Skip to main content
Fig. 1 | Genome Biology

Fig. 1

From: Quantitative profiling of N6-methyladenosine at single-base resolution in stem-differentiating xylem of Populus trichocarpa using Nanopore direct RNA sequencing

Fig. 1

Nanom6A pipeline for identification of m6A at single-base resolution. For the XGBoost-training module, the raw sequence with or without m6A modification was resquiggled. After the corrected sequence was assigned to the raw signal using Tombo, we extracted the signals of separate bases according to RRACH features including signal length, mean, std., and width. The corresponding 12 k-mers were trained to build the XGBoost models separately. For the prediction module, the basecalled files were aligned to the genome sequence. Then, the sequence was corrected with the genome sequence. After the corrected sequence was assigned to the raw signal, signals of individual bases, corresponding features of RRACH k-mer were extracted to predict the modified bases with the trained models

Back to article page