arXiv:2601. 12805v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks.
By Xiaohan Huang, Meng Xiao, Chuan Qin, Qingqing Long, Jinmiao Chen, Yuanchun Zhou, Hengshu Zhu
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
arXiv:2602. 02320v4 Announce Type: replace-cross Abstract: Molecular function is largely determined by structure.
By Feiyang Cai, Guijuan He, Yi Hu, Jingjing Wang, Joshua Luo, Tianyu Zhu, Srikanth Pilla, Gang Li, Ling Liu, Feng Luo
arXiv:2608. 12090v1 Announce Type: new Abstract: Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology.
By Roman Joeres, Ilya Senatorov, Olga V. Kalinina
Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora of protein sequence data, are widely used to translate amino acid sequences into latent-space embeddings, ready for use in diverse downstream tasks (DTs).
The paper introduces OmicsBench, a new reasoning benchmark for multi‑omics sequences that includes 1,160 expert‑validated questions across DNA regulation, RNA processing, and protein function tasks, requiring traceable evidence chains. Evaluation of 17 large language models shows that scientific LLMs, while more accurate in classification, often lack valid evidence, suggesting shortcut learning. To address this, the authors propose tool‑augmented on‑policy distillation (TA‑OPD), a post‑training method that improves both evidence grounding and predictive performance across five Qwen3.5 models of varying sizes.
By Jie Ying, Zhefan Wang, Zihong Chen, Zhengqing Li, Jinzhe Li, Gang Li, Jian Liu, Fang Hu, Tao Luo, Zhonghang Yuan, Wanli Ouyang, Stan Z. Li, Fan Yang, Nanqing Dong