Filters








194 Hits in 7.2 sec

A deep adversarial variational autoencoder model for dimensionality reduction in single-cell RNA sequencing analysis

Eugene Lin, Sudipto Mukherjee, Sreeram Kannan
2020 BMC Bioinformatics  
Single-cell RNA sequencing (scRNA-seq) is an emerging technology that can assess the function of an individual cell and cell-to-cell variability at the single cell level in an unbiased manner.  ...  To overcome these difficulties, we propose DR-A (Dimensionality Reduction with Adversarial variational autoencoder), a data-driven approach to fulfill the task of dimensionality reduction.  ...  Consent for publication Not applicable. Competing interests The authors declare that they have no competing interests.  ... 
doi:10.1186/s12859-020-3401-5 pmid:32085701 fatcat:v3qyw26nzna7ljem4pdvfqzzoq

Emerging deep learning methods for single-cell RNA-seq data analysis

Jie Zheng, Ke Wang
2019 Quantitative Biology  
Anticipating that this will occur soon for the single-cell RNA-seq data analysis, we review newly published deep learning methods that help tackle computational challenges.  ...  Author summary: Single-cell RNA sequencing (scRNA-seq) and deep learning are revolutionizing the fields of biomedicine and artificial intelligence respectively.  ...  Wang and Gu proposed a method called "VASC", which uses the deep variational autoencoder for dimensionality reduction and visualization of scRNA-seq data [50] .  ... 
doi:10.1007/s40484-019-0189-2 fatcat:36nk2crr6rcmtocexv3rjhddhi

Relevant Applications of Generative Adversarial Networks in Drug Design and Discovery: Molecular De Novo Design, Dimensionality Reduction, and De Novo Peptide and Protein Design

Eugene Lin, Chieh-Hsin Lin, Hsien-Yuan Lane
2020 Molecules  
In addition, we describe various GAN models to fulfill the dimension reduction task of single-cell data in the preclinical stage of the drug development pipeline.  ...  In this review, we focus on the latest developments for three particular arenas in drug design and discovery research using deep learning approaches, such as generative adversarial network (GAN) frameworks  ...  In addition, another remarkably intriguing example is that the deep adversarial variational autoencoder structure has shown to fulfill the task of dimensionality reduction for single-cell RNA sequencing  ... 
doi:10.3390/molecules25143250 pmid:32708785 fatcat:rrik322g6vbetaubwjb3rtvajm

Computational strategies for single-cell multi-omics integration

Nigatu Adossa, Sofia Khan, Kalle T Rytkönen, Laura L Elo
2021 Computational and Structural Biotechnology Journal  
Current advances especially in single-cell multi-omics hold high potential for breakthroughs by integration of multiple different omics layers.  ...  Finally, we explore the challenges and prospective future directions of single-cell multi-omics data integration, including examples of adopting multi-view analysis approaches used in other disciplines  ...  Two variations of autoencoders have been recently applied in single-cell multi-omics, variational autoencoders (VAE) [86, 88] , and adversarial autoencoders (AAE) [110] .  ... 
doi:10.1016/j.csbj.2021.04.060 pmid:34025945 pmcid:PMC8114078 fatcat:qap257yttzdetjrqs4aijcwaq4

Computational Methods for Single-Cell Multi-Omics Integration and Alignment [article]

Stefan Stanojevic, Yijun Li, Lana X. Garmire
2022 arXiv   pre-print
Recently developed technologies to generate single-cell genomic data have made a revolutionary impact in the field of biology.  ...  single cell research field.  ...  Many variations of autoencoder models exist, and among them variational autoencoders have proven useful for analyzing single-cell data.  ... 
arXiv:2201.06725v1 fatcat:jo3pmpe2c5fl5lo4g2okpnkm4i

