Goals:
- Fetch annotated articles from variantAnnotations stored in PharmGKB API
- Create a general benchmark for an extraction system that can output a score for an extraction system Given: Article, Ground Truth Variants (Manually extracted and recorded in var_drug_ann.tsv:) Input: Extracted Variants Output: Score
- System for extracting drug related variants annotations from an article. Associations in which the variant affects a drug dose, response, metabolism, etc.
- Continously fetch new pharmacogenomic articles
This repository contains Python scripts for running and building a Pharmacogenomic Agentic system to annotate and label genetic variants based on their phenotypical associations from journal articles.
We manage a few repos externally:
- PubMed Downloader: This repo is used to download all the markdown files from the PMIDs represented in
var_drug_ann.tsv - Huggingface/AutoGKB: This converts the annotations and article text into a dataset format for benchmarking
| Category | Task | Status |
|---|---|---|
| Initial Download | Download the zip of variants from pharmgkb | ✅ |
| Get a PMID list from the variants tsv (column PMID) | ✅ | |
| Convert the PMID to PMCID | ✅ | |
| Update to use non-official pmid to pmcid (aaron's method) | ||
| Fetch the content from the PMCID | ✅ | |
| Benchmark | Create pairings of annotations to articles | ✅ |
| Create a niave score of number of matches | ||
| Create group wise score | ||
| Look into advanced scoring based on distance from truth per term | ||
| Workflows | Integrate Aaron's current approach | ✅ |
| Document on individual annotation meanings | ||
| Delegate annotation groupings to team members | ||
| New Article Fetching | Replicate PharGKB current workflow |
pixi run gdown —-id 1qtQWvi0x_k5_JofgrfsgkWzlIdb6isr9
unzip autogkb-data.zip