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).

• Partially shared multi-modal embedding learns holistic representation of cell state.

  PMID 41741805 · PMC13021527 · Nature computational science · 2026 · 8 claims · 5 setups

  Full-text index only

  APOLLO automatically learns partial information sharing between multiple data modalities using an autoencoder with a partially overlapping latent space trained via latent optimization.

  simulated paired single simulation scrna-seq multiplexed

• scSurv: a deep generative model for single-cell survival analysis.

  PMID 41429574 · PMC12797213 · Bioinformatics (Oxford, England) · 2026 · 8 claims · 6 setups

  Full-text index only

  scSurv combines a Cox proportional hazards model with a deep generative model (VAE) of single-cell transcriptomes to estimate individual cellular contributions to clinical outcomes

  simulated tcga melanoma renal scrna-seq bulk single-cell

• 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

• RNA-Seq alignment to individualized genomes improves transcript abundance estimates in multiparent populations.

  PMID 25236449 · PMC4174954 · Genetics · 2014 · 8 claims · 7 setups

  Has reproduction · 50

  Genetic variants distinguishing an individual genome from the reference cause read misalignment and biased transcript abundance estimates, and fine-tuning of alignment algorithms does not correct this problem.

  liver genomic cast simulated bulk high-density rna-seq

• omnideconv: a unifying framework for using and benchmarking single-cell-informed deconvolution of bulk RNA-seq data.

  PMID 41582216 · PMC12837286 · Genome biology · 2026 · 8 claims · 6 setups

  Full-text index only

  omnideconv is an R package providing a unified interface to twelve second-generation deconvolution methods (AutoGeneS, BayesPrism, Bseq-SC, Bisque, CDseq, CIBERSORTx, CPM, DWLS, MOMF, MuSiC, SCDC, Scaden)

  blood-derived pbmc blood spleen bulk scrna-seq pseudo-bulk

• A cellular epigenetic classification system for glioblastoma.

  PMID 41499453 · PMC13128495 · Neuro-oncology · 2026 · 8 claims · 8 setups

  Full-text index only

  ITHresolveGBM, a hierarchical two-step NMF method, deconvolutes bulk GBM DNA methylation profiles into three non-malignant (immune, glial, neuronal) and three malignant components

  gbm healthy pseudo-bulk tcga illumina single-cell deconvolution

• spliceJAC: transition genes and state-specific gene regulation from single-cell transcriptome data.

  PMID 36321549 · PMC9627675 · Molecular systems biology · 2022 · 8 claims · 8 setups

  Has reproduction · 53

  spliceJAC uses unspliced and spliced mRNA count matrices to construct cell state-specific gene-gene regulatory interaction (Jacobian) matrices from scRNA-seq data

  bistable three-gene emt circuits simulation mixed-state grn

• scLong: a billion-parameter foundation model for capturing long-range gene context in single-cell transcriptomics.

  PMID 41639087 · PMC12982784 · Nature communications · 2026 · 7 claims · 4 setups

  Full-text index only

  scLong performs self-attention across all ~27,874 human genes, including lowly expressed ones, to capture long-range gene dependencies missed by models restricted to highly expressed gene subsets

  million norman self-supervised transcriptional genetic

• Embeddings from language models are good learners for single-cell data analysis.

  PMID 41726097 · PMC12921509 · Patterns (New York, N.Y.) · 2026 · 8 claims · 8 setups

  Full-text index only

  scELMo combines LLM-derived embeddings of gene and cell metadata with raw single-cell expression data via matrix operations to generate cell embeddings without pretraining a new model

  scrna-seq multi-batch diseased perturbation clustering batch cell-type

• Community assessment of methods to deconvolve cellular composition from bulk gene expression.

  PMID 39191725 · PMC11350143 · Nature communications · 2024 · 8 claims · 4 setups

  Has reproduction · 63

  Most deconvolution methods accurately predict coarse-grained immune/stromal cell populations from bulk expression.

  admixtures cancer tumor bulk bulk admixture crowdsourced

• Determination of complete chromosomal haplotypes by bulk DNA sequencing.

  PMID 33957932 · PMC8101039 · Genome biology · 2021 · 8 claims · 8 setups

  Has reproduction · 97

  A hierarchical computational strategy that first builds high-confidence local haplotype blocks from long-range/linked-read linkage and then concatenates them into whole-chromosome haplotypes using Hi-C contacts

  rpe-1 na12878 aneuploid linked-read hi-c bulk

• Forseti: a mechanistic and predictive model of the splicing status of scRNA-seq reads.

  PMID 38940130 · PMC11256924 · Bioinformatics (Oxford, England) · 2024 · 7 claims · 5 setups

  Has reproduction · 87

  Forseti is the first probabilistic model for resolving the splicing status of exonic scRNA-seq reads by scoring putative fragments linking read alignments to proximate priming sites

  training simulated held-out paired-end cubic mlp

• Modeling nascent transcription from chromatin landscape and structure with CLASTER.

  PMID 41691282 · PMC13011747 · Genome biology · 2026 · 7 claims · 8 setups

  Full-text index only

  CLASTER, a deep neural network combining chromatin landscape tracks and 3D contact maps, accurately predicts kilobasepair-resolution nascent RNA (EU-seq) profiles in a DNA-sequence-agnostic manner

  embryonic mescs chromatin k562 eu-seq chip-seq micro-c

• Robust and efficient annotation of cell states through gene signature scoring.

  PMID 41708334 · PMC12951948 · Genome research · 2026 · 8 claims · 8 setups

  Full-text index only

  Established scoring methods (Seurat, SCANPY, UCell, JASMINE) fail to provide robust and comparable score distributions across diverse signatures and experimental conditions, precluding accurate unsupervised cell-state annotation.

  pbmc colorectal esophageal crc scrna-seq cross-implementation signature