Benchmark Sets
Browse retrosynthesis benchmark datasets with ground truth routes
| Name | Description | Targets | Stock |
|---|---|---|---|
SMILES
Cn1cnc2c(C#N)nc(-c3ccc(OCCOS(C)(=O)=O)c(C(F)(F)F)c3)cc21
InChiKey
JZUVNIKDGCTGJB-UHFFFAOYSA-N
Route Signature
dbe0ed43e681a96ea3916726ea634c465b94c6a3af1d6a31c0f8202a2d310714
Synthesis route with 5 steps (convergent)
Route tree structure (JSON format)
{
"route": {
"id": "sa_7355b8eceec94459966f552b",
"signature": "dbe0ed43e681a96ea3916726ea634c465b94c6a3af1d6a31c0f8202a2d310714",
"contentHash": "ba602e46b9256fd4c257dd78e372783771995b912430b51976b7b9090006925a",
"length": 5,
"isConvergent": true
},
"target": {
"id": "sa_994cd4ba88d863e8ae01ab14",
"benchmarkSetId": "3895c2909c53593560c5ba610abc7e6df80513dfd8624165c560451735097d36",
"targetId": "n5-02447",
"moleculeId": "sa_7b716cc8a8628fd4676b44fc",
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(OCCOS(C)(=O)=O)c(C(F)(F)F)c3)cc21",
"routeLength": 5,
"isConvergent": true,
"metadata": null,
"molecule": {
"id": "sa_7b716cc8a8628fd4676b44fc",
"inchikey": "JZUVNIKDGCTGJB-UHFFFAOYSA-N",
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(OCCOS(C)(=O)=O)c(C(F)(F)F)c3)cc21"
},
"hasAcceptableRoutes": true,
"acceptableRoutesCount": 1
},
"rootNode": {
"id": "10721",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_7b716cc8a8628fd4676b44fc",
"parentId": null,
"isLeaf": false,
"molecule": {
"id": "sa_7b716cc8a8628fd4676b44fc",
"inchikey": "JZUVNIKDGCTGJB-UHFFFAOYSA-N",
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(OCCOS(C)(=O)=O)c(C(F)(F)F)c3)cc21"
},
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(OCCOS(C)(=O)=O)c(C(F)(F)F)c3)cc21",
"reactionStepId": "sa_94efcf3c9331999254a0d14c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0159;914978\",\"rsmi\":\"Cl[S:21]([CH3:22])(=[O:23])=[O:24].[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8](-[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([O:17][CH2:18][CH2:19][OH:20])[cH:25][cH:26]1)[n:27][c:28]2[C:29]#[N:30]>CCN(C(C)C)C(C)C.CN1CCCC1=O.O>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8](-[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([O:17][CH2:18][CH2:19][O:20][S:21]([CH3:22])(=[O:23])=[O:24])[cH:25][cH:26]1)[n:27][c:28]2[C:29]#[N:30]\"},\"mapped_reaction_smiles\":\"Cl[S:21]([CH3:22])(=[O:23])=[O:24].[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8](-[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([O:17][CH2:18][CH2:19][OH:20])[cH:25][cH:26]1)[n:27][c:28]2[C:29]#[N:30]>CCN(C(C)C)C(C)C.CN1CCCC1=O.O>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8](-[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([O:17][CH2:18][CH2:19][O:20][S:21]([CH3:22])(=[O:23])=[O:24])[cH:25][cH:26]1)[n:27][c:28]2[C:29]#[N:30]\"}",
"reactionStep": {
"id": "sa_94efcf3c9331999254a0d14c",
"reactionHash": "3b5311955626691fbd51588484c51909452009eace7eae3b2567b6482a71242f"
},
"children": [
{
"id": "10722",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_aa663625d2ad9b1b7f1c7095",
"parentId": "10721",
