RT Journal
A1 Zhang, Shuyu
A1 Zou, Quan
A1 Niu, Mengting
A1 Lv, Zhibin
A1 Stalin, Antony
A1 Luo, Ximei
T1 EnDeep4mC predicts DNA N4-methylcytosine sites using a dual-adaptive feature encoding framework in deep ensembles
JF Genome Research 
JO Genome Research 
YR 2026 
FD March 01 
VO 36 
IS 3 
SP 589 
OP 599 
DO 10.1101/gr.280977.125 
UL http://genome.cshlp.org/content/36/3/589.abstract 
AB DNA N4-methylcytosine (4mC), a key epigenetic modification regulating DNA repair and replication, requires efficient computational detection methods due to experimental limitations. Although machine learning predictors have been proposed, their performance could be enhanced through systematic optimization of feature encoding schemes. Here, we propose EnDeep4mC, a dual-adaptive framework integrating species-specific modeling with ensemble deep learning architectures to systematically optimize feature encoding schemes. Evaluated across six species, EnDeep4mC demonstrates commendable prediction performance and significantly outperforms current state-of-the-art predictors. Cross-species validation confirms its robust transferability from animal to microbe groups. Evolutionary analysis further uncovers the functional differentiation of 4mC sequences in biological evolution: Prokaryotic 4mC relies on stable patterns, whereas eukaryotes achieve regulatory plasticity through dynamic sequence combinations, which provides experimental evidence for species-adaptive encoding strategies.