Research map / Probabilistic and scientific modeling / Molecules and proteins
Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images
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 |
|---|---|---|---|
| Process co-evolution matrices with CNN (plmConv) instead of plmDCA scores | plmDCA · long-range, L contacts | PPV: 0.285 -> 0.430 | Helped |
| Use plmConv instead of plmDCA | plmDCA · all non-local, Top 10 | PPV: 0.598 -> 0.807 | Helped |
| Use plmConv instead of MetaPSICOV | MetaPSICOV · long-range, L contacts | PPV: 0.339 -> 0.430 | Helped |
| Use plmConv instead of MetaPSICOV | MetaPSICOV · all non-local, L contacts | PPV: 0.516 -> 0.573 | Helped |
| Use plmConv instead of MetaPSICOV | MetaPSICOV · short-range, Top 10 | PPV: 0.754 -> 0.724 | Hurt |
| Use plmConv instead of MetaPSICOV | MetaPSICOV · medium-range, L contacts | PPV: 0.302 -> 0.304 | No clear effect |
| Use plmConv instead of plmDCA with few sequences | plmDCA · alignment information content (Fig. 3) | PPV | Helped |
| Use plmConv instead of MetaPSICOV with few sequences | MetaPSICOV · low-count end of alignment (Fig. 3) | PPV | Hurt |
| Maintain amino acid order in feature vector (method #1) (ablation) | plmConv · feature vector construction | PPV | Helped |
| Use plmConv on T0784 instead of plmDCA | plmDCA · CASP11 T0784 contact map | PPV | Helped |
Closest papers by meaning
- Protein Interface Prediction using Graph Convolutional Networks (NeurIPS 2017 · similarity 0.90)
- Clustering for Protein Representation Learning (CVPR 2024 · similarity 0.86)
- Learning Complete Protein Representation by Dynamically Coupling of Sequence and Structure (NeurIPS 2024 · similarity 0.85)
- Evaluating Representation Learning on the Protein Structure Universe (ICLR 2024 · similarity 0.85)
- Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs (NeurIPS 2025 · similarity 0.85)
- Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models (ICML 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.