methCancer-gen: a DNA methylome dataset generator for user-specified cancer type based on conditional variational autoencoder

Choi, Joungmin; Chae, Han‐Jung

doi:10.1186/s12859-020-3516-8

Cited by 11 publications

(17 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…erefore, the cost function of SDAE needs to be determined. At present, cost functions used in deep learning models are mainly cross entropy cost functions, as shown in formula (17) [20]. In addition, the mean square cost function is shown in formula (18) [21].…”

Section: Cost Function Selectionmentioning

confidence: 99%

Research on Bridge Structural Damage Identification

Sun

Sheng

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

The traditional identification methods have limited ability to identify damage location of bridge structures. Therefore, a bridge structural damage location identification method based on deep learning is proposed. In addition, the sigmoid function is the activation function, and the cross entropy is the cost function. Meanwhile, take the Gaussian noise as the addition method and take the softmax as the classifier. So the constructed SDAE deep learning model can realize damage location identification of the simply supported the continuous beam bridges. Compared with the traditional identification methods of bridge structures, namely BP network and SVM, the proposed method shows higher identification accuracy and antinoise performance. Here, the average identification accuracy of the method for continuous beam bridge is 99.8%. As can be seen that the proposed method is more suitable for practical bridge structure damage location identification.

show abstract

Section: Cost Function Selectionmentioning

confidence: 99%

Research on Bridge Structural Damage Identification

Sun

Sheng

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…There are many FS techniques; they can be divided into three categories such as filter, wrapper, and embedded; are different in the way each technique copes with a higher dimension to form a subset of features. Most of the DNA methylation-based cancer studies used variance-based filtering FS techniques to select the most variable CpG sites across several samples before performing VAE and classification algorithms [26]- [31]. The advantages of filter techniques are simple and fewer computations compared to the other two categories.…”

Section: A Feature Selectionmentioning

confidence: 99%

“…However, public cancer data is rapidly increasing, there is also a lack of samples for specific cancer types in research. To alleviate this issue, methCancergen [31] was presented to generate a user-specified cancer type dataset by employing conditional VAE and a neural network-based generative model. It estimates the conditional probability distribution with latent variables and data and produces samples for specific cancer types.…”

Section: B Cancer Classificationmentioning

confidence: 99%

“…By using these pre-trained generative models, researchers attempt to develop similar frameworks for feature extraction. That can be applied to downstream prediction tasks and identify biologically meaningful relationships revealed by VAE latent representation [26]- [31]. Although applications of DL networks to DNA methylation data have become ubiquitous, there still are challenging issues and a lack of practical methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Class-Incremental Learning With Deep Generative Feature Replay for DNA Methylation-Based Cancer Classification

Batbaatar¹,

Park²,

Amarbayasgalan³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Developing lifelong learning algorithms are mandatory for computational systems biology. Recently, many studies have shown how to extract biologically relevant information from high-dimensional data to understand the complexity of cancer by taking the benefit of deep learning (DL). Unfortunately, new cancer growing up into the hundred types that make systems difficult to classify them efficiently. In contrast, the current state-of-the-art continual learning (CL) methods are not designed for the dynamic characteristics of high-dimensional data. And data security and privacy are some of the main issues in the biomedical field. This paper addresses three practical challenges for class-incremental learning (Class-IL) such as data privacy, high-dimensionality, and incremental learning problems. To solve this, we propose a novel continual learning approach, called Deep Generative Feature Replay (DGFR), for cancer classification tasks. DGFR consists of an incremental feature selection (IFS) and a scholar network (SN). IFS is used for selecting the most significant CpG sites from high-dimensional data. We investigate different dimensions to find an optimal number of selected CpG sites. SN employs a deep generative model for generating pseudo data without accessing past samples and a neural network classifier for predicting cancer types. We use a variational autoencoder (VAE), which has been successfully applied to this research field in previous works. All networks are sequentially trained on multiple tasks in the Class-IL setting. We evaluated the proposed method on the publicly available DNA methylation data. The experimental results show that the proposed DGFR achieves a significantly superior quality of cancer classification tasks with various state-of-the-art methods in terms of accuracy.

show abstract

“…Our framework for making VAEs interpretable is generalizable to other VAE-based frameworks. Given that VAEs have been applied to a wide range of genomics data modalities (epigenomics [16][17][18] and miRNA 19 ) and analysis (visualization 20,21 , trajectory inference 22 , data imputation 23 , and perturbation response prediction [24][25][26] ), our work can therefore enable interpretability in a wide range of downstream applications of VAEs.…”

Section: Introductionmentioning

confidence: 99%

Interpretable deep generative models for genomics

Choi¹,

Quon²

2021

Preprint

View full text Add to dashboard Cite

Deep neural networks implementing generative models for dimensionality reduction have been extensively used for the visualization and analysis of genomic data. One of their key limitations is lack of interpretability: it is challenging to quantitatively identify which input features are used to construct the embedding dimensions, thus preventing insight into why cells are organized in a particular data visualization, for example. Here we present a scalable, interpretable variational autoencoder (siVAE) that is interpretable by design: it learns feature embeddings that guide the interpretation of the cell embeddings in a manner analogous to factor loadings of factor analysis. siVAE is as powerful and nearly as fast to train as the standard VAE but achieves full interpretability of the embedding dimensions. We exploit a number of connections between dimensionality reduction and gene network inference to identify gene neighborhoods and gene hubs, without the explicit need for gene network inference. Finally, we observe a systematic difference in the gene neighborhoods identified by dimensionality reduction methods and gene network inference algorithms in general, suggesting they provide complementary information about the underlying structure of the gene co-expression network.

show abstract

methCancer-gen: a DNA methylome dataset generator for user-specified cancer type based on conditional variational autoencoder

Cited by 11 publications

References 27 publications

Research on Bridge Structural Damage Identification

Research on Bridge Structural Damage Identification

Class-Incremental Learning With Deep Generative Feature Replay for DNA Methylation-Based Cancer Classification

Interpretable deep generative models for genomics

Contact Info

Product

Resources

About