Analysis approaches for the identification and prediction of N⁶-methyladenosine sites

Figures & data

Figure 1. Experimental strategies in detection of m⁶A methylation sites.

Table 1. Evaluation of experimental methods for m⁶A sites identification and quantification.

Methods		Resolution	Advantages	Limitations
Antibody-based Method to Identify N^6-Methyladenosine Site	MeRIP-seq(m^6A-seq)^[Citation33,Citation35]	100 ~ 200nt	·Low amount of input material required;	·Inability to distinguish m^6A from m^6Am ·Low reproducibility
	miCLIP-seq^[Citation36]	Single- nucleotide	·Detection of multiple m^6A sites within the same peak. ·Ability to distinguish m^6A from m^6Am. ·Without pretreatment of cells with modified nucleotides	·High quantity of mRNA material required ·Complex library protocol ·Low crosslinking yield
	PA-m^6A-seq^[Citation37]	Single- nucleotide	·Compatible with investigation on nucleic acid–protein interactions.	·Low crosslinking yield
	m^6A-LAIC-seq^[Citation39]	100 ~ 200·nt	·Elucidate tissue or cell-state specificity of m^6A levels	·Empirical titration of the antibody concentration required
Enzymatic Methods to Identify N^6-Methyladenosine Sites	MAZTER-seq^[Citation41]	Single-nucleotide	·Provides the m^6A stoichiometry information ·Low false- positive rate	·Only detects m^6A sites in an ACA sequence context ·Inability to distinguish ACA sites in close proximity
	m^6A-REF-seq^[Citation42]	Single-nucleotide	·Direct identification method	·Only detects m^6A sites in an ACA sequence context
	DART-seq^[Citation44]	Single-nucleotide	·Limited input RNA material ·Versatility to the approach	·Low sensitivity for low-abundance m^6A sites
	m^6A-SAC-seq^[Citation46]	Single-nucleotide	·A quantitative method ·Limited input RNA	·A motif preference of GAC over AAC.
	m^6ACE-seq^[Citation47]	Single-nucleotide	··Precise methylomes uniquely mediated by each methyltransferase/demethylase ·mapping m^6Am	·motif specificity
Chemical Methods to Identify N^6-Methyladenosine Sites	m^6A-label-seq^[Citation50]	Single-nucleotide	·High accuracy ·Direct identification method	·Low labelling yield and labelling time window scale ·Lack stoichiometric information
	m^6A-SEAL^[Citation53]	100–200nt	·Can be optimized for detection of cap m6Am ·High sensitivity and specificity ·Direct identification method	·Lack stoichiometric information
Methods based on Direct RNA Sequencing to Identify N^6-Methyladenosine Sites	Nanopore	Single-nucleotide	·No PCR biases ·Direct measurement of the number of m6A sites per isoform	·High general base error rate ·Method never applied to cellular mRNAs ·High cost
	SMRT	Single-nucleotide	·Direct investigation of m6A relation to isoform and transcript features ·Direct measurement of the number of m6A sites per isoform	·High base error rate ·Low sensitivity level ·High cost

Figure 2. Workflow for analysing and interpreting m⁶A modification data.

Table 2. Bioinformatics analysis tools and software based on MeRIP-seq(m⁶A-seq) data.

