Predicting RNA 5-Methylcytosine Sites by Using Essential Sequence Features and Distributions

Lei, Chen; Li, Zhandong; Zhang, Shiqi; Zhang, Yuhang; Huang, Tao; Cai, Yu-Dong

doi:10.1155/2022/4035462

Cited by 34 publications

(25 citation statements)

References 63 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In summary, our study conducted a systematic evaluation of parameters used in RNA bisulfite sequencing and may shed new light on RNA methylation data generation and analysis. Further improvement may be achieved with improved characterization of false-positive sites ( 47 ), alternative deamination techniques ( 49 ), and advance computational modeling for m 5 C calling ( 50 ).…”

Section: Discussionmentioning

confidence: 99%

Systematic evaluation of parameters in RNA bisulfite sequencing data generation and analysis

Johnson

Pacholec

et al. 2022

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

The presence of 5-methylcytosine (m5C) in RNA molecules has been known for decades and its importance in regulating RNA metabolism has gradually become appreciated. Despite recent advances made in the functional and mechanistic understanding of RNA m5C modifications, the detection and quantification of methylated RNA remains a challenge. In this study, we compared four library construction procedures for RNA bisulfite sequencing and implemented an analytical pipeline to assess the key parameters in the process of m5C calling. We found that RNA fragmentation after bisulfite conversion increased the yield significantly, and an additional high temperature treatment improved bisulfite conversion efficiency especially for sequence reads mapped to the mitochondrial transcriptome. Using Unique Molecular Identifiers (UMIs), we observed that PCR favors the amplification of unmethylated templates. The low sequencing quality of bisulfite-converted bases is a major contributor to the methylation artifacts. In addition, we found that mitochondrial transcripts are frequently resistant to bisulfite conversion and no p-m5C sites with high confidence could be identified on mitochondrial mRNAs. Taken together, this study reveals the various sources of artifacts in RNA bisulfite sequencing data and provides an improved experimental procedure together with analytical methodology.

show abstract

Section: Discussionmentioning

confidence: 99%

Systematic evaluation of parameters in RNA bisulfite sequencing data generation and analysis

Johnson

Pacholec

et al. 2022

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Random forest is widely applied in analyzing biological and biomedical data. Several previous studies indicate the satisfactory performance of RF ( Pan et al, 2010 ; Zhao et al, 2018 ; Jia et al, 2020 ; Chen et al, 2021 , 2022 ; Ding et al, 2022 ; Li Z. et al, 2022 ; Wu and Chen, 2022 ; Zhou et al, 2022 ). RF is a meta-classifier because it consists of numerous decision trees.…”

Section: Methodsmentioning

confidence: 93%

Detecting Brain Structure-Specific Methylation Signatures and Rules for Alzheimer’s Disease

Guo

Zeng

et al. 2022

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is a progressive disease that leads to irreversible behavioral changes, erratic emotions, and loss of motor skills. These conditions make people with AD hard or almost impossible to take care of. Multiple internal and external pathological factors may affect or even trigger the initiation and progression of AD. DNA methylation is one of the most effective regulatory roles during AD pathogenesis, and pathological methylation alterations may be potentially different in the various brain structures of people with AD. Although multiple loci associated with AD initiation and progression have been identified, the spatial distribution patterns of AD-associated DNA methylation in the brain have not been clarified. According to the systematic methylation profiles on different structural brain regions, we applied multiple machine learning algorithms to investigate such profiles. First, the profile on each brain region was analyzed by the Boruta feature filtering method. Some important methylation features were extracted and further analyzed by the max-relevance and min-redundancy method, resulting in a feature list. Then, the incremental feature selection method, incorporating some classification algorithms, adopted such list to identify candidate AD-associated loci at methylation with structural specificity, establish a group of quantitative rules for revealing the effects of DNA methylation in various brain regions (i.e., four brain structures) on AD pathogenesis. Furthermore, some efficient classifiers based on essential methylation sites were proposed to identify AD samples. Results revealed that methylation alterations in different brain structures have different contributions to AD pathogenesis. This study further illustrates the complex pathological mechanisms of AD.

show abstract

“…Here, two classic base classifiers, namely, SVM ( Cortes and Vapnik, 1995 ) and RF ( Breiman, 2001 ), were used, which were widely applied in tackling many biological problems ( Kandaswamy et al, 2011 ; Nguyen et al, 2015 ; Chen et al, 2017 ; Zhou JP. et al, 2020 ; Zhou J.-P. et al, 2020 ; Liang et al, 2020 ; Liu et al, 2021 ; Onesime et al, 2021 ; Wang et al, 2021 ; Zhu et al, 2021 ; Chen et al, 2022 ; Ding et al, 2022 ; Li et al, 2022 ; Wu and Chen, 2022 ).…”

Section: Methodsmentioning

confidence: 99%

Identifying Functions of Proteins in Mice With Functional Embedding Features

Zhang

Chen

et al. 2022

Front. Genet.

Self Cite

View full text Add to dashboard Cite

In current biology, exploring the biological functions of proteins is important. Given the large number of proteins in some organisms, exploring their functions one by one through traditional experiments is impossible. Therefore, developing quick and reliable methods for identifying protein functions is necessary. Considerable accumulation of protein knowledge and recent developments on computer science provide an alternative way to complete this task, that is, designing computational methods. Several efforts have been made in this field. Most previous methods have adopted the protein sequence features or directly used the linkage from a protein–protein interaction (PPI) network. In this study, we proposed some novel multi-label classifiers, which adopted new embedding features to represent proteins. These features were derived from functional domains and a PPI network via word embedding and network embedding, respectively. The minimum redundancy maximum relevance method was used to assess the features, generating a feature list. Incremental feature selection, incorporating RAndom k-labELsets to construct multi-label classifiers, used such list to construct two optimum classifiers, corresponding to two key measurements: accuracy and exact match. These two classifiers had good performance, and they were superior to classifiers that used features extracted by traditional methods.

show abstract

Predicting RNA 5-Methylcytosine Sites by Using Essential Sequence Features and Distributions

Cited by 34 publications

References 63 publications

Systematic evaluation of parameters in RNA bisulfite sequencing data generation and analysis

Systematic evaluation of parameters in RNA bisulfite sequencing data generation and analysis

Detecting Brain Structure-Specific Methylation Signatures and Rules for Alzheimer’s Disease

Identifying Functions of Proteins in Mice With Functional Embedding Features

Contact Info

Product

Resources

About