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).

• sCellST predicts single-cell gene expression from H& E images.

  PMID 41513659 · PMC12858858 · Nature communications · 2026 · 7 claims · 6 setups

  Full-text index only

  sCellST is a weakly supervised (Multiple Instance Learning) deep learning framework that predicts single-cell gene expression from H&E images alone, trained using paired spatial transcriptomics (Visium) and H&E slides

  ovarian kidney prostate breast simulation spot-level nucleus

• Attention-based deep learning for analysis of pathology images and gene expression data in lung squamous premalignant lesions.

  PMID 41952176 · PMC13188385 · Genome medicine · 2026 · 8 claims · 8 setups

  Full-text index only

  A multimodal transformer combining WSIs and gene expression outperforms models trained on either modality alone for classifying bronchial dysplasia or worse vs non-dysplasia.

  endobronchial bronchial colorado jules slide bulk microarray

• FineST: contrastive learning integrates histology and spatial transcriptomics for nuclei-resolved ligand-receptor analysis.

  PMID 41839892 · PMC13201544 · Nature communications · 2026 · 8 claims · 6 setups

  Full-text index only

  FineST, a bimodal contrastive learning model integrating histology (Virchow2 ViT features) and spatial gene expression, enables nuclei-resolved high-resolution RNA imputation.

  colorectal crc breast he-stained spatial type ccc

• Non-negative matrix factorization and deconvolution as a dual simplex problem.

  PMID 41535969 · PMC12888666 · Genome biology · 2026 · 8 claims · 3 setups

  Full-text index only

  The NMF optimization problem can be reduced to searching for K(K-1) variables, independent of the original matrix size M×N.

  unconstrained bulk single-cell image bulk single-cell

• Evaluation of classification and forecasting methods on time series gene expression data.

  PMID 33156855 · PMC7647064 · PloS one · 2020 · 8 claims · 4 setups

  Has reproduction · 74

  Deep learning based methods generally outperform traditional approaches for time series gene expression classification.

  gene gse6186 time short convolutional

• The TREM2-APOE Pathway Drives the Transcriptional Phenotype of Dysfunctional Microglia in Neurodegenerative Diseases.

  PMID 28930663 · PMC5719893 · Immunity · 2017 · 8 claims · 8 setups

  Has reproduction · 67

  A common APOE-dependent microglial molecular signature (MGnD) — loss of homeostatic genes plus induction of inflammatory genes with Apoe among the most upregulated — occurs in ALS, MS and AD mouse models and around neuritic Aβ-plaques in human AD brain.

  facs-isolated fcrls+ sorted app-ps1 nanostring sequencing quantitative

• Genomic and proteomic profiling I: leiomyomas in African Americans and Caucasians.

  PMID 17716379 · PMC2063502 · Reproductive biology and endocrinology : RB&E · 2007 · 7 claims · 6 setups

  Full-text index only

  268 genes (177 over-expressed, 91 under-expressed) are differentially expressed in leiomyomas of African Americans compared to Caucasians (P<0.01, 2-fold cutoff)

  paired same excised paraffin-embedded microarray realtime 2d-page

• LazySlide: accessible and interoperable whole-slide image analysis.

  PMID 41862659 · PMC13076205 · Nature methods · 2026 · 8 claims · 8 setups

  Full-text index only

  LazySlide is an open-source Python package built on the scverse ecosystem for whole-slide image (WSI) analysis and multimodal integration.

  artery gene wsis breast zero-shot bulk multimodal

• Glioblastoma invasion into different organoid hosts reveals cell-intrinsic and proliferative migratory programs.

  PMID 41959666 · PMC13059114 · iScience · 2026 · 8 claims · 8 setups

  Full-text index only

  GB cells invade both neural and endodermal organoid hosts (lineage-independent), whereas non-malignant neural progenitor cells show markedly reduced infiltration

  gbm1 gfp-gbm1 facs-sorted post-invasion image-based immunofluorescence single-cell

• An artificial intelligence optimized hepatic differentiation unveils NR5A2 and AP-1 transcriptional regulation in hepatic maturation.

  PMID 41962865 · PMC13185932 · The Journal of biological chemistry · 2026 · 7 claims · 8 setups

  Full-text index only

  A CNN-based AI algorithm trained on bright-field images of hepatic progenitor cells (HPCs) accurately predicts successful vs. failed differentiation without immunostaining or lineage tracing

  hpsc-derived hlcs cnn-based qpcr flow

• Tissue compartment analysis for biomarker discovery by gene expression profiling.

