> ## Documentation Index
> Fetch the complete documentation index at: https://docs.valyu.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# PCSK9 and LDL-cholesterol evidence map

> Map genetic, mechanistic and intervention evidence linking a drug target to a disease, such as PCSK9 and LDL cholesterol, in a cited evidence table and CSV.

**Example question:** Which genetic, mechanistic and intervention studies connect PCSK9 with LDL cholesterol?

**You get:** An evidence map and CSV separating study types, experimental systems, measured outcomes and limitations.

**Start with:** Target identifier and aliases; phenotype or disease; species; included evidence types; literature cutoff.

## Run with DeepResearch

Set `VALYU_API_KEY` in your environment, then run this illustrative request. Change the question and CSV fields for your own task. The CSV fields below describe the requested output, not a saved result.

<Accordion title="Run the research request">
  ```bash cURL theme={null}
  curl --fail-with-body https://api.valyu.ai/v1/deepresearch/tasks \
    -H "x-api-key: $VALYU_API_KEY" \
    -H "Content-Type: application/json" \
    --data-binary @- <<'JSON'
  {
    "query": "Build an evidence map for PCSK9 and LDL cholesterol using original studies published through 31 December 2024. Separate human genetic association or loss-of-function evidence, mechanistic experiments and intervention studies. Record species or system, variant or perturbation, measured outcome and study limitations. Use curated target databases to locate underlying studies but cite the original evidence. Do not treat association as proof of causality or infer that results in one experimental system establish clinical suitability.",
    "mode": "standard",
    "research_strategy": "Check available target and biomedical sources using the datasource catalogue. Prioritize underlying original studies; database association scores need their own definitions and provenance. Cite every row; mark missing or inaccessible evidence.",
    "report_format": "A concise evidence table, comparison limits and unresolved questions.",
    "deliverables": [
      {
        "type": "csv",
        "description": "One row per evidence item with the requested fields and supporting source URL.",
        "columns": [
          "target_id",
          "phenotype",
          "evidence_type",
          "species_or_system",
          "study_design",
          "perturbation_or_variant",
          "measured_outcome",
          "direction",
          "limitation",
          "primary_source_url",
          "database_reference"
        ]
      }
    ]
  }
  JSON
  ```
</Accordion>

Save the returned `deepresearch_id`. Poll [Get status](/api-reference/endpoint/deepresearch-status) until the task completes, then read the report and download the CSV from `deliverables`.

## How it works

1. Resolve the target and phenotype identifiers. Search human genetics, mechanistic studies and intervention studies separately.

2. Read original papers and inspect curated database entries as indexes to their underlying evidence. Retain study system, direction and measured outcome.

3. Group evidence by type and list gaps or conflicts. Keep association, mechanism and intervention effects separate.

To build the workflow inside your own agent, use [Search](/search/quickstart) to find sources and [Contents](/guides/content-extraction) to read selected pages. Keep the CSV fields above as your extraction schema.

## Check the result

Check target aliases, variant identity and effect direction. Avoid counting a database entry and its cited paper as independent support. Evidence mapping does not establish a therapeutic recommendation.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.