A5100389458- Machine Learning in Bioinformatics
- Fractal and DNA sequence analysis
- RNA and protein synthesis mechanisms
- Genomics and Phylogenetic Studies
- Cancer-related molecular mechanisms research
- Computational Drug Discovery Methods
- Astrophysics and Cosmic Phenomena
- Influenza Virus Research Studies
- RNA Research and Splicing
- RNA modifications and cancer
- vaccines and immunoinformatics approaches
- Circular RNAs in diseases
- Genomics and Chromatin Dynamics
- Protein Structure and Dynamics
- Dark Matter and Cosmic Phenomena
- MicroRNA in disease regulation
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Molecular Biology Techniques and Applications
- Complex Network Analysis Techniques
- Bioinformatics and Genomic Networks
- Lung Cancer Diagnosis and Treatment
- Gene expression and cancer classification
- Metabolomics and Mass Spectrometry Studies
- Gamma-ray bursts and supernovae
Hainan Normal University
2017-2025
University Health Network
2024
Chongqing University
2023-2024
Purple Mountain Observatory
2023
Hebei Normal University
2023
University of Science and Technology of China
2023
Institute of High Energy Physics
2023
Chinese Academy of Sciences
2023
Hainan University
2020-2023
University of Chinese Academy of Sciences
2023
Abstract Breast cancer patients often have recurrence and metastasis after surgery. Predicting the risk of for a breast patient is essential development precision treatment. In this study, we proposed novel multi-modal deep learning prediction model by integrating hematoxylin & eosin (H&E)-stained histopathological images, clinical information gene expression data. Specifically, segmented tumor regions in H&E into image blocks (256 × 256 pixels) encoded each block 1D feature...
Abstract Timely identification of emerging antigenic variants is critical to influenza vaccine design. The accuracy a sequence-based prediction method relies on the choice amino acids substitution matrices. In this study, we first compared comprehensive 95 matrices reflecting various properties in predicting antigenicity viruses by random forest model. We then proposed novel algorithm called joint regression (JRFR) jointly consider top applied JRFR human H3N2 seasonal data from 1968 2003. A...
Genomic islands (GIs) that are associated with microbial adaptations and carry sequence patterns different from of the host sporadically distributed among closely related species. This bias can dominate signal interest in GI detection. However, variations still exist segments host, although no uniform standard exists regarding best methods discriminating GIs rest genome terms compositional bias. In present work, we proposed a robust software, MTGIpick, which used regions pattern showing...
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...
Abstract On the basis of a selected pair physicochemical properties amino acids, we introduce dynamic 2D graphical representation protein sequences. Then, and compare two numerical characterizations graphs as descriptors to analyze nine ND5 proteins. The approach is simple, convenient, fast. Proteins 2008. © 2008 Wiley‐Liss, Inc.
In recent years, it has been increasingly clear that long noncoding RNAs (lncRNAs) play critical roles in many biological processes associated with human diseases. Inferring potential lncRNA-disease associations is essential to reveal the secrets behind diseases, develop novel drugs, and optimize personalized treatments. However, experiments validate are very time-consuming costly. Thus, effective computational models. this study, we have proposed a method called BPLLDA predict based on...
While the intratumoral microbiota has been discovered to have a close connection with tumor immunity, specific role played by in regulating immune microenvironment (TIME) of lung cancer remains largely unexplored. Here, we comprehensively investigated association between and TIME adenocarcinoma (LUAD) squamous cell carcinoma (LUSC). First, found that host transcriptome profile significantly differed LUAD LUSC. Moreover, there were strong associations abundance microbes expression genes both...
An increasing body of research indicates that the circulating microbiome plays a significant role in cancer initiation and progression treatment response. The genomic characteristics microorganisms may influence tumor immune microenvironment, thereby affecting therapeutic outcomes. However, whether can serve as prognostic biomarker for cervical patients its mechanistic microenvironment still requires further investigation. Univariate, Lasso, multivariate Cox regression analyses were utilized...
