Research map / Probabilistic and scientific modeling / Molecules and proteins
Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data
Ehsan Hajiramezanali, Siamak Zamani Dadaneh, Alireza Karbalayghareh, Mingyuan Zhou, Xiaoning Qian
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 domain-specific factor selectors with the beta-Bernoulli process instead of assigning every factor to every domain (ablation) | BMDL versus hGNBP · Lung cancer, low-related domains, Ns=25 and Ns=100 | accuracy (%): 72.94 ± 1.70 -> 78.85 ± 4.55; 74.55 ± 8.84 -> 78.10 ± 5.65 | Improved |
| Use domain-specific factor selectors with the beta-Bernoulli process instead of assigning every factor to every domain (ablation) | BMDL versus hGNBP · Lung cancer, highly-related domains, Ns=25 and Ns=100 | accuracy (%): 74.13 ± 7.07 -> 78.46 ± 5.97; 77.61 ± 3.54 -> 81.49 ± 5.12 | Improved |
| Integrate source-domain data with domain-adaptive factors rather than learn factors from target samples only | BMDL versus hGNBP-NBFA · Lung cancer, highly-related and low-related | accuracy (%): 73.38 ± 7.29 -> 78.46 ± 5.97; 73.38 ± 7.29 -> 78.85 ± 4.55 | Improved |
| Model sample-specific negative-binomial dispersion instead of fixing the NB probability parameter (ablation) | HDP-NBFA versus NB-HDP · Lung cancer, highly-related domains | accuracy (%): 55.22 ± 3.69 -> 63.48 ± 1.23; 56.52 ± 4.61 -> 65.65 ± 4.22 | Improved |
| Use hierarchical gamma-process factor weights rather than hierarchical Dirichlet-process weights | hGNBP versus HDP-NBFA · Lung cancer, low-related domains | accuracy (%): 54.89 ± 7.38 -> 72.94 ± 1.70; 51.83 ± 8.32 -> 74.55 ± 8.84 | Improved |
| Add more source samples under a forced shared-factor structure | HDP-NBFA · Lung cancer, low-related domains | accuracy (%): 54.89 ± 7.38 -> 51.83 ± 8.32 | Hurt |
| Add more source samples under a forced shared-factor structure | NB-HDP · Lung cancer, low-related domains | accuracy (%): 54.57 ± 7.73 -> 53.83 ± 7.79 | Hurt |
| Increase target-domain sample count | BMDL and hGNBP-NBFA · Synthetic data | classification error | Improved |
| Increase the number of shared latent factors between domains | BMDL · Synthetic data | classification error | Improved |
| Add source-domain data through BMDL factor sharing | BMDL versus target-only hGNBP-NBFA · Synthetic data, varying domain relevance | classification error | Improved |
| Add another low-related source domain when the highly-related domain already has 100 samples | BMDL · Lung cancer, three domains | accuracy (%) | No clear effect |
| Add a highly-related source domain with 100 samples to 100 low-related source samples | BMDL · Lung cancer, three domains | accuracy (%): around 4% | Improved |
Closest papers by meaning
- Learning the Finer Things: Bayesian Structure Learning at the Instantiation Level (AAAI 2023 · similarity 0.85)
- Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction (ICLR 2024 · similarity 0.85)
- Exploiting Negative Samples: A Catalyst for Cohort Discovery in Healthcare Analytics (ICML 2024 · similarity 0.84)
- Multimodal Prototyping for cancer survival prediction (ICML 2024 · similarity 0.83)
- WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer (ICML 2024 · similarity 0.83)
- Robust Multimodal Survival Prediction with Conditional Latent Differentiation Variational AutoEncoder (CVPR 2025 · 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.
