Giter Site home page Giter Site logo

pulimeng / biology-network-reduction Goto Github PK

View Code? Open in Web Editor NEW
1.0 2.0 1.0 5.04 MB

Graph representation for system biology networks and the reduction of them for machine learning purposes

License: GNU General Public License v3.0

Python 100.00%
ppi-networks systemsbiology

biology-network-reduction's Introduction

Biology Network Reduction for Graph-Based Machine Learning

This repo provides algorithms and examples for the network reduction for different biological networks (protein-protein interaction, DNA, drug-target interaction). The reduction is necessary for the machine learning applications since most of these networks are large and sparse (both topological and feature-wise). The size of the networks makes them difficult for certain applications (graph classification). And the sparsity in features also poses trouble for the machine learning models since the useful information can be well scattered in the network. Imagine looking at two images with only handful of pixels differen and try to find the underlying difference. Thus it is important to reduce the networks before they can be used for any graph-based machine learning.

This README file is written by Limeng Pu.

Dependencies

Change line 12 of the file accordingly then run conda env create -f environment.yml.

Biology Networks

Protein-protein interaction (PPI) network

This network describes the interaction between the proteins. It comes from STRING database (https://string-db.org/). Version 11 is currently in use. It is established by literature mining. Each interaction has a score, which is the confidence score derived by the authors. The higher the score, more likely the interaction exists in reality. The statistics after initial filtering is as follow:

  • Number of nodes (proteins): 19,144.
  • Number of edges (interactions): 11,759,454.
  • Format: protein1, protein2, score.
  • Direction: undirected graph

biology-network-reduction's People

Contributors

pulimeng avatar

Stargazers

 avatar

Watchers

Kostas Georgiou avatar  avatar

Forkers

aspirincode

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.