Downloads · 30 days
18
17% of all-time downloads
te-ger-superfamilies
Jspinad/te-ger-superfamilies
te-ger-superfamilies is a machine learning model from Jspinad. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Part of the TE-GER (Transposable Elements Genomic Entity Recognition) toolkit.
All-time downloads
109
Public
Repo size
483 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin483 MB · 100%
At a glance
- License
- mit
- Model type
- dnabert2_bilstm_hybrid
- Access
- Public
- Created
- May 12, 2026
- Updated
- May 12, 2026
- SHA
- 2c43918e
Model card
From the Hugging Face model README
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 (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:
python Te_annotator.py genome.fasta output.gff3 --level superfamilies
Labels
0: Background1: ACADEM-12: BELPAO3: CACTA4: COPIA5: CR16: DIRS7: ERV8: GYPSY9: HAT10: HELITRON11: I12: KOLOBOK13: L114: LARD15: LINE16: LTR17: MULE18: P19: PIFHARBINGER20: PIGGYBAC21: PLE22: R123: RTE24: SINE25: TC1MARINER26: TIR27: TRNA
Citation
Developed by Johan S. Piña — 2025
- Type
- dnabert2_bilstm_hybrid
- License
- mit
- Languages
- dna
- Created
- May 12, 2026
- Updated
- May 12, 2026