A Brief Review on Deep Learning Applications in Genomic Studies

Xiaoxi Shen, Chang Jiang, Yalu Wen, Chenxi Li, Qing Lu
2022 Frontiers in Systems Biology  
Deep learning is a powerful tool for capturing complex structures within the data. It holds great promise for genomic research due to its capacity of learning complex features in genomic data.  ...  In this paper, we provide a brief review on deep learning techniques and various applications of deep learning to genomic studies.  ...  A deep variational autoencoder for single-cell RNA sequencing data (VASC) (Wang and Gu, 2018 ) was developed to model the dropout events and to find the nonlinear hierarchical feature representations  ... 
doi:10.3389/fsysb.2022.877717 fatcat:qqrzoqqqmfafxmibvzkc3z33k4

Deep learning tackles single-cell analysis A survey of deep learning for scRNA-seq analysis [article]

Mario Flores, Zhentao Liu, Ting-He Zhang, Md Musaddaqui Hasib, Yu-Chiao Chiu, Zhenqing Ye, Karla Paniagua, Sumin Jo, Jianqiu Zhang, Shou-Jiang Gao, Yu-Fang Jin, Yidong Chen (+1 others)
2021 arXiv   pre-print
in emerging multi-omics and spatial single-cell sequencing.  ...  Specifically, we establish a unified mathematical representation of all variational autoencoder, autoencoder, and generative adversarial network models, compare the training strategies and loss functions  ...  Deep learning approaches are categorized as Deep Neural Network, Generalive Adversarial Network, Variational Autoencoder, and Autoencoder.  ... 
arXiv:2109.12404v1 fatcat:aa5vh34eencjlcemfh7mz7q7py

Style transfer with variational autoencoders is a promising approach to RNA-Seq data harmonization and analysis [article]

Nikolai E. Russkikh, Denis V. Antonets, Dmitry N. Shtokalo, Alexander V. Makarov, Alexey M. Zakharov, Evgeny V. Terentev
2019 bioRxiv   pre-print
The proposed solution is based on Variational Autoencoder artificial neural network. To disentangle the style components, we trained the encoder with discriminator in an adversarial manner.  ...  We demonstrated the applicability of our framework using single cell RNA-Seq data from Mouse Cell Atlas, where we were able to transfer the mammary gland biological state (virgin, pregnancy and involution  ...  Acknowledgements Authors would like to thank the Institute of Computational Technol SB RAS for providing computational resources needed for this pu tion. Conflict of Interest: none declared.  ... 
doi:10.1101/791962 fatcat:pqemdrhapzfo7hxefdchmvbp3m

ScRAE: Deterministic Regularized Autoencoders with Flexible Priors for Clustering Single-cell Gene Expression Data [article]

Arnab Kumar Mondal, Himanshu Asnani, Parag Singla, Prathosh AP
2021 arXiv   pre-print
To address the above issues, we propose a modified RAE framework (called the scRAE) for effective clustering of the single-cell RNA sequencing data. scRAE consists of deterministic AE with a flexibly learnable  ...  Clustering single-cell RNA sequence (scRNA-seq) data poses statistical and computational challenges due to their high-dimensionality and data-sparsity, also known as 'dropout' events.  ...  ACKNOWLEDGMENT The authors would like to thank Ajay Sailopal, IIT Delhi, for his help in running some of the baseline methods.  ... 
arXiv:2107.07709v1 fatcat:6v4wr3irenbb3cktersgyutzji

Deep learning applications in single-cell omics data analysis [article]

Nafiseh Erfanian, A. Ali Heydari, Pablo Ianez, Afshin Derakhshani, Mohammad Ghasemigol, Mohsen Farahpour, Saeed Nasseri, Hossein Safarpour, Amirhossein Sahebkar
2021 bioRxiv   pre-print
However, using DL models for single-cell omics has shown promising results (in many cases outperforming the previous state-of-the-art models) but lacking the needed biological interpretability in many  ...  Single-cell (SC) omics are often high-dimensional, sparse, and complex, making DL techniques ideal for analyzing and processing such data.  ...  Deep Learning in the Integration of Single-Cell Multimodal Omics Data Single-cell sequencing (scSeq) was chosen as Method of the Year in 2013 due to its ability to sequence DNA and RNA in individual cells  ... 
doi:10.1101/2021.11.26.470166 fatcat:3bmpecoza5dedbmwm62jwhfm4e

