ouyang-dong,github

hgclamir

HGCLAMIR model mainly includes hypergraph convolutional network (HGCN), hypergraph contrastive learning, view-aware attention mechanism, integrated representation learning and neural projection.

MOGLAM is an end-to-end interpretable multi-omics integration method, which mainly consists of three modules: dynamic graph convolutional network with feature selection (FSDGCN), multi-omics attention mechanism (MOAM), and omic-integrated representation learning (OIRL).

single-cell-sequencing

Two methods of single cell sequencing are Single cell RNA sequencing and CyTOF

spldhyperawntf_model

More and more evidence indicates that the dysregulations of microRNAs (miRNAs) lead to diseases through various kinds of underlying mechanisms. Identifying the multiple types of disease-related miRNAs plays an important role in studying the molecular mechanism of miRNAs in diseases. Moreover, compared with traditional biological experiments, computational models are time-saving and cost-minimize. However, most tensor-based computational models still face three main challenges: i) easy to fall into bad local minima; ii) preservation of higher-order relations; iii) false-negative samples. To this end, we propose a novel tensor completion framework integrating self-paced learning, hypergraph regularization and adaptive weight tensor into nonnegative tensor factorization, called SPLDHyperAWNTF, for the discovery of potential multiple types of miRNA-disease associations. We first combine self-paced learning with nonnegative tensor factorization to effectively alleviate the model from falling into bad local minima. Then, hypergraphs for miRNAs and diseases are constructed, and hypergraph regularization is used to preserve the higher-order complex relations of these hypergraphs. Finally, we innovatively introduce adaptive weight tensor, which can effectively alleviate the impact of false-negative samples on the prediction performance. We compare SPLDHyperAWNTF with baseline models on four datasets. The average results of 5-fold and 10-fold cross-validation show that SPLDHyperAWNTF can achieve better performance in terms of Top-1 precision, Top-1 recall, and Top-1 F1. Furthermore, we implement case studies to further evaluate the accuracy of SPLDHyperAWNTF. As a result, 98 (MDAv2.0) and 98 (MDAv2.0-2) of top-100 are confirmed by HMDDv3.2 dataset. Moreover, the results of enrichment analysis illustrate that unconfirmed potential associations have biological significance.

splhrnmtf

SPLHRNMTF model that integrates self-paced learning and hypergraph regularization into NMTF using L2,1 norm for predicting the associations between miRNAs and diseases.

ouyang-dong Goto Github PK

ouyang-dong's Projects

hgclamir

moglam

single-cell-sequencing

spldhyperawntf_model

splhrnmtf

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent