Scholarlink

Background <p>N6-methyladenosine (m<sup>6</sup>A), the most abundant post-transcriptional modification in eukaryotic mRNA, plays pivotal roles in diverse biological processes. Dysregulation of m<sup>6</sup>A levels has been implicated in numerous human diseases, particularly cancer. Although several computational tools exist for predicting putative m<sup>6</sup>A sites, none have specifically addressed the identification of cancer-associated (or pro-cancer) m<sup>6</sup>A residues at single-base resolution.</p> Methods <p>To address this gap, we developed m6A-CAPred, a computational framework for accurate prediction of cancer-associated m<sup>6</sup>A sites at base resolution. Our model was trained on a comprehensive dataset comprising experimentally validated m<sup>6</sup>A sites from 25 cancer cell lines and 23 normal tissue samples, based on a hybrid feature extraction approach integrating both sequence- and curated genome-derived features.</p> Results <p>Initial analysis revealed that sequence information alone only provided limited predictive performance. However, by incorporating genomic context features, m6A-CAPred significantly achieved improvement in prediction performance (an average AUROC of 0.885 tested on independent dataset), successfully capturing the distinct characteristics between cancer-associated and normal m<sup>6</sup>A sites. We then applied m6A-CAPred for transcriptome-wide prediction to screen for potential cancer-associated m<sup>6</sup>A sites. The somatic variants derived from 33 types of TCGA cancer projects were extracted for independent validation, and the results showed that cancer-somatic SNP density clearly differentiated the predicted pro-cancer and normal m<sup>6</sup>A sites, further confirming the model's biological relevance. Additionally, the cancer-associated m<sup>6</sup>A sites showed significant enrichment in functional important biological processes and cancer-related pathways.</p> Conclusions <p>Overall, we hope that m6A-CAPred will serve as a valuable resource for cancer epitranscriptome research, with potential applications in cancer biomarker discovery. The web server implementing our model is freely available at <a href="http://www.rnamd.org/m6A-CAPred">www.rnamd.org/m6A-CAPred</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Domain-derived knowledge enabled machine learning and functional characterization of cancer-associated RNA methylation sites

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月13日

查看全文
  • Zeyu Chen,
  • Yuqi Liu,
  • Jia Meng,
  • Jiaming Huang,
  • Xuan Wang,
  • Xiangyu Yin,
  • Wei Zhong,
  • Gang Tu,
  • Yongshuang Xiao

摘要

Background

N6-methyladenosine (m6A), the most abundant post-transcriptional modification in eukaryotic mRNA, plays pivotal roles in diverse biological processes. Dysregulation of m6A levels has been implicated in numerous human diseases, particularly cancer. Although several computational tools exist for predicting putative m6A sites, none have specifically addressed the identification of cancer-associated (or pro-cancer) m6A residues at single-base resolution.

Methods

To address this gap, we developed m6A-CAPred, a computational framework for accurate prediction of cancer-associated m6A sites at base resolution. Our model was trained on a comprehensive dataset comprising experimentally validated m6A sites from 25 cancer cell lines and 23 normal tissue samples, based on a hybrid feature extraction approach integrating both sequence- and curated genome-derived features.

Results

Initial analysis revealed that sequence information alone only provided limited predictive performance. However, by incorporating genomic context features, m6A-CAPred significantly achieved improvement in prediction performance (an average AUROC of 0.885 tested on independent dataset), successfully capturing the distinct characteristics between cancer-associated and normal m6A sites. We then applied m6A-CAPred for transcriptome-wide prediction to screen for potential cancer-associated m6A sites. The somatic variants derived from 33 types of TCGA cancer projects were extracted for independent validation, and the results showed that cancer-somatic SNP density clearly differentiated the predicted pro-cancer and normal m6A sites, further confirming the model's biological relevance. Additionally, the cancer-associated m6A sites showed significant enrichment in functional important biological processes and cancer-related pathways.

Conclusions

Overall, we hope that m6A-CAPred will serve as a valuable resource for cancer epitranscriptome research, with potential applications in cancer biomarker discovery. The web server implementing our model is freely available at www.rnamd.org/m6A-CAPred.