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).

• 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

• Machine learning reveals microbial interactions driving plastic degradation across plastisphere environments.

  PMID 41657981 · PMC12876002 · Frontiers in microbiology · 2025 · 6 claims · 7 setups

  Has reproduction · 87

  Wastewater plastispheres harbor the most diverse and compositionally even microbial communities among the three habitats.

  ocean wastewater surface plastisphere 16s alpha beta

• Predicting deleterious nsSNPs: an analysis of sequence and structural attributes.

  PMID 16630345 · PMC1489951 · BMC bioinformatics · 2006 · 8 claims · 7 setups

  Full-text index only

  Sequence conservation (PSIC score difference) at the nsSNP position is the single most useful attribute for predicting deleterious vs neutral status.

  swissprot nssnp-containing nssnps machine single-attribute sequence

• Identification of Proteins Deregulated by Platinum-Based Chemotherapy as Novel Biomarkers and Therapeutic Targets in Non-Small Cell Lung Cancer.

  PMID 33777753 · PMC7991912 · Frontiers in oncology · 2021 · 7 claims · 8 setups

  Has reproduction · 81

  Cisplatin exposure induces significant deregulation of protein expression networks in NSCLC cells

  h460 nsclc swath-ms western machine

• Predicting positive p53 cancer rescue regions using Most Informative Positive (MIP) active learning.

  PMID 19756158 · PMC2742196 · PLoS computational biology · 2009 · 8 claims · 4 setups

  Full-text index only

  MIP active learning is a novel active learning method that preferentially seeks informative Positive (functionally active) examples rather than only maximizing classifier accuracy.

  engineered p53 computational yeast-based regional homology

• Sequence and structure signatures of cancer mutation hotspots in protein kinases.

  PMID 19834613 · PMC2759519 · PloS one · 2009 · 8 claims · 6 setups

  Full-text index only

  Developed CKMD (Composite Kinase Mutation Database), an integrated bioinformatics resource mapping genetic variation in protein kinase genes to sequence, structural, and functional data

  kinase common egfr autoinhibited database-driven structure-informed evolutionary