Tool		Input format	URL/stand-alone package	Highlight
Peak calling	MACS2^[Citation60]	BAM	https://github.com/taoliu/MACS/	Genome-based ChIP-seq peak calling methods
	exomePeak2^[Citation61]	BAM	https://rdrr.io/github/ZhenWei10/exomePeak2/	A MATLAB package that outputs exome-based peaks (the genomic locus of RNA modification sites)
	MeTPeak^[Citation62]	BAM	https://github.com/compgenomics/MeTPeak	Sensitive to lowly enriched peaks
	HEPeak^[Citation63]	SAM	None	Perform the peak calling on connected exons of a specific gene
	m6AViewer^[Citation64]	BAM	http://dna2.leeds.ac.uk/m6a	Finer resolution
	MeRIP-PF^[Citation65]	FASTQ	http://software.big.ac.cn/MeRIP-PF.html.	Produce outputs in both XLS and graphical format
	BaySeqPeak^[Citation66]	Reads count matrix	https://github.com/liqiwei2000/BaySeqPeak	Outperformed when an excess of zeros are present in the data
	TRES^[Citation67]	Reads count matrix	https://github.com/ZhenxingGuo0015/TRES	Account for all sources of variations and alleviates the problem caused by small sample size.
	MoAIMS^[Citation68]	BAM	https://github.com/rreybeyb/MoAIMS	Intuitive evaluation on the treatment effect of MeRIP-seq
Differential methylation analysis	exomePeak2^[Citation70]	BAM	https://rdrr.io/github/ZhenWei10/exomePeak2/	Method specialized for MeRIP-seq data
	MetDiff^[Citation71]	BAM	https://github.com/compgenomics/MeTDiff	Significantly improved sensitivity and specificity
	MVT^[Citation72]	Read counts matrix	https://github.com/ouyang-lab/DIMER	Control type I error
	DRME^[Citation73]	Reads count matrix	https://github.com/lzcyzm/DRME	MeRIP-seq(m6A-seq) dataset in small sample cases
	QNB^[Citation74]	Reads count matrix	https://cran.rstudio.com/web/packages/QNB/	Improve the test performance of extremely low expression genes
	RADAR^[Citation75]	Reads count matrix	https://github.com/scottzijiezhang/RADAR	Consider the existence of covariates in small-sample sequencing
	bltest^[Citation76]	Reads count matrix	None	Need not an independent procedure to unify different library sizes of the MeRIP-Seq samples
	FET-HMM^[Citation77]	BAM	https://github.com/lzcyzm/RHHMM	Distinguish multiple methylated residues within a single methylated site
Clustering analysis of m^6A sites	Binary clustering^[Citation80]	M-value	None	Connect m^6A sites with different RNA functions
	MeTCluster^[Citation81]	BAM	http://compgenomics.utsa.edu/metcluster	Uncover the co-methylation pattern in MeRIP-seq data
	DPBBM^[Citation82]	Reads count matrix	https://cran.r-project.org/web/packages/DPBBM/	Adopt a nonparametric Dirichlet process to determine the optimal number of clusters
	Four clustering methods^[Citation83]	M-value	None	Unveil the linkage between the global RNA co-methylation patterns and the latent enzymatic regulators
	Biclustering algorithms^[Citation84,Citation85]	M-value	None	Explain local co-methylation patterns (LCPs)
	REW-ISA V2^[Citation86]		None	Find potential local function blocks (LFBs)
	Threshold-Based Measurement Weighting^[Citation87]	Reads count matrix	None	Largely tolerate the various artefacts

Table 3. Bioinformatics tool for nanopore sequencing.

Tool		Feature	Algorithm	URL/stand-alone package
Deviation of current signal between WT and WD	ELIGOS^[Citation97]	The percent Error of Specific Bases(%ESB)	None	https://gitlab.com/piroonj/eligos2
	EpiNano^[Citation98]	Differential base-calling errors	Nanopolish	https://github.com/enovoa/EpiNano
	DiffErr^[Citation99]		None	https://github.com/bartongroup/differr_nanopore_DRS
	DRUMMER^[Citation100]	Matches/Mismatches rates	None	https://github.com/DepledgeLab/DRUMMER
Differences in raw current intensity	MINES^[Citation101]	Methylation values from Tombo denovo	Tombo	https://github.com/YeoLab/MINES
	Nanocompore^[Citation103]	Signal intensity, dwell time	Nanopolish	https://github.com/tleonardi/nanocompore
	xPore^[Citation104]	Signal intensity	Nanopolish	https://github.com/GoekeLab/xpore
	Yanocomp^[Citation105]	Signal intensity	Nanopolish	https://github.com/bartongroup/yanocomp

Table 4. Summary of the reviewed predictors for m⁶A sites.

