EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ARTreeFormer: A faster attention-based autoregressive model for phylogenetic inference

Tianyu Xie iD, Yicong Mao, Cheng Zhang iD

PLOS Computational Biology · 2025

DOI: 10.1371/journal.pcbi.1013768 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2025. Verfasst von Tianyu Xie und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematical Sciences, Peking University, Beijing, China. Hauptthemen laut MEDLINE: Phylogeny, Computational Biology. Die Arbeit nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, National Natural Science Foundation of China, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Probabilistic modeling over the combinatorially large space of tree topologies remains a central challenge in phylogenetic inference. Previous approaches often necessitate pre-sampled tree topologies, limiting their modeling capability to a subset of the entire tree space. A recent advancement is ARTree, a deep autoregressive model that offers unrestricted distributions for tree topologies. However, its reliance on repetitive tree traversals and inefficient local message passing for computing topological node representations may hamper the scalability to large datasets. This paper proposes ARTreeFormer, a novel approach that harnesses fixed-point iteration and attention mechanisms to accelerate ARTree. By introducing a fixed-point iteration algorithm for computing the topological node embeddings, ARTreeFormer allows for fast vectorized computation, especially on CUDA devices. This, together with an attention-based global message passing scheme, significantly improves the computation speed of ARTree while maintaining great approximation performance. We demonstrate the effectiveness and efficiency of our method on a benchmark of challenging real data phylogenetic inference problems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhylogenyComputational BiologyAlgorithmsModels, StatisticalModels, GeneticComputer SimulationSoftware

Autor:innen und Institutionen

  • School of Mathematical Sciences, Peking University, Beijing, China.
  • School of Public Health, Peking University, Beijing, China.
  • Center for Statistical Science, Peking University, Beijing, China.

ORCID-Profile: Tianyu Xie, Cheng Zhang

Förderung

  • NIAID NIH HHS
  • National Natural Science Foundation of China
  • National Institutes of Health

Zitieren

APA

Xie, T., Mao, Y., & Zhang, C. (2025). ARTreeFormer: A faster attention-based autoregressive model for phylogenetic inference. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013768

Vancouver

Xie T, Mao Y, Zhang C. ARTreeFormer: A faster attention-based autoregressive model for phylogenetic inference. PLOS Computational Biology. 2025. doi:10.1371/journal.pcbi.1013768

BibTeX
@article{Xie2025,
  author = {Xie, Tianyu and Mao, Yicong and Zhang, Cheng},
  title = {ARTreeFormer: A faster attention-based autoregressive model for phylogenetic inference},
  journal = {PLOS Computational Biology},
  year = {2025},
  doi = {10.1371/journal.pcbi.1013768}
}
Kostenlos starten →