Research map / Probabilistic and scientific modeling / Molecules and proteins
scChord: A Probabilistic Manifold Rectification Framework for RNA-to-Protein Translation
Jiawei Zhang, Kangjun Jin, Shuai Xiao, Jiachen Yang
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 |
|---|---|---|---|
| add Stage 1 probabilistic manifold rectification (ablation) | scChord · GSE100866 | PCC-P: 0.3572 -> 0.8655 | Improved |
| add Stage 2 RNA-conditioned flow matching (ablation) | scChord · GSE100866 | PCC-P: 0.2066 -> 0.8655 | Improved |
| use ZINB probabilistic decoder instead of deterministic reconstruction (ablation) | scChord · GSE100866 | RMSE: 0.7106 -> 0.5384 | Improved |
| add KL regularization with deterministic decoder (ablation) | scChord · GSE100866 | PCC-P: 0.7788 -> 0.0230 | Hurt |
| add KL regularization on top of probabilistic decoder (ablation) | scChord · GSE100866 | PCC-P: 0.8414 -> 0.8655 | Improved |
| add transcriptomic consistency loss (ablation) | scChord · GSE100866 | RMSE: 0.6220 -> 0.5384 | Improved |
| train the two stages decoupled rather than jointly | scChord · GSE100866 | stability | Improved |
| rectify latent manifold (ablation) | scChord · latent geometry | ODE solver NFE | Improved |
| rectify latent manifold (ablation) | scChord · latent geometry | encoder Lipschitz sensitivity | Improved |
| use multi-step dopri5 ODE sampling | scChord · GSE164378-3P (100k cells) | inference time (s/200): 0.488 vs 0.002 (sciPENN) | Hurt |
Closest papers by meaning
- $\texttt{RNAGenScape}$: property-guided, optimized generation of mRNA sequences with manifold Langevin dynamics (NeurIPS 2026 · similarity 0.86)
- ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching (NeurIPS 2026 · similarity 0.85)
- SE(3)-Stochastic Flow Matching for Protein Backbone Generation (ICLR 2024 · similarity 0.84)
- AlphaFold Meets Flow Matching for Generating Protein Ensembles (ICML 2024 · similarity 0.84)
- Protein Discovery with Discrete Walk-Jump Sampling (ICLR 2024 · similarity 0.84)
- Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction (ICLR 2025 · 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.
