TaxDiff：用于蛋白质序列生成的分类学引导扩散模型
TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation
AI总结：
TaxDiff提出一种分类学引导的扩散模型，通过将物种信息注入transformer各层并结合全局与局部注意力，实现可控蛋白质序列生成，在多个基准上性能优于现有方法且耗时更短。
摘要：
设计具有特定生物功能和结构稳定性的蛋白质序列在生物学和化学中至关重要。生成模型已经展示了其在可靠蛋白质设计方面的能力。然而，以往的模型仅限于无条件生成蛋白质序列，缺乏对生物任务至关重要的可控生成能力。在这项工作中，我们提出了TaxDiff，一种用于可控蛋白质序列生成的分类学引导扩散模型，它将生物物种信息与扩散模型的生成能力相结合，在序列空间内生成结构稳定的蛋白质。具体而言，分类学控制信息被插入到transformer块的每一层中，以实现细粒度控制。全局注意力与局部注意力的结合确保了分类学特异性蛋白质的序列一致性和结构可折叠性。大量实验表明，TaxDiff在分类学引导的可控生成和无条件生成中，均能在多个蛋白质序列生成基准上持续取得更优性能。值得注意的是，TaxDiff生成的序列在基于预测结构的置信度方面甚至超过了直接结构生成模型所产生的序列，并且所需时间仅为基于扩散模型的方法的四分之一。用于生成蛋白质和训练新版TaxDiff的代码可在以下地址获取：https://github.com/Linzy19/TaxDiff。
英文摘要：
Designing protein sequences with specific biological functions and structural stability is crucial in biology and chemistry. Generative models already demonstrated their capabilities for reliable protein design. However, previous models are limited to the unconditional generation of protein sequences and lack the controllable generation ability that is vital to biological tasks. In this work, we propose TaxDiff, a taxonomic-guided diffusion model for controllable protein sequence generation that combines biological species information with the generative capabilities of diffusion models to generate structurally stable proteins within the sequence space. Specifically, taxonomic control information is inserted into each layer of the transformer block to achieve fine-grained control. The combination of global and local attention ensures the sequence consistency and structural foldability of taxonomic-specific proteins. Extensive experiments demonstrate that TaxDiff can consistently achieve better performance on multiple protein sequence generation benchmarks in both taxonomic-guided controllable generation and unconditional generation. Remarkably, the sequences generated by TaxDiff even surpass those produced by direct-structure-generation models in terms of confidence based on predicted structures and require only a quarter of the time of models based on the diffusion model. The code for generating proteins and training new versions of TaxDiff is available at:https://github.com/Linzy19/TaxDiff.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
