Genwei Han’s research while affiliated with Central South University of Forestry and Technology and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (2)


MSCNE:Predict miRNA-Disease Associations Using Neural Network based on Multi-source Biological Information
  • Article

August 2021

·

15 Reads

·

10 Citations

IEEE/ACM Transactions on Computational Biology and Bioinformatics

Genwei Han

·

·

Lei Deng

The important role of microRNA (miRNA) in human diseases has been confirmed by some studies. However, only using biological experiments has greater blindness, leading to higher experimental costs. In this paper a high-efficiency algorithm based on a variety of biological source information and applying a combination of a convolutional neural network (CNN) feature extractor and an extreme learning machine (ELM) classifier is proposed. Specifically, the semantic similarity of diseases, the gaussian interaction profile kernel similarity of the four biological information of miRNA, disease, long non-coding RNA (lncRNA) and environmental factors (EFs), and the similarities of miRNAs are fused together. Among them, miRNAs similarity is composed of miRNA target information, sequence information, family information, and function information. Then, the dimensionality of the data set is reduced by the autoencoder (AE). Finally, deep features are extracted through CNN, and then the association between miRNA and disease is predicted by ELM. The experimental results show that the average AUC value based on the multi-biological source information (MSCNE) model is 0.9630, which can reach higher performance than the other classic classifier, feature extractor mentioned and the other existing algorithms. The results show the MSCNE algorithm is effective to predict the correlation of miRNA-disease.


Flowchart of our method: (A) Obtained the association matrix A; Calculated the gaussian interaction profile kernel similarity of lncRNA and EF respectively. (B) Calculated the chemical structure similarity matrix E. (C) Obtained lncRNA similarity information SL and construct a similarity matrix SE of EF. (D) Integrated three subnets A, SL, and SE to construct a global heterogeneous network. (E) Constructed the adjacency matrix G and obtain the diffusion feature. (F) Calculated the Hetesim score. (G) Combined the diffusion feature and the HeteSim score. (H) Trained the Gradient Boosting Decision Tree classifier (GBDT).
Example of understanding HeteSim masure. Different color circles denote three different kinds of objects in the heterogeneous network. (A–C) represent three different nodes in the heterogeneous network.
The ROC curve comparison with other machine learning methods. (A) The ROC curve with using KNN. (B) The ROC curve with using RF. (C) The ROC curve with using SVM. (D) The ROC curve with using GBDT.
The ROC curves comparison with other machine learning methods on independent dataset.
The performance comparison of different feature groups (Diffusion, HeteSim and combined feature).

+5

GBDTL2E: Predicting lncRNA-EF Associations Using Diffusion and HeteSim Features Based on a Heterogeneous Network
  • Article
  • Full-text available

April 2020

·

147 Reads

·

7 Citations

Interactions between genetic factors and environmental factors (EFs) play an important role in many diseases. Many diseases result from the interaction between genetics and EFs. The long non-coding RNA (lncRNA) is an important non-coding RNA that regulates life processes. The ability to predict the associations between lncRNAs and EFs is of important practical significance. However, the recent methods for predicting lncRNA-EF associations rarely use the topological information of heterogenous biological networks or simply treat all objects as the same type without considering the different and subtle semantic meanings of various paths in the heterogeneous network. In order to address this issue, a method based on the Gradient Boosting Decision Tree (GBDT) to predict the association between lncRNAs and EFs (GBDTL2E) is proposed in this paper. The innovation of the GBDTL2E integrates the structural information and heterogenous networks, combines the Hetesim features and the diffusion features based on multi-feature fusion, and uses the machine learning algorithm GBDT to predict the association between lncRNAs and EFs based on heterogeneous networks. The experimental results demonstrate that the proposed algorithm achieves a high performance.

Download

Citations (2)


... This framework optimizes MDA prediction by integrating the prediction scores of different subnetworks, effectively mitigating the noise problem introduced by random negative case selection, and fuses the strengths of GCN and VAE. The MSCNE model [49] innovatively integrated Convolutional Neural Network with AE to create a multi-level feature extraction subnetwork for the final association prediction. The MDA-GCNFTG method [50] relied on the greedy strategy of GCN and graph sampling to solve the common problem of proliferation of the number of neighboring nodes in GCN. ...

Reference:

Prediction of miRNA-disease associations based on PCA and cascade forest
MSCNE:Predict miRNA-Disease Associations Using Neural Network based on Multi-source Biological Information
  • Citing Article
  • August 2021

IEEE/ACM Transactions on Computational Biology and Bioinformatics

... The weak classifiers were constructed through different iteration rounds in each GBDT iteration, and the gradient of the classifiers from the previous iteration was used to train each classifier. The weights of the weak classifiers are added together to create the final classifier [9], [16]. ...

GBDTL2E: Predicting lncRNA-EF Associations Using Diffusion and HeteSim Features Based on a Heterogeneous Network