Metraipolis › archive › dc_41b8acf882eb

BarcodeMAE+: Rethinking Masked Pretraining and Global Representations for DNA Barcode Foundation Models — arXiv:2609.35877

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35877
License (as archived)
CC0-1.0
Archived
2026-10-07T17:32:25.552Z
SHA-256 of the archived text
4504d8a2305f30b7d2b0b05debc2245cf43f57b2d2a1be31464fbb2669ec7728
Stable URL of this page
https://metraipolis.com/documento/dc_41b8acf882eb

How to cite

BarcodeMAE+: Rethinking Masked Pretraining and Global Representations for DNA Barcode Foundation Models — arXiv:2609.35877 — arXiv (en), https://arxiv.org/abs/2609.35877 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_41b8acf882eb (Metraipolis archive dc_41b8acf882eb, sha256 4504d8a2305f30b7d2b0b05debc2245cf43f57b2d2a1be31464fbb2669ec7728)
BibTeX
@misc{dc41b8acf882eb,
  title = {BarcodeMAE+: Rethinking Masked Pretraining and Global Representations for DNA Barcode Foundation Models — arXiv:2609.35877},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35877},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_41b8acf882eb; sha256 4504d8a2305f30b7d2b0b05debc2245cf43f57b2d2a1be31464fbb2669ec7728},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35877. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many DNA foundation models are pretrained by masking parts of a sequence and asking the model to reconstruct them. Standard masked pretraining exposes the encoder to special [MASK] tokens that are absent at inference, creating a mismatch between training and downstream use. The role of an explicit global sequence representation such as a [CLS] token and how it should be trained also remain poorly understood for DNA barcodes. We introduce BarcodeMAE+ and study model architecture, global [CLS] representation, and auxiliary pretraining objectives across arthropod COI (BIOSCAN-5M) and fungal ITS (UNITE+INSD) barcodes. Across both barcode regions, the encoder-decoder MAE-LM architecture outperforms its matched encoder-only counterpart in nearly all evaluated configurations, supporting MAE-LM as an effective architectural design for DNA barcode foundation models. A trained global [CLS] representation provides substantial additional gains: on BIOSCAN-5M, [CLS] accuracy increases from 47.53% without an auxiliary objective to 80.65% with cross-entropy genus classification. The best auxiliary objective is region-dependent: cross-entropy performs best on BIOSCAN-5M, whereas pairwise same-genus classification performs best on UNITE+INSD, reaching 73.19% on Yeast and 63.07% on Filamentous Fungi. BarcodeMAE+ outperforms published DNA foundation model baselines on BIOSCAN-5M and achieves the highest Yeast accuracy among the evaluated UNITE+INSD baselines using frozen encoder representations. Similarity-weighted softmax KNN voting further stabilizes accuracy as neighbourhood size increases. Overall, encoder-decoder masked pretraining and an explicitly trained global representation are strong design choices for DNA barcode foundation models, while the optimal objective for learning that representation depends on the biological domain.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Genomics (q-bio.GN) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35877 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:59:48.453Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).