EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TriTower-m6Am: A triple-tower heterogeneous deep learning architecture integrating semantic, sequential, and structural information for mRNA N6,2′-O-dimethyladenosine site prediction

Kaifeng Xiong iD, Jianhua Jia iD

PLOS Computational Biology · 05.11.2026 · 22 (11) · e1014939

DOI: 10.1371/journal.pcbi.1014939 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 05.11.2026. Verfasst von Kaifeng Xiong und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Jingdezhen Ceramic University, Jingdezhen, China. Hauptthemen laut MEDLINE: Adenosine, Deep Learning, RNA, Messenger. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

N 6 ,2′-O-dimethyladenosine (m6Am) is a cap-proximal mRNA modification deposited by PCIF1 (phosphorylated C-terminal domain (CTD)-interacting factor 1) at the first transcribed nucleotide of eukaryotic mRNAs. Knowing where m6Am sites sit would help explain how cells tune mRNA stability and translation, but current predictors typically depend on a single representation and do not jointly model multiple views of the same RNA sequence.

Results

We present TriTower-m6Am, combining semantic (RNA-FM, a pretrained RNA foundation model, with BellPooling), sequential (One-Hot BiLSTM, bidirectional long short-term memory), and structural (RGCN, a relational graph convolutional network, over the 41-nt window) representations of each RNA window. On an independent test set of 640 sequences, TriTower-m6Am reaches an area under the ROC curve (AUC) of 0.776 and a Matthews correlation coefficient (MCC) of 0.425, against DTC-m6Am’s AUC = 0.765 and MCC = 0.411, using 4.4 times fewer trainable parameters; at every matched specificity between 0.40 and 0.70 it recovers 1–7 more true sites out of 320 than DTC-m6Am. The AUC-weighted voting keeps every tower’s contribution readable for any individual prediction. Analyses of the graph tower delimit its benefit to the relational aggregation of local backbone adjacency over sequence-derived node features: the edge-type ablation, the node-feature ablation, and a structure-permutation control agree that the specific RNAfold-predicted fold carries no attributable signal, and a probing analysis shows that per-base base-pairing status is largely recoverable from the sequence-derived RNA-FM embeddings (AUC = 0.72 vs. 0.65 from the raw sequence), so the fold annotation is substantially redundant with the semantic representation the ensemble already receives.

Conclusions

Combining semantic, sequential, and structural views of the same RNA sequence improves m6Am prediction beyond any single representation, and the ensemble’s voting weights make each prediction auditable without a post-hoc explainer. Whether the triple-tower pattern transfers to other RNA modification prediction tasks remains to be tested in future work.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AdenosineDeep LearningRNA, MessengerComputational BiologyRNA MethylationSemanticsAnimalsHumans

Substanzen

AdenosineRNA, MessengerN-methyladenosine

Autor:innen und Institutionen

  • School of Information Engineering, Jingdezhen Ceramic University, Jingdezhen, China.

ORCID-Profile: Kaifeng Xiong, Jianhua Jia

Zitieren

APA

Xiong, K., & Jia, J. (2026). TriTower-m6Am: A triple-tower heterogeneous deep learning architecture integrating semantic, sequential, and structural information for mRNA N6,2′-O-dimethyladenosine site prediction. PLOS Computational Biology, 22(11), e1014939. https://doi.org/10.1371/journal.pcbi.1014939

Vancouver

Xiong K, Jia J. TriTower-m6Am: A triple-tower heterogeneous deep learning architecture integrating semantic, sequential, and structural information for mRNA N6,2′-O-dimethyladenosine site prediction. PLOS Computational Biology. 2026;22(11):e1014939. doi:10.1371/journal.pcbi.1014939

BibTeX
@article{Xiong2026,
  author = {Xiong, Kaifeng and Jia, Jianhua},
  title = {TriTower-m6Am: A triple-tower heterogeneous deep learning architecture integrating semantic, sequential, and structural information for mRNA N6,2′-O-dimethyladenosine site prediction},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {11},
  pages = {e1014939},
  doi = {10.1371/journal.pcbi.1014939}
}
Kostenlos starten →