Skip to main content

​
Welcome to Mithrl Docs

Mithrl is your AI lab partner. We’ve built the first commercially available AI Co-Scientist designed specifically for R&D and discovery teams. From raw sequencing files to hypotheses, Mithrl compresses the time it takes to analyze, interpret, and act on biological data, from months to minutes. This documentation outlines what the platform supports today, what is currently in limited release, and what’s in active development. If you’re running RNA-seq experiments, looking for novel targets, or validating mechanisms of action, this guide is for you.

​
🧬 What is Mithrl?

Mithrl is an AI-powered platform that automates RNA-seq data analysis and insight generation. It’s used by therapeutic research teams to extract biological meaning from large datasets without the need for custom coding or manual data wrangling.
Mithrl supports:
  • Bulk RNA-seq and scRNA-seq (10X, Smart-seq, and others)
  • Natural language-driven workflows — ask a scientific question and get real answers
  • Differential expression, enrichment, clustering, and network-based analyses
  • Automated insight reports with plots, gene-level tables, and mechanistic interpretation
  • Target discovery, mechanism-of-action modeling, and hypothesis generation
Designed for scientists, Mithrl handles everything from normalization and statistical testing to literature-backed interpretation all behind the scenes.

​
Clarifying Questions

Mithrl is built to behave like a thoughtful lab partner, not a black box. When your question is ambiguous or missing key details, it won’t make assumptions or fill in gaps with made-up answers. Instead, it will ask for clarification so it can give you a precise and scientifically valid response. For example, if you ask: 
Show me differentially expressed genes
Mithrl might respond with: 
Which groups should I compare? I didn't detect clear treatment and control labels in your question.
Or if you ask: 
Find genes that are statistically significant
It might prompt: 
Could you confirm the p-value threshold you want to use for significance? Default is 0.05.

​
Follow-Up Questions

Mithrl doesn’t just answer one question at a time. It understands context across your entire session and enables a conversational workflow that reflects how scientists naturally think through a problem. When you ask a follow-up, Mithrl uses the results from the previous step. Whether it’s a differential expression list, a filtered dataset, or an enrichment analysis, that result becomes the foundation for the next step. There’s no need to restate the entire prompt or re-select your dataset. This allows you to iterate, refine, and dig deeper just like you would at the bench or in a discussion with a teammate. For example: 
What genes are upregulated in treated vs control?

Which of those are involved in apoptosis?

Show me KEGG pathways enriched in those genes.

Of those pathways, which ones overlap with known toxicity pathways?

​
🧭 How This Documentation is Organized

This site is structured to be navigable by both bench scientists and informatics leads:
  • Supported Features
    Tools available across all standard accounts.
  • Beta Features
    Features in limited release — your team may already have access depending on your configuration.
  • Roadmap
    Features in active development, prioritized based on customer input.
  • Feature Table
    Full matrix of capabilities, with availability and data type support.
If you’re new to Mithrl, we recommend starting with Supported Features for a sense of what’s immediately usable in your workspace.

​
🧪 What Mithrl Replaces

Scientists use Mithrl to eliminate manual bioinformatics bottlenecks:
Without MithrlWith Mithrl
Waiting weeks for differential expression resultsResults in minutes
Manually annotating DE genes in ExcelAutomated KEGG enrichment + plots
Outsourced reports with no reproducibilityReproducible reports with all inputs documented
Hard-to-interpret clustering heatmapsDimensionality-reduced plots with annotated clusters
Fragmented tools across multiple systemsUnified, conversational interface with exportable reports

​
🤝 Support

If you need help with the platform, you have multiple ways to reach us:
  • Email: [email protected]
  • Slack or Teams: Reach out in your dedicated customer success channel
  • Feature questions or analysis blockers: Ping your Customer Success Manager directly
We’re happy to assist with data uploads, enabling beta features, or scientific interpretation of results.
Let’s get started.