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).
-
Full-text index only
Systematic background selection with BasCoD enhances contrastive dimension reduction in single cell genomics.
PMID 41844632 · PMC13144610 · Nature communications · 2026 · 8 claims · 7 setups
BasCoD is a statistical testing framework using spectral subspace inclusion theory to evaluate whether a candidate background dataset is suitable for contrastive dimension reduction of a target dataset
-
Full-text index only
FineST: contrastive learning integrates histology and spatial transcriptomics for nuclei-resolved ligand-receptor analysis.
PMID 41839892 · PMC13201544 · Nature communications · 2026 · 8 claims · 6 setups
FineST, a bimodal contrastive learning model integrating histology (Virchow2 ViT features) and spatial gene expression, enables nuclei-resolved high-resolution RNA imputation.
-
Full-text index only
Multimodal learning reveals plants' hidden sensory integration logic.
PMID 41714925 · PMC13032346 · BMC genomics · 2026 · 8 claims · 8 setups
CoMM-BIP (Contrastive Multi-Modal learning with Biologically Informed Priors) integrates transcriptomic, metabolomic, and phenomic data using pathway-guided attention, information-theoretic disentanglement, and domain-aware augmentations
-
Full-text index only
sCellST predicts single-cell gene expression from H& E images.
PMID 41513659 · PMC12858858 · Nature communications · 2026 · 7 claims · 6 setups
sCellST is a weakly supervised (Multiple Instance Learning) deep learning framework that predicts single-cell gene expression from H&E images alone, trained using paired spatial transcriptomics (Visium) and H&E slides