MycoCirc: a pan-fungal multi-modal pretrained model for fungal circRNA prediction from genome sequence

Exploring the fungal circular RNA (circRNA) landscape is bottlenecked by experimental and computational limits. Standard mRNA-seq systematically discards circRNAs due to their lack of poly(A) tails, while total RNA-seq remains too costly for large-scale screening. Existing computational models trained exclusively on human or plant sequences fail in fungi due to extreme genomic divergence across lineages, which range from intron-poor yeasts to intron-rich filamentous species. Consequently, no dedicated framework currently exists for de novo fungal circRNA prediction, leaving most non-model fungi unexplored. We present mycoCirc, the first end-to-end pan-fungal multi-modal pretrained model for fungal circRNA prediction. It integrates three data modalities, namely genome sequence, gene annotation and junction-level sequence, plus a species identifier, and optionally host-gene expression during fine-tuning, through a hierarchical fusion architecture that includes bidirectional cross-attention to capture donor–acceptor site interactions. Pretrained on 17 training strains spanning 14 fungal species and three taxonomic groups, mycoCirc was fine-tuned per group using leave-one-strain-out cross-validation. On held-out test species under Mode A (Genome + GTF, no RNA-seq), mycoCirc achieved an AUROC of 0.695–0.738, substantially outperforming JEDI (0.51–0.57) and CircPCBL both as published with plant-pretrained weights (0.45–0.57) and when retrained from scratch on fungal data (0.52–0.61). Cross-species evaluation on four independent fungi datasets demonstrated moderate but consistent cross-species transfer (AUROC 0.59–0.70 across all model–species combinations). Furthermore, its JunctionEncoder module enables back-splicing junction ranking with group-dependent accuracy (top-1 accuracy of 90.8% in ascomycete yeasts). To complement the framework, we constructed mycoCircAtlas, a database offering 406,902 prioritized gene–circRNA predictions (probability ≥ 0.85) across 768 fungal species from Ensembl Fungi Release 113. mycoCirc addresses a critical computational gap by providing systematic, RNA-seq-free prioritization of circRNA candidates with moderate, group-dependent accuracy across highly diverged fungal lineages without requiring RNA-seq data. Together with the mycoCircAtlas companion database, this framework empowers researchers to query precomputed predictions and design experimental validation primers across hundreds of non-model fungi without local model deployment.

Authors

Institutions

Publication Details

Journal
BMC Bioinformatics
Published
2026-11-16
DOI
https://doi.org/10.1186/s12859-026-06773-w
Primary Topic
Circular RNAs in diseases
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

MycoCirc: a pan-fungal multi-modal pretrained model for fungal circRNA prediction from genome sequence

Yueqi Jin, Ence Yang, Xueyan Hu
1 links
BMC Bioinformatics
Circular RNAs in diseases
article

MycoCirc: a pan-fungal multi-modal pretrained model for fungal circRNA prediction from genome sequence

Yueqi Jin, Ence Yang, Xueyan Hu
article en

Abstract

Exploring the fungal circular RNA (circRNA) landscape is bottlenecked by experimental and computational limits. Standard mRNA-seq systematically discards circRNAs due to their lack of poly(A) tails, while total RNA-seq remains too costly for large-scale screening. Existing computational models trained exclusively on human or plant sequences fail in fungi due to extreme genomic divergence across lineages, which range from intron-poor yeasts to intron-rich filamentous species. Consequently, no dedicated framework currently exists for de novo fungal circRNA prediction, leaving most non-model fungi unexplored. We present mycoCirc, the first end-to-end pan-fungal multi-modal pretrained model for fungal circRNA prediction. It integrates three data modalities, namely genome sequence, gene annotation and junction-level sequence, plus a species identifier, and optionally host-gene expression during fine-tuning, through a hierarchical fusion architecture that includes bidirectional cross-attention to capture donor–acceptor site interactions. Pretrained on 17 training strains spanning 14 fungal species and three taxonomic groups, mycoCirc was fine-tuned per group using leave-one-strain-out cross-validation. On held-out test species under Mode A (Genome + GTF, no RNA-seq), mycoCirc achieved an AUROC of 0.695–0.738, substantially outperforming JEDI (0.51–0.57) and CircPCBL both as published with plant-pretrained weights (0.45–0.57) and when retrained from scratch on fungal data (0.52–0.61). Cross-species evaluation on four independent fungi datasets demonstrated moderate but consistent cross-species transfer (AUROC 0.59–0.70 across all model–species combinations). Furthermore, its JunctionEncoder module enables back-splicing junction ranking with group-dependent accuracy (top-1 accuracy of 90.8% in ascomycete yeasts). To complement the framework, we constructed mycoCircAtlas, a database offering 406,902 prioritized gene–circRNA predictions (probability ≥ 0.85) across 768 fungal species from Ensembl Fungi Release 113. mycoCirc addresses a critical computational gap by providing systematic, RNA-seq-free prioritization of circRNA candidates with moderate, group-dependent accuracy across highly diverged fungal lineages without requiring RNA-seq data. Together with the mycoCircAtlas companion database, this framework empowers researchers to query precomputed predictions and design experimental validation primers across hundreds of non-model fungi without local model deployment.

BMC Bioinformatics
Peking University (CN)
National Natural Science Foundation of China
Circular RNAs in diseases
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon