# Retrieve Metadata

{% hint style="info" %}
If you are working with your own dataset, then you can skip this step. Go to Organise Metadata to add your own fields.
{% endhint %}

## Locate Metadata

Locate where the metadata is stored. Generally, there will be a section in published papers that describes the location of datasets and associated metadata. 

<figure><img src="/files/t51G8qaFhU2REa2m9DCP" alt=""><figcaption><p>Selecting the underlined BioProject ID, PRJNA834801, will link you directly to the NCBI BioProject page. </p></figcaption></figure>

## Navigate NCBI&#x20;

Under Related Information, select SRA to open up the Sequence Read Archive of the associated BioProject.&#x20;

<figure><img src="/files/pdzbMaF3z5HT32JJgdsO" alt=""><figcaption></figcaption></figure>

## Send Results to Run Selector

Under Summary, select 'Send results to Run selector'.&#x20;

<figure><img src="/files/tVI4xh1qicLMPAtlVcMN" alt=""><figcaption><p>All SRA accessions in the BioProject are displayed here. </p></figcaption></figure>

## Locate the Runs

Scroll down to see the SRA runs from the BioProject. You can download all the run metadata by selecting Metadata in the 'Total' row.&#x20;

For this demonstration, we will download a subset of metadata that matches the run files we just downloaded from the 'Selected' row.&#x20;

## Select Runs

Select the 20 runs from the example subset. For a reminder, below is the accession list.

{% file src="/files/rvfzGBlgtNrC7tDN191O" %}

<figure><img src="/files/loO0BHAjm461Dvk1hxQq" alt=""><figcaption></figcaption></figure>

## Download Metadata

Using our subset of 20 runs, download the metadata by choosing 'Selected' and pressing the 'Metadata' button.

<figure><img src="/files/gsfF3aYPY5KMJdjuIiRJ" alt=""><figcaption></figcaption></figure>

## Locate the Downloaded Metadata

A file called sraruntable.txt will be saved in your Downloads folder. I renamed this to subset\_metadata.csv for clarity and functionality.

{% file src="/files/kakW3iR72Upe8gHRay4E" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://kb.ezbiocloud.net/home/protocols/shotgun-microbiome/describe-profiles/retrieve-metadata.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.