EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

sabinaHSBM : An R package for link prediction and network reconstruction using hierarchical stochastic block models

Herlander Lima, Jennifer Morales‐Barbero, Rubén G. Mateo, Ignacio Morales‐Castilla, Miguel Á. Rodríguez

Methods in Ecology and Evolution · 2026-08 · 17 (8) · 2285-2294

DOI: 10.1111/2041-210x.70365 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Methods in Ecology and Evolution, online erschienen am 09.07.2026. Verfasst von Herlander Lima und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Estatal de Investigación.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Network analysis is a powerful framework for investigating complex systems across disciplines, including ecology. However, ecological network data are often incomplete or error‐prone due to sampling limitations, detection failures and taxonomic uncertainty—leading to missing (false negative) and spurious (false positive) links that obscure structure and hinder inference. The hierarchical stochastic block model (HSBM), particularly in its degree‐corrected form, is among the most effective tools for reconstructing networks under such uncertainty. Despite its robustness, the primary implementation of HSBM in the Python‐based graph‐tool library has remained largely inaccessible to ecologists. Here, we introduce sabinaHSBM , the first R package that makes degree‐corrected HSBM broadly available through a user‐friendly, flexible workflow. By bridging a gap between advanced network modelling and widely used ecological analysis tools, sabinaHSBM facilitates network reconstruction and link prediction from binary data. The workflow involves three main steps: (1) preparing input data, (2) estimating posterior link probabilities and (3) reconstructing the network. The package supports detection of undocumented and spurious links, exploration of hierarchical structure and propagation of uncertainty throughout. Key features include cross‐validation, flexible thresholding, probabilistic evaluation metrics and two link prediction methods: estimating all link probabilities or identifying undocumented ones. We illustrate the package's functionality through a case study using a published global dataset of carnivore–parasite associations, showing that inferred groupings are phylogenetically clustered. To assess predictive accuracy, we examined the top 10 highest probability links identified by the model and found published evidence for eight, despite their absence from the original dataset. This highlights the model's ability to recover biologically meaningful but unrecorded interactions. By providing the first accessible R workflow for HSBM‐based network reconstruction, sabinaHSBM enables researchers to quantify uncertainty and recover overlooked interactions in ecological networks.

Förderung

  • Agencia Estatal de Investigación

Zitieren

APA

Lima, H., Morales‐Barbero, J., Mateo, R. G., Morales‐Castilla, I., & Rodríguez, M. Á. (2026). sabinaHSBM : An R package for link prediction and network reconstruction using hierarchical stochastic block models. Methods in Ecology and Evolution, 17(8), 2285-2294. https://doi.org/10.1111/2041-210x.70365

Vancouver

Lima H, Morales‐Barbero J, Mateo RG, Morales‐Castilla I, Rodríguez MÁ. sabinaHSBM : An R package for link prediction and network reconstruction using hierarchical stochastic block models. Methods in Ecology and Evolution. 2026;17(8):2285-2294. doi:10.1111/2041-210x.70365

BibTeX
@article{Lima2026,
  author = {Lima, Herlander and Morales‐Barbero, Jennifer and Mateo, Rubén G. and Morales‐Castilla, Ignacio and Rodríguez, Miguel Á.},
  title = {sabinaHSBM : An R package for link prediction and network reconstruction using hierarchical stochastic block models},
  journal = {Methods in Ecology and Evolution},
  year = {2026},
  volume = {17},
  number = {8},
  pages = {2285--2294},
  doi = {10.1111/2041-210x.70365}
}
Kostenlos starten →