---
language:
- dna
tags:
- biology
- genomics
- transposable-elements
- dnabert
- bilstm
- sequence-classification
license: mit
---

# TE-GER — Superfamily Classification

Part of the **TE-GER** (Transposable Elements Genomic Entity Recognition) toolkit.

TE-GER superfamily classification model: fine-grained TE annotation across 21 superfamilies (Gypsy, Copia, Mutator, HAT, etc.) in genomic sequences. Architecture: DNABERT-2 + BiLSTM hybrid.

## Model Architecture

- **Base:** [DNABERT-2](https://huggingface.co/zhihan1996/DNABERT-2-117M) (DNA language model)
- **Head:** Bidirectional LSTM + Linear Classifier
- **Input:** 512 bp sliding windows over raw FASTA sequences
- **Task:** Sequence classification (token-level TE annotation)

## Usage

Use this model via the [TE-GER CLI](https://github.com/johanpina/te-ger):

```bash
python Te_annotator.py genome.fasta output.gff3 --level superfamilies
```

## Labels

- `0`: Background
- `1`: ACADEM-1
- `2`: BELPAO
- `3`: CACTA
- `4`: COPIA
- `5`: CR1
- `6`: DIRS
- `7`: ERV
- `8`: GYPSY
- `9`: HAT
- `10`: HELITRON
- `11`: I
- `12`: KOLOBOK
- `13`: L1
- `14`: LARD
- `15`: LINE
- `16`: LTR
- `17`: MULE
- `18`: P
- `19`: PIFHARBINGER
- `20`: PIGGYBAC
- `21`: PLE
- `22`: R1
- `23`: RTE
- `24`: SINE
- `25`: TC1MARINER
- `26`: TIR
- `27`: TRNA

## Citation

Developed by Johan S. Piña — 2025