"isLeaf": false,
"molecule": {
"id": "sa_aa663625d2ad9b1b7f1c7095",
"inchikey": "COODJZOSFKXJEK-UHFFFAOYSA-N",
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(OCCO)c(C(F)(F)F)c3)cc21"
},
"smiles": "Cn1cnc2c(C#N)nc(-c3ccc(OCCO)c(C(F)(F)F)c3)cc21",
"reactionStepId": "sa_3c6cf536c259f4f42fbe714c",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0157;914977\",\"rsmi\":\"Cl[c:8]1[cH:7][c:6]2[n:2]([CH3:1])[cH:3][n:4][c:5]2[c:24]([C:25]#[N:26])[n:23]1.OB(O)[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([O:17][CH2:18][CH2:19][OH:20])[cH:21][cH:22]1>C1CCC(P(C2CCCCC2)C2CCCCC2)CC1.C1COCCO1.CCOC(C)=O.O.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=P(O)(O)O.[K+].[K+].[K+].[Pd].[Pd]>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8](-[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([O:17][CH2:18][CH2:19][OH:20])[cH:21][cH:22]1)[n:23][c:24]2[C:25]#[N:26]\"},\"mapped_reaction_smiles\":\"Cl[c:8]1[cH:7][c:6]2[n:2]([CH3:1])[cH:3][n:4][c:5]2[c:24]([C:25]#[N:26])[n:23]1.OB(O)[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([O:17][CH2:18][CH2:19][OH:20])[cH:21][cH:22]1>C1CCC(P(C2CCCCC2)C2CCCCC2)CC1.C1COCCO1.CCOC(C)=O.O.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=P(O)(O)O.[K+].[K+].[K+].[Pd].[Pd]>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8](-[c:9]1[cH:10][c:11]([C:12]([F:13])([F:14])[F:15])[c:16]([O:17][CH2:18][CH2:19][OH:20])[cH:21][cH:22]1)[n:23][c:24]2[C:25]#[N:26]\"}",
"reactionStep": {
"id": "sa_3c6cf536c259f4f42fbe714c",
"reactionHash": "eda8f551ba8066264d2567b72632052e86d155225d37f6dcf93b9c25854b7d74"
},
"children": [
{
"id": "10723",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_f452bddbefc72ebcde005e37",
"parentId": "10722",
"isLeaf": false,
"molecule": {
"id": "sa_f452bddbefc72ebcde005e37",
"inchikey": "LQHKBWMDRJSRJZ-UHFFFAOYSA-N",
"smiles": "Cn1cnc2c(C#N)nc(Cl)cc21"
},
"smiles": "Cn1cnc2c(C#N)nc(Cl)cc21",
"reactionStepId": "sa_8e34a30b37a3813411b8dc45",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0097;914960\",\"rsmi\":\"CCO[CH:3](OCC)OCC.[CH3:1][NH:2][c:6]1[c:5]([NH2:4])[c:11]([C:12]#[N:13])[n:10][c:8]([Cl:9])[cH:7]1>CC(=O)O.CCOC(C)=O.ClCCl>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8]([Cl:9])[n:10][c:11]2[C:12]#[N:13]\"},\"mapped_reaction_smiles\":\"CCO[CH:3](OCC)OCC.[CH3:1][NH:2][c:6]1[c:5]([NH2:4])[c:11]([C:12]#[N:13])[n:10][c:8]([Cl:9])[cH:7]1>CC(=O)O.CCOC(C)=O.ClCCl>[CH3:1][n:2]1[cH:3][n:4][c:5]2[c:6]1[cH:7][c:8]([Cl:9])[n:10][c:11]2[C:12]#[N:13]\"}",
"reactionStep": {
"id": "sa_8e34a30b37a3813411b8dc45",
"reactionHash": "bed769b624a57d127e9e6597caeb243ef3f7c8e8c73522a6c0a9dcc697d458a8"
},
"children": [
{
"id": "10724",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_dc98236d967ab0cdbd0fcd04",
"parentId": "10723",
"isLeaf": true,
"molecule": {
"id": "sa_dc98236d967ab0cdbd0fcd04",
"inchikey": "GKASDNZWUGIAMG-UHFFFAOYSA-N",
"smiles": "CCOC(OCC)OCC"
},
"smiles": "CCOC(OCC)OCC",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10725",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_a168085438356699773f0c7c",
