batch-correction

Digital Cell Sorter (DCS): single cell RNA-seq analysis toolkit. Documentation:

Detecting and dissecting anomalous anatomic regions in spatial transcriptomics with STANDS

A similarity-assisted variational autoencoder (saVAE) is a new method that adopts similarity information in the framework of the VAE.

Batch Effect Correction framework for metagenomic data

Fast, out-of-core single-cell analysis in Python for RNA, ATAC, protein, and multi-omic data, scaling to 100M+ cells. Mount remote datasets, work within a memory budget, and trace every result through built-in provenance.

A Python tool for performing downstream analysis on Single-Cell RNA-seq datasets

Batman: Batch effect correction via minimum weight MAtchiNg

Detecting and subtyping anomalous single cells with M2ASDA

Adversarial autoencoder for bulk RNA‑seq batch effect correction that removes batch signal while preserving biological variation, outputting a corrected logCPM matrix and latent embeddings with optional supervised label preservation.

Regularized scVI for complex multiome single-cell/nucleus datasets: ambient RNA correction, dispersion prior, and batch-free decoder act as structural inductive biases that make large-architecture VAEs well-behaved without per-dataset tuning.

Code for "Slide-level batch structure limits histology-guided supervision of transcriptomic foundation models" (bioRxiv 2026). H&E-guided refinement of Geneformer, scGPT and CancerFoundation embeddings on 10x Visium spatial transcriptomics.

Extended data for the article "Finding stable clusterings of single-cell RNA-seq data"

Before/after PCA visualisation showing how batch correction removes technical variation while keeping biology.