technion-cs-nlp/BiologicalTokenizers

Effect of tokenization on transformers for biological sequence

28
/ 100
Experimental

This project helps bioinformaticians and computational biologists improve the accuracy and efficiency of deep learning models when working with long biological sequences like DNA or protein data. It takes raw biological sequences as input and outputs optimized 'tokenized' versions, significantly reducing sequence length while boosting model performance. This is for researchers and scientists who use transformer models for tasks like protein function prediction or sequence alignment.

Use this if you are building or training deep learning models on biological sequence data and need to optimize input representation for better accuracy and faster processing.

Not ideal if you are not working with deep learning models, particularly transformer architectures, or if your biological sequence analysis doesn't involve complex prediction or classification tasks.

bioinformatics genomics protein-function-prediction sequence-alignment computational-biology
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

22

Forks

Language

Python

License

MIT

Last pushed

Dec 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/technion-cs-nlp/BiologicalTokenizers"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.