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).

• Boosting accuracy of automated classification of fluorescence microscope images for location proteomics.

  PMID 15207009 · PMC449699 · BMC bioinformatics · 2004 · 8 claims · 8 setups

  Full-text index only

  New classifiers (SVMs, ensembles) and new wavelet-derived (Gabor, Daubechies) features improve recognition of protein subcellular location patterns over the previous neural network approach

  hela automated stepwise training-set-size

• Qualitative Transcriptional Signature for the Pathological Diagnosis of Pancreatic Cancer.

  PMID 33173782 · PMC7538791 · Frontiers in molecular biosciences · 2020 · 8 claims · 7 setups

  Has reproduction · 71

  A 12-gene-pair (17-gene) REO-based signature discriminates PC and cancer-adjacent normal tissue from non-tumor (healthy/pancreatitis) pancreatic tissue.

  pancreatic normal pooled microarray rna-sequencing roc

• JIGSAW, GeneZilla, and GlimmerHMM: puzzling out the features of human genes in the ENCODE regions.

  PMID 16925843 · PMC1810558 · Genome biology · 2006 · 8 claims · 4 setups

  Full-text index only

  Adding model states for specific biological features (signal peptides, CpG islands, etc.) to non-comparative GHMM gene finders did little or nothing to enhance predictive accuracy, sometimes reducing it.

  encode genes invertebrate initio comparative training

• GenTB: A user-friendly genome-based predictor for tuberculosis resistance powered by machine learning.

  PMID 34461978 · PMC8407037 · Genome medicine · 2021 · 8 claims · 6 setups

  Has reproduction · 78

  GenTB is a free, open, web-based application offering two ML predictors (Random Forest and WDNN) that predict resistance to 13 and 10 anti-TB drugs, respectively.

  clinical tuberculosis registered whole-genome targeted retraining

• GeneAlign: a coding exon prediction tool based on phylogenetical comparisons.

  PMID 16845010 · PMC1538901 · Nucleic acids research · 2006 · 8 claims · 5 setups

  Full-text index only

  GeneAlign predicts coding exons by using signal detection (GeneSplicer/WMM) combined with CORAL, a heuristic linear-time alignment tool, to align candidate signal-flanked regions against annotated exons of a homologous organism's genes

  homologous human-mouse same gene comparative parameter micro-exon

• Discovery and identification of potential biomarkers of papillary thyroid carcinoma.

  PMID 19785722 · PMC2761863 · Molecular cancer · 2009 · 8 claims · 7 setups

  Full-text index only

  A 3-peak (m/z 9190, 6631, 8697 Da) SVM classification model discriminates PTC from non-cancer controls with high sensitivity and specificity

  serum hplc-purified trypsin-digested crude seldi-tof-ms solid-phase maldi-tof-ms

• Diagnostic proteomics: serum proteomic patterns for the detection of early stage cancers.

  PMID 15258335 · PMC3851082 · Disease markers · 2003 · 8 claims · 8 setups

  Full-text index only

  Proteomic pattern analysis of serum mass spectra, without identifying the underlying proteins, can distinguish cancer patients from healthy controls with high sensitivity and specificity.

  serum frozen ig-depleted clinical seldi-tof maldi lc-ms

• AUGUSTUS at EGASP: using EST, protein and genomic alignments for improved gene prediction in the human genome.

  PMID 16925833 · PMC1810548 · Genome biology · 2006 · 8 claims · 5 setups

  Full-text index only

  AUGUSTUS predicted significantly more genes correctly than any other ab initio program in EGASP

  genome human-mouse genes initio comparative extrinsic

• Using ESTs to improve the accuracy of de novo gene prediction.

  PMID 16817966 · PMC1534067 · BMC bioinformatics · 2006 · 8 claims · 8 setups

  Full-text index only

  TWINSCAN_EST combines EST alignments with TWINSCAN via a trainable 'ESTseq' representation and improves exact gene structure prediction accuracy on the whole C. elegans genome

  elegans genome chromosome novo gene partial

• Detection of venous thromboembolism by proteomic serum biomarkers.

  PMID 17579716 · PMC1891085 · PloS one · 2007 · 5 claims · 8 setups

  Full-text index only

  A neural network-based classifier built from direct MALDI-TOF MS serum protein expression profiles can diagnose VTE with sensitivity/specificity that exceeds D-dimer assays

  serum anova-selected citrated depleted direct artificial d-dimer

• 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

• Exhaustive prediction of disease susceptibility to coding base changes in the human genome.

  PMID 18793467 · PMC2537574 · BMC bioinformatics · 2008 · 8 claims · 7 setups

  Full-text index only

  Inter-species conservation is the strongest single predictor of disease-associated coding mutations among the factors tested.

  hgmd refseq aligned svm svm reciprocal inter-species

• Development of proteomic patterns for detecting lung cancer.

  PMID 14757945 · PMC3851077 · Disease markers · 2003 · 8 claims · 3 setups

  Full-text index only

  A decision tree classification algorithm built on three serum protein mass peaks (8122Da, 1452Da, 1610Da) can discriminate lung cancer patients from healthy controls

  serum pooled seldi-tof-ms decision reproducibility

• Molecular Classification Models for Triple Negative Breast Cancer Subtype Using Machine Learning.

  PMID 34575658 · PMC8472680 · Journal of personalized medicine · 2021 · 6 claims · 4 setups

  Has reproduction · 86

  A training gene set of 719 unique upregulated DEGs (subtype-specific) can be used to build ML models that classify TNBC into BLIA, BLIS, MES, and LAR subtypes.

  known tnbc unique unknown gene machine term

• Enhancing chemotherapy response prediction via matched colorectal tumor-organoid gene expression analysis and network-based biomarker selection.

  PMID 39754813 · PMC11754497 · Translational oncology · 2025 · 6 claims · 8 setups

  Has reproduction · 78

  A consensus WGCNA approach combining matched tumor-organoid and independent organoid drug-response expression data identifies gene modules and hub genes predictive of 5-FU chemotherapy response

  colorectal matched combined expression microarray rna-seq consensus

• Genome-wide identification of specific oligonucleotides using artificial neural network and computational genomic analysis.

  PMID 17518996 · PMC1892811 · BMC bioinformatics · 2007 · 7 claims · 4 setups

  Full-text index only

  The IAB algorithm (integration of ANN and BLAST) identifies genome-wide specific oligos much faster than pure BLAST search while maintaining comparable success rate and cross homology

  tigr xanthomonas xcc ann wu-blast whole-genome

• A genomic approach to improve prognosis and predict therapeutic response in chronic lymphocytic leukemia.

  PMID 19861443 · PMC2783430 · Clinical cancer research : an official journal of the American Association for Cancer Research · 2009 · 8 claims · 8 setups

  Full-text index only

  A genomic signature derived from CLL patient leukemic cells significantly differentiates stable from progressive disease

  duke nci-60 mayo spanish gene cdna igvh

• Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach.

  PMID 19801557 · PMC2780952 · DNA research : an international journal for rapid publication of reports on genes and genomes · 2009 · 6 claims · 3 setups

  Full-text index only

  An SVM trained on 69 binary features of known PID genes can accurately classify PID vs non-PID genes and predict novel candidate PID genes

  genome training svm support leave-one-out sensitivity

• Limitations in SELDI-TOF MS whole serum proteomic profiling with IMAC surface to specifically detect colorectal cancer.

  PMID 19689818 · PMC2743709 · BMC cancer · 2009 · 7 claims · 3 setups

  Full-text index only

  The previously reported classifier (m/z 8,132 and 4,002) failed to discriminate CRC patients from healthy volunteers in this independent validation cohort

  serum pooled seldi-tof comparative decision

• Classification of real and pseudo microRNA precursors using local structure-sequence features and support vector machine.

  PMID 16381612 · PMC1360673 · BMC bioinformatics · 2005 · 7 claims · 7 setups

  Full-text index only

  A 32-dimensional triplet structure-sequence feature vector combined with SVM (triplet-SVM) can distinguish real human pre-miRNAs from pseudo pre-miRNA hairpins with ~90% accuracy.

  pre-mirnas test conserved-hairpin cross-species secondary svm cross-species