Install Jentic One Beta

Connect the Open Targets Platform REST API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Open Targets Platform REST API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fopentargets.io%2Fopentargets-main" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fopentargets.io%2Fopentargets-main" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Open Targets Platform REST API.

Search for diseases or targets by free-text query via /platform/public/search

Filter target-disease associations with /platform/public/association/filter

Retrieve evidence supporting a target-disease association with /platform/public/evidence

Fetch detailed information about a target by Ensembl ID via /platform/private/target/{target}

GET STARTED

Start building with Open Targets Platform REST API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Open Targets Platform REST API for, with concrete tasks.

★ Target-Disease Association Mining

Drug discovery researchers can call /platform/public/association/filter to retrieve scored evidence linking a gene target to a disease, optionally filtered by data type (genetic_association, somatic_mutation, known_drug, etc.). Each result includes the overall score and per-data-type scores so downstream pipelines can rank candidate targets. POST is supported for queries with many filters.

POST /platform/public/association/filter with body {"target":["ENSG00000157764"],"datatype":["genetic_association"]} and rank the diseases by overall score

Evidence Lookup for a Specific Pair

When a researcher needs the underlying evidence rows behind an association, /platform/public/evidence/filter accepts target and disease IDs and returns individual evidence strings with their source, score, and supporting publications. This is essential for literature review, regulatory submissions, and meta-analyses where the raw evidence is needed rather than the aggregated score.

POST /platform/public/evidence/filter with target=ENSG00000157764 and disease=EFO_0000253 and return the top 20 evidence rows

Target Enrichment for Gene Lists

Bioinformaticians analyzing differentially expressed gene lists can post the gene IDs to /platform/private/enrichment/targets and receive disease enrichment results, ranking the diseases most associated with the input set. This is useful for hypothesis generation from RNA-seq, CRISPR screen, or proteomics outputs without writing custom enrichment code.

POST /platform/private/enrichment/targets with a list of 50 gene Ensembl IDs and return the top 10 enriched diseases

AI Agent Drug Discovery Assistant

An AI agent supporting biomedical research can query Open Targets through Jentic to answer 'what diseases is gene X associated with' or 'what evidence connects target Y to disease Z' without the agent author writing the request URLs. Jentic resolves the natural-language intent to the right /platform/public/search, /association/filter, or /evidence/filter call and returns structured JSON.

Through Jentic, search 'find diseases associated with a gene', resolve to /platform/public/association/filter, and execute with target=ENSG00000157764

Key Endpoints

31 endpoints — the open targets platform rest api provides programmatic access to integrated genetic and clinical evidence linking targets to diseases for drug discovery research.

METHOD

PATH

DESCRIPTION

GET

/platform/public/search

Search for a disease or target by free text

GET

/platform/public/association/filter

Filter target-disease associations

POST

/platform/public/association/filter

Batch query associations with a JSON body

GET

/platform/public/evidence/filter

Filter evidence rows for a target/disease

POST

/platform/private/enrichment/targets

Run target enrichment analysis

GET

/platform/private/target/{target}

Get detailed target information

GET

/platform/private/disease/{disease}

Get detailed disease information

GET

/platform/public/utils/version

Get the current API version

GET

/platform/public/search

Search for a disease or target by free text

GET

/platform/public/association/filter

Filter target-disease associations

POST

/platform/public/association/filter

Batch query associations with a JSON body

GET

/platform/public/evidence/filter

Filter evidence rows for a target/disease

POST

/platform/private/enrichment/targets

Run target enrichment analysis

GET

/platform/private/target/{target}

Get detailed target information

GET

/platform/private/disease/{disease}

Get detailed disease information

GET

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the Open Targets Platform REST API by hand means learning its public versus private endpoint split and threading the right filter parameters into each association or evidence query yourself. Through Jentic you install once, import the Open Targets Platform REST API from the API Directory, and your agent calls it with polite-use defaults already applied.

Permission scoping

Open Targets is read-only research data with no credential, so scoping is by operation: you limit the agent to the operations it needs, such as target-disease association filtering or search, and leave the private enrichment endpoint out unless you want it. Every operation the agent can call is one you chose to allow.

