Matías Rodriguez

TEclass2 classifies transposable elements using a Transformer-based deep learning model, offering reliable results and a user-friendly tool for TE annotation.

The paper presents the first de novo repeat discovery and annotation of a complete human reference genome, identifying novel satellite arrays and characterizing new classes of complex repeats.

The paper evaluates de novo transposon detection tools using simulated and curated data, finding that model-based tools outperform k-mer counting methods but still struggle with fragmented or small TEs.

The paper uses long-read sequencing to improve genome assembly and annotation of Trypanosoma cruzi, revealing new repetitive sequences and gene structures.