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).

• EPInformer: scalable and integrative prediction of gene expression from promoter-enhancer sequences with multimodal epigenomic profiles.

  PMID 41832145 · PMC13133354 · Nature communications · 2026 · 8 claims · 7 setups

  Full-text index only

  EPInformer outperforms existing gene expression prediction models (Xpresso, CREaTor, Seq-GraphReg, Enformer, Borzoi) in rigorous 12-fold cross-chromosome validation for both RNA-seq and CAGE expression prediction

  k562 lines likely cell-type-specific rna-seq cage abc

• An end-to-end generalizable deep learning framework to comprehensively analyze transcriptional regulation.

  PMID 41922356 · PMC13212934 · Nature communications · 2026 · 8 claims · 7 setups

  Full-text index only

  BioSeq2Seq is a transformer-based deep learning framework that predicts genome-wide transcriptional regulatory profiles at 128-bp resolution by jointly using RO-seq data and DNA sequence as tri-modal input

  k562 gm12878 imr-90 ro-seq chip-seq functional

• ChIP-seq guidelines and practices of the ENCODE and modENCODE consortia.

  PMID 22955991 · PMC3431496 · Genome research · 2012 · 8 claims · 8 setups

  Has reproduction · 74

  ENCODE/modENCODE define a set of working standards and guidelines for ChIP-seq covering antibody validation, experimental replication, sequencing depth, data/metadata reporting, and data quality assessment.

  small-genome nuclear whole-cell encode chip-seq chip-chip immunoblot

• 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

• ENCODE whole-genome data in the UCSC Genome Browser.

  PMID 19920125 · PMC2808953 · Nucleic acids research · 2010 · 7 claims · 8 setups

  Full-text index only

  The UCSC ENCODE Data Coordination Center serves as the primary repository for ENCODE experimental results, providing access via Genome Browser, Table Browser, and FTP download.

  lines chip-seq dnase-seq rna-seq

• Transcriptional landscape of repetitive elements in normal and cancer human cells.

  PMID 25012247 · PMC4122776 · BMC genomics · 2014 · 8 claims · 8 setups

  Has reproduction · 76

  RepEnrich, a computational method that uses all mapping reads (uniquely mapping plus multi-mapping reads assigned to repetitive element subfamily assemblies/pseudogenomes), quantifies genome-wide repetitive element enrichment

  chromosomes lines imr-90 prostate simulated pol chip-seq

• CircleBase V2: an eccDNA annotation platform across cancers and species.

  PMID 41273082 · PMC12807720 · Nucleic acids research · 2026 · 8 claims · 7 setups

  Full-text index only

  CircleBase V2 provides a 12-fold increase in human eccDNA data, comprising over 3.8 million entries from >300 cell types/tissues

  raw eccdna tissues cancer circle-seq motif gene