"parentId": "10723",
"isLeaf": false,
"molecule": {
"id": "sa_a168085438356699773f0c7c",
"inchikey": "XIZOPJUMQDTYRX-UHFFFAOYSA-N",
"smiles": "CNc1cc(Cl)nc(C#N)c1N"
},
"smiles": "CNc1cc(Cl)nc(C#N)c1N",
"reactionStepId": "sa_2e223742baef49fd39f9bb46",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0096;914959\",\"rsmi\":\"O=[N+:5]([O-])[c:4]1[c:3]([NH:2][CH3:1])[cH:12][c:10]([Cl:11])[n:9][c:6]1[C:7]#[N:8]>CCO.CCOC(C)=O.Cl[Sn]Cl.O.O.N.O>[CH3:1][NH:2][c:3]1[c:4]([NH2:5])[c:6]([C:7]#[N:8])[n:9][c:10]([Cl:11])[cH:12]1\"},\"mapped_reaction_smiles\":\"O=[N+:5]([O-])[c:4]1[c:3]([NH:2][CH3:1])[cH:12][c:10]([Cl:11])[n:9][c:6]1[C:7]#[N:8]>CCO.CCOC(C)=O.Cl[Sn]Cl.O.O.N.O>[CH3:1][NH:2][c:3]1[c:4]([NH2:5])[c:6]([C:7]#[N:8])[n:9][c:10]([Cl:11])[cH:12]1\"}",
"reactionStep": {
"id": "sa_2e223742baef49fd39f9bb46",
"reactionHash": "2a6e4617c79dde22c0db26768e044bd552b12ac75914d7ab28b3db3e7931ca0f"
},
"children": [
{
"id": "10726",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_a3e8a23b90fdec9b24be7c1f",
"parentId": "10725",
"isLeaf": false,
"molecule": {
"id": "sa_a3e8a23b90fdec9b24be7c1f",
"inchikey": "CPPJTEVGUHCBOT-UHFFFAOYSA-N",
"smiles": "CNc1cc(Cl)nc(C#N)c1[N+](=O)[O-]"
},
"smiles": "CNc1cc(Cl)nc(C#N)c1[N+](=O)[O-]",
"reactionStepId": "sa_668c54e6e82442029b629fb7",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0094;914958\",\"rsmi\":\"I[CH3:1].[NH2:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[c:8]([C:9]#[N:10])[n:11][c:12]([Cl:13])[cH:14]1>CC#N.CCOC(C)=O.O=C(O)O.[K+].[K+]>[CH3:1][NH:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[c:8]([C:9]#[N:10])[n:11][c:12]([Cl:13])[cH:14]1\"},\"mapped_reaction_smiles\":\"I[CH3:1].[NH2:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[c:8]([C:9]#[N:10])[n:11][c:12]([Cl:13])[cH:14]1>CC#N.CCOC(C)=O.O=C(O)O.[K+].[K+]>[CH3:1][NH:2][c:3]1[c:4]([N+:5](=[O:6])[O-:7])[c:8]([C:9]#[N:10])[n:11][c:12]([Cl:13])[cH:14]1\"}",
"reactionStep": {
"id": "sa_668c54e6e82442029b629fb7",
"reactionHash": "7cac1780efc1a60db73d56c7d1ed84bd97ca1330b5d52fd97d70e3d87ce18b87"
},
"children": [
{
"id": "10727",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_82fdccf7d1cc329c9db73f21",
"parentId": "10726",
"isLeaf": true,
"molecule": {
"id": "sa_82fdccf7d1cc329c9db73f21",
"inchikey": "INQOMBQAUSQDDS-UHFFFAOYSA-N",
"smiles": "CI"
},
"smiles": "CI",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10728",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_b4409e3ca75920fc970d0ea5",
"parentId": "10726",
"isLeaf": true,
"molecule": {
"id": "sa_b4409e3ca75920fc970d0ea5",
"inchikey": "KAYQVFYDILZZJH-UHFFFAOYSA-N",
"smiles": "N#Cc1nc(Cl)cc(N)c1[N+](=O)[O-]"
},
"smiles": "N#Cc1nc(Cl)cc(N)c1[N+](=O)[O-]",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
}
]
}
]
}
]
},
{
"id": "10729",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_84c8020dd1b3e5cbb47da811",
"parentId": "10722",
"isLeaf": false,
"molecule": {
"id": "sa_84c8020dd1b3e5cbb47da811",
"inchikey": "MKBBYTQKCOYPMZ-UHFFFAOYSA-N",
"smiles": "OCCOc1ccc(B(O)O)cc1C(F)(F)F"
