||December 10, 2009
||Dr. Jiangning Song, Department of Biochemistry and Molecular Biology, Monash University, Australia
||Characterizing substrate specificity of proteases using machine learning techniques
The ability to catalytically hydrolyse protein substrates after synthesis is fundamental for all forms of life. Indeed, controlled proteolysis is one of the major pathways by which the estimated 1-1.5 million peptides and proteins needed to fulfil the complexity of human
life are produced from ~26,000 human genes (1). Proteases thus have central roles in “life and death” processes, such as neural, endocrine and cardiovascular signalling, digestion, immunity, cell division, and apoptosis.
The key to understanding the physiological role of a protease is to identify its natural substrate(s). Many proteases have the potential to cleave multiple proteins in different physiological compartments.
Knowledge in regards to the substrate specificity of a protease can dramatically improve our ability to predict target protein substrates, however, this information can at present only be derived from experimental approaches. In the absence of such data, the targets of protease function cannot be deduced a priori from the structure or sequence of the protease. Solving the“substrate identification” problem is fundamental for both understanding protease systems biology and the development of therapeutics that target specific protease regulated pathways. To address this problem, I aim to develop novel bioinformatic approaches to make testable predictions in regards to the substrate specificity and biological targets of proteases. In particular, I aim to ascertain whether sequential/structural information can help to improve our ability to predict novel substrates for a wide range of functionally important proteases.