Giter Site home page Giter Site logo

gene_embedding_generator's Introduction

A multi-context feature learning approach to identify disease-specific gene neighborhoods

A network-based representation learning framework which uses both co-expressed and functional gene pairs to learn continuous gene representations.

Training the model

Our model requires two sets of input gene pairs (co-expressed and functionally related). Both the input files should be space-seperated format as shown below:

SERPINB3 SERPINB4
ARMC3 CFAP52
C9orf24 CFAP52
SNTN CFAP52

Then our feature learning methodology can be implemented using the below syntax:

python main_handler.py --infile co_expressed_pairs.txt --fun_infile functional_pairs.txt

We include both sets of inputs used in our manuscript in the data folder of the repository. To see the entire list of parameters/options:

python main_handler.py --help

Using pre-trained embeddings

Our model can also be trained using a set of pre-trained gene embeddings using the below command.

python pre_trained_handler.py --infile co_expressed_pairs.txt --fun_infile functional_pairs.txt 
                              --init_emb embeddings.txt

The input gene embeddings should be provided in a space-delimited file with the first column containing the gene identified or a symbol. The remaining N columns in each row represent the N-dimensional gene representation.

These pre-trained embeddings could be from an earlier training iteration or representations of genes learned within the same disease context.

Code dependencies

Our method was tested in Python 3.7. The required dependencies or packages include PyTorch, numpy, pandas.

gene_embedding_generator's People

Contributors

sudhirghandikota avatar

Stargazers

 avatar

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.