Skip to content

The Farmers

Computational research leveraging high-performance computing infrastructure for genomics and bioinformatics

Get Started → View on GitHub

What We Do

  • Genome Language Models

    Develop and optimize deep learning models for understanding genomic sequences and their functional implications

  • Function Prediction

    Sequence-to-function prediction using state-of-the-art deep learning architectures

  • Gene Expression

    Sequence-to-gene expression modeling to understand regulatory mechanisms

  • Variant Analysis

    Predict and analyze the impact of genetic variants on biological function

  • Multi-Omics

    Single cell and multi-omics data integration and modeling

  • Tool Development

    Build bioinformatics tools and pipelines for the research community

Our Team

The Team

  • Leads: Tuyen, Dat
  • Core Members: Binh, Thuan, Son, Vy, Ty

Infrastructure

  • Primary System: Saga HPC Cluster (SIGMA2/NRIS)
  • Project Account: nn9780k
  • GitHub: farmer-vn
  • Weights & Biases: wandb.ai/datngu

Quick Access

Resource Link
Saga Login ssh username@saga.sigma2.no
Project Directory /cluster/projects/nn9780k
Official Docs documentation.sigma2.no
Storage Check dusage -p nn9780k
CPU Hours cost -p nn9780k

Getting Started

  • 1. Get Access

    Request Saga account through project leader Tuyen and GitHub access through Dat

  • 2. Setup Environment

    Configure SSH keys, two-factor authentication, and follow our Saga Setup Guide

  • 3. Start Computing

    Submit test jobs with SLURM, monitor resources, and follow best practices

Resources

Current Usage Statistics

Check your resource usage anytime:

# Storage quota
dusage -p nn9780k

# CPU hours consumed
cost -p nn9780k

External Documentation

Last updated: December 24, 2025