NeuralTE: an accurate approach for Transposable Element superfamily classification with multi-feature fusion

Transposable Elements (TEs), which make up a significant portion of the genomes in most eukaryotic organisms, can be classified into various superfamilies based on their sequence and structural characteristics. Accurate TE classification at the superfamily level can reveal their distribution and abundance across various genomes, providing deeper insights into species variation and evolution. Recent advancements in third-generation sequencing technologies have made a large number of genomes from non-model species available. However, existing TE classification methods suffer from several limitations, including the necessity to train multiple hierarchical classification models, the incapacity to perform classification at the superfamily level, and deficiencies in both accuracy and robustness. Therefore, there is an urgent need for an accurate TE classification method to improve genome annotation. In this study, we develop NeuralTE, a deep learning method designed to classify TEs at the superfamily level. To achieve accurate TE classification, we identify various structural features of TEs and use different combinations of k-mers for terminal repeats and internal sequences to uncover distinct patterns. Evaluation on all TEs from Repbase shows that NeuralTE outperforms existing machine learning and homology-based methods in classifying TEs. Testing on TEs from novel species highlights the superior performance of NeuralTE compared to existing methods. We also conduct TE annotation experiments on rice using different classification tools, and the results show that NeuralTE achieves annotations nearly identical to the gold standard, highlighting its robustness and accuracy in classifying TEs. NeuralTE is publicly available at https://github.com/CSU-KangHu/NeuralTE.