Tool	Dataset modes	Feature encoding	Feature selection	Algorithm	Evaluation strategy	Web server
WHISTLE^[Citation119]	Both	Nucleotide chemical property Cumulative nucleotide frequency Genome-derived features	Perturb method	SVM	Fivefold cross-validation Independent test	https://whistle-epitranscriptome.com
iRNA-m6A^[Citation120]	One	Physical-chemical property matrix Mono-nucleotide binary Nucleotide chemical property	mRMR	SVM	5-fold cross-validation	https://lin-group.cn/server/iRNA-m6A
MethyRNA^[Citation121]	Both	Nucleotide chemical property Accumulated nucleotide frequenc	None	SVM	Jackknife test	https://lin.uestc.edu.cn/server/methyrna
SRAMP^[Citation122]	Both	Positional binary KNN score Nucleotide pair spectrum	None	RF	Fivefold cross-validation	https://www.cuilab.cn/sramp/
HMpre^[Citation123]	One	Positional binary	None	XGBoost	10-fold cross-validation	None
M6AMRFS^[Citation124]	One	Dinucleotide Binary Local Position-Specific Dinucleotide	SFS	XGBoost	10-fold cross-validation jackknife test	https://server.malab.cn/M6AMRFS/
Gene2vec^[Citation125]	One	One-hot Neighbouring methylation state RNA word embedding	None	CNN	Training and validation	https://server.malab.cn/Gene2vec/
BERMP^[Citation126]	One	Enhanced Nucleic Acid Composition RNA word embedding	None	BGRU	10-fold cross-validation	https://www.bioinfogo.org/bermp
EMDLP^[Citation132]	One	RNA word embedding, One-hot encoding, RGloVe	None	NLP DL	Independent validation	https://www.labiip. net/ EMDLP/ index. php (https://47.104.130.81/EMDLP/ index. php)
EDLm^6APred^[Citation131]	One	One-hot RNA word embedding Word2vec^[Citation176]	None	NLP DL	Independent validation	https://www.xjtlu.edu.cn/biological sciences/ EDLm6 APred
WeakRM^[Citation134]	One	One-hot	None	DL	validation approach based on low-resolution data	https://github.com/daiyun02211/WeakRM
m6A-Maize^[Citation135]	One	One-hot	None	DL	fold cross-validation	https://www.xjtlu.edu.cn/biologicalscien ces/maize.
MultiRM^[Citation136]	One	One-hot Seq2vec^[Citation177] Word2vec	None	CNN RNN	Independent validation	https://www.xjtlu.edu.cn/biologicalsciences/multirm
DeepM6ASeq^[Citation137]	One	One-hot	None	DL	Independent validation	https://github.com/rreybeyb/DeepM6ASeq

Figure 3. The overview of bioinformatics methods to decipher the m6A methylation.

Table 5. m⁶A methylation databases.

Database	Main content	Availability
RMBase^[Citation157,Citation158]	The most comprehensive collection of RNA modification sites	https://rna.sysu.edu.cn/rmbase/
MODOMICS^[Citation159,Citation160]	The most comprehensive source of RNA modification pathway	https://iimcb.genesilico.pl/modomics/
m^6A-Atlas^[Citation164]	m^6A sites with high-confidence	https://www.xjtlu.edu.cn/biologicalsciences/atlas
M6ADD^[Citation165]	Experimentally confirmed m6A-disease association	https://m6add.edbc.org/
M6AREG^[Citation167]	The effects of m^6A-centred regulation on both disease development and drug response	https://idrblab.org/m6areg/
REPIC^[Citation168]	Peaks called from MeRIP-seq data	https://epicmod.uchicago.edu/repic/index.php
MeTDB^[Citation169]	Peaks called from MeRIP-seq data	http://rna.sysu.edu.cn/rmbase/
M6A2Target^[Citation170]	The known m^6A WER target genes	http://m6a2target.canceromics.org

Table 6. Validation Method for N⁶-Methyladenosine Sites.

