Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2311.02401 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915872980860928 |
|---|---|
| author | Arias, Pablo Millan Sadjadi, Niousha Safari, Monireh Gong, ZeMing Wang, Austin T. Haurum, Joakim Bruslund Zarubiieva, Iuliia Steinke, Dirk Kari, Lila Chang, Angel X. Lowe, Scott C. Taylor, Graham W. |
| author_facet | Arias, Pablo Millan Sadjadi, Niousha Safari, Monireh Gong, ZeMing Wang, Austin T. Haurum, Joakim Bruslund Zarubiieva, Iuliia Steinke, Dirk Kari, Lila Chang, Angel X. Lowe, Scott C. Taylor, Graham W. |
| contents | In the global challenge of understanding and characterizing biodiversity, short species-specific genomic sequences known as DNA barcodes play a critical role, enabling fine-grained comparisons among organisms within the same kingdom of life. Although machine learning algorithms specifically designed for the analysis of DNA barcodes are becoming more popular, most existing methodologies rely on generic supervised training algorithms. We introduce BarcodeBERT, a family of models tailored to biodiversity analysis and trained exclusively on data from a reference library of 1.5M invertebrate DNA barcodes. We compared the performance of BarcodeBERT on taxonomic identification tasks against a spectrum of machine learning approaches including supervised training of classical neural architectures and fine-tuning of general DNA foundation models. Our self-supervised pretraining strategies on domain-specific data outperform fine-tuned foundation models, especially in identification tasks involving lower taxa such as genera and species. We also compared BarcodeBERT with BLAST, one of the most widely used bioinformatics tools for sequence searching, and found that our method matched BLAST's performance in species-level classification while being 55 times faster. Our analysis of masking and tokenization strategies also provides practical guidance for building customized DNA language models, emphasizing the importance of aligning model training strategies with dataset characteristics and domain knowledge. The code repository is available at https://github.com/bioscan-ml/BarcodeBERT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_02401 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | BarcodeBERT: Transformers for Biodiversity Analysis Arias, Pablo Millan Sadjadi, Niousha Safari, Monireh Gong, ZeMing Wang, Austin T. Haurum, Joakim Bruslund Zarubiieva, Iuliia Steinke, Dirk Kari, Lila Chang, Angel X. Lowe, Scott C. Taylor, Graham W. Machine Learning In the global challenge of understanding and characterizing biodiversity, short species-specific genomic sequences known as DNA barcodes play a critical role, enabling fine-grained comparisons among organisms within the same kingdom of life. Although machine learning algorithms specifically designed for the analysis of DNA barcodes are becoming more popular, most existing methodologies rely on generic supervised training algorithms. We introduce BarcodeBERT, a family of models tailored to biodiversity analysis and trained exclusively on data from a reference library of 1.5M invertebrate DNA barcodes. We compared the performance of BarcodeBERT on taxonomic identification tasks against a spectrum of machine learning approaches including supervised training of classical neural architectures and fine-tuning of general DNA foundation models. Our self-supervised pretraining strategies on domain-specific data outperform fine-tuned foundation models, especially in identification tasks involving lower taxa such as genera and species. We also compared BarcodeBERT with BLAST, one of the most widely used bioinformatics tools for sequence searching, and found that our method matched BLAST's performance in species-level classification while being 55 times faster. Our analysis of masking and tokenization strategies also provides practical guidance for building customized DNA language models, emphasizing the importance of aligning model training strategies with dataset characteristics and domain knowledge. The code repository is available at https://github.com/bioscan-ml/BarcodeBERT. |
| title | BarcodeBERT: Transformers for Biodiversity Analysis |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2311.02401 |