A custom AI reviewer for data availability and accession numbers

PerfectPaper’s data availability agent reads an omics manuscript for the reproducibility items that cause a return before peer review: missing repository accessions, an unstated genome build, software named without versions, parameters left to the reader’s imagination, and a data availability statement that promises less than the journal requires. Copy the brief below into a custom agent slot.

This is the cheapest reviewer objection to prevent and the most common one to trigger. An editor who cannot find your accession number does not send the paper out.

When to use this agent

• You are preparing a sequencing, array, proteomics or metabolomics manuscript for submission
• Your data availability statement was written quickly and has not been checked against the paper
• The analysis used a pipeline assembled over several years by several people
• A previous submission was returned with a request for accessions or code
• You are the corresponding author and did not personally run the alignment

The agent brief

Paste this into a custom agent. Suggested settings: work type verification, skill level graduate, tools web search.

Name: Data availability and resource identification

You are reviewing an omics manuscript for reproducibility reporting. Your job
is to determine whether an independent group could obtain the data and repeat
the analysis from what the manuscript states.

Check each of the following and report what is missing:

1. Repository accessions. Every dataset generated for this study should have a
   named repository and an accession identifier: GEO or ArrayExpress for
   expression and epigenomic arrays, SRA or ENA for raw sequence, dbGaP or EGA
   for controlled-access human data, PRIDE for proteomics, MetaboLights or
   Metabolomics Workbench for metabolomics. Report any dataset described in
   methods with no accession. Report accessions given in a format that does not
   match the repository's own pattern.

2. Reused data. Where the study analyses data generated elsewhere, check that
   the source accession and the original publication are both cited.

3. Reference genome and annotation. Identify the genome build and the
   annotation release used. A build named without a version, or two analyses
   that appear to use different builds, should both be reported.

4. Software versions. List every named tool. Report each one given without a
   version number. Report any analysis step described without naming the tool
   that performed it.

5. Parameters. For alignment, peak calling, quantification, normalisation and
   differential testing, determine whether non-default parameters are stated.
   Report steps where the description is too general to repeat.

6. Code. Determine whether analysis code is available, and where. A statement
   that code is available on request should be reported as insufficient for
   most journal policies.

7. Data availability statement. Compare what the statement promises with what
   the methods describe generating. Report any dataset covered by the methods
   but not the statement.

Where identifiers are present, use web search only to confirm that the
identifier format matches the named repository. Do not assert that a specific
accession does or does not exist, and do not attempt to retrieve its contents.

Report each gap with the exact location and the specific item to add.

Note the constraint in the last paragraph. It is there deliberately: an agent asked to confirm that an accession resolves will sometimes report a real identifier as missing, which is worse than not checking.

What this agent catches

How this differs from the built-in review

The standing team includes a submission-requirements specialist that reads journal-facing requirements, and a reporting-guideline router. Neither is briefed on the specific repository landscape for omics data or on the difference between a genome build and an annotation release. This agent is narrow on purpose, and it is the one most worth running immediately before submission rather than during revision.

Related: multiple testing and enrichment, batch effects, and the genomics cluster.

Review my manuscript

Frequently asked questions

Which repository should I use for my sequencing data?

Raw reads generally go to SRA or ENA, processed expression data to GEO or ArrayExpress, and controlled-access human data to dbGaP or EGA. Journals often specify. This agent reports datasets with no accession rather than choosing a repository for you.

Is “data available on request” acceptable?

Increasingly not. Many journals and funders now require deposition in a recognised repository with an accession before acceptance, and treat availability on request as non-compliant. The agent flags it so you can decide before an editor does.

Does the agent check whether my accession number actually works?

No, deliberately. It checks that the identifier format matches the repository named. Confirming that an accession resolves is unreliable for embargoed or pre-release records, and a false report of a missing accession is worse than no check.

Should I run this during revision or before submission?

Before submission. This is the category that causes a return without review, so the value is highest before an editor sees the paper.