Minimum Free Energy Coding for DNA Storage

Cao, Ben; Zhang, Xiaokang; Wu, Jieqiong; Wang, Bin; Zhang, Qiang; Wei, Xiaopeng

doi:10.1109/tnb.2021.3056351

Cited by 36 publications

(19 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also a significant research problem to effectively apply related techniques in the fields of medicine and healthcare. Cao et al combined Brownian multi-verse optimizer (BMVO) algorithm [ 7 ] and a Damping Multi-Verse Optimizer (DMVO) algorithm [ 8 ] with DNA storage to show us how closely future disease prediction is linked to DNA storage. Recently, deep-learning methods have been applied for ECG signal processing and heart disease diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Constrained transformer network for ECG signal processing and arrhythmia classification

Che

Zhang

Zhu

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Heart disease diagnosis is a challenging task and it is important to explore useful information from the massive amount of electrocardiogram (ECG) records of patients. The high-precision diagnostic identification of ECG can save clinicians and cardiologists considerable time while helping reduce the possibility of misdiagnosis at the same time.Currently, some deep learning-based methods can effectively perform feature selection and classification prediction, reducing the consumption of manpower. Methods In this work, an end-to-end deep learning framework based on convolutional neural network (CNN) is proposed for ECG signal processing and arrhythmia classification. In the framework, a transformer network is embedded in CNN to capture the temporal information of ECG signals and a new link constraint is introduced to the loss function to enhance the classification ability of the embedding vector. Results To evaluate the proposed method, extensive experiments based on real-world data were conducted. Experimental results show that the proposed model achieve better performance than most baselines. The experiment results also proved that the transformer network pays more attention to the temporal continuity of the data and captures the hidden deep features of the data well. The link constraint strengthens the constraint on the embedded features and effectively suppresses the effect of data imbalance on the results. Conclusions In this paper, an end-to-end model is used to process ECG signal and classify arrhythmia. The model combine CNN and Transformer network to extract temporal information in ECG signal and is capable of performing arrhythmia classification with acceptable accuracy. The model can help cardiologists perform assisted diagnosis of heart disease and improve the efficiency of healthcare delivery.

show abstract

Section: Introductionmentioning

confidence: 99%

Constrained transformer network for ECG signal processing and arrhythmia classification

Che

Zhang

Zhu

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Data could only be read after the correct key was provided, which ensured the security of the data storage. In 2021, Cao et al (2021) proposed a thermodynamic minimum free energy constraint and applied to the construction of DNA storage coding sets. The introduction of this constraint improves the quality of DNA coding and reduces the error rate in the storage process.…”

Section: Introductionmentioning

confidence: 99%

CLGBO: An Algorithm for Constructing Highly Robust Coding Sets for DNA Storage

Zheng

Wang

2021

Front. Genet.

Self Cite

View full text Add to dashboard Cite

In the era of big data, new storage media are urgently needed because the storage capacity for global data cannot meet the exponential growth of information. Deoxyribonucleic acid (DNA) storage, where primer and address sequences play a crucial role, is one of the most promising storage media because of its high density, large capacity and durability. In this study, we describe an enhanced gradient-based optimizer that includes the Cauchy and Levy mutation strategy (CLGBO) to construct DNA coding sets, which are used as primer and address libraries. Our experimental results show that the lower bounds of DNA storage coding sets obtained using the CLGBO algorithm are increased by 4.3–13.5% compared with previous work. The non-adjacent subsequence constraint was introduced to reduce the error rate in the storage process. This helps to resolve the problem that arises when consecutive repetitive subsequences in the sequence cause errors in DNA storage. We made use of the CLGBO algorithm and the non-adjacent subsequence constraint to construct larger and more highly robust coding sets.

show abstract

“…The successful solution of this problem led DNA computing to become a field of great development. It has since been widely used to solve problems in many domains, including PCR amplification (Sze and Schloss, 2019), DNA sequencing (Shendure et al, 2017), bioinformatics (Zou and Liu, 2019), prediction of disease genes (Zeng et al, 2020a,b), image encryption (Zhou et al, 2020), and DNA data storage (Zhang et al, 2019;Cao et al, 2021), among others. Benenson et al (2004) made decisions through simple Boolean logic and successfully used RNA interference to construct molecular computing cores in human kidney cells.…”

Section: Introductionmentioning

confidence: 99%

Stable DNA Sequence Over Close-Ending and Pairing Sequences Constraint

Wei

Wang

et al. 2021

Front. Genet.

Self Cite

View full text Add to dashboard Cite

DNA computing is a new method based on molecular biotechnology to solve complex problems. The design of DNA sequences is a multi-objective optimization problem in DNA computing, whose objective is to obtain optimized sequences that satisfy multiple constraints to improve the quality of the sequences. However, the previous optimized DNA sequences reacted with each other, which reduced the number of DNA sequences that could be used for molecular hybridization in the solution and thus reduced the accuracy of DNA computing. In addition, a DNA sequence and its complement follow the principle of complementary pairing, and the sequence of base GC at both ends is more stable. To optimize the above problems, the constraints of Pairing Sequences Constraint (PSC) and Close-ending along with the Improved Chaos Whale (ICW) optimization algorithm were proposed to construct a DNA sequence set that satisfies the combination of constraints. The ICW optimization algorithm is added to a new predator–prey strategy and sine and cosine functions under the action of chaos. Compared with other algorithms, among the 23 benchmark functions, the new algorithm obtained the minimum value for one-third of the functions and two-thirds of the current minimum value. The DNA sequences satisfying the constraint combination obtained the minimum of fitness values and had stable and usable structures.

show abstract

Minimum Free Energy Coding for DNA Storage

Cited by 36 publications

References 48 publications

Constrained transformer network for ECG signal processing and arrhythmia classification

Constrained transformer network for ECG signal processing and arrhythmia classification

CLGBO: An Algorithm for Constructing Highly Robust Coding Sets for DNA Storage

Stable DNA Sequence Over Close-Ending and Pairing Sequences Constraint

Contact Info

Product

Resources

About