Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning a Hybrid Architecture for Sequence Regression and Annotation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| joint training with real-valued responses instead of two-stage Baum-Welch then regression (ablation) | HMM · Synthetic PBM data (all state + linear) | prediction MSE: 1.355 -> 0.969 | Helped |
| joint training instead of two-stage (ablation) | HMM · Synthetic PBM data (all state + linear) | test log-likelihood: -29.81 -> -29.14 | Helped |
| joint training instead of two-stage (ablation) | HMM · Synthetic PBM data (all state + linear) | emission matrix error: 1.16 -> 0.19 | Helped |
| joint training instead of two-stage (ablation) | HMM · Synthetic PBM data (all state + linear) | transition A(B->M) error: 3.6\times10^{-4} -> 4.5\times10^{-5} | Helped |
| joint training instead of two-stage (ablation) | HMM · Synthetic PBM data (all state + linear) | beta estimation (true 4): 20.61 -> 4.10 | Helped |
| allow transitions to vary along the sequence (ablation) | RegHMM · Synthetic PBM | performance | No clear effect |
| different summary/link functions (6 setups) (ablation) | RegHMM · Synthetic PBM | performance | No clear effect |
| RegHMM vs K-mer and other PBM methods | RegHMM · DREAM5 (66 TFs) | Pearson correlation / AUROC | No clear effect |
Closest papers by meaning
- Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis (NeurIPS 2025 · similarity 0.85)
- Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context (NeurIPS 2025 · similarity 0.84)
- What DNA Foundation Models Learn Beyond Sequence Composition (NeurIPS 2026 · similarity 0.84)
- Learning Extrapolative Sequence Transformations from Markov Chains (ICML 2025 · similarity 0.83)
- Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing (ICML 2025 · similarity 0.83)
- Training Compute-Optimal Protein Language Models (NeurIPS 2024 · similarity 0.83)
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.