Protocol: PERMANOVA on a community distance matrix

Tier: D (cMD paper) · Type: atomic · Category: Statistical Analysis

What

Test whether community composition differs by a grouping variable, by permutational multivariate analysis of variance on a distance matrix — partitioning distance-matrix variation among sources and assessing significance by permutation.

Why it matters

Split from ANOSIM, per review. They are different tests by different authors testing different nulls; one atomic protocol cannot carry both citations. Taking a distance matrix as input rather than an abundance table also removes the third bundled method: Aitchison distance is just Euclidean distance on CLR output, so it comes from the transformation protocol and this one stays agnostic about how the distances were made.

PERMANOVA is the standard first-look community test and is routinely over-read. A protocol can state plainly what a significant result does and does not mean.

Source material

• Anderson (2001), Austral Ecology — "A new method for non-parametric multivariate analysis of variance". VERIFY the DOI before merging
• Applied in: 10.1038/s41467-025-66888-1 — Aitchison distances, 999 permutations
• waldronlab/curatedMetagenomicDataAnalyses — vignettes/explorecirrhosis.Rmd

Scope

In: the required input (a distance matrix plus a sample-level design); the pseudo-F statistic and the permutation scheme; stratification / restricted permutation for multi-dataset designs, without which study effects are tested rather than the variable of interest; 999 permutations as a default and the p-value granularity that implies; a dispersion check as a required companion step, since PERMANOVA responds to differences in within-group spread as well as in group centroids; how much variance explained is reported alongside the p-value.

Out: computing distances; ANOSIM; ordination plotting.

Frontmatter starting point

type: "atomic"
category: "Statistical Analysis"
citation: ""   # Anderson 2001, Austral Ecology — candidate 10.1111/j.1442-9993.2001.01070.x. VERIFY.
tags: [permanova, beta-diversity, permutation, multivariate, distance-matrix]

Acceptance criteria

• Takes a distance matrix as input, with no transformation assumed
• Requires a dispersion check alongside the location test
• Specifies permutation stratification for multi-dataset designs
• ## Notes states the dispersion-versus-location caveat explicitly

---

Cite the method's origin, not its users

PROTOCOL_STANDARD.md is explicit: an atomic protocol carries "strictly 1 citation... corresponding
to the primary literature where the method was originally published." Find the paper that proposed
the method. Do not cite a paper that merely applied it — including the BugSigDB and curatedMetagenomicData
papers, which are the source of the analysis these protocols were extracted from but almost never the
source of the method.

Tracing a method back to its first publication is real work, and it is part of the task, not a
formality. Three things to expect:

• Candidate DOIs in this issue are leads, not answers. Anything marked VERIFY has not been checked.
• Some methods predate modern citation practice or have no single identifiable origin. If that is
  genuinely the case, say so in the pull request rather than reaching for a convenient recent paper.
  Raise it as an issue in waldronlab/agent-protocol-standard — the standard may need a way to express
  "classical method, no primary source".
• If you cannot name one paper that proposed everything the protocol does, it is more than one
  protocol. That test has now split four protocols out of this batch: enrichment into three methods,
  filtering from transformation, LODO from random forest, and PERMANOVA from ANOSIM.

Where the lab's own paper genuinely did propose the method — the oral-to-gut score, and LODO
cross-validation in Pasolli et al. 2016 — citing it is correct. That is the exception, not the pattern.

Before you start

Read CONTRIBUTING.md and
PROTOCOL_STANDARD.md.
The format is defined in the standard repo, not this one. Protocols are prose, not code: they say what to do
and why, precisely enough that two people — or two agents, in two languages — get the same answer. The existing
independent-filtering-variance
protocol is the model to imitate for tone and level of detail.

Validate locally before opening the PR:

git clone https://github.com/waldronlab/agent-protocol-standard.git
Rscript agent-protocol-standard/scripts/validate-protocol.R protocols

Read CONTRIBUTING.md, PROTOCOL_STANDARD.md, and protocols/independent-filtering-variance/protocol.md for format and tone. Verify the primary Anderson (2001) citation, then draft the PERMANOVA protocol from the supplied frontmatter and scope, including restricted permutations, dispersion checks, and variance reporting. Run the provided Rscript validation command; done means all acceptance criteria pass and the citation is verified.