GithubHelp home page GithubHelp logo

computesuda / sgad Goto Github PK

View Code? Open in Web Editor NEW
2.0 0.0 1.0 15.5 MB

Protein Interaction Network Reconstruction with a Structural Gated Attention Deep Model by Incorporating Network Structure Information

Python 100.00%
protein-protein-interaction protein-protein-interaction-network

sgad's Introduction

Contents for SGAD

Overview

Protein-protein interactions (PPIs) represent a delicate but universal mechanism for a wide range of biological processes in living cells. Many aberrant PPIs have been identified to be involved in various diseases, which greatly enlarge the therapeutic targets for cancers, infectious disease, neurodegenerative diseases, and so on. Nowadays, multiple descriptors based on sequence information have been employed in many deep learning predictors. However, these models are mostly lacking the sufficient description of the original structure of protein networks and incapable of capturing the highly nonlinear structure of protein networks. As a result, the predictive models suffer from generalizability and are not applicable to the unseen datasets. On the other word, most of the predictive models are not robust in dealing with the noise in the dataset, leading to the fragility in predictive models. Herein, we proposed a novel computational framework, Structural Gated Attention Deep (SGAD) Model, for PPIs network reconstruction.

Repo Contents

System Requirements

The SGAD package requires only a standard computer with enough RAM to support the operations defined by a user. All the experiments were run on CentOS 8, CUDA 10.1.243, CuDnn 7.0, Python 3.7, Keras 2.0, and PyTorch 1.3.0.

Installation Guide

Dependencies

The following dependencies are required to run SGAD properly:

  • scikit-learn==0.23.0
  • numpy==1.16.2
  • torch==1.3.1
  • keras==2.0.8
  • networkx==2.4.0

Download

git clone https://github.com/ComputeSuda/SGAD.git

Citation

For usage of the package, please cite the following paper.

Fei Zhu, et al, Protein Interaction Network Reconstruction with a Structural Gated Attention Deep
Model by Incorporating Network Structure Information, J. Chem. Inf. Model., 2022, 62, 2, 258โ€“273.

This repository is distributed under GNU General Public License v3.0.

sgad's People

Contributors

fanwangm avatar

Stargazers

 avatar  avatar

Forkers

dl0520

sgad's Issues

Q for code

# 2
# Keep the proteins involved
proteinID1 = [Po_pairs[i][0] for i in range(len(Po_pairs))]
proteinID2 = [Po_pairs[i][1] for i in range(len(Po_pairs))]
proteinID3 = [Ne_pairs[i][0] for i in range(len(Ne_pairs))]
proteinID4 = [Ne_pairs[i][1] for i in range(len(Ne_pairs))]
proteinID = list(set(proteinID1 + proteinID2 + proteinID3 + proteinID4))
add_nodes = list(set(proteinID3 + proteinID4) - set(proteinID1 + proteinID1))  ##

In SGAD.py,line 477 (the last line above), "proteinID1 + proteinID1", Why use "proteinID1" twice, and use "proteinID1" once is also the same result. Would you please take the time to answer my questions

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.