Enhancing Taxonomic Categorization of DNA Sequences with Deep Learning: A Multi-Label Approach

Hossain, Prommy Sultana; Kim, Kyungsup; Uddin, Jia; Samad, Md Abdus; Choi, Kwonhue

doi:10.3390/bioengineering10111293

Cited by 4 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional autoencoder (CAE) [31][32][33] is a deep learning neural network model commonly used for feature learning and data dimensionality reduction. It combines the concepts of convolutional neural networks (CNNs) and the structure of autoencoders.…”

Section: Convolutional Autoencodermentioning

confidence: 99%

QPWS Feature Selection and CAE Fusion of Visible/Near-Infrared Spectroscopy Data for the Identification of Salix psammophila Origin

Ma,

Li,

Peng

et al. 2023

Forests

View full text Add to dashboard Cite

Salix psammophila, classified under the Salicaceae family, is a deciduous, densely branched, and erect shrub. As a leading pioneer tree species in windbreak and sand stabilization, it has played a crucial role in combating desertification in northwestern China. However, different genetic sources of Salix psammophila exhibit significant variations in their effectiveness for windbreak and sand stabilization. Therefore, it is essential to establish a rapid and reliable method for identifying different Salix psammophila varieties. Visible and near-infrared (Vis-NIR) spectroscopy is currently a reliable non-destructive solution for origin traceability. This study introduced a novel feature selection strategy, called qualitative percentile weighted sampling (QPWS), based on the principle of the long tail effect for Vis-NIR spectroscopy. The core idea of QPWS combines weighted sampling and percentage wavelength selection to identify key wavelengths. By employing a multi-threaded parallel execution of multiple QPWS instances, we aimed to search for the optimal feature bands to address the instability issues that can arise during the feature selection process. To address the problem of reduced prediction performance in one-dimensional convolutional neural network (1D-CNN) models after feature selection, we have introduced convolutional autoencoders (CAEs) to reduce the dimensions of wavelengths that are discarded during feature selection. Subsequently, these reduced dimensions are fused with the selected wavelengths, thereby enhancing the model’s performance. With our completed model, we selected outstanding models for model fusion and established a decision system for Salix psammophila. It is worth noting that all 1D-CNN models in this study were developed using Bayesian optimization methods. In comparison with principal component analysis (PCA) and full spectrum methods, QPWS exhibits superior predictive performance in the field of machine learning. In the realm of deep learning, the fusion of data combining QPWS with CAE demonstrated even greater potential with an improvement of average accuracy of approximately 2.13% when compared to QPWS alone and a 228% increase in operational speed compared to a model with full spectra. These results indicated that the combination of CAE with QPWS can be an effective tool for identifying the origin of Salix psammophila.

show abstract

Section: Convolutional Autoencodermentioning

confidence: 99%

QPWS Feature Selection and CAE Fusion of Visible/Near-Infrared Spectroscopy Data for the Identification of Salix psammophila Origin

Ma,

Li,

Peng

et al. 2023

Forests

View full text Add to dashboard Cite

show abstract

Deep Learning Approach to Taxonomic Classification with CNN-ELM

Abd-Alhalem,

Takieldeen,

Ali

et al. 2024

2024 International Telecommunications Conference (ITC-Egypt)

View full text Add to dashboard Cite

Using Artificial Intelligence to Optimize Genetic Research

Liadskyi

2024

Anim. Breed. and Genet.

View full text Add to dashboard Cite

The purpose of the article is to analyse the main achievements and prospects for the introduction of artificial intelligence in genetics, to improve the efficiency of research and the reliability of the results obtained. The article analyses publications that reveal the areas of integration of neural networks into DNA fingerprinting, in particular PCR-PCR analysis, sequencing, FISH diagnostics, etc., increasing the sensitivity of these technologies and reducing the cost of research. The author also discusses technologies for processing huge data sets of Big Data and their effectiveness on the example of international projects in theoretical and applied genetics. Attention is paid to artificial intelligence in genomics, proteomics and genetic engineering, in particular, optimisation of GED (genome editing) methods based on CRISPR (short palindromic repeats regularly interspaced in groups) to achieve better accuracy of genome editing. Neural networks are important in creating guide RNAs (gRNAs) for CRISPR-Cas systems, which determine the direction of endonuclease function. In addition to specialised applications and resources, artificial intelligence generally improves research work by optimising many processes that used to take a lot of time and effort. Examples of neural network-based applications that are widely used by the scientific community are presented.

show abstract

Enhancing Taxonomic Categorization of DNA Sequences with Deep Learning: A Multi-Label Approach

Cited by 4 publications

References 36 publications

QPWS Feature Selection and CAE Fusion of Visible/Near-Infrared Spectroscopy Data for the Identification of Salix psammophila Origin

QPWS Feature Selection and CAE Fusion of Visible/Near-Infrared Spectroscopy Data for the Identification of Salix psammophila Origin

Deep Learning Approach to Taxonomic Classification with CNN-ELM

Using Artificial Intelligence to Optimize Genetic Research

Contact Info

Product

Resources

About