Predicting lncRNA–protein interactions based on graph autoencoders and collaborative training

Last update: Nov 29, 2022

Related tags

Overview

Predicting lncRNA–protein interactions based on graph autoencoders and collaborative training

Code for our paper "Predicting lncRNA–protein interactions based on graph autoencoders and collaborative training" (IEEE BIBM 2021)

Requirements

The code has been tested running under Python 3.7.4, with the following packages and their dependencies installed:

numpy==1.16.5
pytorch==1.3.1
sklearn==0.21.3

Usage

git clone https://github.com/zhanglabNKU/LPIGAC.git
cd LPIGAC
python fivefoldcv.py

Options

We adopt an argument parser by package argparse in Python, and the options for running code are defined as follow:

parser = argparse.ArgumentParser()
parser.add_argument('--no-cuda', action='store_true', default=False,
                    help='Disables CUDA training.')
parser.add_argument('--seed', type=int, default=1, help='Random seed.')
parser.add_argument('--epochs', type=int, default=300,
                    help='Number of epochs to train.')
parser.add_argument('--lr', type=float, default=0.01,
                    help='Learning rate.')
parser.add_argument('--weight_decay', type=float, default=1e-7,
                    help='Weight decay (L2 loss on parameters).')
parser.add_argument('--hidden', type=int, default=144,                    help='Dimension of representations')
parser.add_argument('--alpha', type=float, default=0.5,
                    help='Weight between lncRNA space and protein space')
parser.add_argument('--beta', type=float, default=1.0,
                    help='Hyperparameter beta')

args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()

Data

Files of data are listed as follow:

LncRNAName.txt includes the names of all lncRNAs.
ProteinName.txt includes the names of all proteins.
interaction.txt is a matrix Y that shows lncRNA-protein associations. Y[i,j]=1 if lncRNA i and protein j are known to be associated, otherwise 0.
protfeat.txt is the feature matrix of proteins.
rnafeat.txt is the feature matrix of lncRNAs.

Citation

@inproceedings{jin2021lpigac,
    author = {Jin, Chen and Shi, Zhuangwei and Zhang, Han and Yin, Yanbin},
    title = {Predicting lncRNA–protein interactions based on graph autoencoders and collaborative training},
    year = {2021},
    booktitle = {IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},
}

Predicting lncRNA–protein interactions based on graph autoencoders and collaborative training

Related tags

Overview

Predicting lncRNA–protein interactions based on graph autoencoders and collaborative training

Requirements

Usage

Options

Data

Citation

Owner

zhanglabNKU

PyTorch implementation of "ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context" (INTERSPEECH 2020)

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

NeurIPS-2021: Neural Auto-Curricula in Two-Player Zero-Sum Games.

Detectron2 for Document Layout Analysis

Real-Time Multi-Contact Model Predictive Control via ADMM

Automatically measure the facial Width-To-Height ratio and get facial analysis results provided by Microsoft Azure

PyTorch common framework to accelerate network implementation, training and validation

Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"

Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary Differential Equations

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)

Augmented CLIP - Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.

Pca-on-genotypes - Mini bioinformatics project - PCA on genotypes

BMVC 2021 Oral: code for BI-GCN: Boundary-Aware Input-Dependent Graph Convolution for Biomedical Image Segmentation

A large-scale benchmark for co-optimizing the design and control of soft robots, as seen in NeurIPS 2021.

Cossim - Sharpened Cosine Distance implementation in PyTorch

This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

Code release for DS-NeRF (Depth-supervised Neural Radiance Fields)

Repository for tackling Kaggle Ultrasound Nerve Segmentation challenge using Torchnet.

TensorFlow implementation of Adaptive Information Transfer Multi-task (AITM) framework. Code for the paper submitted to KDD21: Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning for Customer Acquisition.

2021-MICCAI-Progressively Normalized Self-Attention Network for Video Polyp Segmentation