Metabolomics Navigator Tools, strategies & workflow guidance for metabolomics

Normalization and batch correction

RALPS

An R-based regularized adversarial-learning method for harmonizing metabolomics batches using shared reference samples while preserving biological similarity structure.

Platform-independentUntargeted metabolomicsR packageOpen source
Access toolSuggest an update

Overview

RALPS harmonizes batches of quantified metabolomics data using regularized adversarial learning and shared reference measurements. It targets inter-batch variation after each batch has first been normalized for within-batch problems.

What can this tool do?

Batch-effect correction

Common uses

  • Harmonize multiple metabolomics batches using embedded shared reference samples.

Scientific fit

Primary function

Normalization and batch correction

Other functions

Machine learning and prediction

Analysis types

Untargeted metabolomics

Data compatibility

Inputs

Feature or peak table, Sample metadata

Outputs

Feature or peak table

Input formats

Abundance CSV, batch/group/benchmark CSV and configuration CSV

Output formats

Normalized abundance CSV, model checkpoints and evaluation plots

Scope and considerations

Designed for

  • An R-based regularized adversarial-learning method for harmonizing metabolomics batches using shared reference samples while preserving biological similarity structure.

Not designed for

  • Replacing the preceding within-batch drift correction or inferring batch effects without the required reference information.

Important requirements

  • The documented Python/PyTorch environment, an abundance CSV, batch/replicate metadata and configuration file; reference replicate arrangements must connect the batches being harmonized.

Considerations

  • Training and parameter selection affect the reconstructed data. Check reference-sample agreement, variance and biological signal preservation; distinguish regularization replicates from evaluation benchmarks.

Access and documentation

Primary accessDocumentation

GPL-3.0 source distribution. External datasets, dependent packages and any hosted routes retain their own terms; software operation was not tested.

License: GPL-3.0

Evidence and review

Enveda intake rechecked against official repository documentation, package/license metadata and primary publication identity on 2026-10-27. Editorial source review only; no software execution or independent benchmark. See docs/enveda-expansion-review-2026-10-27-batch2.md.

Core publications

Resource papers, direct updates and tool-specific methods. Selection policy.

  1. Regularized adversarial learning for normalization of multi-batch untargeted metabolomics data. Bioinformatics (2023). doi:10.1093/bioinformatics/btad096

Related tools

CordBatSimilar function · An R package implementing concordance-based batch-effect correction for large-scale metabolomics studies.hRUVSimilar function · An R package for hierarchical normalization of multi-batch metabolomics studies using intra-batch and inter-batch replicate information to estimate and remove unwanted variation.MultiBaCSimilar function · A Bioconductor R package for batch-effect correction in single-omics and multi-omics datasets, including metabolomics.NOREVASimilar function · Normalize metabolomics data and compare the performance of alternative normalization strategies.

Entry history

Changes to this catalogue entry, not the tool's software release history. Acceptance and editorial review are separate.

  1. 2026-10-27 · First committed entry

    Add 24 reviewed Enveda tools in a separate second batch

    View change · Entry at this revision

Full GitHub history