  PMID 19901995 · PMC2771357 · PloS one · 2009 · 8 claims · 5 setups

  Full-text index only

  TCA method quantifies the fractional volume of constitutive structures in a heterogeneous tissue sample by comparing marker mRNA levels in the whole sample to those in pure isolated structures

  kidney pure serial rt-pcr sage histo-morphometry

• GenomeRNAi: a database for cell-based RNAi phenotypes. 2009 update.

  PMID 19910367 · PMC2808900 · Nucleic acids research · 2010 · 7 claims · 7 setups

  Full-text index only

  GenomeRNAi is a database integrating RNAi phenotypes, reagents, and gene annotations from cell-based screens in Drosophila and human cells

  drosophila hela genome-scale image-based rna-seq

• InSituPREP enables 3D single-cell mapping of interaction-associated gene programs in the breast cancer tumor microenvironment.

  PMID 42109251 · PMC13158666 · Nucleic acids research · 2026 · 8 claims · 6 setups

  Full-text index only

  InSituPREP is a computational framework that quantifies proximity-associated gene programs across multiple analytical layers (binary contacts, graded distance, density, triplets, RNA velocity) in 3D single-cell spatial data

  breast adjacent exseq-imaged exseq-derived expansion 16s scrna-seq

• Integromics: challenges in data integration.

  PMID 12186644 · PMC139396 · Genome biology · 2002 · 8 claims · 7 setups

  Full-text index only

  There is no simple solution to database integration in genomics/bioinformatics

  lines molecular gene monsanto high-throughput cluster-correlation microarray

• Artificial Intelligence Meets Whole Slide Images: Deep Learning Model Shapes an Immune-Hot Tumor and Guides Precision Therapy in Bladder Cancer.

  PMID 36245985 · PMC9553530 · Journal of oncology · 2022 · 8 claims · 8 setups

  Has reproduction

  A three-class WSI cluster (C0/C1/C2) derived via mini batch K-means clustering on Inception V3-extracted image features is significantly associated with overall survival and is an independent prognostic predictor in BLCA.

  tcga-blca gse32894 deep transfer machine

• Single-cell dissection of chronic lung allograft dysfunction reveals convergent and distinct fibrotic mechanisms.

  PMID 41122970 · PMC12581678 · JCI insight · 2025 · 8 claims · 8 setups

  Has reproduction · 75

  CLAD exhibits specific cellular subsets including Fibro.AT2 cells, exhausted CD8+ T cells, and superactivated macrophages

  clad covid-19 million formalin-fixed single-cell single-nucleus integrated

• Artificial Intelligence Approach in Machine Learning-Based Modeling and Networking of the Coronavirus Pathogenesis Pathway.

  PMID 40699865 · PMC12191508 · Current issues in molecular biology · 2025 · 8 claims · 8 setups

  Has reproduction

  The coronavirus pathogenesis pathway is activated in SARS-CoV-2-infected iPSC-derived cardiac cells and in SARS-CoV/SARS-CoV-2-infected LUAD cells

  ace2-transfected calu-3 luad ipsc-derived ipa sequencing convolutional

• Expression profiling of drug response--from genes to pathways.

  PMID 17117610 · PMC3181826 · Dialogues in clinical neuroscience · 2006 · 8 claims · 8 setups

  Full-text index only

  Understanding individual response to a drug (efficacy/tolerability) is the major bottleneck in current drug development and clinical trials.

  blastocyst skin specified cortex pathway two-color microarray

• Connecting synthetic chemistry decisions to cell and genome biology using small-molecule phenotypic profiling.

  PMID 19825513 · PMC2787914 · Current opinion in chemical biology · 2009 · 8 claims · 8 setups

  Full-text index only

  Multidimensional phenotypic profiling leverages information content from multiple parallel or multiplexed measurements of compound action on cells, unlike hierarchical screening which filters to few 'interesting' compounds.

  one nci60 cerevisiae cancer multidimensional cellular two-color

• TNF-⍺-mediated myeloid-instructed CD14(+)CD4(+) T cells are associated with poor survival in lung adenocarcinoma.

  PMID 41666923 · PMC12923953 · Cell reports. Medicine · 2026 · 8 claims · 5 setups

  Full-text index only

  Tumors stratify into lymphoid-enriched, myeloid-enriched, and mixed immune-infiltrated subtypes independent of oncogenic driver status

  resected luad cd4+ multiplex spatial image