FANTASIA

Functional ANnoTAtion based on embedding space SImilArity

FANTASIA is an advanced pipeline designed for automatic functional annotation of protein sequences using state-of-the-art protein language models. It integrates deep learning embeddings and similarity searches in vector databases to associate Gene Ontology (GO) terms with proteins.

Contents

• Key Features
• Data Source
  • References
• Methods
  • Step 1: Setup and Input File Preprocessing
  • Step 2: Embedding Computation
  • Step 3: Embedding Similarity
  • Step 4: GO Transfer
  • Step 5: Output Description and Optional Formatting
  • References
• Performance on HPC
  • Input Data
  • Execution Parameters
  • Hardware Configuration
  • Summary
  • Execution Times
  • Conclusions
• Acknowledgments
• Citing FANTASIA
• Contact Information

Use cases

• Benchmarking
  • Objective
  • Step-by-Step Procedure
  • Input Data
  • Configuration Parameters
  • Results
  • References
• Functional Annotation
  • Objective
  • Functional Annotation Procedure
  • Input Data
  • Functional Annotation Configuration
  • Results

Deployment

• FANTASIA Deployment Guide
  • Prerequisites
  • Starting Required Services
  • Configuration
  • Initialization
  • Running the Pipeline
• HPC Deployment Guide
  • Step 1: Connect to the HPC via VPN
  • Step 2: Reserve Resources on the Cluster
  • Step 3: Connect to the Assigned Node
  • Step 3.1: Create Separate Screen Sessions
  • Step 4: Load Required Modules
  • Step 5: Build and Configure the Singularity Container for PostgreSQL in RAM
  • Step 6: Configure PostgreSQL User, Database, and Restart the Server
  • Step 7: Build and Run RabbitMQ
  • Step 8: Build and Configure the Singularity Container for FANTASIA
  • Step 9: Initialize FANTASIA
  • Step 10: Run FANTASIA
  • Explanation of the Commands