> ## 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.

# Cellulase assay protocol comparison

> Compare reported assay conditions, units and normalization across papers, such as cellulase activity assays, before comparing measurements. Cited CSV output.

**Example question:** Can we compare cellulase activity measurements across three papers using carboxymethyl cellulose assays?

**You get:** A protocol comparison and CSV showing assay conditions, activity-unit definitions, normalization and missing methods details.

**Start with:** Enzyme or assay family; substrate; selected papers or publication window; units of interest; comparison question.

## 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": "Compare three original papers published from 2020 through 2024 that measure cellulase activity using carboxymethyl cellulose assays. Extract the assay type, substrate, reported assay conditions, detection method, activity-unit definition and normalization. Cite the methods section or supplement for each row. If details refer to another paper, identify that citation and mark fields unverified until the original method is read. Do not combine activities with incompatible units or supply an assumed standard protocol. Return a protocol evidence table and explain comparability limits, not a recommended experimental procedure.",
    "mode": "standard",
    "research_strategy": "Prioritize original methods sections and supplements. Follow method citations when necessary and record whether those sources were actually accessible. 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": [
          "paper_id",
          "assay_type",
          "substrate",
          "substrate_concentration",
          "temperature",
          "pH",
          "duration",
          "detection_method",
          "activity_unit_definition",
          "normalization",
          "evidence_location",
          "source_url",
          "missing_condition"
        ]
      }
    ]
  }
  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. Find original methods papers or studies that report cellulase activity assays. Select a bounded set with accessible methods.

2. Extract substrate identity, assay type, measurement definition, units and reported conditions. Separate experimental details from values inferred from cited methods.

3. Group comparable assays and identify differences that prevent pooling. Retain missing conditions as unknown rather than filling in a standard protocol.

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 enzyme activity units, normalization, assay duration and substrate definitions. Reported activity per mass, per volume and per protein quantity are not interchangeable. The output compares published evidence and does not validate an executable lab protocol.


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