MetaMLP: A Fast Word Embedding Based Classifier to Profile Target Gene Databases in Metagenomic Samples
MetaMLP: A Fast Word Embedding Based Classifier to Profile Target Gene Databases in Metagenomic Samples
复制标题
MetaMLP：一种基于快速词嵌入的分类器，用于分析宏基因组样本中的目标基因数据库
DOI：
10.1089/cmb.2021.0273
复制
发表时间：
2021
影响因子：
1.7
通讯作者：
Zhang, Liqing
中科院分区：
文献类型：
--
作者：
Arango-argoty, Gustavo A.;Heath, Lenwood S.;Pruden, Amy;Vikesland, Peter J.;Zhang, Liqing
宏基因组样品的功能谱使得能够更好地理解环境中的微生物种群。这种分析包括将短测序读数分配给特定的功能类别。通常，人工管理的数据库用于功能分配，基因被排列成不同的类别。序列比对已被广泛用于针对策展数据库对宏基因组样品进行分析。然而，该方法是耗时的并且需要高计算资源。虽然近年来已经开发了几种基于k-mer组成的无干扰方法，但它们仍然需要大量的计算机内存。在这篇文章中，MetaMLP（Metagenomics Machine Learning Profiler）是一种机器学习方法，它将序列表示为数字向量（嵌入），并使用一个简单的隐藏层神经网络来分析功能类别。与其他方法不同，MetaMLP通过使用简化的字母表从完整和部分alk-mer构建序列嵌入来实现部分匹配。与DIAMOND（最快的序列比对方法之一）相比，MetaMLP能够识别略多的读数，并以0.99的精度和0.99的召回率进行准确的预测。MetaMLP可以在10分钟内在笔记本电脑上处理1亿次读取，比DIAMOND快50倍。
The functional profile of metagenomic samples enables improved understanding of microbial populations in the environment. Such analysis consists of assigning short sequencing reads to a particular functional category. Normally, manually curated databases are used for functional assignment, and genes are arranged into different classes. Sequence alignment has been widely used to profile metagenomic samples against curated databases. However, this method is time consuming and requires high computational resources. While several alignment-free methods based onk-mer composition have been developed in recent years, they still require large amounts of computer main memory. In this article, MetaMLP (Metagenomics Machine Learning Profiler), a machine learning method that represents sequences as numerical vectors (embeddings) and uses a simple one hidden layer neural network to profile functional categories, is developed. Unlike other methods, MetaMLP enables partial matching by using a reduced alphabet to build sequence embeddings from full and partialk-mers. MetaMLP is able to identify a slightly larger number of reads compared with DIAMOND (one of the fastest sequence alignment methods), as well as to perform accurate predictions with 0.99 precision and 0.99 recall. MetaMLP can process 100M reads in ∼10 minutes on a laptop computer, which is 50 times faster than DIAMOND.