# Yeast Database

> Use when working inside the local `yeast_genome_learning` project to download, validate, and analyze Saccharomyces cerevisiae reference data through its teaching scripts.

- Skill: `vimalinx/yeast-database` (Agent Skill)
- Install (CLI): `npx skillmds add vimalinx/yeast-database`
- Raw SKILL.md: https://api.skillmd.com/api/skills/vimalinx/yeast-database/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: vimalinx (https://skillmd.com/u/vimalinx)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/vimalinx/yeast-database

---


# yeast_database

Project-specific gateway for `/home/vimalinx/Projects/bio_studio/projects/yeast_genome_learning`. This is a learning project, not a single executable: the real entrypoints are the staged Bash scripts under `scripts/`, while `scripts/pipeline.py` provides a compatibility wrapper for `--steps` and `--validate`.

## Quick Start

- **Project root:** `/home/vimalinx/Projects/bio_studio/projects/yeast_genome_learning`
- **Primary entrypoint:** `bash scripts/01_setup_database.sh`
- **Compatibility entrypoint:** `python scripts/pipeline.py --steps`

## When To Use This Tool

- Downloading and organizing the local yeast reference genome and annotations
- Verifying that the learning project's database files and helper tools are ready
- Walking through the yeast learning workflow step by step
- Running simple gene extraction, sequence analysis, and BLAST exercises inside the project

## Common Patterns

```bash
# List the available learning steps
cd /home/vimalinx/Projects/bio_studio/projects/yeast_genome_learning
python scripts/pipeline.py --steps
```

```bash
# Download the yeast database bundle
cd /home/vimalinx/Projects/bio_studio/projects/yeast_genome_learning
bash scripts/01_setup_database.sh
```

```bash
# Verify the setup, then extract a gene
cd /home/vimalinx/Projects/bio_studio/projects/yeast_genome_learning
bash scripts/02_verify_install.sh
bash scripts/03_extract_gene.sh ACT1
```

## Recommended Workflow

1. Enter the local project directory first.
2. Run the setup script to download the reference genome, annotations, proteins, and BLAST databases.
3. Validate the installation before doing gene-level or BLAST exercises.
4. Use the numbered Bash scripts as the primary learning flow, and use `pipeline.py` only as a compatibility helper for listing/validating steps.

## Guardrails

- This is explicitly a learning project. The README says the main entrypoints are the staged Bash scripts, not a unified production pipeline.
- `python scripts/pipeline.py --steps` works locally and lists the current teaching steps, but `pipeline.py` is only a compatibility wrapper.
- `scripts/01_setup_database.sh` downloads data from NCBI/SGD over FTP/HTTP, so network access is required.
- `samtools` and `makeblastdb` are optional in the setup script: if missing, indexing or BLAST database creation is skipped with warnings.
- The old autogenerated skill pointed at `~/bio_studio/projects/yeast_genome_learning/`; the actual workspace path is `/home/vimalinx/Projects/bio_studio/projects/yeast_genome_learning`.