Tsukasa Fukunaga

BWR-finder detects interspersed repeats in large genomes using a BWT-based algorithm, outperforming existing tools in speed and memory usage.

LinearCapR computes per-nucleotide structural-context probabilities for RNA in linear time without span limits, outperforming existing methods on long-range structures and large RNAs.

MitoNGS improves fish metabarcoding analysis by enhancing reference databases and introducing a species group strategy to resolve ambiguous taxa.

CoLaML infers latent evolutionary modes from gene content heterogeneity across clades and gene families, outperforming previous models in fitting empirical datasets.

REPrise improves de novo interspersed repeat detection by incorporating inexact seeding and other techniques, outperforming RepeatScout in sensitivity for mutated repeats.

DeepRaccess predicts RNA accessibility using deep learning, achieving high correlation with Raccess and significant speed improvements.

The paper introduces IPM-based evaluation measures to reduce biases in phylogenetic profiling and shows they improve prediction accuracy.

This paper introduces LinAliFold and CentroidLinAliFold, fast RNA consensus secondary structure prediction tools that outperform existing methods in speed while maintaining accuracy.

This paper introduces a novel metric for hyperbolic phylogenetic tree embeddings and demonstrates its effectiveness in reconstructing evolutionary distances and predicting nearest-neighbor nodes.

This paper reviews the application of representation learning in biological sequence analysis, focusing on how embedding techniques transform sequences for functional and structural insights.

MotiMul discovers significant sequence motifs with multiple testing correction, improving statistical power and reducing type-1 error rates.

Mirage reconstructs gene-content evolutionary history using a realistic rate model, showing better fit to empirical data and frequent gains/losses in metabolic gene families.

RIblast predicts RNA-RNA interactions quickly and accurately, outperforming existing tools in speed while maintaining comparable accuracy.