A5060381913- Neural Networks and Applications
- Machine Learning in Bioinformatics
- Bioinformatics and Genomic Networks
- Face and Expression Recognition
- Advanced Computational Techniques and Applications
- Cognitive Computing and Networks
- RNA and protein synthesis mechanisms
- Gene expression and cancer classification
- Blind Source Separation Techniques
- Protein Structure and Dynamics
- Genomics and Phylogenetic Studies
- Cancer-related molecular mechanisms research
- Image Retrieval and Classification Techniques
- Advanced Algorithms and Applications
- Genomics and Chromatin Dynamics
- Computational Drug Discovery Methods
- Video Surveillance and Tracking Methods
- Spectroscopy and Chemometric Analyses
- Remote-Sensing Image Classification
- Machine Learning and ELM
- MicroRNA in disease regulation
- Image and Signal Denoising Methods
- Circular RNAs in diseases
- Face recognition and analysis
- Genetics, Bioinformatics, and Biomedical Research
Tongji University
2015-2025
Guangxi Academy of Sciences
2021-2025
Shanghai East Hospital
2024
Eastern Institute of Technology
2024
Eastern Institute of Technology, Ningbo
2023-2024
Guiyang Medical University
2024
Zhejiang Institute of Science and Technology Information
2023
Sir Run Run Shaw Hospital
2020
Zhejiang University
2020
Genomics (United Kingdom)
2020
This paper investigates the capabilities of radial basis function networks (RBFN) and kernel neural (KNN), i.e. a specific probabilistic (PNN), studies their similarities differences. In order to avoid huge amount hidden units KNNs (or PNNs) reduce training time for RBFNs, this proposes new feedforward network model referred as (RBPNN). inherits merits two old odels great extent, avoids defects in some ways. Finally, we apply RBPNN recognition one-dimensional cross-images radar targets (five...
A major challenge for effective application of CRISPR systems is to accurately predict the single guide RNA (sgRNA) on-target knockout efficacy and off-target profile, which would facilitate optimized design sgRNAs with high sensitivity specificity. Here we present DeepCRISPR, a comprehensive computational platform unify sgRNA site prediction into one framework deep learning, surpassing available state-of-the-art in silico tools. In addition, DeepCRISPR fully automates identification...
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> In this paper, a novel heuristic structure optimization methodology for radial basis probabilistic neural networks (RBPNNs) is proposed. First, minimum volume covering hyperspheres (MVCH) algorithm proposed to select the initial hidden-layer centers of RBPNN, and then recursive orthogonal least square (ROLSA) combined with particle swarm (PSO) adopted further optimize RBPNN. The algorithms are...
It is well known that DNA sequence contains a certain amount of transcription factors (TF) binding sites, and only part them are identified through biological experiments. However, these experiments expensive time-consuming. To overcome problems, some computational methods, based on k-mer features or convolutional neural networks, have been proposed to identify TF sites from sequences. Although methods good performance, the context information relates still lacking. Research indicates...
Identification of enhancers and their strength is important because they play a critical role in controlling gene expression. Although some bioinformatics tools were developed, are limited discriminating from non-enhancers only. Recently, two-layer predictor called 'iEnhancer-2L' was developed that can be used to predict the enhancer's as well. However, its prediction quality needs further improvement enhance practical application value.A new 'iEnhancer-EL' proposed contains two layer...
Abstract Graph is a natural data structure for describing complex systems, which contains set of objects and relationships. Ubiquitous real-life biomedical problems can be modeled as graph analytics tasks. Machine learning, especially deep succeeds in vast bioinformatics scenarios with represented Euclidean domain. However, rich relational information between biological elements retained the non-Euclidean graphs, not learning friendly to classic machine methods. representation aims embed...
Abstract Motivation: Microarrays are capable of determining the expression levels thousands genes simultaneously. One important application gene data is classification samples into categories. In combination with methods, this technology can be useful to support clinical management decisions for individual patients, e.g. in oncology. Standard statistic methodologies or prediction do not work well when number variables p (genes) far too exceeds n. So, modification existing statistical...
Abstract Motivation: High-throughput protein interaction data, with ever-increasing volume, are becoming the foundation of many biological discoveries, and thus high-quality protein–protein (PPI) maps critical for a deeper understanding cellular processes. However, unreliability paucity current available PPI data key obstacles to subsequent quantitative studies. It is therefore highly desirable develop an approach deal these issues from computational perspective. Most previous works...
Tumor clustering is becoming a powerful method in cancer class discovery. Nonnegative matrix factorization (NMF) has shown advantages over other conventional techniques. Nonetheless, there still considerable room for improving the performance of NMF. To this end, paper, gene selection and explicitly enforcing sparseness are introduced into process. Particularly, independent component analysis employed to select subset genes so that effect irrelevant or noisy can be reduced. The NMF its...
In this paper, a new density-based clustering framework is proposed by adopting the assumption that cluster centers in data space can be regarded as target objects image space. First, level set evolution adopted to find an approximation of using initial boundary formation scheme. Accordingly, three types boundaries are defined so each them evolve approach different ways. To avoid long iteration time space, efficient termination criterion presented stop process circumstance no more found....
We propose a sequence-based multiple classifier system, i.e., rotation forest, to infer protein-protein interactions (PPIs). Moreover, Moran autocorrelation descriptor is used code an interaction protein pair. Experimental results on Saccharomyces cerevisiae and Helicobacter pylori datasets show that our approach outperforms those previously published in literature, which demonstrates the effectiveness of proposed method. Keywords: Protein-protein interactions, descriptor, sequence, system
Cervical cancer is the third most common malignancy in women worldwide. It remains a leading cause of cancer-related death for developing countries. In order to contribute treatment cervical cancer, our work, we try find few key genes resulting cancer. Employing functions several bioinformatics tools, selected 143 differentially expressed (DEGs) associated with The results analysis show that these DEGs play important roles development Through comparing two differential co-expression networks...