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
Identification of diagnostic markers for tuberculosis by proteomic fingerprinting of serum.
PMID 16980117 · PMC7159276 · Lancet (London, England) · 2006 · 8 claims · 5 setups
An SVM classifier trained on serum proteomic profiles discriminated patients with active tuberculosis from controls with clinically overlapping conditions
-
Full-text index only
Estimation of relevant variables on high-dimensional biological patterns using iterated weighted kernel functions.
PMID 18509521 · PMC2396875 · PloS one · 2008 · 7 claims · 6 setups
wKIERA combines a weighted-kernel discriminant (kernel perceptron) with an iterative stochastic probability estimation-of-distribution algorithm to estimate a relevance distribution over variables
-
Full-text index only
Constructing support vector machine ensembles for cancer classification based on proteomic profiling.
PMID 16689692 · PMC5173238 · Genomics, proteomics & bioinformatics · 2005 · 7 claims · 4 setups
CSVME, built by selecting a subset of base SVMs via SVM-RFE ranking and fusing them with a trained upper-layer SVM, achieves better classification performance than an ensemble of all base SVMs.
-
Full-text index only
Identification of serum biomarkers for colon cancer by proteomic analysis.
PMID 16755300 · PMC2361335 · British journal of cancer · 2006 · 8 claims · 8 setups
Complement C3a des-arg, α1-antitrypsin and transferrin were identified as serum proteins with diagnostic potential for CRC.
-
Full-text index only
Logical Analysis of Data (LAD) model for the early diagnosis of acute ischemic stroke.
PMID 18616825 · PMC2492849 · BMC medical informatics and decision making · 2008 · 7 claims · 5 setups
An LAD classification model built from a support-set of 3 peptide peaks can distinguish stroke patients from controls with 75% accuracy on an independent validation set
-
Full-text index only
A novel wavelet-based thresholding method for the pre-processing of mass spectrometry data that accounts for heterogeneous noise.
PMID 18615428 · PMC2855839 · Proteomics · 2008 · 6 claims · 4 setups
Noise in SELDI-TOF/MALDI-TOF mass spectrometry data is heteroscedastic across the m/z range, with larger variance at lower m/z values, contrary to the homogeneous noise assumption of existing wavelet denoising methods.