Research map / Architectures and efficiency / Attention and transformers
MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation
Kangjie Zheng, Amirhossein Vahidi, Liying Jin, Joseph Clarke, Vijaya Baskar, Connor Rogerson, mj zhang, Muzlifah Haniffa, Anshul Kundaje, Mohammad Lotfollahi
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes MUSS, a multi-scale, sequence-based model that jointly represents DNA sequence, chromatin accessibility and gene expression for single-cell gene regulation. (Based on abstract only.)
Problem
Modeling single-cell gene regulation requires jointly representing DNA sequence, chromatin accessibility, and gene expression across regulatory scales; sequence models lack cell-level resolution while single-cell omics models treat genes and peaks as fixed vocabulary tokens.
Approach
Unifies a sequence-based view with cell-state modeling by treating genes and peaks as sequences rather than fixed vocabulary tokens, across multiple regulatory scales. (Abstract only; details unavailable.)
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add frozen DNA sequence embeddings (vs random) (ablation) | MUSS · BMMC gene expression ablation, unseen sequence | PCC: 0.196 -> 0.745 | Improved |
| add cross-scale peak-gene interaction (ablation) | MUSS · BMMC gene expression ablation, unseen sequence | PCC: 0.009 -> 0.745 | Improved |
| add RBF distance bias (ablation) | MUSS · BMMC gene expression ablation, unseen sequence | PCC: 0.707 -> 0.745 | Improved |
| add peak RoPE (ablation) | MUSS · BMMC gene expression ablation, unseen sequence | PCC: 0.725 -> 0.745 | Improved |
| add distance reweighting (ablation) | MUSS · BMMC gene expression ablation, unseen sequence | PCC: 0.736 -> 0.745 | Improved |
| add peak MLM pretraining stage (ablation) | MUSS · BMMC gene expression ablation, unseen sequence | PCC: 0.734 -> 0.745 | Improved |
| add peak MLM pretraining stage (ablation) | MUSS · zero-shot clustering / enhancer linking | ARI / retrieval | Improved |
| add cross-scale interaction (ablation) | MUSS · BMMC gene expression ablation, seen sequence | PCC: 0.967 -> 0.969 | No clear effect |
| use AlphaGenome or Borzoi instead of NT-v3 encoder (ablation) | MUSS · unseen-sequence PCC (BMMC) | PCC: 0.452 -> 0.745 | Improved |
| use AlphaGenome instead of Borzoi encoder (ablation) | MUSS · unseen-sequence PCC | PCC: BMMC 0.695 -> 0.745; PBMC10K 0.698 -> 0.684 | Mixed |
| add cell-contextualized MUSS over underlying sequence encoder | AlphaGenome · PBMC169K clustering | ARI: 0.1032 -> 0.5377 | Improved |
| use MUSS in place of scooby | sequence-based predictors · unseen-sequence pseudobulk PCC | PCC: 0.533 -> 0.684 (PBMC10K) | Improved |
Closest papers by meaning
- STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations (NeurIPS 2026 · similarity 0.87)
- A Simple and Comprehensive Benchmark for Single-Cell Transcriptomics (AAAI 2025 · similarity 0.86)
- KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference (NeurIPS 2025 · similarity 0.85)
- sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models (ICML 2025 · similarity 0.85)
- C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation (NeurIPS 2026 · similarity 0.85)
- CellVerse: Do Large Language Models Really Understand Cell Biology? (NeurIPS 2025 · similarity 0.85)
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.
