A5101588917- Epigenetics and DNA Methylation
- Single-cell and spatial transcriptomics
- RNA modifications and cancer
- Cancer-related molecular mechanisms research
- Machine Learning in Bioinformatics
- Ferroptosis and cancer prognosis
- Cell Image Analysis Techniques
- Cancer Genomics and Diagnostics
- Bioinformatics and Genomic Networks
- Immune responses and vaccinations
- Scientific Computing and Data Management
- Big Data and Business Intelligence
- Topic Modeling
- Genetic Syndromes and Imprinting
- Advanced Graph Neural Networks
- Genomics and Chromatin Dynamics
University of Electronic Science and Technology of China
2019-2022
Determination of genome-wide DNA methylation is significant for both basic research and drug development. As a key epigenetic modification, this biochemical process can modulate gene expression to influence the cell differentiation which possibly lead cancer. Due involuted mechanism methylation, obtaining precise prediction considerably tough challenge. Existing approaches have yielded good predictions, but methods either need combine plenty features prerequisites or deal with only...
Single-cell DNA methylation sequencing detects levels with single-cell resolution, while this technology is upgrading our understanding of the regulation gene expression through epigenetic modifications. Meanwhile, almost all current technologies suffer from inherent problem detecting low coverage number CpGs. Therefore, addressing sparsity raw data essential for quantitative analysis whole genome.Here, we reported CaMelia, a CatBoost gradient boosting method predicting missing states based...
Abstract Background The computational prediction of methylation levels at single CpG resolution is promising to explore the CpGs uncovered by existing array techniques, especially for 450 K beadchip data with huge reserves. General models concentrate on improving overall accuracy bulk loci while neglecting whether each locus precisely predicted. This leads limited application results, when performing downstream analysis high precision requirements. Results Here we reported PretiMeth, a...
Lots of researches have been conducted in the selection gene signatures that could distinguish cancer patients from normal. However, it is still an open question on how to extract robust features.In this work, a signature strategy for TCGA data was proposed by integrating expression data, methylation and prior knowledge about biomarkers. Different traditional integration method, expanded 450 K were applied instead original array reported biomarkers weighted feature selection. Fuzzy rule...
DNA methylation is a widely investigated epigenetic mark that plays vital role in tumorigenesis. Advancements high-throughput assays, such as the Infinium 450K platform, provide genome-scale landscapes single-CpG locus resolution, and identification of differentially methylated loci has become an insightful approach to deepen our understanding cancers. However, situation with extremely unbalanced numbers samples (approximately 1:1,000) makes it rather difficult explore differential between...
Advances in high throughput sequencing have enabled DNA methylation profiling at single-cell resolution. The generation of (scM-Seq) data provides unprecedented opportunities for a comprehensive dissection epigenetic heterogeneity. An important step exploring heterogeneity is clustering cells according to their profiles. However, the inherent sparsity and stochastic measurement characteristic make it challenging. To this end, we introduce SINCEF, using spectral embedding fusion reconstruct...
Background DNA methylation is a key heritable epigenetic modification that plays crucial role in transcriptional regulation and therefore broad range of biological processes. The complex patterns highlight the significance profiling landscape. Results In this review, main high‐throughput detection technologies are summarized, then three trends computational estimation levels were analyzed, especially expanding data with lower coverage. Furthermore, methods differential for sequencing array...
The main challenge of single-cell RNA sequencing (scRNA-seq) studies arises from the large data sizes and various technical noises such as excess zero counts within individual cells (called dropout events). This inaccurate measurement gene expressions may introduce bias in downstream analyses scRNA-seq data, so it is necessary to correct false expression by computational imputation methods. Most current pipelines typically use unsupervised modeling approaches that expect recover biologically...