Prediction of Ionizing Radiation Resistance in Bacteria Using a Multiple Instance Learning Model

Ionizing-radiation-resistant bacteria (IRRB) are important in biotechnology. In this context, in silico methods of phenotypic prediction and genotype-phenotype relationship discovery are limited. In this work, we analyzed basal DNA repair proteins of most known proteome sequences of IRRB and ionizing-radiation-sensitive bacteria (IRSB) in order to learn a classifier that correctly predicts this bacterial phenotype. We formulated the problem of predicting bacterial ionizing radiation resistance (IRR) as a multiple-instance learning (MIL) problem, and we proposed a novel approach for this purpose. We provide a MIL-based prediction system that classifies a bacterium to either IRRB or IRSB. The experimental results of the proposed system are satisfactory with 91.5% of successful predictions.

[1]  E. Stackebrandt,et al.  Phylogenetic diversity of the deinococci as determined by 16S ribosomal DNA sequence comparison. , 1997, International journal of systematic bacteriology.

[2]  Eugene V Koonin,et al.  Comparative genomics of Thermus thermophilus and Deinococcus radiodurans: divergent routes of adaptation to thermophily and radiation resistance , 2005, BMC Evolutionary Biology.

[3]  I-Min A. Chen,et al.  The Genomes On Line Database (GOLD) in 2007: status of genomic and metagenomic projects and their associated metadata , 2007, Nucleic Acids Res..

[4]  Nikos Kyrpides,et al.  The Genomes On Line Database (GOLD) in 2007: status of genomic and metagenomic projects and their associated metadata , 2007, Nucleic Acids Res..

[5]  J. Ramírez-Prado,et al.  prfectBLAST: a platform-independent portable front end for the command terminal BLAST+ stand-alone suite. , 2012, BioTechniques.

[6]  John R. Battista,et al.  Extensive Diversity of Ionizing-Radiation-Resistant Bacteria Recovered from Sonoran Desert Soil and Description of Nine New Species of the Genus Deinococcus Obtained from a Single Soil Sample , 2005, Applied and Environmental Microbiology.

[7]  Yixin Chen,et al.  Implementation of multiple-instance learning in drug activity prediction , 2012, BMC Bioinformatics.

[8]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[9]  F. Rainey,et al.  Characterization and radiation resistance of new isolates of Rubrobacter radiotolerans and Rubrobacter xylanophilus , 1999, Extremophiles.

[10]  Haïtham Sghaier,et al.  Contrasted resistance of stone-dwelling Geodermatophilaceae species to stresses known to give rise to reactive oxygen species. , 2012, FEMS microbiology ecology.

[11]  Hiroshi Yamakawa,et al.  Predicting Types of Protein-Protein Interactions Using a Multiple-Instance Learning Model , 2006, JSAI.

[12]  Mikhail S. Gelfand,et al.  Deinococcus geothermalis: The Pool of Extreme Radiation Resistance Genes Shrinks , 2007, PloS one.

[13]  Daniela Billi,et al.  Ionizing-Radiation Resistance in the Desiccation-Tolerant CyanobacteriumChroococcidiopsis , 2000, Applied and Environmental Microbiology.

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

[15]  M. Daly,et al.  Death by protein damage in irradiated cells. , 2012, DNA repair.

[16]  Hiroshi Iizuka,et al.  Taxonomic Studies on a Radio-resistant Pseudomonas , 1971 .

[17]  I. Bousfield,et al.  Emendation of Methylobacterium Patt, Cole, and Hanson 1976; Methylobacterium rhodinum (Heumann 1962) comb. nov. corrig.; Methylobacterium radiotolerans (Ito and Iizuka 1971) comb. nov. corrig.; and Methylobacterium mesophilicum (Austin and Goodfellow 1979) comb. nov. , 1983 .

[18]  Tomás Lozano-Pérez,et al.  A Framework for Multiple-Instance Learning , 1997, NIPS.

[19]  Hiroshi Iizuka,et al.  Taxonomic Studies on a Radio-resistant Pseudomonas :Part XII. Studies on the Microorganisms of Cereal Grain , 1971 .

[20]  H. Sghaier,et al.  There are more small amino acids and fewer aromatic rings in proteins of ionizing radiation-resistant bacteria , 2013, Annals of Microbiology.

[21]  Jun Wang,et al.  Solving the Multiple-Instance Problem: A Lazy Learning Approach , 2000, ICML.

[22]  Haïtham Sghaier,et al.  Basal DNA repair machinery is subject to positive selection in ionizing-radiation-resistant bacteria , 2008, BMC Genomics.

[23]  K. Makarova,et al.  Accumulation of Mn(II) in Deinococcus radiodurans Facilitates Gamma-Radiation Resistance , 2004, Science.

[24]  Mykola Pechenizkiy,et al.  ReliefF-MI: An extension of ReliefF to multiple instance learning , 2012, Neurocomputing.

[25]  Y. Trotsenko,et al.  1-Aminocyclopropane-1-carboxylate (ACC) deaminases from Methylobacterium radiotolerans and Methylobacterium nodulans with higher specificity for ACC. , 2013, FEMS microbiology letters.

[26]  Zhang Qing,et al.  Completion of the Genome Sequence of Brucella abortus and Comparison to the Highly Similar Genomes of Brucella melitensis and Brucella suis , 2005, Journal of bacteriology.

[27]  Lawrence P Wackett,et al.  How radiation kills cells: survival of Deinococcus radiodurans and Shewanella oneidensis under oxidative stress. , 2005, FEMS microbiology reviews.

[28]  L. Bromham,et al.  Increased rates of sequence evolution in endosymbiotic bacteria and fungi with small effective population sizes. , 2003, Molecular biology and evolution.

[29]  Jian Pei,et al.  Data Mining: Concepts and Techniques, 3rd edition , 2006 .

[30]  Douglas L. Brutlag,et al.  Remote homology detection: a motif based approach , 2003, ISMB.

[31]  Luciana Albuquerque,et al.  Truepera radiovictrix gen. nov., sp. nov., a new radiation resistant species and the proposal of Trueperaceae fam. nov. , 2005, FEMS microbiology letters.

[32]  Mykola Pechenizkiy,et al.  HyDR-MI: A hybrid algorithm to reduce dimensionality in multiple instance learning , 2013, Inf. Sci..

[33]  Sabeur Aridhi,et al.  Feature extraction in protein sequences classification: a new stability measure , 2012, BCB.

[34]  M. Radman,et al.  Oxidative Stress Resistance in Deinococcus radiodurans , 2011, Microbiology and Molecular Reviews.

[35]  R. Murray,et al.  Nomenclature for “Micrococcus radiodurans” and Other Radiation-Resistant Cocci: Deinococcaceae fam. nov. and Deinococcus gen. nov., Including Five Species , 1981 .

[36]  H. Iizuka,et al.  Isolation and Identification of Radiation-resistant Cocci Belonging to the Genus Deinococcus from Sewage Sludges and Animal Feeds , 1983 .

[37]  Engelbert Mephu Nguifo,et al.  Protein sequences classification by means of feature extraction with substitution matrices , 2010, BMC Bioinformatics.

[38]  Sabeur Aridhi,et al.  Computational phenotype prediction of ionizing-radiation-resistant bacteria with a multiple-instance learning model , 2013, BioKDD '13.

[39]  Juergen Wiegel,et al.  Kineococcus radiotolerans sp. nov., a radiation-resistant, gram-positive bacterium. , 2002, International journal of systematic and evolutionary microbiology.

[40]  Thomas Hofmann,et al.  Support Vector Machines for Multiple-Instance Learning , 2002, NIPS.