fcf24f7144d03783",
"reactionHash": "751ec72caf5bd2b68deaad11609d0c686bf5af4035c9a0c239c48eb80196e1dd"
},
"children": [
{
"id": "9535",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_cc124dbe464f71b3fc0e7957",
"parentId": "9534",
"isLeaf": false,
"molecule": {
"id": "sa_cc124dbe464f71b3fc0e7957",
"inchikey": "KYRGXHJJVLHTSE-UHFFFAOYSA-N",
"smiles": "C[Si](C)(C)C#Cc1cncc(C#N)c1"
},
"smiles": "C[Si](C)(C)C#Cc1cncc(C#N)c1",
"reactionStepId": "sa_099748594b90bea692846d0f",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194647A1;0194;600761\",\"rsmi\":\"Br[c:7]1[cH:8][c:9]([C:10]#[N:11])[cH:12][n:13][cH:14]1.[CH3:1][Si:2]([CH3:3])([CH3:4])[C:5]#[CH:6]>CCN(CC)CC.CCOC(C)=O.[Cu]I.c1ccc([PH]([Pd][PH](c2ccccc2)(c2ccccc2)c2ccccc2)(c2ccccc2)c2ccccc2)cc1>[CH3:1][Si:2]([CH3:3])([CH3:4])[C:5]#[C:6][c:7]1[cH:8][c:9]([C:10]#[N:11])[cH:12][n:13][cH:14]1\"},\"mapped_reaction_smiles\":\"Br[c:7]1[cH:8][c:9]([C:10]#[N:11])[cH:12][n:13][cH:14]1.[CH3:1][Si:2]([CH3:3])([CH3:4])[C:5]#[CH:6]>CCN(CC)CC.CCOC(C)=O.[Cu]I.c1ccc([PH]([Pd][PH](c2ccccc2)(c2ccccc2)c2ccccc2)(c2ccccc2)c2ccccc2)cc1>[CH3:1][Si:2]([CH3:3])([CH3:4])[C:5]#[C:6][c:7]1[cH:8][c:9]([C:10]#[N:11])[cH:12][n:13][cH:14]1\"}",
"reactionStep": {
"id": "sa_099748594b90bea692846d0f",
"reactionHash": "99f1d17e6016de101f591f26308758af00bf2d27ad5d7d1d06e6ea6b0912bc6d"
},
"children": [
{
"id": "9536",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_95a9277ba0d873f43bb42b7f",
"parentId": "9535",
"isLeaf": true,
"molecule": {
"id": "sa_95a9277ba0d873f43bb42b7f",
"inchikey": "CWMFRHBXRUITQE-UHFFFAOYSA-N",
"smiles": "C#C[Si](C)(C)C"
},
"smiles": "C#C[Si](C)(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9537",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_fb476cdd226c03fb4fad4967",
"parentId": "9535",
"isLeaf": true,
"molecule": {
"id": "sa_fb476cdd226c03fb4fad4967",
"inchikey": "FTFFHWWIPOQCBC-UHFFFAOYSA-N",
"smiles": "N#Cc1cncc(Br)c1"
},
"smiles": "N#Cc1cncc(Br)c1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
},
{
"id": "9538",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_8f88d7e863fdde29620f8ee7",
"parentId": "9533",
"isLeaf": false,
"molecule": {
"id": "sa_8f88d7e863fdde29620f8ee7",
"inchikey": "JDGBFLDXIZQLLT-UHFFFAOYSA-N",
"smiles": "Oc1cc(I)ccc1F"
},
"smiles": "Oc1cc(I)ccc1F",
"reactionStepId": "sa_afbb3a64a07757a420195862",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194647A1;0228;600776\",\"rsmi\":\"OB(O)[c:2]1[c:3]([F:4])[cH:5][cH:6][c:7]([I:8])[cH:9]1.O[OH:1]>C1CCOC1.[Mn+4].[Na+].[O-2].[O-2].O>[OH:1][c:2]1[c:3]([F:4])[cH:5][cH:6][c:7]([I:8])[cH:9]1\"},\"mapped_reaction_smiles\":\"OB(O)[c:2]1[c:3]([F:4])[cH:5][cH:6][c:7]([I:8])[cH:9]1.O[OH:1]>C1CCOC1.[Mn+4].[Na+].[O-2].[O-2].O>[OH:1][c:2]1[c:3]([F:4])[cH:5][cH:6][c:7]([I:8])[cH:9]1\"}",
"reactionStep": {
"id": "sa_afbb3a64a07757a420195862",
"reactionHash": "53975f108632e990e5b0b824117767961e07257cb93cb904191d65e9218bc279"
},
"children": [
{
"id": "9539",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_4dba68d938224067da688ab5",
"parentId": "9538",
"isLeaf": true,
"molecule": {
"id": "sa_4dba68d938224067da688ab5",
"inchikey": "MHAJPDPJQMAIIY-UHFFFAOYSA-N",
"smiles": "OO"
},
"smiles": "OO",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9540",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_1ee93ff53821278525644b49",
"parentId": "9538",
"isLeaf": false,
"molecule": {
"id": "sa_1ee93ff53821278525644b49",
"inchikey": "QZPDCZSOVJLEKB-UHFFFAOYSA-N",
"smiles": "OB(O)c1cc(I)ccc1F"
},
"smiles": "OB(O)c1cc(I)ccc1F",
"reactionStepId": "sa_59cf0b0edbd0ca7888b67643",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20080194647A1;0227;600775\",\"rsmi\":\"CC(C)O[B:2]([O:1]C(C)C)[O:3]C(C)C.[cH:4]1[c:5]([F:6])[cH:7][cH:8][c:9]([I:10])[cH:11]1>C1CCOC1.CC1(C)CCCC(C)(C)N1.Cl.[Li]CCCC>[OH:1][B:2]([OH:3])[c:4]1[c:5]([F:6])[cH:7][cH:8][c:9]([I:10])[cH:11]1\"},\"mapped_reaction_smiles\":\"CC(C)O[B:2]([O:1]C(C)C)[O:3]C(C)C.[cH:4]1[c:5]([F:6])[cH:7][cH:8][c:9]([I:10])[cH:11]1>C1CCOC1.CC1(C)CCCC(C)(C)N1.Cl.[Li]CCCC>[OH:1][B:2]([OH:3])[c:4]1[c:5]([F:6])[cH:7][cH:8][c:9]([I:10])[cH:11]1\"}",
"reactionStep": {
"id": "sa_59cf0b0edbd0ca7888b67643",
"reactionHash": "c4932f6ccfdffbd9643bcd64d04c0a1c14564f6f5d068348481b4cbf46e5368a"
},
"children": [
{
"id": "9541",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_7c161641a8e0d59b0cd8344c",
"parentId": "9540",
"isLeaf": true,
"molecule": {
"id": "sa_7c161641a8e0d59b0cd8344c",
"inchikey": "KGNQDBQYEBMPFZ-UHFFFAOYSA-N",
"smiles": "Fc1ccc(I)cc1"
},
"smiles": "Fc1ccc(I)cc1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "9542",
"routeId": "sa_32d9601b99d1a99a8c842010",
"moleculeId": "sa_0c3a1c72e8778c8e8b205e29",
"parentId": "9540",
"isLeaf": true,
"molecule": {
"id": "sa_0c3a1c72e8778c8e8b205e29",
"inchikey": "NHDIQVFFNDKAQU-UHFFFAOYSA-N",
"smiles": "CC(C)OB(OC(C)C)OC(C)C"
},
"smiles": "CC(C)OB(OC(C)C)OC(C)C",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
}
]
}
}