OpenParable
Skip to content
← Back to skills

Deepvariant Caller

Others
deepvariant-caller

Deepvariant Caller is an Agent Skill for general use published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

DeepVariant deep learning variant calling skill for high-accuracy SNV and indel detection

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/domains/science/bioinformatics/skills/deepvariant-caller/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/deepvariant-caller, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

DeepVariant Caller Skill

Purpose

Enable DeepVariant deep learning variant calling for high-accuracy SNV and indel detection.

Capabilities

  • GPU-accelerated variant calling
  • WGS/WES/PacBio mode selection
  • Model customization and retraining
  • Confidence calibration
  • Multi-sample variant calling
  • Docker/Singularity deployment

Usage Guidelines

  • Select appropriate model for sequencing type
  • Use GPU acceleration when available
  • Validate accuracy against benchmark datasets
  • Consider container deployment for reproducibility
  • Document model version and parameters
  • Compare with traditional callers for validation

Dependencies

  • DeepVariant
  • Parabricks

Process Integration

  • Whole Genome Sequencing Pipeline (wgs-analysis-pipeline)
  • Long-Read Sequencing Analysis (long-read-analysis)
  • Analysis Pipeline Validation (pipeline-validation)