| Type: | Package |
| Title: | Optimized Ensemble Model for C and A Methylation Search in Plant |
| Version: | 0.1.1 |
| Author: | Abhik Sarkar [aut, cre], Dipro Sinha [aut], Sneha Murmu [aut], Md Yeasin [aut], Dwijesh Chandra Mishra [aut], Sunil Archak [aut] |
| Maintainer: | Abhik Sarkar <abhik.iasri@gmail.com> |
| Description: | DNA methylation is an important epigenetic process that regulates gene activity through chemical modifications of DNA without changing its sequence. 'OpEnCAST' is a plant-specific ensemble-based prediction package that identifies 4mC, 5mC and 6mA methylation sites directly from DNA sequences. It combines multiple machine learning algorithms trained on monocot (Oryza sp.) and dicot (Arabidopsis sp.) reference models to deliver accurate predictions. This methodology is being inspired by the ensemble algorithm for methylation prediction developed by Wang et al. (2022) <doi:10.1186/s12859-022-04756-1>. |
| Imports: | Biostrings, seqinr, stringr, tibble, entropy, ftrCOOL, stats |
| Suggests: | caret, kernlab, ranger, xgboost, gbm |
| Encoding: | UTF-8 |
| License: | GPL-3 |
| RoxygenNote: | 7.3.3 |
| NeedsCompilation: | no |
| Packaged: | 2025-12-22 20:24:59 UTC; Abhik |
| Repository: | CRAN |
| Date/Publication: | 2026-01-08 19:20:22 UTC |
DNA Methylation Prediction in Dicot Plants
Description
Predicting sequences with DNA methylation sites like 4mC or 6mA based on Arabidopsis as reference model.
Usage
Dicot_MethPred(fasta_file_path, Reference = "Arabidopsis")
Arguments
fasta_file_path |
Sequence file (.fasta format) |
Reference |
Arabidopsis as Reference Model for Dicot plants |
Value
Methylation Status: Sequences with their probable DNA methylation state such as 4mC, 6mA or Non Methhylated.
References
Lv, H., Dao, F. Y., Zhang, D., Guan, Z. X., Yang, H., Su, W., ... & Lin, H. (2020). iDNA-MS: an integrated computational tool for detecting DNA modification sites in multiple genomes. Iscience, 23(4).
Examples
library(OpEnCAST)
data<-system.file("exdata/test.fasta", package = "OpEnCAST")
pred<-Dicot_MethPred(fasta_file_path=data, Reference="Arabidopsis")
DNA Methylation Prediction in Monocot Plants
Description
Predicting sequences with DNA methylation sites like 5mC or 6mA based on Rice as reference model.
Usage
Monocot_MethPred(fasta_file_path, Reference = "Rice")
Arguments
fasta_file_path |
Sequence file (.fasta format) |
Reference |
Rice as Reference Model for Monocot plants |
Value
Methylation Status: Sequences with their probable DNA methylation state such as 5mC, 6mA or Non Methhylated.
References
Lv, H., Dao, F. Y., Zhang, D., Guan, Z. X., Yang, H., Su, W., ... & Lin, H. (2020). iDNA-MS: an integrated computational tool for detecting DNA modification sites in multiple genomes. Iscience, 23(4).
Examples
library(OpEnCAST)
data<-system.file("exdata/test.fasta", package = "OpEnCAST")
pred<-Monocot_MethPred(fasta_file_path=data, Reference="Rice")