<p>Proteins are involved in all of life's processes and are also responsible for many diseases. Thus, engineering proteins to perform new tasks could revolutionize many areas of biomedical research. One promising technique for protein engineering is computational structure-based protein design (CSPD). CSPD algorithms search large protein conformational spaces to approximate biophysical quantities. In this dissertation we present new algorithms to realistically and accurately model how amino acid mutations change protein structure. These algorithms model continuous flexibility, protein ensembles and positive/negative design, while providing guarantees on the output. Using these algorithms and the OSPREY protein design program we design and apply protocols for three biomedically-relevant problems: (i) prediction of new drug resistance mutations in bacteria to a new preclinical antibiotic, (ii) the redesign of llama antibodies to potentially reduce their immunogenicity for use in preclinical monkey studies, and (iii) scaffold-based anti-HIV antibody design. Experimental validation performed by our collaborators confirmed the importance of the algorithms and protocols.</p> / Dissertation

HIV/AIDS is widely spread and ranks as the sixth biggest killer all over the world. Moreover, due to the rapid replication rate and the lack of proofreading mechanism of HIV virus, drug resistance is commonly found and is one of the reasons causing the failure of the treatment. Even though the drug resistance tests are provided to the patients and help choose more efficient drugs, such experiments may take up to two weeks to finish and are expensive. Because of the fast development of the computer, drug resistance prediction using machine learning is feasible. In order to accurately predict the HIV drug resistance, two main tasks need to be solved: how to encode the protein structure, extracting the more useful information and feeding it into the machine learning tools; and which kinds of machine learning tools to choose. In our research, we first proposed a new protein encoding algorithm, which could convert various sizes of proteins into a fixed size vector. This algorithm enables feeding the protein structure information to most state of the art machine learning algorithms. In the next step, we also proposed a new classification algorithm based on sparse representation. Following that, mean shift and quantile regression were included to help extract the feature information from the data. Our results show that encoding protein structure using our newly proposed method is very efficient, and has consistently higher accuracy regardless of type of machine learning tools. Furthermore, our new classification algorithm based on sparse representation is the first application of sparse representation performed on biological data, and the result is comparable to other state of the art classification algorithms, for example ANN, SVM and multiple regression. Following that, the mean shift and quantile regression provided us with the potentially most important drug resistant mutants, and such results might help biologists/chemists to determine which mutants are the most representative candidates for further research.