Abstract A (two‐dimensional) 2D graphical representation of protein sequences based on six physicochemical properties amino acids is outlined. The numerical characterization graphs given as descriptors sequences. It not only useful for comparative study proteins but also encoding innate information about the structure proteins. coefficient determination proposed a new similarity/dissimilarity measure. Finally, simple example taken to highlight behavior measure from ND6 (NADH dehydrogenase...
Abstract Background Small non-coding RNAs (ncRNAs) are important regulators of gene expression in eukaryotes. Previously, only microRNAs (miRNAs) and piRNAs have been identified the silkworm, Bombyx mori . Furthermore, ncRNAs (50-500nt) intermediate size systematically silkworm. Results Here, we performed a systematic identification analysis small (18-50nt) associated with argonaute2 (BmAgo2) protein. Using RIP-seq, various types BmAGO2. These showed multimodal length distribution, three...
Low-rank matrix completion has been demonstrated to be powerful in predicting antigenic distances among influenza viruses and vaccines from partially revealed hemagglutination inhibition table. Meanwhile, hemagglutinin (HA) protein sequences are also effective inferring distances. Thus, it is natural integrate HA sequence information into low-rank model help infer antigenicity, which critical vaccine development.We have proposed a novel algorithm called biological with side (BMCSI), first...
Residue-residue contact prediction has become an increasingly important tool for modeling the three-dimensional structure of a protein when no homologous is available. Ultradeep residual neural network (ResNet) most popular method making predictions because it captures contextual information between residues. In this paper, we propose novel deep framework which combines ResNet and DenseNet. This uses 1D to process sequential features, besides PSSM, SS3, solvent accessibility, have introduced...
Automatic detection of pulmonary nodules is great significance for early diagnosis and prevention lung cancer. Computed tomography (CT) an effective economical method. In CT images, the size shape are different, some very similar to surrounding tissues. Therefore, automatic localization in images a challenging task. this study, attention embedded three-dimensional convolutional neural network proposed nodule detection. Specifically, 1) channel-spatial guides 3D ResNet down sample input...
Abstract Deep learning technology is changing the landscape of cybersecurity research, especially study large amounts data. With rapid growth in number malware, developing an efficient and reliable method for classifying malware has become one research priorities. In this paper, a new method, BIR-CNN, proposed to classify Android malware. It combines convolution neural network (CNN) with batch normalization inception-residual (BIR) modules by using 347-dim traffic features. CNN layer that...
Based on the chaos game representation, a 2D graphical representation of protein sequences was introduced in which 20 amino acids are rearranged cyclic order according to their physicochemical properties. The Euclidean distances between corresponding from 2-D representations computed find matching (or conserved) fragments two proteins. Again, cumulative distance 2D-graphical is defined compare similarity protein. And, examination among ND5 proteins nine species shows utility our approach.
Although domesticated tomato is cultivated by wild tomato, there are a lot of differences between and such as shape, physiological function life history. Many studies show that has better salt resistance drought resistance. In addition to, tomato's fruit bigger more nutritious than tomato. The different features closely related to differentially expressed genes. We identified 126 up-regulated genes 87 down-regulated in RNA-Seq. These may be associated with resistance, nutrition. also further...
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...
Based on the concepts of cell and system graphical representation, a class 2D representations RNA secondary structures are given in terms classifications bases nucleic acids. The can completely avoid loss information associated with crossing overlapping corresponding curve. As an application, we make quantitative comparisons for set at 3'-terminus different viruses based representations. examination similarities/dissimilarities illustrates utility approach.
Complexes formed by proteins binding to RNAs are essential in biological processes, and can also be useful for identifying causal disease variants, gene expression regulation translation. Protein-RNA interactions identified vivo affected experimental condition, noise, some bias, while vitro experiments yield clearer signals. Therefore, accurately inferring RNA-protein models from data, predict bound unbound RNA transcripts vivo, has become a key challenge. We constructed RDense, novel deep...