Research map / Label-efficient and robust learning / Recognition and long-tail
Unsupervised Identification of Protein Compositions and Conformations via Implicit Content-Transformation Disentanglement
Mostofa Rafid Uddin, Jana Armouti, Min Xu
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 content contrastive loss Lcon(c) (ablation) | DualContrast · Simulated protein subtomograms | SAP(c): 0.13 -> 0.44 | Improved |
| add content contrastive loss Lcon(c) (ablation) | DualContrast · LineMod | SAP(c): 0.55 -> 0.47 | Hurt |
| add content contrastive loss Lcon(c) (ablation) | DualContrast · Simulated protein subtomograms | SAP(z): 0.03 -> 0.22 | Improved |
| add transformation contrastive loss Lcon(z) (ablation) | DualContrast · LineMod | SAP(c): 0.07 -> 0.47 | Improved |
| add transformation contrastive loss Lcon(z) (ablation) | DualContrast · Simulated protein subtomograms | SAP(c): 0.13 -> 0.44 | Improved |
| add transformation contrastive loss Lcon(z) (ablation) | DualContrast · Simulated protein subtomograms | SAP(z): 0.23 -> 0.22 | No clear effect |
| add both contrastive losses to a two-latent VAE (ablation) | VAE with 2 latent space · LineMod | SAP(c): 0.0 -> 0.47 | Improved |
| replace Harmony with DualContrast for composition clustering | Harmony · Simulated protein subtomograms (composition) | ARI: 0.72 -> 0.99 | Improved |
| replace Hydra with DualContrast for composition clustering | Hydra · Simulated protein subtomograms (composition) | ARI: 0.01 -> 0.99 | Improved |
| replace Harmony with DualContrast for conformation clustering | Harmony · Simulated protein subtomograms (conformation) | ARI: 0.12 -> 0.22 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Barlow Twins — Barlow Twins: Self-Supervised Learning via Redundancy Reduction (ICML 2021) · better on 3 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression (NeurIPS 2025 · similarity 0.84)
- Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models (ICML 2025 · similarity 0.84)
- Evaluating Representation Learning on the Protein Structure Universe (ICLR 2024 · similarity 0.84)
- 3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation (AAAI 2025 · similarity 0.84)
- Protein Discovery with Discrete Walk-Jump Sampling (ICLR 2024 · similarity 0.84)
- Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings (NeurIPS 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.
