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).

• Early feature extraction drives model performance in high-resolution chromatin accessibility prediction.

  PMID 41526189 · PMC12951969 · Genome research · 2026 · 8 claims · 6 setups

  Full-text index only

  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.

  lines cancer sets gm12878 atac-seq peak input-shift

• Uncertainty-aware genomic deep learning with knowledge distillation.

  PMID 41523993 · PMC12779563 · NPJ artificial intelligence · 2026 · 7 claims · 6 setups

  Full-text index only

  DEGU distills an ensemble of teacher DNNs into a single student model by jointly predicting the ensemble mean and the variability (epistemic uncertainty) across ensemble predictions.

  drosophila k562 deepstarr starr-seq starr-seq-derived lentimpra base-resolution

• ChromBERT: A foundation model for learning interpretable representations for context-specific transcriptional regulatory networks.

  PMID 41592570 · PMC13069865 · Cell genomics · 2026 · 8 claims · 7 setups

  Full-text index only

  ChromBERT is pre-trained via masked reconstruction on the Cistrome-Human-6K dataset (6,391 cistromes, 991 transcription regulators) to learn genome-wide interaction syntax of transcription regulators

  lines chromosome embryonic transcription chip-seq chromhmm hi-c