Genomic MSA Transformer

This repository contains the code for the Genomic MSA Transformer project. The project uses DNA sequences in a multiple sequence alignment transformer. These are trained in an unsupervised fashion. A classifier then uses the embeddings from the transformer to classify operons within genomes of various organisms.

Table of Contents

• Paper
• Installation
• Usage
• Results

Paper

For more details on the project, please refer to our paper: Learning Genome Architecture Using MSA Transformers

Installation

To install the dependencies, run:

pip install -r requirements.txt

Usage

To train the model, run:

python train.py

To test the model, run:

python test.py

Results

The model achieved an accuracy of 90% on the test set.

I hope this helps! Let me know if you have any other questions.