Search Docs…

Search Docs…

Orpheus API Reference

Admet Prediction Query

POST Admet Prediction Query

https://api.wisecube.ai/orpheus/graphql

This API retrieves prediction using ADMET models and sagemaker.


1. Model: LogS

- Category: Basic physicochemical property

- Description: The log of aqueous solubility value

- Method: Random Forests

- Accuracy: 0.860


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "logS",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"logS\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": -3.9198139,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": -4.642688,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": -3.6882942,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "logS"
        }
    }
}


2. Model: LogD7.4

- Category: Basic physicochemical property

- Description: The log of the n-octanol/water distribution coefficients at pH=7.4

- Method: Random Forests

- Accuracy: 0.877


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "LogD7",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"LogD7\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 1.9834658,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.48287967,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 1.3930833,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "LogD7"
        }
    }
}


3. Model: Caco2

- Category: Absorption

- Description: Caco-2 cell permeability

- Method: Random Forests

- Accuracy: 0.845

BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "Caco2",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "c1coc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"Caco2\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"c1coc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

 {
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": -5.0087986,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": -5.0954404,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": -5.1016064,
                    "smiles": "c1coc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "Caco2"
        }
    }
}


4. Model: PGPi

- Category: Absorption

- Description: The inhibitor of P-glycoprotein

- Method: SVM

- Accuracy: 0.848


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "PGPi",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"PGPi\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.8844528,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.62586796,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4"
                }
            ],
            "modelName": "PGPi"
        }
    }
}

5. Model: PGPs

- Category: Absorption

- Description: The substrate of P-glycoprotein

- Method: SVM

- Accuracy: 0.824


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "PGPs",
    "smiles": [
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"PGPs\",\"smiles\":[\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.5,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.5,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4"
                }
            ],
            "modelName": "PGPs"
        }
    }
}

6. Model: HIA

- Category: Absorption

- Description: The human intestinal absorption

- Method: Random Forests

- Accuracy: 0.782


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "HIA",
    "smiles": [
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4",
        "c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"HIA\",\"smiles\":[\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4\",\"c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.478,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.658,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4"
                },
                {
                    "predict": 0.464,
                    "smiles": "c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "HIA"
        }
    }
}

7. Model: F (20%)

- Category: Absorption

- Description: The human oral bioavailability (20%)

- Method: Random Forests

- Accuracy: 0.689


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "F20",
    "smiles": [

        "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4",
        "c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"F20\",\"smiles\":[\"c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4\",\"c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.538,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4"
                },
                {
                    "predict": 0.574,
                    "smiles": "c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "F20"
        }
    }
}

8. Model: F (30%)

- Category: Absorption

- Description: The human oral bioavailability (30%)

- Method: Random Forests

- Accuracy: 0.669


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "F30",
    "smiles": [

        "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4",
        "c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"F30\",\"smiles\":[\"c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4\",\"c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.534,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCCNC(=O)c3ccc(cc3)-c4ccccc4"
                },
                {
                    "predict": 0.35,
                    "smiles": "c1coc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "F30"
        }
    }
}

9. Model: PPB

- Category: Distribution

- Description: The plasma protein binding

- Method: Random Forests

- Accuracy: 0.691


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "PPB",
    "smiles": [
        "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO",
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"PPB\",\"smiles\":[\"CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO\",\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 86.35817,
                    "smiles": "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO"
                },
                {
                    "predict": 90.41538,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "PPB"
        }
    }
}

10. Model: VD

- Category: Distribution

- Description: The volume of distribution

- Method: Random Forests

- Accuracy: 0.912


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "VD",
    "smiles": [

        "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO",
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"VD\",\"smiles\":[\"CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO\",\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": -0.16493928,
                    "smiles": "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO"
                },
                {
                    "predict": 0.10914946,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "VD"
        }
    }
}

11. Model: BBB

- Category: Distribution

- Description: The blood-brain barrier

- Method: SVM

- Accuracy: 0.926


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "BBB",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"BBB\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.9857907,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.95660263,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "BBB"
        }
    }
}

12. Model: CYPIA2i

- Category: Metabolism

- Description: CYP 1A2-Inhibitor

- Method: SVM

- Accuracy: 0.849


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYPIA2i",
    "smiles": [
        "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO",
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYPIA2i\",\"smiles\":[\"CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO\",\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.15794268,
                    "smiles": "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO"
                },
                {
                    "predict": 0.37188825,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.471529,
                    "smiles": "O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "CYPIA2i"
        }
    }
}

13. Model: CYPIA2s

- Category: Metabolism

- Description: CYP 1A2-substrate

- Method: Random Forests

- Accuracy: 0.702


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYPIA2s",
    "smiles": [
        "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO",
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYPIA2s\",\"smiles\":[\"CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO\",\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.477,
                    "smiles": "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO"
                },
                {
                    "predict": 0.552,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.573,
                    "smiles": "O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "CYPIA2s"
        }
    }
}

14. Model: CYP3A4i

- Category: Metabolism

- Description: CYP 3A4-Inhibitor

- Method: SVM

- Accuracy: 0.817


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYP3A4i",
    "smiles": [
        "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO",
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYP3A4i\",\"smiles\":[\"CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO\",\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.58575815,
                    "smiles": "CN1CCOc(c12)cc(c(Br)c2)NC(=O)C(=O)NCc(c3)ccc(c34)[N+](C)CC(C4)CO"
                },
                {
                    "predict": 0.4695666,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.8644264,
                    "smiles": "O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "CYP3A4i"
        }
    }
}

15. Model: CYP3A4s

- Category: Metabolism

- Description: CYP 3A4-Substrate

- Method: Random Forests

- Accuracy: 0.757


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYP3A4s",
    "smiles": [
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYP3A4s\",\"smiles\":[\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.652,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.728,
                    "smiles": "O1COc(c12)cc(Cl)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "CYP3A4s"
        }
    }
}

