Skip to content

sheng-n/DL-miRNA-disease-association-methods

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
README.md
README.md
 
 

Repository files navigation

🏎💨miRNA-disease association prediction methods

A survey of deep learning for detecting miRNA-disease associations: databases, computational methods, challenges, and future directions

GitHub stars GitHub forks

Visitor count

Paper [Paper link]

What is miRNA?

RNA can be divided into two categories based on its coding function: (1) RNAs with coding potential, and (2) RNAs without coding potential, also known as non-coding RNA (ncRNA), which includes microRNAs (miRNA), snoRNAs, circRNAs and lncRNAs. Long non-coding RNAs (lncRNAs) are a major class of important ncRNAs with the lengths more than 200 nucleotides. An increasing number of lncRNA have been found to be abnormally expressed in human diseases, and play a critical role in tumor development.

Table of Contents

Overview

  • We collect miRNA- and disease-related databases for MDA prediction, including miRNA-disease association databases, miRNA-related databases, and disease-related databases.
  • We provide the first a comprehensive overview of 45 MDA prediction models based on deep learning and graph neural networks. We classify the two types of models in detail, deep learning models such as autoencoder, multi-layer perceptron, convolutional neural network, variational autoencoder, gated recurrent unit, and generative adversarial network; graph neural network models such as graph convolutional network, graph attention network, graph autoencoder, as shown below figure 1. image

Fig 1: Deep learning and Graph neural network computational methods for MDA prediction.

Data resources

miRNA-disease association data resources

Database Description URL
HMDD v3.2 Collects 35547 experimentally confirmed MDAs, involving 1206 miRNA genes and 893 diseases http://www.cuilab.cn/hmdd
dbDEMC 3.0 Contains 3268 differentially expressed miRNAs for 40 cancer types from humans, mics, and rats https://www.biosino.org/dbDEMC
miR2Disease Records 349 miRNAs, 163 diseases, and 3273 entries http://www.mir2disease.org/
miRCancer Provides 9080 associations between 196 human cancers and 57984 miRNAs http://mircancer.ecu.edu/
miRwayD Collects 663 miRNA-pathway association entries for 76 diseases, involving 232 miRNAs, 122 pathways, and 328 targeted genes http://www.mirway.iitkgp.ac.in/
MNDR (RNADisease v4.0) Stores 343,273 associations between more than 18 RNA categories, 117 species, and 4090 diseases http://www.rnadisease.org/

miRNA-related data resources

Database Description URL
miRbase v22 Responsible for miRNA naming and is the primary public repository for miRNA sequences and annotations https://www.mirbase.org/
mirTarbase Stores experimentally verified miRNA-target interactions. containing 19912394 interactions between 4630 miRNAs and 27172 mRNAs (target genes) https://miRTarBase.cuhk.edu.cn/
miRWalk Provides experimentally verified miRNA-gene interactions http://mirwalk.umm.uni-heidelberg.de/
starbase (ENCORI) Collects regulatory relationships on miRNA-ceRNA, miRNA-ncRNA, and protein-RNA interaction https://starbase.sysu.edu.cn/
lncRNASNP2 Contains experimentally verified miRNA-lncRNA interactions http://bioinfo.life.hust.edu.cn/lncRNASNP
miREnvironment Records experimentally supported interactions between miRNAs, environmental factors, and phenotypes http://www.cuilab.cn/miren

Disease-related data resources

Database Description URL
MeSH Is the NLM controlled vocabulary thesaurus used for indexing, cataloging, and searching of biomedical and health-related information http://www.nlm.nih.gov/
HPO Offers a comprehensive logical standard to depict and computationally analyze phenotypic abnormalities within human disease https://hpo.jax.org/app/
OMIM Records collated information about genes and genetic phenotypes and the relations between them, with 26,588 entries covering 7,248 diseases and 4,685 genes http://www.ncbi.nlm.nih.gov/omim
DisGeNet Contains publicly available collections of genes and variants related to human diseases https://www.disgenet.org/
LncRNADisease Provides experimentally verified and predicted lncRNA-disease associations and circRNA-disease associations, as well as regulatory relationships between lncRNAs, mRNAs, and miRNAs http://www.rnanut.net/lncrnadisease/

