pigauto: Fill in Missing Species Traits Using a Phylogenetic Tree

Imputes missing species trait data for comparative analyses by combining three sources of information: phylogenetic similarity (closely related species share similar traits), cross-trait correlations (observed traits inform missing ones), and optional environmental covariates (climate, habitat, geography). Handles continuous measurements, counts, binary variables, ordered categories, unordered categories, bounded proportions, zero-inflated counts, and compositional multi-proportion data in a single call. The default method is a phylogenetic baseline calibrated on held-out data; an optional graph neural network prediction is blended in through a per-trait gate that retains a baseline fallback. Covariates can inform the network and selected baseline paths. Provides conformal prediction intervals for continuous, count, ordinal, and proportion traits and an experimental analysis-aware multiple-imputation workflow for one missing continuous covariate in Gaussian linear, binomial-logit, and Gaussian random-intercept models, with Rubin pooling limited to fixed effects. Stochastic graph-network and posterior-tree completions are prediction diagnostics rather than validated inferential imputations. Bundled datasets include 300-species and 9,993-species bird-trait subsets with matching example phylogenetic trees. Rubin (1987, ISBN:978-0-471-08705-2); Vovk et al. (2005, ISBN:978-0-387-25061-8); Nakagawa and de Villemereuil (2019) <doi:10.1093/sysbio/syy089>.

Version:	0.11.1
Depends:	R (≥ 4.1)
Imports:	torch, ape, ggplot2, Matrix, rlang, stats, utils, graphics, grDevices, withr
Suggests:	testthat, covr, yaml, jsonlite, knitr, rmarkdown, pkgdown, RSpectra, Rphylopars, jomo, MCMCglmm, brms, glmmTMB, lme4, nlme, phangorn, phylolm, rgbif, smcfcs, terra, phytools
Published:	2026-11-09
DOI:	10.32614/CRAN.package.pigauto
Author:	Shinichi Nakagawa [aut, cre, cph], Daniel Noble [ctb]
Maintainer:	Shinichi Nakagawa <itchyshin at gmail.com>
BugReports:	https://github.com/itchyshin/pigauto/issues
License:	MIT + file LICENSE
URL:	https://itchyshin.github.io/pigauto/, https://github.com/itchyshin/pigauto
NeedsCompilation:	no
Citation:	pigauto citation info
Materials:	README, NEWS
CRAN checks:	pigauto results

Documentation:

Reference manual:

pigauto.html , pigauto.pdf

Vignettes:

Common pitfalls / FAQ (source, R code) Getting started with pigauto (source, R code) GNN architecture and the math behind pigauto (source, R code) Mixed-Type Trait Imputation (source, R code) Multiple imputation and downstream models (source, R code) Posterior-Tree Prediction Sensitivity (source, R code) Pigauto validation results and limits (source, R code) Visualising missingness and imputation (source, R code)

Downloads:

Package source:	pigauto_0.11.1.tar.gz
Windows binaries:	r-devel: pigauto_0.11.0.zip, r-release: pigauto_0.11.1.zip, r-oldrel: pigauto_0.11.1.zip
macOS binaries:	r-release (arm64): pigauto_0.11.1.tgz, r-oldrel (arm64): pigauto_0.11.1.tgz, r-release (x86_64): pigauto_0.11.1.tgz, r-oldrel (x86_64): pigauto_0.11.1.tgz
Old sources:	pigauto archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=pigauto to link to this page.