> For the complete documentation index, see [llms.txt](https://docs.mithrl.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mithrl.com/getting-started/inference-algorithms.md).

# Inference Algorithms

Curated statistical analyses available through the inference API. Each connects a molecular signature you provide to a different kind of curated biological knowledge, tests it against a background your experiment could actually observe, and returns a ranked, evidence-linked result. This list grows over time — see the pages below for what's available today.

To submit and monitor a run, see [Running and managing Inference](/guides/workflow-cli.md).

| Inference                                                                                                 | Answers                                                                                       |
| --------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
| [`CPA` Canonical Pathway Analysis](/getting-started/inference-algorithms/canonical-pathway-analysis.md)   | Which curated pathways are over-represented in my selected genes?                             |
| [`URA` Upstream Regulator Analysis](/getting-started/inference-algorithms/upstream-regulator-analysis.md) | Which upstream regulators have an unexpectedly large number of known targets in my signature? |
| [`TOX` Toxicity Endpoint Analysis](/getting-started/inference-algorithms/toxicity-endpoint-analysis.md)   | Which curated toxicity endpoints are over-represented in my signature?                        |

When submitting a run, use the full preset ids: `canonical-pathway-analysis`, `upstream-regulator-analysis`, and `toxicity-endpoint-analysis`. The abbreviations above are shorthand for these pages only.