Experimentally determining protein structure is a hard problem, with applications in both medicine and industry. Predicting protein structure is also difficult. Predicted contacts between residues within a protein is helpful during protein structure prediction. