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).

• The specificity and polymorphism of the MHC class I prevents the global adaptation of HIV-1 to the monomorphic proteasome and TAP.

  PMID 18949050 · PMC2569417 · PloS one · 2008 · 6 claims · 5 setups

  Full-text index only

  Within individual hosts, proteasome and TAP escape mutations in HIV-1 occur frequently

  hiv-1 hla-genotyped predicted bioinformatic longitudinal ancestral

• Aggregation propensity of the human proteome.

  PMID 18927604 · PMC2557143 · PLoS computational biology · 2008 · 8 claims · 7 setups

  Full-text index only

  Long proteins have, on average, less intense/pronounced aggregation peaks than short proteins

  proteome non-membrane proteins membrane sequence-based correlation statistical

• PlasmoDraft: a database of Plasmodium falciparum gene function predictions based on postgenomic data.

  PMID 18925948 · PMC2605471 · BMC bioinformatics · 2008 · 8 claims · 4 setups

  Full-text index only

  Gonna, a supervised k-nearest-neighbor Guilt-By-Association predictor, proposes GO annotations for a gene based on similarity of its transcriptome, proteome, or interactome profile to genes already annotated by GeneDB

  plasmodium genedb-annotated k-nn leave-one-out

• Improving the specificity of exon prediction using comparative genomics.

  PMID 18831778 · PMC2559877 · BMC genomics · 2008 · 8 claims · 6 setups

  Full-text index only

  A log-odds ratio scoring method based on codon conservation across human-mouse/human-dog alignments and adjacent-codon dependency can classify putative exons as coding vs non-coding.

  human-mouse human-dog genome simulated comparative single-genome simulated

• Zebrafish whole-adult-organism chemogenomics for large-scale predictive and discovery chemical biology.

  PMID 18618001 · PMC2442223 · PLoS genetics · 2008 · 8 claims · 6 setups

  Full-text index only

  Zebrafish whole-adult-organism chemogenomics generates robust prediction models that discriminate P(H)AHs from ECs across independent experiments

  zebrafish computational seven consolidated whole-adult-organism supervised quantitative

• An efficient method for the prediction of deleterious multiple-point mutations in the secondary structure of RNAs using suboptimal folding solutions.

  PMID 18445289 · PMC2386494 · BMC bioinformatics · 2008 · 8 claims · 6 setups

  Full-text index only

  Using RNAsubopt suboptimal solutions computed once for the wild-type sequence, specific multiple-point mutations likely to cause conformational rearrangement can be selected without brute-force enumeration.

  example hepatitis minimum suboptimal multiple-point

• Integrated reiterative pipeline for rapid epitope-based pan-alphavirus vaccines.

  PMID 41811958 · PMC12978219 · Science advances · 2026 · 6 claims · 7 setups

  Full-text index only

  An integrated pipeline combining ML-based epitope prediction (netMHCpan, EpiDope, BepiPred), TCRpMHC structural modeling/docking, and JessEV vaccine design can prioritize viral peptides by immunogenicity, allele coverage, solubility, and stability.

  preexposed alphaviral peptide-hla modeled peptide epitope structural

• Separating selection from mutation in antibody language models.

  PMID 41944291 · PMC13056363 · eLife · 2026 · 8 claims · 6 setups

  Full-text index only

  Masked antibody language models such as AbLang2 are biased by nucleotide-level mutation processes (germline memorization, codon table, SHM rate variation)

  single nine antibody reconstructed masked-site correlation functional

• Critical evaluation of drug response prediction models with DrEval.

  PMID 42120410 · PMC13168506 · Nature communications · 2026 · 8 claims · 6 setups

  Full-text index only

  DrEval is a living open-source benchmarking pipeline for unbiased, biologically meaningful evaluation of cancer drug response prediction models, integrating standardized preprocessing, hyperparameter tuning, statistically rigorous evaluation, cross-study benchmarks, and ablation studies.

  ctrpv2 ccle beataml2 pdx_bruna viability drug pdx

• 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

• Learning collective multicellular dynamics with an interacting mean field neural SDE model.

