Metraipolis › archive › dc_802e1138e7bc

VenusGenome: Genome-Aware Masked Autoencoding for Microbial Genome Representation Learning — arXiv:2611.05405

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05405
License (as archived)
CC0-1.0
Archived
2026-11-05T18:17:18.075Z
SHA-256 of the archived text
186af1cd01c642ddd66bb8848526461ab9cc2c7195d4711d3ecf5e9b3c729558
Stable URL of this page
https://metraipolis.com/documento/dc_802e1138e7bc

How to cite

VenusGenome: Genome-Aware Masked Autoencoding for Microbial Genome Representation Learning — arXiv:2611.05405 — arXiv (en), https://arxiv.org/abs/2611.05405 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_802e1138e7bc (Metraipolis archive dc_802e1138e7bc, sha256 186af1cd01c642ddd66bb8848526461ab9cc2c7195d4711d3ecf5e9b3c729558)
BibTeX
@misc{dc802e1138e7bc,
  title = {VenusGenome: Genome-Aware Masked Autoencoding for Microbial Genome Representation Learning — arXiv:2611.05405},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05405},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_802e1138e7bc; sha256 186af1cd01c642ddd66bb8848526461ab9cc2c7195d4711d3ecf5e9b3c729558},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05405. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Genomic-context models have shown that contextualizing protein embeddings can improve predictions of microbial function. We observe that a gene's protein embedding is partially predictable from the embeddings of neighboring genes in the genome, motivating high-ratio masking that requires reconstruction from sparser genomic context. Genomic modeling must also distinguish biological relationships from assembly conventions, since the ordering of separate contigs does not imply adjacency and strand labels depend on the reference orientation. We therefore introduce VenusGenome, a gene-resolution masked autoencoder that combines visible-only encoding with genome-aware attention incorporating contig boundaries, relative strand orientations, and gene positions. We pretrain this model on a curated corpus of over 1.7 million microbial genome assemblies from isolate and metagenomic sources, using frozen protein embeddings as gene-level inputs. Across genome-level phenotype prediction and gene-level tasks, the resulting frozen representations achieve the highest mean performance among the evaluated models on nine of eleven primary metrics. An exploratory gene-input perturbation analysis further links representation sensitivity to experimentally measured fitness defects. Ablations support the contribution of genome-aware attention and show the benefits of masked autoencoding over BERT-style masked modeling, with further gains from higher masking ratios.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Genomics (q-bio.GN) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.05405 — 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 2026-11-05T18:12:49.023Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).