Mira documentation¶
Open Targets Mira (Multi-source Indication and Report Analytics) harmonises clinical trials, regulatory records, drug indications, and safety evidence into consistent datasets for drug-discovery analysis.
The documentation is being developed around three questions:
- What are a Clinical Report and a Clinical Indication?
- How does Open Targets generate them with Mira's default workflow?
- How can a user change the YAML configuration for a different use case?
Tip
Start with How Mira works for the complete path from provider data to Clinical Reports, mapped entities, and Clinical Indications.
Installation¶
Install the core package from PyPI:
The legacy private ChEMBL Oracle curation utilities require the optional Oracle extra:
The Oracle curation process is not required for the public default workflow and is intended for deprecation.
Data documentation¶
-
How Mira works
Follow the complete path from provider data to mapped Clinical Reports and Clinical Indications.
-
Clinical Report
Understand one traceable evidence record, its clinical stage, source, provider, and core fields.
-
Clinical Indication
See how Mira groups reports into drug–disease relationships and derives their maximum clinical stage.
-
Entity mapping
Learn how source labels become ChEMBL and EFO identifiers, including the NER fallback paths.
Providers¶
Each provider page explains what that source contributes and the selection rules applied before its records enter the shared Clinical Report dataset.
Using Mira¶
-
Generate with Python
Call provider, mapping, and aggregation functions directly to make the data flow visible.
-
Run recipes
Use the CLI and YAML recipes for repeatable runs and deployment-specific configuration.
-
Prepare the inputs
Find the upstream releases, database tables, file formats, and expected local layout.