A novel semi-supervised learning approach to analyzing metagenomic reads

A novel semi-supervised learning approach is proposed to partition metagenomic reads by combining supervised learning method and unsupervised learning method. In this paper, corresponding analytic methods and dedicated simulating studies were conducted within the scope of a controlled framework emphasizing performance improvement, especially when reads from similar species are applied. According to the experimentation and the learning deliverables, the proposed method outperforms the existing algorithms in the case that the reads partitioning has a considerable number of similar species.

[1]  S. Salzberg,et al.  Phymm and PhymmBL: Metagenomic Phylogenetic Classification with Interpolated Markov Models , 2009, Nature Methods.

[2]  Jonathan Dushoff,et al.  Unsupervised statistical clustering of environmental shotgun sequences , 2009, BMC Bioinformatics.

[3]  Yu-Wei Wu,et al.  A Novel Abundance-Based Algorithm for Binning Metagenomic Sequences Using l-Tuples , 2010, RECOMB.

[4]  Siu-Ming Yiu,et al.  MetaCluster 4.0: A Novel Binning Algorithm for NGS Reads and Huge Number of Species , 2012, J. Comput. Biol..

[5]  J. Handelsman,et al.  Molecular biological access to the chemistry of unknown soil microbes: a new frontier for natural products. , 1998, Chemistry & biology.

[6]  Daniel H. Huson,et al.  MetaSim—A Sequencing Simulator for Genomics and Metagenomics , 2008, PloS one.

[7]  E. Myers,et al.  Basic local alignment search tool. , 1990, Journal of molecular biology.

[8]  Wolfgang Gerlach,et al.  WebCARMA: a web application for the functional and taxonomic classification of unassembled metagenomic reads , 2009, BMC Bioinformatics.

[9]  Tin Chi Nguyen,et al.  MarkovBin: An Algorithm to Cluster Metagenomic Reads Using a Mixture Modeling of Hierarchical Distributions , 2013, BCB.

[10]  Alexander F. Auch,et al.  MEGAN analysis of metagenomic data. , 2007, Genome research.

[11]  Siu-Ming Yiu,et al.  MetaCluster: unsupervised binning of environmental genomic fragments and taxonomic annotation , 2010, BCB '10.

[12]  Lior Pachter,et al.  Bioinformatics for Whole-Genome Shotgun Sequencing of Microbial Communities , 2005, PLoS Comput. Biol..

[13]  Frank Oliver Glöckner,et al.  TETRA: a web-service and a stand-alone program for the analysis and comparison of tetranucleotide usage patterns in DNA sequences , 2004, BMC Bioinformatics.