Methods	Advantages	Limitations
LS-MS/MS^[Citation171]	Standardized method Easy preparation steps	Inability to distinguish m^6A on mRNA from m^6A on rRNA or snRNA contaminants
MeRIP-qPCR^[Citation172]	Semi- stoichiometric information at specific m^6A sites Low amount of input material required	Inability to distinguish stoichiometry of adjacent m^6A sites Need for external methylated and non-methylated spike- in controls
SCARLET^[Citation173]	Exact measurement of the m^6A stoichiometry at the specific site	Low throughput Ability to detect only one site per transcript at a time
T3/T4DNA ligase-qPCR^[Citation174]	Easy preparation steps Potential measurement of m6A stoichiometry	Dependence on efficiency of the ligation reaction Low throughput
SELECT [175]	Easy preparation steps Measurement of m6A stoichiometry	Dependence on two selective steps: efficiency of the Bst polymerase and efficiency of the ligation reaction

Dominissini D, Moshitch-Moshkovitz S, Schwartz S, et al. Topology of the human and mouse m(6)A RNA methylomes revealed by m(6)A-seq. Nature. 2012 May 10;485(7397):201–U84.

 PubMed Web of Science ®Google Scholar

Meyer KD, Saletore Y, Zumbo P, et al. Comprehensive Analysis of mRNA Methylation Reveals Enrichment in 3 ‘ UTRs and near Stop Codons. Cell. 2012 Jun 22;149(7):1635–1646.

 PubMed Web of Science ®Google Scholar

Linder B, Grozhik AV, Olarerin-George AO, et al. Single-nucleotide-resolution mapping of m6A and m6Am throughout the transcriptome. Nat Methods. 2015 Aug;12(8):767–U114.

 PubMed Web of Science ®Google Scholar

Chen K, Luo G-Z, He C. High-Resolution Mapping of N-6-Methyladenosine in Transcriptome and Genome Using a Photo-Crosslinking-Assisted Strategy. Methods in Enzymology. 2015;560:161–185.

 Google Scholar

Molinie B, Wang J, Lim KS, et al. m(6)A-LAIC-seq reveals the census and complexity of the m(6)A epitranscriptome. Nat Methods. 2016 Aug;13(8):692.

 PubMed Web of Science ®Google Scholar

Garcia-Campos MA, Edelheit S, Toth U, et al. Deciphering the “m(6)A Code” via Antibody-Independent Quantitative Profiling. Cell. 2019 Jul 25;178(3):731.

 PubMed Web of Science ®Google Scholar

Zhang Z, Chen L-Q, Zhao Y-L, et al. Single-base mapping of m 6 A by an antibody-independent method. Sci Adv. 2019 Jul;5(7):eaax0250.

 PubMed Web of Science ®Google Scholar

Meyer KD. DART-seq: an antibody-free method for global m(6)A detection. Nat Methods. 2019 Dec;16(12):1275.

 PubMed Web of Science ®Google Scholar

Hu L, Liu S, Peng Y, et al. m(6)A RNA modifications are measured at single-base resolution across the mammalian transcriptome. Nat Biotechnol. 2022 Aug;40(8):1210.

 PubMed Web of Science ®Google Scholar

Koh CWQ, Goh YT, Goh WSS. Atlas of quantitative single-base-resolution N-6-methyl-adenine methylomes. Nat Commun. 2019 Dec 10;10(5636).

 Google Scholar

Shu X, Cao J, Cheng M, et al. A metabolic labeling method detects m(6)A transcriptome-wide at single base resolution. Nat Chem Biol. 2020 Aug;16(8):887.

 PubMed Web of Science ®Google Scholar

Wang Y, Xiao Y, Dong S, et al. Antibody-free enzyme-assisted chemical approach for detection of N-6-methyladenosine. Nat Chem Biol. 2020 Aug 1;16(8):896.

 PubMed Web of Science ®Google Scholar

Zhang Y, Liu T, Meyer CA, et al. Model-based Analysis of ChIP-Seq (MACS). Genome Biol. 2008;9(9). 137.

