Path Signatures Enable Model-Free Mapping of RNA Modifications

2025-11-12

AI Summary

RNA modification detection is hindered by reverse transcription biases and the reliance of nanopore sequencing tools on labeled training data. To address these limitations, we propose an unsupervised, training-free anomaly detection method: raw nanopore direct RNA sequencing current signals are transformed via path signatures to extract modification-sensitive features; modification sites are then localized through nearest-neighbor comparison and statistical significance testing—enabling robust, cross-RNA-type and cross-chemistry detection. This work introduces path signatures to epitranscriptomics for the first time, eliminating dependence on prior knowledge of modifications or large-scale annotated datasets. The method accurately recapitulates multiple known modifications in *E. coli* rRNA and discovers a novel, qRT-PCR-validated 2′-O-methylation site in dengue virus sfRNA, demonstrating high sensitivity and cross-species applicability.

Technology Category

• Machine Learning: Bio-inspired Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Detecting chemical modifications on RNA molecules remains a key challenge in epitranscriptomics. Traditional reverse transcription-based sequencing methods introduce enzyme- and sequence-dependent biases and fragment RNA molecules, confounding the accurate mapping of modifications across the transcriptome. Nanopore direct RNA sequencing offers a powerful alternative by preserving native RNA molecules, enabling the detection of modifications at single-molecule resolution. However, current computational tools can identify only a limited subset of modification types within well-characterized sequence contexts for which ample training data exists. Here, we introduce a model-free computational method that reframes modification detection as an anomaly detection problem, requiring only canonical (unmodified) RNA reads without any other annotated data. For each nanopore read, our approach extracts robust, modification-sensitive features from the raw ionic current signal at a site using the signature transform, then computes an anomaly score by comparing the resulting feature vector to its nearest neighbors in an unmodified reference dataset. We convert anomaly scores into statistical p-values to enable anomaly detection at both individual read and site levels. Validation on densely-modified extit{E. coli} rRNA demonstrates that our approach detects known sites harboring diverse modification types, without prior training on these modifications. We further applyied this framework to dengue virus (DENV) transcripts and mammalian mRNAs. For DENV sfRNA, it led to revealing a novel 2'-O-methylated site, which we validate orthogonally by qRT-PCR assays. These results demonstrate that our model-free approach operates robustly across different types of RNAs and datasets generated with different nanopore sequencing chemistries.

Problem

• Detecting RNA modifications without enzyme-dependent biases in sequencing
• Overcoming limitations of current tools requiring extensive training data
• Developing model-free anomaly detection using canonical RNA reference data

Innovation

• Model-free anomaly detection for RNA modifications
• Signature transform extracts features from nanopore signals
• Statistical p-values enable modification detection without training