humaninfinder 1.0.2

A professional evolutionary discovery tool for Humanin-like peptides (sORFs) using a Hybrid AI approach.

HumaninFinder v1.0.0

HumaninFinder is a professional bioinformatics tool for the discovery and classification of Humanin-like peptides (sORFs). It uses a Hybrid AI approach, combining deep learning (ESM-2) with biophysical properties and a specialized AI Research Agent.

---

🚀 Installation

Option 1: Fast Install (Recommended)

Install the latest stable version directly from PyPI:

pip install humaninfinder

Note: Ensure you have HMMER3 installed on your system.

Option 2: Conda/Mamba (Full Environment)

Best for scientific reproducibility, as it installs all dependencies (including HMMER3):

git clone https://github.com/LaBiOmicS/humanin-finder
cd humanin-finder
mamba env create -f environment.yml
mamba activate humanin_env

---

⚡ Quick Start

To scan a mitochondrial genome and identify Humanin candidates:

humanin-finder predict --input genome.fasta --output results --hmm --rescue

---

🌟 Key Features

• Hybrid AI Engine: ESM-2 structural embeddings + Biophysical analysis.
• Evolutionary Rescue: Detects non-canonical starts and pseudogenic relics.
• Smart Filtering: Automatically removes technical windowing artifacts.
• AI Research Agent: Expert interpretation of results via local LLMs (Ollama).

---

🤖 AI Research Agent (Optional)

Consult the integrated AI specialist for biological insights:

# Install agent support
pip install "humaninfinder[agent]"
# Run interpretation
humanin-finder agent --results results_csv.csv

---

📖 Main Commands

• setup: Verify environment and prerequisites.
• predict: Run the discovery and classification pipeline.
• agent: Interpret results with the specialized AI assistant.

---

Developed by LaBiOmicS, UMC, Brazil.