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).

• Retentive Network promotes efficient RNA language modeling of long sequences.

  PMID 41814064 · PMC13111708 · Communications biology · 2026 · 8 claims · 6 setups

  Full-text index only

  RNAret, a RetNet-based RNA language model with O(n) complexity, achieves training parallelism and low computational overhead while processing long RNA sequences

  million rnacentral mirtarraw rnastralign self-supervised t-sne mirna-mrna

• Candidate vaccine sequences to represent intra- and inter-clade HIV-1 variation.

  PMID 19812689 · PMC2753653 · PloS one · 2009 · 7 claims · 5 setups

  Full-text index only

  Natural CTL immunodominance toward variable proteome regions increases epitope mismatch with challenge strains and recapitulates the escape-driven CTL failure seen in natural infection, contributing to HIV vaccine failure

  hiv-1 polyclonally shannon cross-clade ctl

• A model-based approach to selection of tag SNPs.

  PMID 16776821 · PMC1525207 · BMC bioinformatics · 2006 · 7 claims · 5 setups

  Full-text index only

  The Li and Stephens hidden Markov model outperforms other tested models (simple Markov, two-state HMM, HMM-4D, greedy GR-1/GR-2) in description code-length, tag set information content, and prediction of tagged SNPs.

  hapmap encode enr112 tag cross-validated entropy tagged

• Prediction of catalytic residues using Support Vector Machine with selected protein sequence and structural properties.

  PMID 16790052 · PMC1534064 · BMC bioinformatics · 2006 · 8 claims · 7 setups

  Full-text index only

  The Sequential Minimal Optimization (SMO) SVM algorithm was the best-performing classifier among 26 WEKA classifiers for predicting catalytic residues

  benchmarking same pirsf pdb supervised wrapper sequence

• In silico segmentations of lentivirus envelope sequences.

  PMID 17376229 · PMC1847453 · BMC bioinformatics · 2007 · 8 claims · 8 setups

  Full-text index only

  C and V regions of lentivirus SU sequences have distinct statistical (oligonucleotide/amino-acid) compositions that HMMs can learn and use to delimit them.

  eiav hiv hmm-based hmm artificial

• Correlating novel variable and conserved motifs in the Hemagglutinin protein with significant biological functions.

  PMID 18681973 · PMC2553082 · Virology journal · 2008 · 8 claims · 6 setups

  Full-text index only

  14 MEME blocks were identified in the HA protein of H3N2 strains (1968-1999), with blocks 1, 2, 3, and 7 correlating with several biological functions

  h3n2 meme sequence entropy

• Combining evidence of preferential gene-tissue relationships from multiple sources.

  PMID 23950964 · PMC3741196 · PloS one · 2013 · 8 claims · 8 setups

  Has reproduction · 53

  A high-level integration approach combining three methods across four human microarray datasets, merged by consensus voting and a rule-based inner/total score, predicts preferentially expressed genes while reducing method- and study-specific bias.

  normal four microarray genes microarray computational bayes

• Biocomputing enters its adolescence.

  PMID 15960815 · PMC1175967 · Genome biology · 2005 · 8 claims · 8 setups

  Full-text index only

  A 'match augmentation' algorithm efficiently matches structural motifs by prioritizing functionally significant residues, enabling function prediction between evolutionarily unrelated proteins

  bank antibody-antigen yeast genome protein-protein empirical integrative