},
"smiles": "OCCOc1ccc(B(O)O)cc1C(F)(F)F",
"reactionStepId": "sa_bef2b07925e59728d3cf215d",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0155;914976\",\"rsmi\":\"C1CCC([O:1][CH2:2][CH2:3][O:4][c:5]2[c:6]([C:7]([F:8])([F:9])[F:10])[cH:11][c:12]([B:13]([OH:14])[OH:15])[cH:16][cH:17]2)OC1>Cl>[OH:1][CH2:2][CH2:3][O:4][c:5]1[c:6]([C:7]([F:8])([F:9])[F:10])[cH:11][c:12]([B:13]([OH:14])[OH:15])[cH:16][cH:17]1\"},\"mapped_reaction_smiles\":\"C1CCC([O:1][CH2:2][CH2:3][O:4][c:5]2[c:6]([C:7]([F:8])([F:9])[F:10])[cH:11][c:12]([B:13]([OH:14])[OH:15])[cH:16][cH:17]2)OC1>Cl>[OH:1][CH2:2][CH2:3][O:4][c:5]1[c:6]([C:7]([F:8])([F:9])[F:10])[cH:11][c:12]([B:13]([OH:14])[OH:15])[cH:16][cH:17]1\"}",
"reactionStep": {
"id": "sa_bef2b07925e59728d3cf215d",
"reactionHash": "d7ea25f430c278905a67ad6da6c915aa8824c5d4853468ac2a94d7821b92e81b"
},
"children": [
{
"id": "10730",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_154dd3c95cae58530e239d1b",
"parentId": "10729",
"isLeaf": false,
"molecule": {
"id": "sa_154dd3c95cae58530e239d1b",
"inchikey": "RMYYGQKTVVRDRN-UHFFFAOYSA-N",
"smiles": "OB(O)c1ccc(OCCOC2CCCCO2)c(C(F)(F)F)c1"
},
"smiles": "OB(O)c1ccc(OCCOC2CCCCO2)c(C(F)(F)F)c1",
"reactionStepId": "sa_0c05969821f18a4f3081e975",
"template": null,
"metadata": "{\"annotations\":{\"ID\":\"US20100184761A1;0153;914975\",\"rsmi\":\"Br[c:4]1[cH:5][c:6]([C:7]([F:8])([F:9])[F:10])[c:11]([O:12][CH2:13][CH2:14][O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][cH:23]1.CC(C)O[B:2]([O:1]C(C)C)[O:3]C(C)C>C1CCOC1.[Li]CCCC>[OH:1][B:2]([OH:3])[c:4]1[cH:5][c:6]([C:7]([F:8])([F:9])[F:10])[c:11]([O:12][CH2:13][CH2:14][O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][cH:23]1\"},\"mapped_reaction_smiles\":\"Br[c:4]1[cH:5][c:6]([C:7]([F:8])([F:9])[F:10])[c:11]([O:12][CH2:13][CH2:14][O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][cH:23]1.CC(C)O[B:2]([O:1]C(C)C)[O:3]C(C)C>C1CCOC1.[Li]CCCC>[OH:1][B:2]([OH:3])[c:4]1[cH:5][c:6]([C:7]([F:8])([F:9])[F:10])[c:11]([O:12][CH2:13][CH2:14][O:15][CH:16]2[CH2:17][CH2:18][CH2:19][CH2:20][O:21]2)[cH:22][cH:23]1\"}",
"reactionStep": {
"id": "sa_0c05969821f18a4f3081e975",
"reactionHash": "85f0c6aaa61bd140e84b0952004349c386393e440bcfbcc581aac554748f9b04"
},
"children": [
{
"id": "10731",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_2578a72b1e73c5a6944b4c08",
"parentId": "10730",
"isLeaf": true,
"molecule": {
"id": "sa_2578a72b1e73c5a6944b4c08",
"inchikey": "IOCQOVHGKQQIHI-UHFFFAOYSA-N",
"smiles": "FC(F)(F)c1cc(Br)ccc1OCCOC1CCCCO1"
},
"smiles": "FC(F)(F)c1cc(Br)ccc1OCCOC1CCCCO1",
"reactionStepId": null,
"template": null,
"metadata": null,
"reactionStep": null,
"children": []
},
{
"id": "10732",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_0c3a1c72e8778c8e8b205e29",
"parentId": "10730",
"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": []
}
]
}
]
}
]
},
{
"id": "10733",
"routeId": "sa_7355b8eceec94459966f552b",
"moleculeId": "sa_d2a31ea58046b00856f61ca5",
"parentId": "10721",
"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": []
}
]
}
}