Information Technology seminars
Applying Machine Learning Techniques to Structural Bioinformatics: Applications and Results
- Date and time:
- 10/09/2008, 14:00
- Location:
- Seminar Room 135, Bldg 26, Clayton School of I.T.
- Presenters:
- Dr Jiangning Song, Department of Biochemistry and Molecular Biology, Faculty of Medicine, Monash University
- Abstract:
- Disulfide bonds are primary covalent crosslinks between two cysteine residues in proteins that play critical roles in stabilizing the protein structures and are commonly found in extracytoplasmatic or secreted proteins. In protein folding prediction, the localization of disulfide bonds can greatly reduce the search in conformational space. Therefore, there is a great need to develop computational methods capable of accurately predicting disulfide connectivity patterns in proteins that could have potentially important applications.
Half-sphere exposure (HSE) is a newly developed two-dimensional solvent exposure measure. By conceptually separating an amino acid's sphere in a protein structure into two half spheres which represent its distinct spatial neighborhoods in the upward and downward directions. HSE measure shows superior performance compared with other measures such as accessible surface area and contact number. Therefore, accurate prediction of the HSE measure from amino acid sequence would be beneficial for the protein structure and function prediction.
In this talk, I will describe the applications of machine learning techniques in Structural Bioinformatics, in particular the application of support vector regression (SVR) to predict disulfide connectivity patterns and the HSE measures from protein sequences. The results indicate that the SVR approach is powerful in successfully quantifying the protein sequence-structure relationship and predicting the structural property profiles from protein sequences. This method should be very helpful in the annotation of protein sequences generated by large-scale whole-genome projects.
- Speaker biographies:
- After receiving a Ph.D. in Bioinformatics in 2005, Dr. Jiangning Song had his postdoctoral training at Institute for Molecular Bioscience and Advanced Computational Modelling Centre, University of Queensland in Brisbane. In 2007 he got the JSPS Postdoctoral Fellowship in Kyoto University, Kyoto, Japan and worked as a bioinformatician in the field of Structural Bioinformatics before becoming the NHMRC Peter Doherty Fellow at Department of Biochemistry and Molecular Biology, Monash University.
- Enquiries:
- Contact: Jeanette Niehus
- Research group website:
-
http://www.infotech.monash.edu.au/research/centres/cris/index.html
