ivive.app · Schema

PredictionResponse

CompanyIVIVEDrug DiscoveryHepaticClearanceOpen Source

Properties

Name Type Description
fu_p object Random forest on RDKit descriptors, ~3,600 structures.
fu_inc number Kilford 2008 / Hallifax & Houston 2006 from RDKit logP.
logp number RDKit Crippen logP.
applicability object
ionizable array Groups mostly charged at pH 7.4, from substructure patterns (carboxylic acid, tetrazole, aliphatic amine, amidine). The pKa is not predicted: this only says that treating the compound as neutral in Vs
known_animal_pk object Published rat/dog/monkey in-vivo plasma CL, if this structure is a drug in the PKSmart animal compilation. A literature lookup, not a prediction: a novel compound never matches, and anything that does
structure_cl object Human plasma CL from an extra-trees model on the same descriptors, trained on ~1,200 drugs with observed IV clearance. Independent of every IVIVE input, so it is a check on the mechanistic result rath
structure_vdss object Human Vss from gradient boosting on the same descriptors, trained on ~1,200 drugs with observed IV Vss. A second opinion on the Schmitt 2008 path, which it beats on unseen structures while covering hu
View JSON Schema on GitHub

JSON Schema

ivive-app-prediction-response-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/ivive-app/json-schema/ivive-app-prediction-response-schema.json",
  "title": "PredictionResponse",
  "x-generated": "2026-11-12",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/ivive-app-openapi.json#/components/schemas/PredictionResponse",
  "properties": {
    "fu_p": {
      "$ref": "#/$defs/RangedValue",
      "description": "Random forest on RDKit descriptors, ~3,600 structures."
    },
    "fu_inc": {
      "type": "number",
      "title": "Fu Inc",
      "description": "Kilford 2008 / Hallifax & Houston 2006 from RDKit logP."
    },
    "logp": {
      "type": "number",
      "title": "Logp",
      "description": "RDKit Crippen logP."
    },
    "applicability": {
      "$ref": "#/$defs/Applicability"
    },
    "ionizable": {
      "items": {
        "type": "string",
        "enum": [
          "acid",
          "base"
        ]
      },
      "type": "array",
      "title": "Ionizable",
      "description": "Groups mostly charged at pH 7.4, from substructure patterns (carboxylic acid, tetrazole, aliphatic amine, amidine). The pKa is not predicted: this only says that treating the compound as neutral in Vss is probably wrong."
    },
    "known_animal_pk": {
      "anyOf": [
        {
          "$ref": "#/$defs/KnownAnimalPK"
        },
        {
          "type": "null"
        }
      ],
      "description": "Published rat/dog/monkey in-vivo plasma CL, if this structure is a drug in the PKSmart animal compilation. A literature lookup, not a prediction: a novel compound never matches, and anything that does has a published human CL too."
    },
    "structure_cl": {
      "$ref": "#/$defs/StructureCL",
      "description": "Human plasma CL from an extra-trees model on the same descriptors, trained on ~1,200 drugs with observed IV clearance. Independent of every IVIVE input, so it is a check on the mechanistic result rather than a part of it. Human only."
    },
    "structure_vdss": {
      "$ref": "#/$defs/StructureVdss",
      "description": "Human Vss from gradient boosting on the same descriptors, trained on ~1,200 drugs with observed IV Vss. A second opinion on the Schmitt 2008 path, which it beats on unseen structures while covering human only."
    }
  },
  "type": "object",
  "required": [
    "fu_p",
    "fu_inc",
    "logp",
    "applicability",
    "structure_cl",
    "structure_vdss"
  ],
  "$defs": {
    "Applicability": {
      "properties": {
        "max_similarity": {
          "type": "number",
          "title": "Max Similarity",
          "description": "Tanimoto (Morgan r2) to the nearest fu,p training structure."
        },
        "status": {
          "type": "string",
          "enum": [
            "in_domain",
            "borderline",
            "out_of_domain"
          ],
          "title": "Status"
        }
      },
      "type": "object",
      "required": [
        "max_similarity",
        "status"
      ],
      "title": "Applicability"
    },
    "KnownAnimalPK": {
      "properties": {
        "name": {
          "type": "string",
          "title": "Name"
        },
        "cl_rat": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "Cl Rat"
        },
        "cl_dog": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "Cl Dog"
        },
        "cl_monkey": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "Cl Monkey"
        },
        "fu_p_rat": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "Fu P Rat"
        },
        "cl_human": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "Cl Human",
          "description": "Published human plasma CL, mL/min/kg, where the compilation has one"
        },
        "source": {
          "type": "string",
          "title": "Source"
        }
      },
      "type": "object",
      "required": [
        "name",
        "source"
      ],
      "title": "KnownAnimalPK",
      "description": "Published animal clearance for a drug already in the literature.\n\nA lookup, not a prediction, and it only ever matches a known drug. `cl_human` is carried\nbecause that is the catch: if this matched, the human answer is already published."
    },
    "RangedValue": {
      "properties": {
        "value": {
          "type": "number",
          "title": "Value"
        },
        "low": {
          "type": "number",
          "title": "Low",
          "description": "Lower end of the range holding the measured value for half of held-out drugs."
        },
        "high": {
          "type": "number",
          "title": "High"
        },
        "coverage": {
          "type": "number",
          "title": "Coverage"
        }
      },
      "type": "object",
      "required": [
        "value",
        "low",
        "high",
        "coverage"
      ],
      "title": "RangedValue"
    },
    "StructureCL": {
      "properties": {
        "value": {
          "type": "number",
          "title": "Value",
          "description": "Plasma clearance, mL/min/kg."
        },
        "low": {
          "type": "number",
          "title": "Low"
        },
        "high": {
          "type": "number",
          "title": "High"
        },
        "coverage": {
          "type": "number",
          "title": "Coverage"
        },
        "applicability": {
          "$ref": "#/$defs/Applicability"
        }
      },
      "type": "object",
      "required": [
        "value",
        "low",
        "high",
        "coverage",
        "applicability"
      ],
      "title": "StructureCL",
      "description": "Human plasma CL predicted from structure alone: a second opinion, not an IVIVE input."
    },
    "StructureVdss": {
      "properties": {
        "value": {
          "type": "number",
          "title": "Value",
          "description": "Volume of distribution at steady state, L/kg."
        },
        "low": {
          "type": "number",
          "title": "Low"
        },
        "high": {
          "type": "number",
          "title": "High"
        },
        "coverage": {
          "type": "number",
          "title": "Coverage"
        },
        "applicability": {
          "$ref": "#/$defs/Applicability"
        }
      },
      "type": "object",
      "required": [
        "value",
        "low",
        "high",
        "coverage",
        "applicability"
      ],
      "title": "StructureVdss",
      "description": "Human Vss predicted from structure alone: a second opinion on the Schmitt 2008 result."
    }
  }
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/ivive-app-prediction-response"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.