https://github.com/joerivandervelde/alphamissense-vkgl-threshold

Optimal AlphaMissense threshold based on VKGL variant classifications
https://github.com/joerivandervelde/alphamissense-vkgl-threshold

alphafold2 genome-analysis missense-mutations molecular-diagnostics vkgl

Last synced: about 2 months ago
JSON representation

Optimal AlphaMissense threshold based on VKGL variant classifications

• Host: GitHub
• URL: https://github.com/joerivandervelde/alphamissense-vkgl-threshold
• Owner: joerivandervelde
• Created: 2024-02-06T14:56:19.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-02-07T11:04:21.000Z (11 months ago)
• Last Synced: 2024-02-07T13:26:34.491Z (11 months ago)
• Topics: alphafold2, genome-analysis, missense-mutations, molecular-diagnostics, vkgl
• Language: R
• Homepage:
• Size: 404 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# The optimal AlphaMissense threshold based on 52799 VKGL variant classifications is 0.2977 with PPV 61%, NPV 96%, sensitivity 87% and specificity 86%.

![AM-VKGL-thr-dens](outputs/alphamissense-vkgl-threshold-density.png)

## Sanity check (i.e. verification): re-determining AlphaMissense's own threshold using AlphaMissense classifications resulting from applying that same threshold. The optimal AlphaMissense threshold based on AlphaMissense's own classifications is 0.5641 with PPV 100%, NPV 100%, sensitivity 100% and specificity 100%.

![AM-AM-thr-dens](outputs/alphamissense-amclass-threshold-density.png)