6 papers · ranked by Valyu relevance
Hao Ding, Nannan Wu, Tianyi Qiu
DNA foundation models such as Evo2 7B adopt hybrid Hyena/attention architectures (Striped-Hyena2) whose single-stream autoregressive decoding is bounded by weight bandwidth at ∼45 tok/s. Speculative decoding on such hybrids faces a systems problem that prior SSM work solves only partially: after a draft is verified…
Alp Tartici, Mihajlo Stojkovic, Anru Tian, Michael C. Jewett + 2 more
Protein engineering has important implications in the bioeconomy, enabling applications in materials, medicine, and energy. A key challenge is designing protein sequences that have a specific form and function. Protein inverse folding seeks to address this challenge by identifying amino acid sequences compatible with a…
Yuesong Wu, Haohao Su, Yuehua Cui
Cell-cell communication (CCC) is essential for maintaining tissue organization and driving biological progression, yet its inference from transcriptomic data has long been limited by the absence of spatial context. Advances in spatial transcriptomics (ST) now enable mechanistically grounded analyses of CCC by…
Yiming Xue, Xiaojian Liu, Weimin Zhu, Shengfan Wang + 2 more
While protein-RNA interactions are fundamental to post-transcriptional processes, achieving a holistic understanding of their regulatory logic remains challenging. Current computational models often treat binding affinity, interface mapping, and RNA design as isolated tasks, thereby failing to provide a unified…
Eun Joo Kim, Ji Hoon Jeong, June-Seek Choi, Jeansok J. Kim
A fundamental challenge for animals and humans is resolving competing survival demands under naturalistic threat, yet circuit-level mechanisms remain poorly understood. We developed a paradigm recapitulating a predator-prey encounter: Long-Evans rats emerged from a nest to forage in an open arena, choosing between…
Giansalvo Cirrincione, Elisa Ficarra, Marta Lovino
Protein language models (pLMs) such as ESM-2 and ProtBERT rely on pretraining corpora of tens to hundreds of millions of sequences and on encoder architectures whose depth, width and number of attention heads are chosen by the practitioner and never revisited during training. The entry cost of state-of-the-art pLMs is…