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.
Get full access to this article
View all access options for this article.
References
1.
AlbuquerqueL., SimoesC., NobreM.F., et al.2005. Truepera radiovictrix gen. nov., sp. nov., a new radiation resistant species and the proposal of Trueperaceae fam. nov. FEMS Microbiol. Lett., 247, 161–169.
2.
AltschulS.F., GishW., MillerW., et al.1990. Basic local alignment search tool. J. Mol. Biol., 215, 403–410.
3.
AndrewsS., TsochantaridisI., and HofmannT.2003. Support vector machines for 11 multiple-instance learning, 561–568. In Advances in Neural Information Processing Systems. MIT Press, Cambridge, MA.
4.
AridhiS., SghaierH., MaddouriM., et al.2013. Computational phenotype prediction of ionizing-radiation-resistant bacteria with a multiple-instance learning model, 18–24. In Proceedings of the 12th International Workshop on Data Mining in Bioinformatics (BioKDD13). ACM, New York, NY.
5.
Ben-HurA., and BrutlagD.2003. Remote homology detection: A motif based approach. Bioinformatics. 19, 26–33.
6.
BilliD., FriedmannE.I., HoferK.G., et al.2002. Ionizing-radiation resistance in the desiccation-tolerant cyanobacterium Chroococcidiopsis. Appl. Environ. Microbiol., 66, 1489–1492.
7.
BrooksB.W., and MurrayR.G.E.1981. Nomenclature for Micrococcus radiodurans and other radiation-resistant cocci: Deinococcaceae fam. nov. and Deinococcus gen. nov., including five species. Int. J. Syst. Bacteriol., 31, 353–360.
8.
DalyM.J.2012. Death by protein damage in irradiated cells. DNA Repair. 11, 12–21.
9.
DalyM.J., GaidamakovaE.K., MatrosovaV.Y., et al.2004. Accumulation of Mn(II) in Deinococcus radiodurans facilitates gamma-radiation resistance. Science. 306, 1025–1028.
10.
DietterichT.G., LathropR.H., and Lozano-PérezT.1997. Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell., 89, 31–71.
11.
FederighiM., and TholozanJ.-L.2001. Traitements ionisants et hautes pressions des aliments. Economica. 247, 161–169.
12.
FedorovD.N., EkimovaG.A., DoroninaN.V., et al.2013. 1-Aminocyclopropane-1- carboxylate (ACC) deaminases from Methylobacterium radiotolerans and Methylobacterium nodulans with higher specificity for ACC. FEMS Microbiol. Lett., 343, 70–76.
13.
FerreiraA.C., NobreM.F., MooreE., et al.1999. Characterization and radiation resistance of new isolates of Rubrobacter radiotolerans and Rubrobacter xylanophilus, Extremophiles. Int. J. Syst. Bacteriol., 3, 235–238.
14.
FuG., NanX., LiuH., et al.2012. Implementation of multiple-instance learning in drug activity prediction. BMC Bioinformatics. 13, S3.
15.
GhosalD., OmelchenkoM.V., GaidamakovaE.K., et al.2005. How radiation kills cells: Survival of Deinococcus radiodurans and Shewanella oneidensis under oxidative stress. FEMS Microbiol. Rev., 29, 361–375.
16.
GreenP.N., and BousfieldI.J., 1983. 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. Int. J. Syst. Bacteriol., 33, 875–877.
17.
GtariM., EssoussiI., MaaouiR., et al.2012. Contrasted resistance of stone-dwelling Geodermatophilaceae species to stresses known to give rise to reactive oxygen species. FEMS Microbiol. Ecol., 80, 566–577.
18.
HallingS.M., Peterson-BurchB.D., BrickerB.J., et al.2005. Completion of the genome sequence of Brucella abortus and comparison to the highly similar genomes of Brucella melitensis and Brucella suis. Am. Soc. Microbiol., 187, 2715–2726.
19.
HanJ., KamberM., and PeiJ.2011. Data Mining: Concepts and Techniques, 3rd edition. Morgan Kaufmann Publishers Inc., San Francisco, CA.
20.
ItoH., and IizukaH.1971. Taxonomic studies on a radio-resistant Pseudomonas. Part XII. Studies on the microorganisms of cereal grain. Agric. Biol. Chem., 35, 1566–1571.
