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
arXiv:2608.29207v1 Announce Type: new
Abstract: Protein structure modeling rests on a single computational primitive: the interaction between what a residue is (sequence content) and where it sits (t...
By Yifan Feng, Guanjie Cheng, Shihui Ying, Shaoyi Du, Yue Gao
The paper introduces a scalable method to interpret sparse autoencoder (SAE) features in the ESM-2 protein language model by leveraging geometrically inspired features of the protein α‑carbon backbone. Across 8M layers of ESM-2, a false discovery rate–controlled analysis shows that local geometry is significantly associated with many SAE features, revealing substructure within known biological labels and enabling annotation of unannotated metagenomic proteins. Ablation experiments demonstrate that removing these geometric features shifts ESM-2’s predicted contact maps toward the descriptor, linking mechanistic interpretability with structural biology.
By Siddharth Setlur, Djordje Mihajlovic, Darrick Lee
This paper introduces a new method for predicting transmembrane protein topology by employing the graph neural network SchNet. The model is trained on the same dataset used for DeepTMHMM, using 5‑fold cross‑validation, and incorporates all atom‑level embeddings rather than just sequence or alpha‑carbon features. Results indicate that GNNs hold significant promise for topological predictions without relying on pre‑trained weights.
By Sitong Chen, Xiaopeng Mao
arXiv:2607.01630v2 Announce Type: replace
Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our...
By Bingchen Huang, Yifu Chen, Zhiling Wang, Yuanchao Du
Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classification supervision alone does not sufficiently preserve task-agnostic shared backbone representations over long incremental sequences. We identify two intertwined challenges: cross-task confusion from sequential training on predominantly current-task data, which biases decision boundaries toward recent tasks; and under-optimized shared representations in the backbone that cap long-term discriminability as tasks accumulate.