metalncrna 1.1.4

A portable and modular meta-predictor for identifying Long Non-coding RNAs (lncRNAs).

metaLncRNA v1.1.4 🧬🤖

---

metaLncRNA is a modular, high-performance Python framework designed to identify Long Non-coding RNAs (lncRNAs) by orchestrating an ensemble of seven diverse computational tools. It resolves the "reproducibility gap" by automating environment management and providing a robust consensus prediction through weighted soft-voting.

---

📂 Repository Structure

• src/metalncrna/: Core package logic and adapters.
  • data/: Internal default configurations and pre-packaged models.
  • third_party/: Integrated source code for legacy predictors (LGC, CPPred, CNCI).
• scripts/: Production Bash utilities for HPC and long-running jobs.
• tests/: Automated unit and integration test suite.
• docs/: Technical guides and architecture details.
• deploy/: Docker and Singularity definitions.
• INPI_Registration/: Legal software registration assets.

---

⚙️ Configuration

metaLncRNA follows a robust configuration loading order:

1. Internal Defaults: Built-in weights and paths in src/metalncrna/data/default_config.yaml.
2. Local Config: metaLncRNA_config.yaml in your current working directory.
3. User Home: ~/.metalncrna/config.yaml.
4. Explicit Path: Provided via the -c or --config flag.

---

🚀 Key Features

• Ensemble Prediction: Combines 7 tools (RNAsamba, CPAT, CPC2, PLEK, CNCI, CPPred, LGC).
• Interactive AI Agent: Integrated local LLM assistant (Llama-3.2 or OpenBioLLM) to interpret results and explain classification decisions.
• Reproducibility First: Built-in environment isolation via Mamba and Pixi.
• Scientific Dashboard: Interactive HTML reports with tool congruence matrices.
• Publication Ready: Formatted according to JOSS standards for scientific software.

---

📖 Documentation

For detailed instructions, please refer to our Documentation Hub:

• 🛠️ User Guide: Installation, common commands, and AI Chat usage.
• 🏗️ Technical Architecture: Ensemble methodology and AI-driven interpretation layer.
• 🔧 Troubleshooting: Common issues and hardware requirements.

---

🛠️ Quick Start

1. Installation

The easiest way to install metaLncRNA is via pip. We recommend using a virtual environment:

# Create and activate a virtual environment (optional but recommended)
python3 -m venv venv
source venv/bin/activate

# Install the core package
pip install metalncrna

# Recommended: Install with AI Agent support
pip install "metalncrna[agent]"

# Finalize setup (downloads models and creates isolated tool environments)
metalncrna setup

2. Run Integrated Pipeline

metalncrna predict -i transcripts.fasta -o ./results -p MyAnalysis

3. Ask the AI Agent

# Get a summary of your findings
metalncrna ask "Summarize the analysis results" -r ./results/MyAnalysis/metalncrna_results.tsv

---

🐳 Deployment

Pre-configured definitions are available for Docker and Singularity/Apptainer in the deploy/ directory.

🤝 Contributing

Contributions are welcome! Please see our CONTRIBUTING.md for details.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

Developed by LaBiOmicS - Laboratory of Bioinformatics and Omics Sciences. Institution: Universidade de Mogi das Cruzes (UMC)