 PubMed Web of Science ®Google Scholar

Meng J, Cui X, Rao MK, et al. Exome-based analysis for RNA epigenome sequencing data. Bioinformatics. 2013 Jun 15;29(12):1565–1567.

 PubMed Web of Science ®Google Scholar

Cui X, Meng J, Zhang S, et al. A novel algorithm for calling mRNA m(6)A peaks by modeling biological variances in MeRIP-seq data. Bioinformatics. 2016 Jun 15;32(12):378–385.

 PubMed Web of Science ®Google Scholar

Cui X, Meng J, Rao MK, et al. HEPeak: an HMM-based exome peak-finding package for RNA epigenome sequencing data. Bmc Genomics. 2015 Apr 21;16(S2).

 Google Scholar

Antanaviciute A, et al. m6aViewer: software for the detection, analysis, and visualization of N-6-methyladenosine peaks from m(6)A-seq/ME-RIP sequencing data. Rna. 2017 Oct;23(10):1493–1501.

 PubMed Web of Science ®Google Scholar

Li Y, Song S, Li C, et al. MeRIP-PF: an easy-to-use pipeline for high-resolution peak-finding in MeRIP-Seq data. Genomics Proteomics Bioinformatics. 2013 Feb;11(1):72–75.

 PubMedGoogle Scholar

Zhang M, Li Q, Xie Y. A Bayesian hierarchical model for analyzing methylated RNA immunoprecipitation sequencing data. Quantitative Biology. 2018 Sep;6(3):275–286.

 PubMedGoogle Scholar

Guo Z, Shafik AM, Jin P, et al. Detecting m(6)A methylation regions from Methylated RNA Immunoprecipitation Sequencing. Bioinformatics. 2021 Sep 15;37(18):2818–2824.

 PubMed Web of Science ®Google Scholar

Zhang Y, Hamada M. MoAIMS: efficient software for detection of enriched regions of MeRIP-Seq. Bmc Bioinformatics. 2020 Mar 14;21(1):103.

 PubMed Web of Science ®Google Scholar

Meng J, Lu Z, Liu H, et al. A protocol for RNA methylation differential analysis with MeRIP-Seq data and exomePeak R/Bioconductor package. Methods. 2014 Oct 1;69(3):274–281.

 PubMed Web of Science ®Google Scholar

Cui X, Zhang L, Meng J, et al. MeTDiff: a Novel Differential RNA Methylation Analysis for MeRIP-Seq Data. Ieee-Acm Transactions on Computational Biology and Bioinformatics. 2018 Mar-Apr;15(2):526–534.

 PubMed Web of Science ®Google Scholar

Ayyala DN, Lin J, Ouyang Z. Differential RNA methylation using multivariate statistical methods. Brief Bioinform. 2022 Jan 17;23(1):309.

 Web of Science ®Google Scholar

Liu L, Zhang S-W, Gao F, et al. DRME: count-based differential RNA methylation analysis at small sample size scenario. Anal Biochem. 2016 Apr 15;499:15–23.

 PubMed Web of Science ®Google Scholar

Liu L, Zhang S-W, Huang Y, et al. QNB: differential RNA methylation analysis for count-based small-sample sequencing data with a quad-negative binomial model. Bmc Bioinformatics. 2017 Aug 31;18(387).

 Google Scholar

Zhang Z, Zhan Q, Eckert M, et al. RADAR: differential analysis of MeRIP-seq data with a random effect model. Genome Biol. 2019 Dec 23;20(1).

 Web of Science ®Google Scholar

Zhang L, Meng, J, Liu, H, et al., “Detecting differentially methylated mRNA from MeRIP-Seq with likelihood ratio test,” in IEEE Global Conference on Signal and Information Processing (GlobalSIP), Atlanta, GA, 2014. Dec 03–05 2014, pp. 1368–1371

 Google Scholar

Zhang Y-C, Zhang S-W, Liu L, et al. Spatially Enhanced Differential RNA Methylation Analysis from Affinity-Based Sequencing Data with Hidden Markov Model. Biomed Res Int. 2015;2015:852070.

