scientific-variant-effect-prediction

Integrate AlphaMissense, CADD, and SpliceAI to score and classify variant pathogenicity.

3|1|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/nahisaho/satori --skill scientific-variant-effect-prediction
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scientific-variant-effect-prediction
Source: https://github.com/nahisaho/satori/tree/main/src/.github/skills/scientific-variant-effect-prediction
Command: npx skills add https://github.com/nahisaho/satori --skill scientific-variant-effect-prediction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a unified framework to predict and prioritize the pathogenic effects of genetic variants by integrating AlphaMissense, CADD, and SpliceAI, with Ensembl VEP linkage and variant filtering to support downstream interpretation.

Core Features & Use Cases

  • Integrates AlphaMissense, CADD, and SpliceAI into a single reusable pipeline for variant pathogenicity assessment.
  • Produces per-variant scores and a consensus label to prioritize variants for follow-up in WES/WGS analyses.
  • Leverages ToolUniverse SMCP tools and Ensembl VEP integration for annotation and prioritization in clinical and research workflows.

Quick Start

Run the consensus variant-effect-prediction workflow on your variant list to obtain per-variant scores and a consensus pathogenicity label.

Frequently Asked Questions about scientific-variant-effect-prediction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I predict variant pathogenicity using AlphaMissense, CADD, and SpliceAI together?

Variant pathogenicity prediction integrates AlphaMissense, CADD, and SpliceAI scores into a single pipeline, outputting per-variant scores and a consensus pathogenicity label for WES/WGS datasets.

What is the best way to prioritize genetic variants in whole-exome and whole-genome analyses?

Prioritizing genetic variants in whole-exome and whole-genome analyses is done by applying a consensus scoring framework across multiple predictors to generate a unified pathogenicity label for downstream interpretation.

Does this variant pathogenicity prediction approach require Ensembl VEP integration?

Ensembl VEP integration is required for this variant pathogenicity prediction approach to perform variant annotation and filtering, leveraging ToolUniverse SMCP tools for clinical and research workflows.

Can I get a consensus pathogenicity label for a custom variant list?

You can obtain a consensus pathogenicity label for a custom variant list by running the unified variant-effect-prediction workflow, which aggregates scores from AlphaMissense, CADD, and SpliceAI.

What data do I need to access for variant pathogenicity scoring?

Variant pathogenicity scoring requires access to AlphaMissense, CADD, and SpliceAI data, along with Ensembl VEP integration to properly assess and annotate genetic variants.

Are there limitations to using consensus pathogenicity labels for clinical interpretation?

Consensus pathogenicity labels support prioritization in clinical workflows but require access to AlphaMissense, CADD, and SpliceAI data, meaning results are constrained by the coverage and limitations of those individual predictors.