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
Early feature extraction drives model performance in high-resolution chromatin accessibility prediction.
PMID 41526189 · PMC12951969 · Genome research · 2026 · 8 claims · 6 setups
Early feature extraction (via ConvNeXt V2 blocks), rather than downstream architecture type, is the primary determinant of prediction accuracy in high-resolution chromatin accessibility prediction.
-
Full-text index only
Atlas-guided discovery of transcription factors for T cell programming.
PMID 41639465 · PMC13017511 · Nature · 2026 · 8 claims · 8 setups
A multi-omics atlas (Taiji pipeline) integrating RNA-seq and ATAC-seq across nine CD8+ T cell states can predict TF activity and identify state-selective versus multi-state TFs
-
Full-text index only
Parameter-efficient fine-tuning enables scalable transfer of regulatory sequence models to novel contexts.
PMID 41618434 · PMC12930932 · Genome biology · 2026 · 8 claims · 7 setups
PEFT enables accurate transfer of Borzoi to new datasets while significantly reducing GPU memory and runtime compared to joint training or full fine-tuning
-
Full-text index only
Beyond blacklists: a critical assessment of exclusion set generation strategies and alternative approaches.
PMID 41826793 · PMC13020910 · Bioinformatics (Oxford, England) · 2026 · 8 claims · 8 setups
Pre-generated Blacklist exclusion sets were difficult to reproduce due to sensitivity to input BAM data, aligner choice, and read length