arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.05949cs.LGq-bio.QM
收藏

生物序列分析的分布式表示

Distributed Representations for Biological Sequence Analysis

IIIT Delhi(德里印度理工学院);Yahoo! Research(雅虎研究院);Queensland University of Technology (QUT)(昆士兰理工大学)

Dhananjay Kimothi, Akshay Soni, Pravesh Biyani, James M. Hogan

摘要:

生物序列比较是推断各种生物的相关性及其组分的功能相似性的关键步骤。由于下一代测序的努力,现在有大量的序列数据可供处理,用于一系列生物信息学应用。在较低维向量空间中的核苷酸或氨基酸字母表上嵌入生物序列使得数据更适合当前机器学习工具使用,只要嵌入的质量高并且它捕获原始序列的最有意义的信息。受文本文档嵌入文献的最新进展的启发,我们提出了一种新的方法,称为seq2vec,在欧氏空间中表示一个完整的生物序列。新的表示法有可能捕获序列比较任务所需的原始序列的上下文信息。我们用蛋白质序列分类和检索任务测试了我们的嵌入,并展示了令人鼓舞的结果。

英文摘要:

Biological sequence comparison is a key step in inferring the relatedness of various organisms and the functional similarity of their components. Thanks to the Next Generation Sequencing efforts, an abundance of sequence data is now available to be processed for a range of bioinformatics applications. Embedding a biological sequence over a nucleotide or amino acid alphabet in a lower dimensional vector space makes the data more amenable for use by current machine learning tools, provided the quality of embedding is high and it captures the most meaningful information of the original sequences. Motivated by recent advances in the text document embedding literature, we present a new method, called seq2vec, to represent a complete biological sequence in an Euclidean space. The new representation has the potential to capture the contextual information of the original sequence necessary for sequence comparison tasks. We test our embeddings with protein sequence classification and retrieval tasks and demonstrate encouraging outcomes.

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。

↑