Machine learning methods for prediction of disulphide bonding states of cysteine residues in proteins

The goal of this thesis work is to develop a computational method based on machine learning techniques for predicting disulfide-bonding states of cysteine residues in proteins, which is a sub-problem of a bigger and yet unsolved problem of protein structure prediction. Improvement in the prediction of disulfide bonding states of cysteine residues will help in putting a constraint in the three dimensional (3D) space of the respective protein structure, and thus will eventually help in the prediction of 3D structure of proteins. Results of this work will have direct implications in site-directed mutational studies of proteins, proteins engineering and the problem of protein folding. We have used a combination of Artificial Neural Network (ANN) and Hidden Markov Model (HMM), the so-called Hidden Neural Network (HNN) as a machine learning technique to develop our prediction method. By using different global and local features of proteins (specifically profiles, parity of cysteine residues, average cysteine conservation, correlated mutation, sub-cellular localization, and signal peptide) as inputs and considering Eukaryotes and Prokaryotes separately we have reached to a remarkable accuracy of 94% on cysteine basis for both Eukaryotic and Prokaryotic datasets, and an accuracy of 90% and 93% on protein basis for Eukaryotic dataset and Prokaryotic dataset respectively. These accuracies are best so far ever reached by any existing prediction methods, and thus our prediction method has outperformed all the previously developed approaches and therefore is more reliable. Most interesting part of this thesis work is the differences in the prediction performances of Eukaryotes and Prokaryotes at the basic level of input coding when ‘profile’ information was given as input to our prediction method. And one of the reasons for this we discover is the difference in the amino acid composition of the local environment of bonded and free cysteine residues in Eukaryotes and Prokaryotes. Eukaryotic bonded cysteine examples have a ‘symmetric-cysteine-rich’ environment, where as Prokaryotic bonded examples lack it.

Production of bioactive peptides through sequencial action of Yarrowia lipolytica proteases and chemical glycation

This PhD thesis is aimed at studying the suitability of proteases realised by Yarrowia lipolytica to hydrolyse proteins of different origins available as industrial food by-products. Several strains of Y. lipolytica have been screened for the production of extracellular proteases by zymography. On the basis of the results some strains released only a protease having a MW of 37 kDa, which corresponds to the already reported acidic protease, while other produced prevalently or only a protease with a MW higher than 200 kDa. The proteases have been screened for their "cold attitude" on gelatin, gluten and skim milk. This property can be relevant from a biotechnological point of view in order to save energy consumption during industrial processes. Most of the strains used were endowed with proteolytic activity at 6 °C on all the three proteins. The proteolytic breakdown profiles of the proteins, detected at 27 °C, were different related to the specific strains of Y. lipolytica. The time course of the hydrolysis, tested on gelatin, affected the final bioactivities of the peptide mixtures produced. In particular, an increase in both the antioxidant and antimicrobial activities was detected when the protease of the strain Y. lipolytica 1IIYL4A was used. The final part of this work was focused on the improvement of the peptides bioactivities through a novel process based on the production of glycopeptides. Firstly, the main reaction parameters were optimized in a model system, secondly a more complex system, based on gluten hydrolysates, was taken into consideration to produce glycopeptides. The presence of the sugar moiety reduced the hydrophobicity of the glycopeptides, thus affecting the final antimicrobial activity which was significantly improved. The use of this procedure could be highly effective to modify peptides and can be employed to create innovative functional peptides using a mild temperature process.