DeepTE | Neural network classification of TE

DeepTE is a Python library typically used in Telecommunications, Media, Advertising, Marketing applications. DeepTE has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. You can download it from GitHub.

Transposable elements (TEs) classification is an essential step decoding their roles in a genome. With reference genomes from non-model species available, it has begun to overstep efforts to annotate TEs, and more tools are needed to efficiently handle the emerged sequence information. We developed a novel tool, DeepTE, which classifies unknown TEs on basis of convolutional neural network. DeepTE utilized co-occurrence of k-mers towards TE sequences as input vector, and seven k-mer size was testified to be suitable for the classification. Eight models have been trained for different TE classification purposes. DeepTE applied domains from TEs to correct false classification. An additional model was also trained to distinguish between non-TEs and TEs targeting plant species. Given exclusive TEs of different species type, it can therefore classify seven orders, and 11-24 superframilies towards Plants, Metazoans, Fungi, and Others. This tool successfully leverages convolutional neural network to TE classification, assisting to precisely identify and annotate TEs in a new sequenced eukaryotic genome.