ABSTRACT
This study investigates an efficient and accurate computational method for predicating mycobacterial membrane protein. Mycobacterium is a pathogenic bacterium which is the causative agent of tuberculosis and leprosy. The existing feature encoding algorithms for protein sequence representation such as composition and translation, and split amino acid composition cannot suitably express the mycobacterium membrane protein and their types due to biasness among different types. Therefore, in this study a novel un-biased dipeptide composition (Unb-DPC) method is proposed. The proposed encoding scheme has two advantages, first it avoid the biasness among the different mycobacterium membrane protein and their types. Secondly, the method is fast and preserves protein sequence structure information. The experimental results yield SVM based classification accurately of 97.1% for membrane protein types and 95.0% for discriminating mycobacterium membrane and non-membrane proteins by using jackknife cross validation test. The results exhibit that proposed model achieved significant predictive performance compared to the existing algorithms and will lead to develop a powerful tool for anti-mycobacterium drugs.
Subject(s)
Dipeptides/chemistry , Membrane Proteins/chemistry , Models, Theoretical , Mycobacteriaceae/chemistry , Algorithms , Amino Acid Sequence , Bias , Computational Biology/methods , Membrane Proteins/classification , Mycobacteriaceae/ultrastructureABSTRACT
The identification of Mycobacterium tuberculosis complex (MT), using non-molecular methods, is time-consuming. The objective of this study was to evaluate a screening test for the presumptive identification of MT, which could potentially decrease laboratory turn-around time for reporting preliminary results. From January 1998 to December 1999, 3056 cultures were analysed at the Mycobacterial Laboratory, Instituto Adolfo Lutz, S los o Paulo, Brasil. The screening test consisted of observation of colony morphology on L que wenstein Jensen medium and evaluation of cord formation on smear microscopy from those positive cultures. After the screening test, the cultures identified as non-tuberculous mycobacteria were identified to species by conventional methods (growth on culture and biochemical tests). Those identified as MT were submitted to drug susceptibility tests. The presumptive identification of MT using the proposed screening test, when compared with conventional tests, presented 98.9, 86.9, 97.8 and 93.0 percent of sensitivity, specificity, positive and negative predictive values, respectively. The conclusion is that it is possible to make a presumptive identification of MT using visual analysis of colony morphology and cord formation on microscopy examination. This method could be used to report the presumptive identification of MT and to guide laboratory decisions regarding susceptibility and identification tests with little cost and in a very practical way.
Subject(s)
Cord Factors , Mycobacterium tuberculosis , Bacteriological Techniques/methods , Culture Media , Mycobacteriaceae/ultrastructure , Sensitivity and SpecificityABSTRACT
Recent progress towards an understanding of the architecture of the mycobacterial cell envelope (P.J. Brennan and H. Nikaido, Annual Review of Biochemistry 64 (1995) 29-63) provides a model with features more generally applicable to cell envelope organisation in other mycolic acid-containing bacteria. Using this archetype, a model for the organisation of the rhodococcal cell envelope is presented here, with particular reference to cell envelope composition in Rhodococcus equi. The likelihood that mycolic acids bound to the cell wall arabinogalactan contribute to the formation of a distinct outer lipid layer is emphasised. Furthermore, the model incorporates recent work which has characterised rhodococcal macroamphiphiles (lipoglycans and lipoproteins), including the VapA virulence-associated lipoproteins of R. equi.
