DNABERT-S: LEARNING SPECIES-AWARE DNA EMBEDDING WITH GENOME FOUNDATION MODELS

DNABERT-S is a genome foundation model designed to generate effective, species-aware DNA embeddings. The model uses a combination of Manifold Instance Mixup and Curriculum Contrastive Learning to learn species-aware embeddings.

Data and Resources

Cite this as

Zhihan Zhou, Weimin Wu, Harrison Ho, Jiayi Wang, Lizhen Shi, Ramana V Davuluri, Zhong Wang, Han Liu (2024). Dataset: DNABERT-S: LEARNING SPECIES-AWARE DNA EMBEDDING WITH GENOME FOUNDATION MODELS. https://doi.org/10.57702/euv7e7ls

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2402.08777
Author Zhihan Zhou
More Authors
Weimin Wu
Harrison Ho
Jiayi Wang
Lizhen Shi
Ramana V Davuluri
Zhong Wang
Han Liu
Homepage https://github.com/Zhihan1996/DNABERT_S