Classical deep learning models for predicting MDAs

Autoencoder

  1. [DeepMDA] Fu L, Peng Q. A deep ensemble model to predict miRNA-disease association, Scientific Reports 2017;7(1):14482. [Download] [Code]

  2. [DRMLDA] Chen X, Gong Y, Zhang D-H et al. DRMDA: deep representations-based miRNA–disease association prediction, Journal of Cellular and Molecular Medicine 2018;22(1):472-485. [Download]

  3. [MLMDA] Zheng K, You Z-H, Wang L et al. MLMDA: a machine learning approach to predict and validate MicroRNA–disease associations by integrating of heterogenous information sources, Journal of Translational Medicine 2019;17(1):260. [Download]

  4. [DFELMDA] Liu W, Lin H, Huang L et al. Identification of miRNA–disease associations via deep forest ensemble learning based on autoencoder, Briefings in Bioinformatics 2022;23(3). [Download] [Code]

  5. [MDA-CF] Dai Q, Chu Y, Li Z et al. MDA-CF: Predicting MiRNA-Disease associations based on a cascade forest model by fusing multi-source information, Computers in Biology and Medicine 2021;136:104706. [Download] [Code]

  6. [PMDFI] Tang M, Liu C, Liu D et al. PMDFI: Predicting miRNA–Disease Associations Based on High-Order Feature Interaction, Frontiers in genetics 2021;12. [Download]

  7. [MSCNE] Han G, Kuang Z, Deng L. MSCNE:Predict miRNA-Disease Associations Using Neural Network based on Multi-source Biological Information, IEEE/ACM Transactions on Computational Biology and Bioinformatics 2021:1-1. [Download]

  8. [SMALF] Liu D, Huang Y, Nie W et al. SMALF: miRNA-disease associations prediction based on stacked autoencoder and XGBoost, BMC Bioinformatics 2021;22(1):219. [Download] [Code]

  9. [MDA-CNN] Peng J, Hui W, Li Q et al. A learning-based framework for miRNA-disease association identification using neural networks, Bioinformatics 2019;35(21):4364-4371. [Download] [Code]

  10. [AEMDA] Ji C, Gao Z, Ma X et al. AEMDA: inferring miRNA–disease associations based on deep autoencoder, Bioinformatics 2020;37(1):66-72. [Download] [Code]

  11. [iMDA-BN] Zheng K, You Z-H, Wang L et al. iMDA-BN: Identification of miRNA-disease associations based on the biological network and graph embedding algorithm, Computational and Structural Biotechnology Journal 2020;18:2391-2400. [Download]

  12. [DANE-MDA] Ji B-Y, You Z-H, Wang Y et al. DANE-MDA: Predicting microRNA-disease associations via deep attributed network embedding, iScience 2021;24(6):102455. [Download] [Code]

  13. [DBNMDA] Chen X, Li T-H, Zhao Y et al. Deep-belief network for predicting potential miRNA-disease associations, Briefings in Bioinformatics 2020;22(3). [Download]

  14. [SAEMD] Wang C-C, Li T-H, Huang L et al. Prediction of potential miRNA–disease associations based on stacked autoencoder, Briefings in Bioinformatics 2022;23(2). [Download] [Code]

  15. [DBMDA] Zheng K, You Z-H, Wang L et al. DBMDA: A Unified Embedding for Sequence-Based miRNA Similarity Measure with Applications to Predict and Validate miRNA-Disease Associations, Molecular Therapy - Nucleic Acids 2020;19:602-611. [Download]

  16. [VAEMDA] Zhang L, Chen X, Yin J. Prediction of Potential miRNA–Disease Associations Through a Novel Unsupervised Deep Learning Framework with Variational Autoencoder, Cells 2019;8(9):1040. [Download]

  17. [SVAEMDA] Ji C, Wang Y, Gao Z et al. A Semi-Supervised Learning Method for MiRNA-Disease Association Prediction Based on Variational Autoencoder, IEEE/ACM Transactions on Computational Biology and Bioinformatics 2022;19(4):2049-2059. [Download]

Multi-layer perceptron

  1. [EPMDA] Dong Y, Sun Y, Qin C et al. EPMDA: Edge Perturbation Based Method for miRNA-Disease Association Prediction, IEEE/ACM Transactions on Computational Biology and Bioinformatics 2020;17(6):2170-2175. [Download]