 PubMed Web of Science ®Google Scholar

Schwartz S, Mumbach M, Jovanovic M, et al. Perturbation of m6A Writers Reveals Two Distinct Classes of mRNA Methylation at Internal and 5 ‘ Sites. Cell Rep. 2014 Jul 10;8(1):284–296.

 PubMed Web of Science ®Google Scholar

Cui X, Meng J, Zhang S, et al. A hierarchical model for clustering m(6)A methylation peaks in MeRIP-seq data. Bmc Genomics. 2016 Aug 22;17(520).

 Google Scholar

Zhang L, He Y, Wang H, et al. Clustering Count-based RNA Methylation Data Using a Nonparametric Generative Model. Curr Bioinf. 2019;14(1):11–23.

 Web of Science ®Google Scholar

Liu L, Zhang S-W, Zhang Y-C, et al. Decomposition of RNA methylome reveals co-methylation patterns induced by latent enzymatic regulators of the epitranscriptome. Mol Biosyst. 2015 Jan;11(1):262–274.

 PubMedGoogle Scholar

Chen S, Zhang L, Lu L, et al. FBCwPlaid: a Functional Biclustering Analysis of Epi-Transcriptome Profiling Data Via a Weighted Plaid Model. Ieee-Acm Transactions on Computational Biology and Bioinformatics. 2022 May-Jun;19(3):1640–1650.

 PubMed Web of Science ®Google Scholar

Liu Z, Xiao Y, Yin H, et al. BDBB: a Novel Beta-Distribution-Based Biclustering Algorithm for Revealing Local Co-Methylation Patterns in Epi-Transcriptome Profiling Data. IEEE J Biomed Health Inform. 2022 Jun;26(6):2405–2416.

 PubMed Web of Science ®Google Scholar

Zhang L, Chen S, Ma J, et al. REW-ISA V2: a Biclustering Method Fusing Homologous Information for Analyzing and Mining Epi-Transcriptome Data. Front Genet. 2021 May 28;12(654820).

 Google Scholar

Chen K, Wei Z, Liu H, et al. Enhancing Epitranscriptome Module Detection from m(6)A-Seq Data Using Threshold-Based Measurement Weighting Strategy. Biomed Res Int. 2018;2018:2075173.

 PubMed Web of Science ®Google Scholar

Jenjaroenpun P, Wongsurawat T, Wadley TD, et al. Decoding the epitranscriptional landscape from native RNA sequences. Nucleic Acids Res, vol. 49, no. 2, 2021 Jan 25:7.

 PubMed Web of Science ®Google Scholar

Liu H, Begik O, Novoa EM. EpiNano: detection of m6A RNA Modifications Using Oxford Nanopore Direct RNA Sequencing. Methods Mol Biol. 2021;2298:31–52.

 PubMedGoogle Scholar

Parker MT, Knop K, Sherwood AV, et al. Nanopore direct RNA sequencing maps the complexity of Arabidopsis mRNA processing and m(6)A modification. Elife. 2020 Jan 14;9:e49658.

 PubMed Web of Science ®Google Scholar

Abebe JS, Price AM, Hayer KE, et al. DRUMMER-rapid detection of RNA modifications through comparative nanopore sequencing. Bioinformatics. 2022 May 26;38(11):3113–3115.

 PubMed Web of Science ®Google Scholar

Lorenz DA, Sathe S, Einstein JM, et al. Direct RNA sequencing enables m(6)A detection in endogenous transcript isoforms at base-specific resolution. Rna. 2020 Jan;26(1):19–28.

 PubMed Web of Science ®Google Scholar

Leger A, Amaral PP, Pandolfini L, et al. RNA modifications detection by comparative Nanopore direct RNA sequencing. Nat Commun. 2021 Dec 10;12(1).

 Web of Science ®Google Scholar

Pratanwanich PN, Yao F, Chen Y, et al. Identification of differential RNA modifications from nanopore direct RNA sequencing with xPore. Nat Biotechnol. 2021 Nov;39(11):1394.

