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
Discovery of protein-protein interactions using a combination of linguistic, statistical and graphical information.
PMID 15941473 · PMC1164402 · BMC bioinformatics · 2005 · 8 claims · 5 setups
A combined linguistic+statistical+rule-based method achieves precision 0.61 and recall 0.97 (f=0.74) detecting yeast protein-protein interactions across 12,300 Medline abstracts.
-
Full-text index only
Exogean: a framework for annotating protein-coding genes in eukaryotic genomic DNA.
PMID 16925841 · PMC1810556 · Genome biology · 2006 · 8 claims · 5 setups
Exogean is a framework using directed acyclic coloured multigraphs (DACMs) to represent biological objects (mRNA, ESTs, protein alignments, exons) and iteratively combine them into complex protein-coding transcript models.
-
Has reproduction · 64
GeMI: interactive interface for transformer-based Genomic Metadata Integration.
PMID 35657113 · PMC9216561 · Database : the journal of biological databases and curation · 2022 · 8 claims · 5 setups
GeMI is a web tool that uses a fine-tuned GPT2 model to extract 15 structured key-value attributes from free-text GEO sample metadata.
-
Has reproduction · 69
A comparison across non-model animals suggests an optimal sequencing depth for de novo transcriptome assembly.
PMID 23496952 · PMC3655071 · BMC genomics · 2013 · 8 claims · 8 setups
Representative de novo transcriptome assemblies are generated with as few as ~20 million reads for single-tissue samples and ~30 million reads for whole animals at the mRNA-coverage level.