  2. [MLRDFM] Ding Y, Lei X, Liao B et al. MLRDFM: a multi-view Laplacian regularized DeepFM model for predicting miRNA-disease associations, Briefings in Bioinformatics 2022;23(3). [Download] [Code]

Convolutional neural network

  1. [CNNDMP] Xuan P, Dong Y, Guo Y et al. Dual Convolutional Neural Network Based Method for Predicting Disease-Related miRNAs, International journal of molecular sciences 2018;19(12):3732. [Download]

  2. [CNNMDA] Xuan P, Sun H, Wang X et al. Inferring the Disease-Associated miRNAs Based on Network Representation Learning and Convolutional Neural Networks, International journal of molecular sciences 2019;20(15):3648. [Download]

  3. [DNRLCNN] Zhong J, Zhou W, Kang J et al. DNRLCNN: A CNN Framework for Identifying MiRNA–Disease Associations Using Latent Feature Matrix Extraction with Positive Samples, Interdisciplinary Sciences: Computational Life Sciences 2022;14(2):607-622. [Download]

Graph neural models for predicting MDAs

graph convolutional network

  1. [HGCNMDA(1)] Li C, Liu H, Hu Q et al. A Novel Computational Model for Predicting microRNA–Disease Associations Based on Heterogeneous Graph Convolutional Networks, Cells 2019;8(9):977. [Download]

  2. [Zhu’s method] Zhu R, Ji C, Wang Y et al. Heterogeneous graph convolutional networks and matrix completion for miRNA-disease association prediction, Frontiers in bioengineering and biotechnology 2020;8:901. [Download]

  3. [NIMCGCN] Li J, Zhang S, Liu T et al. Neural inductive matrix completion with graph convolutional networks for miRNA-disease association prediction, Bioinformatics 2020;36(8):2538-2546. [Download] [Code]

  4. [FCGCNMDA] Li J, Li Z, Nie R et al. FCGCNMDA: predicting miRNA-disease associations by applying fully connected graph convolutional networks, Molecular Genetics and Genomics 2020;295(5):1197-1209. [Download]

  5. [MMGCN] Tang X, Luo J, Shen C et al. Multi-view Multichannel Attention Graph Convolutional Network for miRNA–disease association prediction, Briefings in Bioinformatics 2021;22(6). [Download] [Code]

  6. [GSCENet] Li Z, Jiang K, Qin S et al. GCSENet: A GCN, CNN and SENet ensemble model for microRNA-disease association prediction, PLOS Computational Biology 2021;17(6):e1009048. [Download] [Code]

  7. [MVIFMDA] Xie X, Wang Y, Sheng N et al. Predicting miRNA-disease associations based on multi-view information fusion, Frontiers in genetics 2022;13. [Download]

  8. [MDA-GCNFTD] Chu Y, Wang X, Dai Q et al. MDA-GCNFTG: identifying miRNA-disease associations based on graph convolutional networks via graph sampling through the feature and topology graph, Briefings in Bioinformatics 2021;22(6). [Download] [Code]

  9. [MINIMDA] Lou Z, Cheng Z, Li H et al. Predicting miRNA–disease associations via learning multimodal networks and fusing mixed neighborhood information, Briefings in Bioinformatics 2022. [Download] [Code]

  10. [HGCNMDA(2)] Peng W, Che Z, Dai W et al. Predicting miRNA-disease associations from miRNA-gene-disease heterogeneous network with multi-relational graph convolutional network model, IEEE/ACM Transactions on Computational Biology and Bioinformatics 2022:1-12. [Download] [Code]

  11. [MuCoMid] Dong TN, Mucke S, Khosla M. MuCoMiD: A Multitask graph Convolutional Learning Framework for miRNA-Disease Association Prediction, IEEE/ACM Transactions on Computational Biology and Bioinformatics 2022:1-1. [Download] [Code]

  12. [SGNNMD] Zhang G, Li M, Deng H et al. SGNNMD: signed graph neural network for predicting deregulation types of miRNA-disease associations, Briefings in Bioinformatics 2021;23(1). [Download] [Code]

graph attention network

  1. [HGATMDA] Ji C, Wang Y, Ni J et al. Predicting miRNA-Disease Associations Based on Heterogeneous Graph Attention Networks, Frontiers in genetics 2021;12. [Download]

