A5066912329- RNA modifications and cancer
- Cancer-related molecular mechanisms research
- RNA and protein synthesis mechanisms
- Genomics and Phylogenetic Studies
- Cancer-related gene regulation
- Genomics and Chromatin Dynamics
- Chromosomal and Genetic Variations
- Genomic variations and chromosomal abnormalities
- Bioinformatics and Genomic Networks
- Image Processing Techniques and Applications
- RNA Research and Splicing
- Advanced Vision and Imaging
- Cell Image Analysis Techniques
- Metabolomics and Mass Spectrometry Studies
- Single-cell and spatial transcriptomics
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Machine Learning in Materials Science
- Gastric Cancer Management and Outcomes
- Computational Drug Discovery Methods
- AI in cancer detection
- Digital Imaging for Blood Diseases
- Advanced Neural Network Applications
- Gene expression and cancer classification
- Machine Learning in Bioinformatics
Xi’an Jiaotong-Liverpool University
2019-2024
Fujian Medical University
2024
Fudan University
2024
University of Liverpool
2021-2023
Abstract Recent studies suggest that epi-transcriptome regulation via post-transcriptional RNA modifications is vital for all types. Precise identification of modification sites essential understanding the functions and regulatory mechanisms RNAs. Here, we present MultiRM, a method integrated prediction interpretation from sequences. Built upon an attention-based multi-label deep learning framework, MultiRM not only simultaneously predicts putative twelve widely occurring transcriptome (m 6...
Abstract 5-Methylcytosine (m5C) is one of the most prevalent covalent modifications on RNA. It known to regulate a broad variety RNA functions, including nuclear export, stability and translation. Here, we present m5C-Atlas, database for comprehensive collection annotation 5-methylcytosine. The contains 166 540 m5C sites in 13 species identified from 5 base-resolution epitranscriptome profiling technologies. Moreover, condition-specific methylation levels are quantified 351 bisulfite...
Recent advances in epitranscriptomics have unveiled functional associations between RNA modifications (RMs) and multiple human diseases, but distinguishing the or disease-related single nucleotide variants (SNVs) from majority of 'silent' remains a major challenge. We previously developed RMDisease database for unveiling association genetic RMs concerning disease pathogenesis. In this work, we present v2.0, an updated with expanded coverage. Using deep learning models 873 819 experimentally...
N 6-Methyladenosine (m6A) is one of the most abundant internal chemical modifications on eukaryote mRNA and involved in numerous essential molecular functions biological processes. To facilitate study this important post-transcriptional modification, we present here m6A-Atlas v2.0, an updated version m6A-Atlas. It was expanded to include a total 797 091 reliable m6A sites from 13 high-resolution technologies two single-cell profiles. Additionally, three methods (exomePeaks2, MACS2 TRESS)...
The National Genomics Data Center (NGDC), which is a part of the China for Bioinformation (CNCB), offers comprehensive suite database resources to support global scientific community. Amidst unprecedented accumulation multi-omics data, CNCB-NGDC committed continually evolving and updating its core through big data archiving, integrative analysis value-added curation. Over past year, has expanded collaborations with international databases established new subcenters focusing on biodiversity,...
As the most pervasive epigenetic marker present on mRNAs and long non-coding RNAs (lncRNAs), N
Abstract As the most pervasive epigenetic mark present on mRNA and lncRNA, N6-methyladenosine (m6A) RNA methylation regulates all stages of life in various biological processes disease mechanisms. Computational methods for deciphering modification have achieved great success recent years; nevertheless, their potential remains underexploited. One reason this is that existing models usually consider only sequence transcripts, ignoring regions (or geography) transcripts such as 3′UTR intron,...
Abstract Motivation Increasing evidence suggests that post-transcriptional ribonucleic acid (RNA) modifications regulate essential biomolecular functions and are related to the pathogenesis of various diseases. Precise identification RNA modification sites is for understanding regulatory mechanisms RNAs. To date, many computational approaches predicting have been developed, most which were based on strong supervision enabled by base-resolution epitranscriptome data. However, high-resolution...
Abstract Post- and co-transcriptional RNA modifications are found to play various roles in regulating essential biological processes at all stages of life. Precise identification modification sites is thus crucial for understanding the related molecular functions specific regulatory circuitry. To date, a number computational approaches have been developed silico sites; however, most them require learning from base-resolution epitranscriptome datasets, which generally scarce available only...