21.
ItoH., WatanabeH., TakeshiaM., et al.1983. Isolation and identification of radiationresistant cocci belonging to the genus Deinococcus from sewage sludges and animal feeds. Agric. Biol. Chem., 47, 1239–1247.
22.
LioliosK., MavromatisK., TavernarakisN., et al.2008. The Genomes On Line Database (GOLD) in 2007: Status of genomic and metagenomic projects and their associated metadata. Nucleic Acids Res. 36, D475–D479.
23.
MakarovaK.S., OmelchenkoM.V., GaidamakovaE.K., et al.2007. Deinococcus geothermalis: The pool of extreme radiation resistance genes shrinks. PLoS ONE. 2, e955.
24.
MaronO., and PéerezT.L.1998. A framework for multiple-instance learning, 570–576. In Proceedings of the 1997 Conference on Advances in Neural Information Processing Systems. MIT Press, Cambridge, MA.
25.
OmelchenkoM.V., WolfY.I., GaidamakovaE.K., et al.2005. Comparative genomics of Thermus thermophilus and Deinococcus radiodurans: Divergent routes of adaptation to thermophily and radiation resistance. BMC Evol. Biol., 5, 57.
26.
PhillipsR.W., WiegelJ., BerryC.J., et al.2002. Kineococcus radiotolerans sp. nov., a radiation-resistant, gram-positive bacterium. Int. J. Syst. Evol. Microbiol., 52, 933–938.
27.
RaineyF.A., NobreM.F., SchumannP., et al.1997. Phylogenetic diversity of the deinococci as determined by 16S ribosomal DNA sequence comparison. Int. J. Syst. Bacteriol., 47, 510–514.
28.
RaineyF.A., RayK., FerreiraM., et al.2005. 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. Appl. Environ. Microbiol., 71, 5225–5235.
29.
SaidiR., AridhiS., Mephu NguifoE., et al.2012. Feature extraction in protein sequences classiffication: A new stability measure, 683–689. In Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine (BCB 12). ACM, New York, NY.
30.
SaidiR., MaddouriM., and Mephu NguifoE.2010. Protein sequences classification by means of feature extraction with substitution matrices. BMC Bioinformatics. 11, 175.
31.
Santiago-SoteloP., and Ramirez-PradoJ.H.2012. prfectBLAST: A platform-independent portable front end for the command terminal BLAST+ stand-alone suite. BioTechniques. 53, 299–300.
32.
SghaierH., GhediraK., BenkahlaA., et al.2008. Basal DNA repair machinery is subject to positive selection in ionizing-radiation-resistant bacteria. BMC Genomics. 9, 297.
33.
SghaierH., ThorvaldsenS., and Malek SaiedN.2013. There are more small amino acids and fewer aromatic rings in proteins of ionizing radiation-resistant bacteria. Ann. Microbiol. 63, 1483–1491.
34.
SladeD., and RadmanM.2011. Oxidative stress resistance in Deinococcus radiodurans. Microbiol. Mol. Biol. Rev. 75, 133–191.
35.
WangJ., and ZuckerJ.D.2000. Solving the multiple-instance problem: A lazy learning approach, 1119–1126. In Proceedings of the Seventeenth International Conference on Machine Learning (ICML '00). Morgan Kaufmann Publishers Inc., San Francisco, CA.
36.
WoolfitM., and BromhamL.2003. Increased rates of sequence evolution in endosymbiotic bacteria and fungi with small effective population sizes. Mol. Biol. Evol., 20, 1545–1555.
37.
YamakawaH., MaruhashiK., and NakaoY.2007. Predicting types of proteinprotein interactions using a multiple-instance learning model, 42–53. New Frontiers in Artificial Intelligence. Springer, Berlin.
38.
ZafraA., PechenizkiyM., and VenturaS.2012. ReliefF-MI: An extension of ReliefF to multiple instance learning. Neurocomputing. 75, 210–218.
39.
ZafraA., PechenizkiyM., and VenturaS.2013. Hydr-mi: A hybrid algorithm to reduce dimensionality in multiple instance learning. Inf. Sci., 222, 282–301.