  2. [GRPAMDA] Zhong T, Li Z, You Z-H et al. Predicting miRNA–disease associations based on graph random propagation network and attention network, Briefings in Bioinformatics 2022;23(2). [Download] [Code]

  3. [HGANMDA] Li Z, Zhong T, Huang D et al. Hierarchical graph attention network for miRNA-disease association prediction, Molecular Therapy 2022;30(4):1775-1786. [Download] [Code]

  4. [MDPBMP] Yu L, Zheng Y, Gao L. MiRNA–disease association prediction based on meta-paths, Briefings in Bioinformatics 2022;23(2). [Download] [Code]

graph autoencoder

  1. [GCAEMDA] Li L, Wang Y-T, Ji C-M et al. GCAEMDA: Predicting miRNA-disease associations via graph convolutional autoencoder, PLOS Computational Biology 2021;17(12):e1009655. [Download] [Code]

  2. [NIMGSA] Jin C, Shi Z, Lin K et al. Predicting miRNA-Disease Association Based on Neural Inductive Matrix Completion with Graph Autoencoders and Self-Attention Mechanism, Biomolecules 2022;12(1):64. [Download] [Code]

  3. [GAEMDA] Li Z, Li J, Nie R et al. A graph auto-encoder model for miRNA-disease associations prediction, Briefings in Bioinformatics 2020;22(4). [Download] [Code]

  4. [AGAEMD] Zhang H, Fang J, Sun Y et al. Predicting miRNA-disease associations via node-level attention graph auto-encoder, IEEE/ACM Transactions on Computational Biology and Bioinformatics 2022:1-1. [Download] [Code]

  5. [VGAE-MDA] Ding Y, Tian L-P, Lei X et al. Variational graph auto-encoders for miRNA-disease association prediction, Methods 2021;192:25-34. [Download]

  6. [VGAMF] Shi Z, Zhang H, Jin C et al. Ding Y, Lei X, Liao B et al. Predicting miRNA-Disease Associations Based On Multi-View Variational Graph Auto-Encoder With Matrix Factorization, IEEE Journal of Biomedical and Health Informatics 2022;26(1):446-457. [Download] [Code]

Other deep learning methonds

  1. [CEMDA] Liu B, Zhu X, Zhang L et al. Combined embedding model for MiRNA-disease association prediction, BMC Bioinformatics 2021;22(1):161. [Download] [Code]

  2. [GMDA] Xuan P, Wang D, Cui H et al. Integration of pairwise neighbor topologies and miRNA family and cluster attributes for miRNA–disease association prediction, Briefings in Bioinformatics 2021;23(1). [Download]