 PubMed Web of Science ®Google Scholar

Parker MT, Barton GJ, Simpson GG. Yanocomp: robust prediction of m6A modifications in individual nanopore direct RNA reads. bioRxiv. 2021.

 Google Scholar

Chen K, et al. WHISTLE: a high-accuracy map of the human N-6-methyladenosine (m(6)A) epitranscriptome predicted using a machine learning approach. Nucleic Acids Res. 2019 Apr 23;47(7):e41–e41.

 PubMed Web of Science ®Google Scholar

Dao F-Y, Lv H, Yang Y-H, et al. Computational identification of N6-methyladenosine sites in multiple tissues of mammals. Comput Struct Biotechnol J. 2020;18:1084–1091.

 PubMed Web of Science ®Google Scholar

Chen W, Tang H, Lin H. MethyRNA: a web server for identification of N-6-methyladenosine sites. J Biomol Struct Dyn. 2017;35(3):683–687.

 PubMed Web of Science ®Google Scholar

Zhou Y, Zeng P, Li Y-H, et al. SRAMP: prediction of mammalian N 6 -methyladenosine (m 6 A) sites based on sequence-derived features. Nucleic Acids Res. 2016 Jun 2;44(10):e91–e91.

 PubMed Web of Science ®Google Scholar

Zhao Z, Peng H, Lan C, et al. Imbalance learning for the prediction of N-6-Methylation sites in mRNAs. Bmc Genomics. 2018 Aug 1;19(574).

 Google Scholar

Qiang X, Chen H, Ye X, et al. M6AMRFS: robust Prediction of N6-Methyladenosine Sites With Sequence-Based Features in Multiple Species. Front Genet. 2018 Oct 25;9(495).

 PubMedGoogle Scholar

Zou Q, Xing P, Wei L, et al. Gene2vec: gene subsequence embedding for prediction of mammalian N-6-methyladenosine sites from mRNA. Rna. 2019 Feb;25(2):205–218.

 PubMed Web of Science ®Google Scholar

Huang Y, He N, Chen Y, et al. BERMP: a cross-species classifier for predicting m(6)A sites by integrating a deep learning algorithm and a random forest approach. Int J Biol Sci. 2018;14(12):1669–1677.

 PubMed Web of Science ®Google Scholar

Wang H, Liu H, Huang T, et al. EMDLP: ensemble multiscale deep learning model for RNA methylation site prediction. Bmc Bioinformatics. 2022 Jun 8;23(1):221

 PubMed Web of Science ®Google Scholar

Zhang L, Li G, Li X, et al. EDLm(6)APred: ensemble deep learning approach for mRNA m(6)A site prediction. Bmc Bioinformatics. 2021 May 29;22(1):288.

 PubMed Web of Science ®Google Scholar

Kumari A, Lobiyal DK. Efficient estimation of Hindi WSD with distributed word representation in vector space. Journal of King Saud University-Computer and Information Sciences. Sep 2022;34(8):6092–6103.

 Web of Science ®Google Scholar

Huang D, Song B, Wei J, et al. Weakly supervised learning of RNA modifications from low-resolution epitranscriptome data. Bioinformatics. 2021 Jul;37(Supplement_1):I222–I230.

 PubMedGoogle Scholar

Liang Z, Zhang L, Chen H, et al. m6A-Maize: weakly supervised prediction of m(6)A-carrying transcripts and m(6)A-affecting mutations in maize (Zea mays). Methods. 2022Jul;203:226–232.

 PubMed Web of Science ®Google Scholar

Song Z, Huang D, Song B, et al. Attention-based multi-label neural networks for integrated prediction and interpretation of twelve widely occurring RNA modifications. Nat Commun. 2021 Jun 29;12(1):4011.

 PubMed Web of Science ®Google Scholar

Dai H, Umarov R, Kuwahara H, et al. Sequence2Vec: a novel embedding approach for modeling transcription factor binding affinity landscape. Bioinformatics. 2017 Nov 15;33(22):3575–3583.

