Experiments

Searchable full-text extractions: founding hypothesis, core claims, experimental setups, key results and statistics — pulled out of each paper as structure. Search a cell line, an assay or an entity (e.g. HUH7) and find every paper that worked with it. This corpus stands on its own: most entries carry no reproduction assessment (yet).

• Semi-parametric empirical bayes method for multiplet detection in snATAC-seq with probabilistic multi-omic integration.

  PMID 42054434 · PMC13148828 · PLoS computational biology · 2026 · 8 claims · 5 setups

  Full-text index only

  SEBULA models the singlet background directly from observed HCLC (high-coverage locus count) statistics using fragment-level snATAC-seq information, avoiding reliance on synthetic/artificial doublets.

  dogma-seq dogma-seq-derived seven snatac-seq q-q density

• A multi-modal diffusion model with dual-cross-attention for multi-omics data generation and translation.

  PMID 41980989 · PMC13253844 · Nature communications · 2026 · 8 claims · 7 setups

  Full-text index only

  scDiffusion-X is a multi-modal latent denoising diffusion probabilistic model for single-cell multi-omics data generation, translation, and interpretation.

  openproblem 10x babel miniatlas paired modality augmentation

• GAMMI: graph-guided contrastive and adversarial integration of single-cell and spatial multi-omics data.

  PMID 42108634 · PMC13158126 · Briefings in bioinformatics · 2026 · 6 claims · 5 setups

  Full-text index only

  GAMMI consistently outperforms state-of-the-art integration methods (GLUE, Harmony, MIDAS, scMoMaT) in biological conservation and batch correction across five mosaic single-cell multi-omics benchmarks

  pbmc postmortem gse138852 gammi-derived multi-omics scrna-seq differential

• Partially shared multi-modal embedding learns holistic representation of cell state.

  PMID 41741805 · PMC13021527 · Nature computational science · 2026 · 8 claims · 5 setups

  Full-text index only

  APOLLO automatically learns partial information sharing between multiple data modalities using an autoencoder with a partially overlapping latent space trained via latent optimization.

  simulated paired single simulation scrna-seq multiplexed