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).

• A reference profile-free deconvolution method to infer cancer cell-intrinsic subtypes and tumor-type-specific stromal profiles.

  PMID 32111252 · PMC7049190 · Genome medicine · 2020 · 8 claims · 8 setups

  Has reproduction · 91

  DeClust is a reference-profile-free deconvolution method that incorporates molecular subtyping directly into the deconvolution process, outputting cohort-level cancer subtype and stromal reference profiles rather than per-individual profiles

  tcga simulated muscle-invasive ccrcc computational simulation-based deconvolution

• HapMap-based study of the 17q21 ERBB2 amplicon in susceptibility to breast cancer.

  PMID 17117180 · PMC2360759 · British journal of cancer · 2006 · 6 claims · 5 setups

  Full-text index only

  Common genetic variation (tSNPs and haplotypes) across the 400-kb 17q21 ERBB2 amplicon is not associated with breast cancer risk in British women.

  white same hapmap snp haplotype tagging

• A platelet-related signature for predicting the prognosis and immunotherapy benefit in bladder cancer based on machine learning combinations.

  PMID 39280688 · PMC11399026 · Translational andrology and urology · 2024 · 8 claims · 8 setups

  Has reproduction · 51

  An Enet (alpha=0.4) machine-learning algorithm built from 10 platelet-related genes yields the optimal platelet-related signature (PRS) for bladder cancer prognosis, with average C-index 0.73

  bladder tcga bulk univariate integrative

• Machine learning developed an intratumor heterogeneity signature for predicting clinical outcome and immunotherapy benefit in bladder cancer.

  PMID 39100839 · PMC11291408 · Translational andrology and urology · 2024 · 8 claims · 8 setups

  Has reproduction · 40

  An integrative machine learning procedure (10 methods, 101 algorithm combinations) identified an Enet (alpha=0.2)-based intratumor heterogeneity-related signature (IRS) with the highest average C-index (0.69) across TCGA and GEO cohorts

  bladder skin bulk integrative immune

• Novel fatty acid metabolism-related molecular subtyping and prognostic signature for breast cancer.

  PMID 41674979 · PMC12885896 · Translational cancer research · 2026 · 8 claims · 8 setups

  Full-text index only

  A FAM-related gene prognostic model (FAMGM) built using CoxBoost and random survival forest was identified as the optimal model among 101 machine learning combinations, based on highest average C-index across TCGA-BRCA and GSE96058 cohorts

  tcga-brca gse96058 brca breast bulk single-cell spatial

• Machine learning-driven transcriptomic and single-cell profiling of programed cell death patterns in colon cancer.

  PMID 41854308 · PMC13009810 · Science progress · 2026 · 8 claims · 8 setups

  Full-text index only

  Disulfidptosis and anoikis are consistently identified as the most robust prognostic PCD patterns in colon cancer across six independent machine learning algorithms

  colon coad ssgsea-based machine differential

• Deubiquitination enzyme USP35 negatively regulates MAVS signaling to inhibit anti-tumor immunity.

  PMID 40016186 · PMC11868397 · Cell death & disease · 2025 · 8 claims · 8 setups

  Has reproduction · 81

  USP35 interacts with MAVS and removes its K63-linked polyubiquitin chains, inhibiting viral-induced MAVS-TBK1-IRF3 activation and downstream inflammatory gene expression

  tumor melanoma tcga-skcm hek293t bioinformatics geo kaplan-meier

• DNA methylation biomarkers-based pan-cancer classifier: predictive modeling for cancer classification.

  PMID 42152108 · PMC13185202 · Genome medicine · 2026 · 8 claims · 5 setups

  Full-text index only

  Relatively simple ML models (logistic regression) outperform complex algorithms such as deep neural networks for methylation-based cancer classification

  validation cns healthy genes methylation copy-number gene-set

• Endothelial-derived PANoptosis factor IL33 is a potential immunotherapy in breast cancer.

  PMID 42095097 · PMC13141053 · iScience · 2026 · 8 claims · 8 setups

  Full-text index only

  NMF clustering of PANoptosis-related gene expression stratifies breast cancer patients into three distinct molecular clusters (C1, C2, C3)

  tcga-brca meta-cohort training breast nmf univariate gsva

• Fibroblast-associated CTHRC1 as a key indicator of recurrence risk in prostate cancer.

  PMID 41832493 · PMC13101373 · World journal of surgical oncology · 2026 · 7 claims · 8 setups

  Full-text index only

  Pathological T stage, N stage, Gleason score, and TP53 mutation are associated with higher PRAD recurrence risk

  tcga geo prad scrna-seq bulk single-cell cell-cell

• Machine Learning-Based Integrated Analysis of PANoptosis Patterns in Acute Myeloid Leukemia Reveals a Signature Predicting Survival and Immunotherapy.

  PMID 38322112 · PMC10846924 · International journal of clinical practice · 2024 · 8 claims · 8 setups

  Has reproduction · 71

  AML cases can be categorized into two distinct PANRG (PANoptosis-related gene) clusters with differentially expressed prognostic genes (PRDEGs)

  aml hovon cancer tcga bulk consensus machine