 PubMed Web of Science ®Google Scholar

Zhang Y, Hamada M. DeepM6ASeq: prediction and characterization of m6A-containing sequences using deep learning. Bmc Bioinformatics. 2018 Dec 31;19(524).

 Google Scholar

Sun W-J, Li J-H, Liu S, et al. RMBase: a resource for decoding the landscape of RNA modifications from high-throughput sequencing data. Nucleic Acids Res. 2016 Jan 4;44(D1):D259–D265.

 PubMed Web of Science ®Google Scholar

Xuan -J-J, Sun W-J, Lin P-H, et al. RMBase v2.0: deciphering the map of RNA modifications from epitranscriptome sequencing data. Nucleic Acids Res. 2018 Jan 4;46(D1):D327–D334.

 PubMed Web of Science ®Google Scholar

Machnicka MA, Milanowska K, Osman Oglou O, et al. MODOMICS: a database of RNA modification pathways-2013 update. Nucleic Acids Res. 2013 Jan;41(D1):D262–D267.

 PubMed Web of Science ®Google Scholar

Boccaletto P, Machnicka MA, Purta E, et al. MODOMICS: a database of RNA modification pathways. 2017 update. Nucleic Acids Res. 2018 Jan 4;46(D1):D303–D307.

 PubMed Web of Science ®Google Scholar

Tang Y, Chen K, Song B, et al. m(6)A-Atlasm6A-Atlas: a comprehensive knowledgebase for unraveling the N-6-methyladenosine N 6-methyladenosine (m6A) epitranscriptome. Nucleic Acids Res. 2021 Jan 8;49(D1):D134–D143.

 PubMed Web of Science ®Google Scholar

Zhou D, Wang H, Bi F, et al. M6ADD: a comprehensive database of m 6 A modifications in diseases. RNA Biol. 2021 Dec 2;18(12):2354–2362.

 PubMed Web of Science ®Google Scholar

Liu S, Chen L, Zhang Y, et al. M6AREG: m(6)A-centered regulation of disease development and drug response. Nucleic Acids Res. 2022.

 Web of Science ®Google Scholar

Liu S, Zhu A, He C, et al. REPIC: a database for exploring the N-6-methyladenosine methylome. Genome Biol. 2020 Apr 28;21(1:100.

 PubMed Web of Science ®Google Scholar

Liu H, Flores MA, Meng J, et al. MeT-DB: a database of transcriptome methylation in mammalian cells. Nucleic Acids Res. 2015 Jan 28;43(D1):D197–D203.

 PubMed Web of Science ®Google Scholar

Deng S, Zhang H, Zhu K, et al. M6A2Target: a comprehensive database for targets of m 6 A writers, erasers and readers. Brief Bioinform. 2021;22(3).

 Web of Science ®Google Scholar

Thuring K, Schmid K, Keller P, et al. LC-MS Analysis of Methylated RNA. Methods Mol Biol. 2017;1562:3–18.

 PubMedGoogle Scholar

Wang Y, Li Y, Toth JI, et al. N-6-methyladenosine modification destabilizes developmental regulators in embryonic stem cells. Nat Cell Biol. 2014 Feb;16(2):191–198.

 PubMed Web of Science ®Google Scholar

Liu N, Parisien M, Dai Q, et al. Probing N-6-methyladenosine RNA modification status at single nucleotide resolution in mRNA and long noncoding RNA. Rna. 2013 Dec;19(12):1848–1856.

 PubMed Web of Science ®Google Scholar

Liu W, Yan J, Zhang Z, et al. Identification of a selective DNA ligase for accurate recognition and ultrasensitive quantification of N-6-methyladenosine in RNA at one-nucleotide resolution. Chem Sci. 2018 Apr 7;9(13):3354–3359.

 PubMed Web of Science ®Google Scholar

Xiao Y, Wang Y, Tang Q, et al. An elongation- and ligation-based qPCR amplification method for the radiolabeling-free detection of locus-specific N-6-methyladenosine modification. Angew Chem-Int Ed. 2018 Dec 3;57(49):15995–16000.

 PubMed Web of Science ®Google Scholar