The performance of deep generative models for learning joint embeddings of single-cell multi-omics data [article]

Eva Brombacher, Maren Hackenberg, Clemens Kreutz, Harald Binder, Martin Treppner
2022 bioRxiv   pre-print
In particular, deep learning approaches, such as deep generative models (DGMs), can potentially uncover complex patterns via a joint embedding.  ...  and RNA expression are measured in thousands of cells (10x Multiome).  ...  In single-cell applications, the most frequently used DGMs to date are Variational autoencoders (VAEs) [26] and generative adversarial networks (GANs) [20] , which we present in more detail below.  ... 
doi:10.1101/2022.06.06.494951 fatcat:nwbitt4a2zg4fiymreckvazfly

Latent representation learning in biology and translational medicine

Andreas Kopf, Manfred Claassen
2021 Patterns  
We anticipate that a wider dissemination of latent variable modeling in the life sciences will enable a more effective and productive interpretation of studies based on heterogeneous and high-dimensional  ...  Latent variable modeling allows for such interpretation by learning non-measurable hidden variables from observations.  ...  ACKNOWLEDGMENTS We thank the anonymous reviewers for their feedback and insightful suggestions to improve this review. A.K. was supported by the grants SystemsX.ch HDL-X and PHRT 2017-103.  ... 
doi:10.1016/j.patter.2021.100198 pmid:33748792 pmcid:PMC7961186 fatcat:d6ttueb5rbhotbsztha3wyvjt4

Deep Denerative Models for Drug Design and Response [article]

Karina Zadorozhny, Lada Nuzhna
2021 arXiv   pre-print
Recent success of deep generative modeling holds promises of generation and optimization of new molecules.  ...  We present commonly used chemical and biological databases, and tools for generative modeling.  ...  For example, a classifier can be fitted on top of a learned latent space. Compared to Principal Component Analysis (PCA), autoencoders can perform nonlinear dimensionality reduction.  ... 
arXiv:2109.06469v1 fatcat:vea47ew6gvdadftz5sgqdhikgy

Cancer classification based on chromatin accessibility profiles with deep adversarial learning model

Hai Yang, Qiang Wei, Dongdong Li, Zhe Wang, Anna R. Panchenko
2020 PLoS Computational Biology  
In this study, based on the deep adversarial learning, we present an end-to-end approach ClusterATAC to leverage high-dimensional features and explore the classification results.  ...  In this solution, more than 70% of the clustering are single-tumor-type-dominant, and the vast majority of the remaining clusters are associated with similar tumor types.  ...  In deep learning, autoencoder is frequently used for nonlinear dimensionality reduction in an unsupervised manner.  ... 
doi:10.1371/journal.pcbi.1008405 pmid:33166290 fatcat:w767ufm33zaefdkwovryciwzvi

Sampling from Disentangled Representations of Single-Cell Data Using Generative Adversarial Networks [article]

Hengshi Yu, Joshua D Welch
2021 bioRxiv   pre-print
Deep generative models, including variational autoencoders (VAEs) and generative adversarial networks (GANs), have achieved remarkable successes in generating and manipulating high-dimensional images.  ...  data in a similar way.  ...  .: Parameter tuning is a key part of dimensionality reduction via deep variational autoencoders for single cell rna transcriptomics. In: PSB. pp. 362-373. World Scientific (2019) 35.  ... 
doi:10.1101/2021.01.15.426872 fatcat:kzyiuxkntbfcvfzfperxwnvkpy
« Previous Showing results 1 — 15 out of 194 results