cancervariants / cancervariants/therapy-normalization

Unable to normalize MetaKB drugs

Open
#291 1 comment 0 reactions 0 assignees View on GitHub
analysis data-cleaning
Dominant language
Python
Stars
15
Forks
3
PR merge metrics
No merged PRs in 30d

Description

During an analysis in MetaKB with only approved and predictive evidence items, 54 CIViC drugs failed to normalize. This resulted in not being able to capture 105 evidence items in MetaKB.

[Here](https://github.com/cancervariants/therapy-normalization/files/9527462/civic_unable_to_normalize_drugs.txt) is the file that contains the CIViC drugs with the associated queries that were unable to normalize.

We should see if we're missing these terms in the source we already import or if we need to create new issue(s) to import additional sources so that we can capture these terms.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the attached civic_unable_to_normalize_drugs.txt file and inspect the existing imported sources used by therapy-normalization. Compare the failed queries against those sources to determine whether terms are missing or additional sources are needed. Done means the affected drugs normalize and the 105 evidence items can be captured, or any required source additions are documented as follow-up issues.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
bioinformatics, data
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.