Multifactorial diseases demand therapeutics that can modulate multiple targets for enhanced safety and efficacy, yet the clinical approval of multitarget drugs remains rare. The integration machine learning (ML) deep (DL) in drug discovery has revolutionized virtual screening. This study investigates synergy between ML/DL methodologies, molecular representations, data augmentation strategies. Notably, we found SVM match or even surpass performance state-of-the-art DL methods. However,...
One of the most abundant non-canonical bases widely occurring on various RNA molecules is 5-methyluridine (m5U). Recent studies have revealed its influences development breast cancer, systemic lupus erythematosus, and regulation stress responses. The accurate identification m5U sites crucial for understanding their biological functions. We propose RNADSN, first transfer learning deep neural network that learns common features between tRNA mRNA to enhance prediction m5U. Without seeing...
Abstract As the most pervasive epigenetic marker present on mRNA and lncRNA, N 6 -methyladenosine (m A) RNA methylation has been shown to participate in essential biological processes. Recent studies revealed distinct patterns of m A methylome across human tissues, a major challenge remains elucidating tissue-specific presence circuitry methylation. We here comprehensive online platform m6A-TSHub for unveiling context-specific genetic mutations that potentially regulate mark. consists four...
Precise segmentation of chromosome in the real image achieved by a microscope is significant for karyotype analysis. The usually pixel-level classification task, which considers different instances as classes. Many instance methods predict Intersection over Union (IoU) through head branch to correct confidence. Their effectiveness based on correlation between tasks. However, none these consider input and output Herein, we propose network regression correction. First, adopt two branches...
The development of high-throughput omics technologies has enabled the quantification vast amounts genes and gene products in whole genome. Pathway enrichment analysis (PEA) provides an intuitive solution for extracting biological insights from massive data. Topology-based pathway (TPA) represents latest generation PEA methods, which exploit topology addition to lists differentially expressed their expression profiles. A subset these TPA such as BPA, BNrich, PROPS, reconstruct structures by...
In medical imaging, chromosome straightening plays a significant role in the pathological study of chromosomes and development cytogenetic maps. Whereas different approaches exist for task, typically geometric algorithms are used whose outputs characterized by jagged edges or fragments with discontinued banding patterns. To address flaws algorithms, we propose novel framework based on image-to-image translation to learn pertinent mapping dependence synthesizing straightened uninterrupted...
DNA methylation is one of the earliest epigenetic regulation mechanisms studied extensively, and it critical for normal development, diseases, gene expression. As a recently identified chemical modification DNA, N4-acetyldeoxycytosine (4acC) was shown to be abundant in Arabidopsis highly associated with expression actively transcribed genes. Precise identification 4acC essential studying its biological function. We proposed 4acCPred, first computational framework predicting 4acC-carrying...
Chemically modified therapeutic mRNAs have gained momentum recently. In addition to commonly used modifications (
N
Background: 2’-O-Methylation (2’-O-Me) is a post-transcriptional RNA modification that occurs in the ribose sugar moiety of all four nucleotides and abundant both coding non-coding RNAs. Accurate prediction each subtype 2’-O-Me (Am, Cm, Gm, Um) helps understand their role metabolism function. Objective: This study aims to build models can predict from sequence nanopore signals exploit model interpretability for motif mining. Methods: We first propose novel deep learning DeepNm better capture...
Karyotyping of human chromosomes generally consists three steps: pre-processing, segmentation and classification. By analyzing the number structure chromosomes, diseases such as cancers genetic disorders can be diagnosed. Besides traditional methods, The Convolutional Neural Network have improved computer vision area dramatically. When it comes to chromosome karyotyping, few research methods been proposed solve problem This paper proposes an innovative automatic strategy named...
Abstract Computer-aided image classification has achieved start-of-the-art performance since Convolutional Neural Network structures were employed. Classical neural networks such as AlexNet and VGG-Net inspired several rules of designing network models. Besides benchmark datasets MNIST, CIFAR ImageNet, medical images chromosome karyotyping also improved via Network. However, there are few studies on generalization among different datasets. In this paper, we designed a with nine layers,...
Stomach adenocarcinoma (STAD) is a subtype of gastric cancer with high incidence and mortality. Lack early detection results in the poor prognosis this cancer, leading to low survival rate patients. In study, machine learning methods, specifically support vector (SVM) based recursive feature elimination (SVM-RFE), were applied discover potential biomarkers STAD data form Cancer Genome Atlas (TCGA). After optimal parameter set was determined, random sampling conducted minimize limitation...