Research map / Probabilistic and scientific modeling / Variational and generative sampling
Count Bridges enable Modeling and Deconvolving Transcriptomic Data
Nic Fishman, Gokul Gowri, Tanush Kumar, Jiaqi Lu, Valentin De Bortoli, Jonathan S. Gootenberg, Omar Abudayyeh
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use Count Bridge instead of fine-tuned Enformer for nucleotide-level expression prediction | PBMC scRNA-seq sequence-to-expression · PBMC nucleotide-level bulk | Bulk MSE: 2.590 -> 0.601 | Improved |
| use Count Bridge instead of fine-tuned Enformer for cell-type-specific prediction | PBMC scRNA-seq sequence-to-expression · PBMC nucleotide-level cell-type | CT MSE: 3.142 -> 1.410 | Improved |
| use Count Bridge deconvolved profiles instead of the bulk mean | bulk RNA-seq deconvolution · Bulk RNA-seq count profile deconvolution | Energy: 56.800 -> 28.583 | Improved |
| use Count Bridge instead of CIBERSORTx for cell-type proportions | bulk RNA-seq deconvolution · Bulk RNA-seq cell-type proportions | JSD: 0.194 -> 0.113 | Improved |
| use Count Bridge instead of MuSiC for cell-type proportions | bulk RNA-seq deconvolution · Bulk RNA-seq cell-type proportions | Spearman: 0.186 -> 0.267 | Improved |
| use Count Bridge instead of STDeconvolve for spatial cell-type proportions | spatial transcriptomics deconvolution · Spatial transcriptomics cell-type proportions (MERFISH) | RMSE: 0.177 -> 0.110 | Improved |
| use Count Bridge instead of the spot-mean baseline for count profiles | spatial transcriptomics deconvolution · Spatial transcriptomics count profile deconvolution | Energy: 41.717 -> 8.903 | Improved |
| use Count Bridge instead of MuSiC for cell-type proportions | bulk RNA-seq deconvolution · Bulk RNA-seq cell-type proportions | RMSE: 0.140 -> 0.073 | Improved |
Closest papers by meaning
- Flow Matching for Count Data (NeurIPS 2026 · similarity 0.90)
- Inferring stochastic dynamics with growth from cross-sectional data (NeurIPS 2025 · similarity 0.85)
- A Simple and Comprehensive Benchmark for Single-Cell Transcriptomics (AAAI 2025 · similarity 0.85)
- On the Recoverability of Causal Relations from Bulk Gene Expression Data (NeurIPS 2026 · similarity 0.84)
- Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images (ICLR 2025 · similarity 0.84)
- A versatile informative diffusion model for single-cell ATAC-seq data generation and analysis (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
