通过多模态检索增强基础模型理解蛋白质功能
Understanding protein function with a multimodal retrieval-augmented foundation model
AI总结：
PoET-2通过多模态检索增强方法提升蛋白质功能理解与预测能力
摘要：
蛋白质语言模型（PLMs）学习自然蛋白质序列的概率分布。通过从数以千万计的自然蛋白质序列中学习，蛋白质理解和设计能力得以显现。最近的研究表明，扩大这些模型可以提高结构预测，但似乎并未提高突变理解和蛋白质功能预测的表示质量。我们引入了PoET-2，这是一种多模态、检索增强的蛋白质基础模型，它结合了上下文学习家族特定的进化约束，并可选地结合结构条件，以学习蛋白质序列上的生成分布。PoET-2使用了一个层次Transformer编码器，该编码器对序列上下文顺序具有等价性，并采用双解码器架构，具有因果和掩码语言建模目标，使PoET-2能够在完全生成和双向表示学习模式下运行。PoET-2在零样本变体效应预测上实现了最先进的性能，特别是在评分具有多个突变的变体和挑战插入缺失突变方面表现突出。在监督设置中，PoET-2的嵌入优于以前的方法，特别是在小数据集上学习序列-功能关系方面。这项工作强调了结合检索增强与多模态、以家族为中心的建模在推进蛋白质基础模型方面的益处。
英文摘要：
Protein language models (PLMs) learn probability distributions over natural protein sequences. By learning from hundreds of millions of natural protein sequences, protein understanding and design capabilities emerge. Recent works have shown that scaling these models improves structure prediction, but does not seem to improve mutation understanding and representation quality for protein function prediction. We introduce PoET-2, a multimodal, retrieval-augmented protein foundation model that incorporates in-context learning of family-specific evolutionary constraints with optional structure conditioning to learn generative distributions over protein sequences. PoET-2 uses a hierarchical transformer encoder that is equivariant to sequence context ordering and a dual decoder architecture with both causal and masked language modeling objectives, allowing PoET-2 to operate in both fully generative and bidirectional representation learning modes. PoET-2 achieves state-of-the-art performance on zero-shot variant effect prediction, excelling at scoring variants with multiple mutations and challenging indel mutations. In supervised settings, PoET-2 embeddings outperform previous methods for learning sequence-function relationships, especially with small datasets. This work highlights the benefits of combining retrieval augmentation with multimodal, family-centric modeling for advancing protein foundation models.
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。
