A5068439289- Machine Learning in Bioinformatics
- Microwave Dielectric Ceramics Synthesis
- Ferroelectric and Piezoelectric Materials
- RNA and protein synthesis mechanisms
- Computational Drug Discovery Methods
- Bioinformatics and Genomic Networks
- Genomics and Phylogenetic Studies
- Advanced ceramic materials synthesis
- Cancer-related molecular mechanisms research
- RNA modifications and cancer
- Fractal and DNA sequence analysis
- Gene expression and cancer classification
- Protein Structure and Dynamics
- Lepidoptera: Biology and Taxonomy
- MicroRNA in disease regulation
- Epigenetics and DNA Methylation
- vaccines and immunoinformatics approaches
- Genomics and Chromatin Dynamics
- Intermetallics and Advanced Alloy Properties
- Boron and Carbon Nanomaterials Research
- Plant and animal studies
- RNA Research and Splicing
- MXene and MAX Phase Materials
- Antimicrobial Peptides and Activities
- Genetics, Bioinformatics, and Biomedical Research
Hunan University of Finance and Economics
2023-2025
Shaoyang University
2016-2025
Hunan Agricultural University
2022-2024
Suizhou Central Hospital
2022-2023
Nanning Normal University
2004-2022
Hainan Normal University
2022
Shanghai University
2013-2021
Hunan University
2008-2018
Guangxi University
2004-2016
Shanghai Institutes for Biological Sciences
2013
Background: Bioinformatics research comes into an era of big data. Mining potential value in biological data for scientific and health care field has the vital significance. Deep learning as new machine algorithms, on basis high performance distributed parallel computing, show excellent processing. Objective: Provides a valuable reference researchers to use deep their studies processing large Methods: This paper introduces model storage computational facilities analyzing. Then, application...
Bioactive peptides are typically small functional with 2-20 amino acid residues and play versatile roles in metabolic biological processes. multi-functional, so it is vastly challenging to accurately detect all their functions simultaneously. We proposed a convolution neural network (CNN) bi-directional long short-term memory (Bi-LSTM)-based deep learning method (called MPMABP) for recognizing multi-activities of bioactive peptides. The MPMABP stacked five CNNs at different scales, used the...
Long non-coding RNAs (lncRNA) are a class of RNA transcripts with more than 200 nucleotide residues. LncRNAs play versatile roles in cellular processes and thus becoming hot topic the field biomedicine. The function lncRNAs was discovered to be closely associated subcellular localization. Although many methods have been developed identify localization lncRNAs, there still is much room for improvement. Herein, we present lightGBM-based computational predictor recognizing lncRNA localization,...
Identification of potential drug-target interactions (DTIs) is a crucial step in drug discovery and repurposing. Although deep learning effectively deciphers DTIs, most learning-based methods represent features from only single perspective. Moreover, the fusion method protein needs further refinement. To address above two problems, this study, we develop novel end-to-end framework named DO-GMA for DTI identification by incorporating Depthwise Overparameterized convolutional neural network...
ABSTRACT Cancer is a serious and complex disease caused by uncontrolled cell growth becoming one of the leading causes death worldwide. Anticancer peptides (ACPs), as bioactive peptide with lower toxicity, emerge promising means effectively treating cancer. Identifying ACPs challenging due to limitation experimental conditions. To address this, we proposed dual‐channel‐based deep learning method, termed ACP‐DPE, for ACP prediction. The ACP‐DPE consisted two parallel channels: was an...
Aptamers are oligonucleic acid or peptide molecules that bind to specific target molecules. As a novel and powerful class of ligands, aptamers thought have excellent potential for applications in the fields biosensing, diagnostics therapeutics. In this study, new method predicting aptamer-target interacting pairs was proposed by integrating features derived from both their targets. Features nucleotide composition traditional amino as well pseudo were utilized represent targets, respectively....
Lysine succinylation is a typical protein post-translational modification and plays crucial role of regulation in the cellular process. Identifying sites fundamental to explore its functions. Although many computational methods were developed deal with this challenge, few considered semantic relationship between residues. We combined long short-term memory (LSTM) convolutional neural network (CNN) into deep learning method for predicting site. The proposed obtained Matthews correlation...
Background: Post-translational modifications (PTMs) are a key regulating mechanism in the cellular process. It is of importance to quickly and accurately identify PTMs. Both next generation sequencing as well bioinformatics techniques greatly facilitated discovery Most followed machine learning framework where feature extraction occupies position. Conclusion: The article focuses mainly on reviewing various extractions from protein sequence, structure, function, physicochemical biochemical...
N4-methylcytosine (4mC) is an important epigenetic mechanism, which regulates many cellular processes such as cell differentiation and gene expression. The knowledge about the 4mC sites a key foundation to exploring its roles. Due limitation of techniques, precise detection still challenging task. In this paper, we presented multi-scale convolution neural network (CNN) adaptive embedding-based computational method for predicting in mouse genome, was referred MultiScale-CNN-4mCPred....
Enhancers are short DNA segments that play a key role in biological processes, such as accelerating transcription of target genes. Since the enhancer resides anywhere genome sequence, it is difficult to precisely identify enhancers. We presented bi-directional long-short term memory (Bi-LSTM) and attention-based deep learning method (Enhancer-LSTMAtt) for recognition. Enhancer-LSTMAtt an end-to-end model consists mainly residual neural network, Bi-LSTM, feed-forward attention. extensively...
Abstract From the perspective of neighboring dual nucleotides, we introduce a novel 2D graphical representation DNA sequences based on magic circle, which correspond to 16 nucleotides. So, can reduce sequence into plot set in two‐dimensional space and get two‐component vector relatively introduced covariance matrix. The utility our approach be illustrated by examination similarities/dissimilarities among complete coding β‐ globin gene belonging 11 species. © 2008 Wiley Periodicals, Inc. Int...
MicroRNAs (miRNAs) performs crucial roles in various human diseases, but miRNA-related pathogenic mechanisms remain incompletely understood. Revealing the potential relationship between miRNAs and diseases is a critical problem biomedical research. Considering limitation of existing computational approaches, we develop improved low-rank matrix recovery (ILRMR) for miRNA-disease association prediction. ILRMR global method that can simultaneously prioritize all does not require negative...
Colorectal cancer can be grouped into Dukes A, B, C, and D stages based on its developments. Generally speaking, more advanced patients have poorer prognosis. To integrate progression stage prediction systems with recurrence systems, we proposed an ensemble prognostic model for colorectal cancer. In this model, each patient was assigned a most possible status. If predicted to in stage, he would classified high risk group. The considered both High low by the had significant different disease...