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).

• scMILD: Single-cell multiple instance learning for sample classification and associated subpopulation discovery.

  PMID 41907409 · PMC13019583 · iScience · 2026 · 8 claims · 8 setups

  Full-text index only

  scMILD identifies condition-associated cells using only sample-level labels via a dual-branch MIL architecture with a shared encoder

  simulated lupus covid-19 ulcerative simulated mixture scrna-seq

• Exploring phenotype-related single-cells through attention-enhanced representation learning.

  PMID 41566378 · PMC12906058 · Genome medicine · 2026 · 6 claims · 5 setups

  Full-text index only

  scPhase, an attention-based multiple instance learning (AMIL) framework with Mixture-of-Experts aggregation, predicts sample-level clinical phenotypes from raw scRNA-seq data and generalizes across patient cohorts

  pbmcs brain tumor scrna-seq

• Trajectory-guided dimensionality reduction for multi-sample single-cell RNA-seq data reveals biologically relevant sample-level heterogeneity.

  PMID 42024616 · PMC13188987 · Bioinformatics (Oxford, England) · 2026 · 8 claims · 6 setups

  Full-text index only

  MUSTARD is a trajectory-guided dimensionality reduction method for multi-sample, multi-condition scRNA-seq data that simultaneously captures gene expression variation along pseudotime and across samples

  simulated covid-su covid-stephenson tuberculosis data-driven scrna-seq pseudobulk-pca