BioTechniques News
Maddy Chapman
Original story from Pusan National University (Busan, South Korea).
A novel AI tool, circMAC, predicts where microRNAs (miRNAs) may bind within full-length circular RNA (circRNA) isoforms at nucleotide resolution. The framework could help researchers prioritize candidate binding regions for experimental studies of gene regulation.
circRNAs are loop-shaped molecules that can influence gene regulation through interactions with miRNAs. This matters because circRNAs can exist as different full-length isoforms, and their back-splice junction (BSJ) connects the two ends of the RNA. Treating a circRNA like a linear transcript can therefore overlook sequence information near this junction.
A research team led by Giltae Song, along with his colleagues from the School of Computer Science and Engineering at Pusan National University (Busan, South Korea), developed circMAC, an AI bioinformatics tool for predicting candidate miRNA binding sites on circRNAs. The framework takes a full-length circRNA isoform and a mature miRNA as inputs and predicts a binding probability for every circRNA nucleotide.
“The key advance is moving beyond asking whether a circRNA and miRNA interact to asking where that interaction is likely to occur,” commented Song.
To preserve the distinctive circular sequence, circMAC combines three complementary sequence-modeling approaches: attention captures information from across the circRNA, Mamba models sequential dependencies, and a one-dimensional convolutional neural network identifies short local sequence patterns associated with binding sites. Circular padding in the convolutional branch allows patterns spanning the BSJ to be considered continuously rather than interrupted at the sequence boundary. The model also uses cross-attention to incorporate information from the specific miRNA being analyzed, allowing each circRNA nucleotide to be evaluated in its miRNA-specific context. It also uses structure-aware pretraining based on base-pairing prediction.
How RNA can unlock the origins of life, secrets of extinct megafauna and impacts of aging
Explore four scintillating studies that perfectly illustrate the most exciting contemporary applications and investigations of RNA.
The researchers evaluated circMAC using full-length circRNA isoforms supported by AGO-CLIP binding-site annotations. The main pair-disjoint dataset contained 19,674 training pairs and 7838 test pairs, with 5.7% of nucleotide positions labeled as binding sites. At the 1000-nucleotide setting, circMAC with base-pairing prediction pretraining achieved an F1-macro score of 0.762, an AUROC of 0.902 and an AUPRC of 0.545, outperforming the evaluated pretrained RNA language models. It also showed the strongest overall performance among evaluated full-length models under isoform-disjoint and BSJ-disjoint tests.
“By retaining full-length sequence context and conditioning predictions on the specific miRNA, the framework can provide more focused candidate regions for follow-up experiments,” explained Song.
circMAC can help computational biology researchers identify potential miRNA binding regions on circRNA at nucleotide resolution, enabling more targeted experimental validation. In an illustrative case, it concentrated prediction signals near an annotated BSJ region of circCDYL2. However, these predictions are intended to prioritize candidate binding regions rather than establish functional interactions or clinical applications.
Overall, circMAC provides a machine-learning framework for prioritizing candidate circRNA–miRNA binding regions. By combining RNA sequence modeling, circular sequence continuity and miRNA-specific conditioning, it could support more precise studies of RNA-mediated regulation. Further validation using independent datasets and experiments is needed before broader biological or clinical applications can be considered.
This article has been republished from the following materials. Material may have been edited for length and house style. For further information, please contact the cited source. Our press release publishing policy can be accessed here.
The post New AI tool maps microRNA binding sites on circular RNAs appeared first on BioTechniques.
Powered by WPeMatico