A custom AI reviewer for batch effects and replicate structure

PerfectPaper’s batch effects agent reads a sequencing or array manuscript for the design failures that cannot be fixed after the fact: batches that align with the experimental condition, batch never entered into the model, technical replicates counted as biological, and replicate numbers too small to support the claim being made. Copy the brief below into a custom agent slot.

A confounded batch is the one problem in this list that no reanalysis can rescue. It is worth finding before a reviewer does, because the honest remedy is usually a limitation paragraph rather than a new figure.

When to use this agent

• Samples were collected, prepared or sequenced across more than one run, day or site
• Cases and controls were processed at different times
• Your replicates are cell culture passages, technical repeats, or repeated measures
• Your differential result rests on three or fewer samples per group
• A reviewer has previously asked what n refers to

The agent brief

Paste this into a custom agent. Suggested settings: work type statistics_methods, skill level expert, no tools required.

Name: Batch effects and replicate structure

You are reviewing a high-throughput experiment for confounding by batch and
for the validity of its replicate structure. Read the methods, the sample
table and any supplementary design description together.

Determine and report:

1. Batch structure. Identify every source of batch in the design: collection
   date, library preparation day, sequencing run, flow cell, plate, reagent
   lot, operator, site. If the manuscript does not describe how samples were
   grouped across these, report that the design cannot be assessed and say
   exactly which detail is missing.

2. Confounding. Determine whether any batch variable aligns with the
   experimental condition. If all cases were processed in one batch and all
   controls in another, the condition effect and the batch effect cannot be
   separated. State this plainly when it is true, and state that no
   computational correction resolves it.

3. Modelling. Determine whether batch was included as a covariate, used in an
   explicit correction step, or ignored. If a correction method is named,
   check whether the same variable is also the variable of interest, which
   would remove the effect being measured.

4. Replicate type. For every reported n, determine whether the units are
   biological replicates, technical replicates, or repeated measures of the
   same unit. Cell culture passages from one parental line, multiple libraries
   from one RNA extraction, and multiple lanes of one library are not
   biological replicates. Report every n where the type cannot be determined
   from the text.

5. Replicate number. Note where a differential or comparative claim rests on
   fewer than three biological replicates per group, and describe what the
   claim can and cannot support at that n.

6. Diagnostics. Determine whether the manuscript shows any assessment of batch
   structure, such as a clustering or dimension-reduction plot annotated by
   batch. Report its absence as a gap rather than as an error.

Do not recommend a specific correction method. Report the design as it stands,
what it can support, and what the author should state explicitly.

What this agent catches

How this differs from the built-in review

The standing team’s cohort accounting specialist reconciles sample numbers across the manuscript, and the statistical models specialist reads the analysis. Neither is briefed on what constitutes a batch in a sequencing workflow or on the distinction between a passage and a biological replicate — distinctions that are obvious to a working molecular biologist and invisible to a general statistical reader.

Pairs naturally with multiple testing and enrichment, since an uncorrected batch effect and an uncorrected p-value inflate the same result. Full set: AI peer review for genomics.

Review my manuscript

Frequently asked questions

What counts as a biological replicate in a sequencing experiment?

An independent biological unit subject to the same condition — a separate animal, a separate donor, or an independently derived culture. Multiple libraries from one RNA sample, or multiple passages of one cell line, are technical replicates and do not license the same generalisation.

Can batch correction fix a confounded design?

No. If every case was processed in one batch and every control in another, no method can separate the condition effect from the batch effect, because the two are the same variable. The remedy is to state the limitation or to repeat part of the experiment with mixed batches.

Is n=3 enough for RNA-seq?

It is the common convention and it supports modest claims about large effects. It does not support claims about small effects, subtle interactions, or generalisation across genetic backgrounds. The agent reports what an n supports rather than declaring a number acceptable.

Should I include batch as a covariate even if it looks small?

Generally yes, when batch is not confounded with the condition. This agent reports whether batch was modelled, not whether the modelling choice was optimal, because that decision depends on the design.