Discrete Ricci curvature offers lightweight protein fold classification

Researchers have developed a novel method for protein fold classification using discrete Ricci curvature on protein contact graphs. This approach generates a lightweight, 22-dimensional feature vector that outperforms larger, pretrained protein language model embeddings like ESM-2 on benchmark datasets. Combining Ricci curvature with persistent homology further improved performance, suggesting that interpretable graph descriptors can be a practical alternative to complex language models for certain biological tasks. AI

IMPACT This research suggests that lightweight graph descriptors can be a practical alternative to large protein language models for specific biological classification tasks.

RANK_REASON The cluster contains a research paper detailing a new method for protein fold classification. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv cs.LG →

• arXiv
• ASTRAL
• ESM-2
• Forman-Ricci curvature and persistent homology of unweighted complex networks
• Ollivier-Ricci Curvature-Based Method to Community Detection in Complex Networks
• Protein Contact Graphs
• Ricci curvature
• SCOPe

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →