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.

NMR Based Foodomics to Investigate the Digestibility of Protein-Rich Food Products

Nowadays, in developed countries, the excessive food intake, in conjunction with a decreased physical activity, has led to an increase in lifestyle-related diseases, such as obesity, cardiovascular diseases, type -2 diabetes, a range of cancer types and arthritis. The socio-economic importance of such lifestyle-related diseases has encouraged countries to increase their efforts in research, and many projects have been initiated recently in research that focuses on the relationship between food and health. Thanks to these efforts and to the growing availability of technologies, the food companies are beginning to develop healthier food. The necessity of rapid and affordable methods, helping the food industries in the ingredient selection has stimulated the development of in vitro systems that simulate the physiological functions to which the food components are submitted when administrated in vivo. One of the most promising tool now available appears the in vitro digestion, which aims at predicting, in a comparative way among analogue food products, the bioaccessibility of the nutrients of interest.. The adoption of the foodomics approach has been chosen in this work to evaluate the modifications occurring during the in vitro digestion of selected protein-rich food products. The measure of the proteins breakdown was performed via NMR spectroscopy, the only techniques capable of observing, directly in the simulated gastric and duodenal fluids, the soluble oligo- and polypeptides released during the in vitro digestion process. The overall approach pioneered along this PhD work, has been discussed and promoted in a large scientific community, with specialists networked under the INFOGEST COST Action, which recently released a harmonized protocol for the in vitro digestion. NMR spectroscopy, when used in tandem with the in vitro digestion, generates a new concept, which provides an additional attribute to describe the food quality: the comparative digestibility, which measures the improvement of the nutrients bioaccessibility.

Ruolo del gene umano CYYR1: dallo studio funzionale dell'ortologo in Danio rerio alla potenziale implicazione in processi tumorigenici

Il locus CYYR1 identificato e clonato sul cromosoma 21 umano è stato caratterizzato dal punto di vista molecolare come un sistema multitrascritto, esclusivo dei vertebrati che ad oggi è orfano di una funzione specifica. Dati presenti in lettura e rintracciati mostrano una possibile relazione tra il gene CYYR1 e il pathway di Sonic Hedgehog (SHH). In questo progetto di tesi è stato utilizzato il modello animale Danio rerio per indagare il ruolo funzionale dell’ortologo (cyyr1), attraverso esperimenti di gain e loss of function che hanno permesso di dimostrare un suo coinvolgimento nello sviluppo del sistema nervoso centrale, del cuore e del tessuto muscolare. Lo studio dell’ortologo in zebrafish è stato associato all’utilizzo di linee cellulari di rabdomiosarcoma umano. I risultati ottenuti dall’induzione al differenziamento miogenico di queste linee, insieme ai dati ottenuti in Danio rerio, confermano il possibile coinvolgimento del gene CYYR1 nella miogenesi. Lo studio delle relazione tra il pathway di SHH e l’espressione del gene CYYR1 è stato condotto in entrambi i modelli con l’utilizzo di differenti inibitori della via di segnalazione. I risultati ottenuti mostrano che sistemi inibitori agenti direttamente sul recettore SMO riducono l’espressione del gene. Un dato inaspettato in Danio rerio ottenuto durante questi esperimenti di inibizione, ha aperto una nuova linea di ricerca in collaborazione con l’Università di Warwick tesa a verificare la relazione tra il gene cyyr1 e il gene lefty1. Gli esperimenti condotti presso il laboratorio della Prof.ssa Sampath hanno dimostrato la localizzazione del prodotto proteico cyyr1 in Danio rerio e indagato co-localizzazioni con la proteina lefty1. Infine, in collaborazione con Dr. Deflorian e della Prof.ssa Pistocchi, è stato generato un mutante di Danio rerio deleto per il gene cyyr1 con la tecnica CRISPR/Cas9. La caratterizzazione del mutante cyyr1 -/- ha confermato alcuni dei dati ottenuti attraverso esperimenti di loss of function.