A Summary of Methodology Details for predicting MDAs

Methods Descriptions Program code
DeepMDA A novel method based on stacked autoencoders and deep neural networks that encode integrated miRNAs and disease similarities http://mirwalk.umm.uni-heidelberg.de/
DRMLDA A computational model using stacked autoencoders and SVM in integrated miRNAs and disease similarities NA
MLMDA A framework that incorporates multi-source similarity information with stacked autoencoder and RF NA
DFELMDA A method based on autoencoder and RF for predicting MDAs https://github.com/Zj-Teng/DFELMDA
MDA-CF A model based on autoencoder and CR by fusing multi-source information https://github.com/a1622108/MDA-CF
PMDFI A framework with stacked autoencoders, RF, and logistic regression for prediction NA
MSCNE A framework that incorporates multi-source biological information with stacked autoencoder and CNN NA
SMALF A method based on autoencoder and XGBoost for predicting MDAs https://github.com/dayunliu/SMALF
MDA-CNN A learning framework in a miRNA-gene-disease using autoencoder and CNN https://github.com/Issingjessica/MDA-CNN
AEMDA A method using representation algorithms and deep autoencoder for inferring MDAs https://github.com/CunmeiJi/AEMDA
iMDA-BN An improved model that utilizes Node2Vec to extract feature and uses stacked autoencoder and RF for discovering MDAs NA
DANE-MDA A deep attributed network embedding method based on deep stacked autoencoder and RF for prediction https://github.com/jiboya123/DANE-MDA
DBNMDA A deep learning-based model that adopts deep-belief network NA
SAEMD An unsupervised computational model using staked autoencoder for identifying MDAs https://github.com/xpnbs/SAEMDA
DBMDA A method based on autoencoder and rotation forest, which improves miRNA sequence similarity NA
VAEMDA An unsupervised deep learning approach using variational autoencoder NA
SVAEMDA A method based on variational autoencoder for identifying MDAs NA
EPMDA A method based on edge perturbation method using MLP to predict MDAs NA
MLRDFM A multi-view Laplacian regularized DeepFM model for discovering MDAs https://github.com/XYDBCS/MLRDFM
CNNDMP A deep learning approach that employs dual convolutional neural network NA
CNNMDA A method performs prediction using matrix factorization and convolutional neural network NA
DNRLCNN A CNN framework utilizing latent feature matrix extraction with positive samples for predicting MDAs NA
HGCNMDA(1) A PPI-based heterogeneous GCN model for MDA prediction NA
Zhu’s method A matrix completion method based on GCN in heterogeneous miRNA-disease network NA
NIMCGCN A computational method for discovering new MDAs based on neural inductive matrix completion with GCN https://github.com/ljatynu/NIMCGCN/
FCGCNMDA A fully connected graph-based GCN method for predicting MDAs NA
MMGCN A computational method that adaptively integrates multi-source similarity information with multi-view multichannel attention GCN https://github.com/Txinru/MMGCN
GSCENet A learning framework in a miRNA-gene-disease network using GCN, CNN, and SENet https://github.com/Appleabc123/GCSENet
MVIFMDA A multi-view information fusion-based method that utilizes GCN and CNN NA
MDA-GCNFTD A method that discovers underlying MDAs based on GCN via graph sampling https://github.com/a96123155/MDA-GCNFTG
MINIMDA A method that fuses mixed neighborhood information in multimodal networks https://github.com/chengxu123/MINIMDA
HGCNMDA(2) A multi-relational GCN-based method that can allocate proper weights to various types of edges https://github.com/weiba/HGCNMDA
MuCoMiD A multitask graph convolutional learning framework for identifying underlying MDAs https://git.l3s.uni-hannover.de/dong/cmtt
SGNNMD A signed GNN method for exploring deregulation types of MDAs https://github.com/bubblecode/SGNNMD
HGATMDA A novel method that uses weighted DeepWalk to learn the dense embeddings and utilizes GAT to further obtain node representations NA
GRPAMDA A new computational model for MDA prediction utilizing graph random propagation network and attention network https://github.com/ZTangBo/GRPAMDA
HGANMDA A hierarchical graph attention network-based method for discovering novel MDAs https://github.com/ZTangBo/HGANMDA
MDPBMP A graph attention network based on meta-path for discovering potential MDAs https://github.com/LiangYu-Xidian/MDPBMP
GCAEMDA A computational model using GCAE in miRNA-based and disease-based sub-networks NA
NIMGSA A neural inductive matrix completion-based method with GCAE and self-attention mechanism https://github.com/zhanglabNKU/NIMGSA
GAEMDA A designed GAE for identifying novel MDAs https://github.com/chimianbuhetang/GAEMDA
AGAEMD A MDA prediction model that employs node-level attention GAE and inner product decoder https://github.com/Zhhuizhe/AGAEMD
VGAE-MDA A variational graph auto-encoder-based method for MDA prediction NA
VGAMF A new method for revealing MDAs with variational graph auto-encoder and non-negative matrix factorization https://github.com/XYDBCS/VGAMF
CEMDA A framework uses meta-path features, which extracted by GRU https://github.com/liubailong/CEMDA
GMDA A model based on GAN that integrates pairwise neighbor topologies, miRNA family, and cluster attributes NA

NA denotes a lack of a code.

Cite

Sheng N, Xie X, Wang Y, et al. A Survey of Deep Learning for Detecting miRNA-Disease Associations: Databases, Computational Methods, Challenges, and Future Directions. IEEE/ACM Transactions on Computational Biology and Bioinformatics, doi: 10.1109/TCBB.2024.3351752, 2024.

Welcome to contribute

If you would like to help contribute this list, please feel free to contact me by email:

About

No description or website provided.

Topics

deep-learning computational-methods mirna-disease-association

Resources

Readme
Activity

Stars

14 stars

Watchers

1 watching

Forks

4 forks
Report repository

Releases

No releases published

Packages