Credential isolation

Open Targets needs no credential, so nothing secret is stored for this API. Jentic still routes each call through its audited execution path, and no key ever enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'find target disease evidence' or 'search for a disease', and Jentic returns the matching Open Targets operation with its parameter schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Open Targets Platform REST API through Jentic.

What authentication does the Open Targets Platform REST API use?

The Open Targets Platform REST API is openly accessible and does not require authentication. The spec defines no security schemes. Through Jentic the calls go out unauthenticated, with no key management needed.

Can I batch query target-disease associations with the Open Targets Platform REST API?

Yes - POST /platform/public/association/filter accepts a JSON body with target or disease arrays so you can submit many IDs in one call. The same applies to /platform/public/evidence/filter.

What are the rate limits for the Open Targets Platform REST API?

Open Targets does not document a fixed rate limit, but asks that integrations avoid abusive patterns. Heavy users are encouraged to download the platform data dumps. Status and metrics are available at /platform/public/utils/metrics and /platform/public/utils/ping.

How do I look up evidence for a target and disease through Jentic?

Search Jentic for 'find evidence target disease', load the POST /platform/public/evidence/filter schema, and execute with the target Ensembl ID and disease EFO ID. Jentic returns the evidence rows directly.

Are the private endpoints in the Open Targets Platform REST API stable?

Open Targets explicitly marks the /platform/private/* methods as web-app-driven and subject to change without notice. Use /platform/public/* for production integrations. The /platform/swagger endpoint returns the current schema if you need to verify a method's status.

What ID formats does the Open Targets Platform REST API expect?

Targets use Ensembl gene IDs (ENSG...), diseases use EFO IDs (EFO_...), drugs use CHEMBL IDs (CHEMBL...), and evidence codes use ECO IDs. Free-text queries via /platform/public/search resolve names to these canonical IDs.

Can I limit what my agent is allowed to do with the Open Targets Platform REST API?

Yes. Because you run Jentic One yourself, your own rules decide which Open Targets operations the agent may call, so you can allow only what it needs, such as free-text search and target-disease association filtering, while leaving out the private target enrichment endpoint. Open Targets is read-only research data with no credential, so scoping is purely by operation: every endpoint the agent can reach is one you explicitly permitted. This lets you keep an agent to public association and evidence queries and deny access to the web-app private methods.

Open Targets Platform REST API

Name: Open Targets Platform REST API
Brand: Open Targets Platform REST API
Availability: InStock

Browse all Opentargets APIs

AI ReadinessAI-Aware (A-)73/100

See full scorecard

Community OpenAPI document · agent-readyHealthcareClinical Datanone31 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Query Open Targets target-disease associations, supporting evidence, drug records, and search across the integrated bioinformatics platform.

Use for: Find evidence linking BRCA1 to breast cancer, Search the Open Targets platform for 'Alzheimer', Get all associations for target ENSG00000157764, Look up disease details for EFO_0000253

Not supported: Does not handle clinical trial registry data, raw sequence retrieval, or molecular structure files - use for Open Targets curated target-disease associations and evidence only.

The Open Targets Platform REST API provides programmatic access to integrated genetic and clinical evidence linking targets to diseases for drug discovery research. Endpoints fall into public methods (stable, fully supported) for associations, evidence, and search; private methods used by the Open Targets web app for autocomplete, drug, disease, and target detail; and utils for service metrics and version info. Responses are JSON by default with optional xml, csv, and tab formats on some endpoints. The API is openly accessible and is the standard programmatic entry point for the Open Targets Platform's curated bioinformatics data.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

97%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: CSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

25%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

93%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: CSignals: 4

59%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

53%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

100

Security

Trust, risk posture, and security compliance.

Grade: A+Signals: 1

100%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

100

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A+Signals: 1

100%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Open Targets Platform REST API to your agent

Capabilities

Start building with Open Targets Platform REST API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Open Targets Platform REST API

Jentic AI Readiness Score

Open Targets Platform REST API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness