> For the complete documentation index, see [llms.txt](https://docs.omics.ai/products/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.omics.ai/products/workbench/variant-interpreter.md).

# Variant Interpreter

The Variant Interpreter is an interactive workspace for reviewing the variants called from a sample's long-read genome and producing a clinical report. It takes the output of a completed tertiary analysis workflow and presents it as a single, navigable case covering small variants, structural variants, copy-number variants, tandem repeats, and paralogs, so that a clinical geneticist can move from raw calls to a submitted interpretation in one sitting.

## Who this is for

Everyone who works on a case does so through a workspace **role** that controls what they can do. There are three — see [Workspaces & roles](/products/workbench/variant-interpreter/workspaces-and-roles.md) for the full capability matrix:

* **Contributor** — the day-to-day interpreter, typically a clinical geneticist or analyst: reviews prioritized candidate variants, evaluates evidence, classifies variants, and drafts the report.
* **Admin** — everything a Contributor can do, plus report **sign-off** (typically the lab director) and workspace administration.
* **Viewer** — read-only access, for anyone who needs to follow a case without changing it.

## Where it fits

The Variant Interpreter is the final, tertiary stage of analysis. It sits downstream of:

1. **Secondary analysis**: the long-read WGS workflow (run in [Workbench](/products/workbench/introduction.md)) that aligns reads and calls variants. This produces phased VCFs, structural and copy-number calls, tandem repeat genotypes, and methylation pileups.
2. **Annotation & filtering**: population-frequency annotation and candidate filtering that reduce millions of raw calls to a reviewable shortlist.

The Variant Interpreter then loads that prepared case so the CG can interpret it. For the exact tools and versions behind a given case, see [Pipeline & caller versions](/products/workbench/variant-interpreter/pipeline-and-caller-versions.md).

{% hint style="info" %}
The Variant Interpreter does not call variants itself. What you review here reflects the workflow version that produced the case; the sample drawer records which workflow and caller versions were used.
{% endhint %}

## What you can do

* Find a sample and open its analysis from the [Data Page](/products/workbench/variant-interpreter/getting-started/the-data-page.md).
* Orient on the [Summary tab](/products/workbench/variant-interpreter/getting-started/the-summary-tab.md) and triage the priority findings.
* Review [small variants](/products/workbench/variant-interpreter/reviewing-variants/small-variants.md), [structural variants](/products/workbench/variant-interpreter/reviewing-variants/structural-variants.md), [copy number](/products/workbench/variant-interpreter/reviewing-variants/copy-number.md), [tandem repeats](/products/workbench/variant-interpreter/reviewing-variants/tandem-repeats.md), and [paralogs](/products/workbench/variant-interpreter/reviewing-variants/paralogs.md).
* Apply lab and case-level [filters](/products/workbench/variant-interpreter/filtering-and-prioritization.md).
* [Generate and submit a report](/products/workbench/variant-interpreter/generating-a-report.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.omics.ai/products/workbench/variant-interpreter.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.