arXiv Machine Learning July 21, 2026 By Jianru Shen

Discrete Ricci Curvature on Protein Contact Graphs for Lightweight Fold Classification

Read the original on arXiv Machine Learning →

arXiv:2607. 16553v1 Announce Type: new Abstract: Protein fold classification can be approached via sequence-based representations or structural descriptors, but direct comparisons between lightweight handcrafted descriptors and pretrained protein language model embeddings remain limited.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 15

PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies

arXiv:2605. 01625v3 Announce Type: replace Abstract: Proteins are inherently multiscale physical systems whose functional properties emerge from coordinated structural organization across multiple spatial resolutions, ranging from atomic interactions to global fold topology.

By Viet Thanh Duy Nguyen, John K. Johnstone, Truong-Son Hy

benchmarks

arXiv AI

Jul 28

LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning

arXiv:2607. 22777v1 Announce Type: cross Abstract: Protein language models learn transferable sequence representations.

By Chen Wang, Boming Kang, Qinghua Cui

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 16

Learning Topological Representations for Molecular Dynamics

arXiv:2606. 14737v1 Announce Type: cross Abstract: Molecular dynamics (MD) simulations generate trajectories in a high-dimensional configuration space whose analysis critically depends on molecular descriptors, typically handcrafted observables or learned kinetic embeddings.

By Dominik Geng, Florian Graf, Martin Uray, Roland Kwitt

rag

arXiv AI

Jul 3

MKGR: Multimodal Knowledge-Graph Representation Learning for Cold-Start Protein-Protein Interaction Prediction

arXiv:2607. 01627v1 Announce Type: cross Abstract: Accurate protein-protein interaction (PPI) prediction is central to functional genomics, disease mechanism discovery, and drug development.

By Wenbo Zhang

rag multimodal benchmarks

arXiv Machine Learning

Jun 11

GLACIER: A Multimodal Student-Teacher Foundation Model for Molecular Property Prediction

arXiv:2606. 11382v1 Announce Type: new Abstract: Deep learning models facilitate the discovery of molecules with tailored properties among billions of candidate compounds.

By Emily Nguyen, Yongchan Hong, Harsh Toshniwal, Yan Liu, Andreas Luttens

llms rag multimodal benchmarks safety

arXiv AI

Jun 9

SurfDesign: Effective Protein Design on Molecular Surfaces

arXiv:2606. 07567v1 Announce Type: cross Abstract: Protein function is largely determined by molecular surface geometry and physicochemical complementarity, yet most protein design methods condition only on backbone structure.

By Fang Wu, Shuting Jin, Xiangru Tang, Mark Gerstein, Xiangxiang Zeng, Yejin Choi, Jure Leskovec, Jinbo Xu

llms fine-tuning benchmarks

Related stories

PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies

LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning

Learning Topological Representations for Molecular Dynamics

MKGR: Multimodal Knowledge-Graph Representation Learning for Cold-Start Protein-Protein Interaction Prediction

GLACIER: A Multimodal Student-Teacher Foundation Model for Molecular Property Prediction

SurfDesign: Effective Protein Design on Molecular Surfaces