Memristive Circuit Implementation of Biological Nonassociative Learning Mechanism and Its Applications

Hong, Qinghui; Yan, Renao; Wang, Chunhua; Sun, Jingru

doi:10.1109/tbcas.2020.3018777

Cited by 77 publications

(28 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method has good robustness and shows good generalization performance on BRCA1 and PTEN gene datasets. For future research directions, computational intelligence such as neural networks (Song et al, 2017(Song et al, , 2020Hong et al, 2020), evolutionary algorithms (Xu et al, 2017), and unsupervised learning (Zou et al, 2018;Zeng et al, 2019a), which have been applied in the prediction of drug targets (Quan et al, 2019;Zeng et al, 2019b;Lin et al, 2020b), disease related miRNAs (Zhang et al, 2017;Zeng et al, 2018), can be employed in this field.…”

Section: Resultsmentioning

confidence: 99%

Predicting the Disease Risk of Protein Mutation Sequences With Pre-training Model

Zhong

Lin

et al. 2020

Front. Genet.

View full text Add to dashboard Cite

Accurately identifying the missense mutations is of great help to alleviate the loss of protein function and structural changes, which might greatly reduce the risk of disease for tumor suppressor genes (e.g., BRCA1 and PTEN). In this paper, we propose a hybrid framework, called BertVS, that predicts the disease risk for the missense mutation of proteins. Our framework is able to learn sequence representations from the protein domain through pre-training BERT models, and also integrates with the hydrophilic properties of amino acids to obtain the sequence representations of biochemical characteristics. The concatenation of two learned representations are then sent to the classifier to predict the missense mutations of protein sequences. Specifically, we use the protein family database (Pfam) as a corpus to train the BERT model to learn the contextual information of protein sequences, and our pre-training BERT model achieves a value of 0.984 on accuracy in the masked language model prediction task. We conduct extensive experiments on BRCA1 and PTEN datasets. With comparison to the baselines, results show that BertVS achieves higher performance of 0.920 on AUROC and 0.915 on AUPR in the functionally critical domain of the BRCA1 gene. Additionally, the extended experiment on the ClinVar dataset can illustrate that gene variants with known clinical significance can also be efficiently classified by our method. Therefore, BertVS can learn the functional information of the protein sequences and effectively predict the disease risk of variants with an uncertain clinical significance.

show abstract

Section: Resultsmentioning

confidence: 99%

Predicting the Disease Risk of Protein Mutation Sequences With Pre-training Model

Zhong

Lin

et al. 2020

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…For example, sparse representation has been applied to the field of pattern recognition and has yielded fruitful results. The low-rank sparse representation model based on sparse representation has also become a research focus in machine vision, machine learning, and image processing, and has been applied successfully in video image processing, target recognition, task learning, bioinformatics ( Ding et al, 2020 ; Hong et al, 2020 ; Hu et al, 2020 ; Lu et al, 2020 ; Hu et al, 2021a ; Hu et al, 2021b ; Wang et al, 2021b ), and recommendation systems ( Wei et al, 2014 ; Wei et al, 2017a ; Wei et al, 2017b ). However, further attention should be paid to low-rank representation learning.…”

Section: Pending Issues and Prospectsmentioning

confidence: 99%

Application of Sparse Representation in Bioinformatics

Han

Wang²,

Guo

et al. 2021

Front. Genet.

View full text Add to dashboard Cite

Inspired by L1-norm minimization methods, such as basis pursuit, compressed sensing, and Lasso feature selection, in recent years, sparse representation shows up as a novel and potent data processing method and displays powerful superiority. Researchers have not only extended the sparse representation of a signal to image presentation, but also applied the sparsity of vectors to that of matrices. Moreover, sparse representation has been applied to pattern recognition with good results. Because of its multiple advantages, such as insensitivity to noise, strong robustness, less sensitivity to selected features, and no “overfitting” phenomenon, the application of sparse representation in bioinformatics should be studied further. This article reviews the development of sparse representation, and explains its applications in bioinformatics, namely the use of low-rank representation matrices to identify and study cancer molecules, low-rank sparse representations to analyze and process gene expression profiles, and an introduction to related cancers and gene expression profile database.

show abstract

“…It confirmed the existence of the fourth basic circuit element, that is memristor. The memristor have attracted the attention of many scholars for their potential applications in cellular neural network [2,3], associative and non-associative learning [4,5], circuit implemented electronic neurons [6], memory circuit [7], nonlinear oscillating circuits and other fields [8][9][10][11]. Because of the unique nonlinear characteristics of memristor, the chaotic circuit based on memristor has more abundant dynamic behaviors.…”

Section: Introductionmentioning

confidence: 99%

Dynamics Analysis of Memristor Chaotic Circuit with Coexisting Hidden Attractors

Guo

Zhao

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, a novel Sr 0.97 Ba 0.03 TiO 3-δ memristor-based fifth-order chaotic circuit was proposed. A new cubic nonlinear magnetic control model was established by analyzing the measured data. The equilibrium points and its stability of the circuit system were analyzed by the Jacobi matrix method, and the effects of the initial states and circuit parameters on the system were discussed though methods of Lyapunov exponents spectra, bifurcation diagrams, phase diagrams, and poincaré maps. The results show that the chaotic circuit can produce complex dynamic phenomena with the variation of initial states and circuit parameters. The dynamic phenomena such as coexisting attractors have been discovered. In particular, coexisting hidden attractors were generated in the chaotic circuit, which was of great significance in engineering applications.

show abstract

Memristive Circuit Implementation of Biological Nonassociative Learning Mechanism and Its Applications

Cited by 77 publications

References 35 publications

Predicting the Disease Risk of Protein Mutation Sequences With Pre-training Model

Predicting the Disease Risk of Protein Mutation Sequences With Pre-training Model

Application of Sparse Representation in Bioinformatics

Dynamics Analysis of Memristor Chaotic Circuit with Coexisting Hidden Attractors

Contact Info

Product

Resources

About