  PMID 41564117 · PMC12854464 · PLoS computational biology · 2026 · 7 claims · 5 setups

  Full-text index only

  scIMF models multicellular dynamics as interacting diffusion processes using a McKean-Vlasov SDE solved via Neural SDE, with a Transformer-based cell-wise attention mechanism approximating the distribution-dependent drift term

  zebrafish embryonic pancreatic temporal umap cell-wise

• Development of lead hammerhead ribozyme candidates against human rod opsin mRNA for retinal degeneration therapy.

  PMID 19094986 · PMC3388947 · Experimental eye research · 2009 · 8 claims · 3 setups

  Full-text index only

  Three lead hhRz candidates (CUC↓266, CUC↓1411, AUA↓1414) significantly knock down human RHO protein expression relative to control (p<0.05)

  rho expression secondary western dicistronic

• SNAP predicts effect of mutations on protein function.

  PMID 18757876 · PMC2562009 · Bioinformatics (Oxford, England) · 2008 · 8 claims · 3 setups

  Full-text index only

  SNAP is a publicly available web-server implementation predicting functional effects (neutral/non-neutral) of single amino acid substitutions.

  mutant insulin neural alanine mutation

• ASPIC: a web resource for alternative splicing prediction and transcript isoforms characterization.

  PMID 16845044 · PMC1538898 · Nucleic acids research · 2006 · 8 claims · 2 setups

  Full-text index only

  The ASPIC algorithm, using an optimization procedure that minimizes splice site predictions and transcript isoforms from multiple EST-genome alignments, outperforms other similar AS-prediction tools in sensitivity and selectivity

  hnrpr specified comparative algorithm

• SEMdag: Fast learning of Directed Acyclic Graphs via node or layer ordering.

  PMID 39775401 · PMC11709272 · PloS one · 2025 · 8 claims · 5 setups

  Has reproduction · 81

  SEMdag() is a two-step order-based algorithm for fast learning of high-dimensional linear SEMs, using knowledge-based (KB) or data-driven bottom-up (BU) node/layer ordering followed by penalized (L1) DAG estimation

  amyotrophic breast coronavirus st-elevation rna-seq comparative

• Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility.

  PMID 40106407 · PMC11964219 · PLoS genetics · 2025 · 7 claims · 6 setups

  Has reproduction · 95

  Mouse-Geneformer, a Transformer Encoder model pre-trained via masked-token self-supervised learning on mouse-Genecorpus-20M, was successfully constructed following the original human Geneformer architecture.

  healthy scrna-seq disease scrna-seq type perturbation

• The COMBAT-TB Workbench: Making Powerful Mycobacterium tuberculosis Bioinformatics Accessible.

  PMID 35138128 · PMC8827006 · mSphere · 2022 · 8 claims · 5 setups

  Has reproduction · 90

  The COMBAT-TB Workbench combines the IRIDA web platform and the Galaxy workflow platform into a single easy-to-install, Docker-based application

  tuberculosis outlier whole-genome maximum-likelihood read

• Streaming Long-Read Sequence Alignments for HLA Predictions Using HLAminer.

  PMID 40145684 · PMC11948951 · Current protocols · 2025 · 6 claims · 5 setups

  Has reproduction · 90

  Streaming minimap2 alignment output directly into HLAminer via Unix pipe (-a stream mode) enables HLA class I and II allele prediction without storing bulky SAM alignment files on disk

  wgs

• Analysis of protein sequence and interaction data for candidate disease gene prediction.

  PMID 17020920 · PMC1636487 · Nucleic acids research · 2006 · 8 claims · 7 setups

  Full-text index only

  Combining CPS and CMP using known disease genes as input achieves sensitivity 0.52 and specificity 0.97, reducing candidate lists 13-fold

  ophid biocarta kegg pfam-annotated common benchmarking multiple-interval

• MiPred: classification of real and pseudo microRNA precursors using random forest prediction model with combined features.

  PMID 17553836 · PMC1933124 · Nucleic acids research · 2007 · 8 claims · 8 setups

  Full-text index only

  A hybrid feature combining local contiguous triplet structure-sequence composition, MFE of the secondary structure, and P-value of a randomization test improves classification of real vs pseudo pre-miRNAs

  real combined pre-mirna training random independent repeated