16. Model: CYP2C9i

- Category: Metabolism

- Description: CYP 2C9-Inhibitor

- Method: SVM

- Accuracy: 0.837


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYP2C9i",
    "smiles": [
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYP2C9i\",\"smiles\":[\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.37629077,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.4176257,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                }
            ],
            "modelName": "CYP2C9i"
        }
    }
}

17. Model: CYP2C9s

- Category: Metabolism

- Description: CYP 2C9-Substrate

- Method: Random Forests

- Accuracy: 0.728


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYP2C9s",
    "smiles": [
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYP2C9s\",\"smiles\":[\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.29466668,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.48875,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                }
            ],
            "modelName": "CYP2C9s"
        }
    }
}

18. Model: CYP2CI9i

- Category: Metabolism

- Description: CYP 2C19-Inhibitor

- Method: SVM

- Accuracy: 0.822


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYP2CI9i",
    "smiles": [
        "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYP2CI9i\",\"smiles\":[\"C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.5828041,
                    "smiles": "C1CCc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.5767354,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                }
            ],
            "modelName": "CYP2CI9i"
        }
    }
}

19. Model: CYP2C19s

- Category: Metabolism

- Description: CYP 2C19-Substrate

- Method: Random Forests

- Accuracy: 0.740


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYP2C19s",
    "smiles": [
        "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3",
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYP2C19s\",\"smiles\":[\"c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3\",\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.342,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3"
                },
                {
                    "predict": 0.69,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.541,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "CYP2C19s"
        }
    }
}

20. Model: CYP2D6i

- Category: Metabolism

- Description: CYP 2D6-Inhibitor

- Method: Random Forests

- Accuracy: 0.793


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYP2D6i",
    "smiles": [
        "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3",
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYP2D6i\",\"smiles\":[\"c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3\",\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.42333335,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3"
                },
                {
                    "predict": 0.697,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.52,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "CYP2D6i"
        }
    }
}

21. Model: CYP2D6s

- Category: Metabolism

- Description: CYP 2D6-Substrate

- Method: Random Forests

- Accuracy: 0.748


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CYP2D6s",
    "smiles": [
        "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3",
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CYP2D6s\",\"smiles\":[\"c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3\",\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.5123,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3"
                },
                {
                    "predict": 0.56516665,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.47883335,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "CYP2D6s"
        }
    }
}

22. Model: CL

- Category: Excretion

- Description: The clearance of a drug

- Method: Random Forests

- Accuracy: 0.877


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "CL",
    "smiles": [
        "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO",
        "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"CL\",\"smiles\":[\"c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\",\"C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 1.3219831,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3"
                },
                {
                    "predict": 0.99979377,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                },
                {
                    "predict": 0.8132012,
                    "smiles": "C1COc(c12)cc(Br)c(c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "CL"
        }
    }
}


23. Model: Ames

- Category: Toxicity

- Description: Ames test for mutagenicity

- Method: Random Forests

- Accuracy: 0.820


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "Ames",
    "smiles": [
        "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"Ames\",\"smiles\":[\"c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.266,
                    "smiles": "c1cccc(c12)[nH]c(c2)C(=O)NCCNC(=O)c3c(F)c(CO)ccc3"
                },
                {
                    "predict": 0.338,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "Ames"
        }
    }
}

24. Model: DILI

- Category: Toxicity

- Description: Drug-induced liver injury

- Method: Random Forests

- Accuracy: 0.840


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "DILI",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"DILI\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.31399998,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.264,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "DILI"
        }
    }
}


25. Model: SkinS

- Category: Toxicity

- Description: Skin Sensitivity

- Method: Random Forests

- Accuracy: 0.706


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "SkinS",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"SkinS\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.25,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.232,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "SkinS"
        }
    }
}

26. Model: T-HALF

- Category: Excretion

- Description: The half-life of a drug

- Method: Random Forests

- Accuracy: 0.897


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "THALF",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"THALF\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 1.8262397,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 1.508456,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "THALF"
        }
    }
}


27. Model: hERG

- Category: Toxicity

- Description: The human ether-a-go-go related gene

- Method: Random Forests

- Accuracy: 0.844


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "hERG",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"hERG\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.768,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.576,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "hERG"
        }
    }
}


28. Model: H-HT

- Category: Toxicity

- Description: human hepatotoxicity

- Method: Random Forests

- Accuracy: 0.690


BODY graphql

QUERY

query ($smiles: [String!], $modelName: String)
{ 
  admetPredict(smiles: $smiles, modelName: $modelName)
}

GRAPHQL VARIABLES

{
    "modelName": "HHT",
    "smiles": [
        "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4",
        "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
    ]
}

Example Request:

POST /orpheus/graphql HTTP/1.1 
Host: api.wisecube.ai 
Content-Type: application/json 
Content-Length: 1324 

{\"query\":\"query ($smiles: [String!], $modelName: String){ admetPredict(smiles: $smiles, modelName: $modelName)\\n    \\n}\",\"variables\":{\"modelName\":\"HHT\",\"smiles\":[\"O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4\",\"O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO\"]}}

Example Response

{
    "data": {
        "admetPredict": {
            "dataframe": [
                {
                    "predict": 0.81,
                    "smiles": "O1COc(c12)ccc(c2)NC(=O)C(=O)NCCc(c3)ccc(c34)N(C)CCC4"
                },
                {
                    "predict": 0.828,
                    "smiles": "O1COc(c12)cc(c(C#N)c2)NC(=O)C(=O)NCc(c3)ccc(c34)N(C)CC(C4)CO"
                }
            ],
            "modelName": "HHT"
        }
    }
}



Wisecube AI

© 2024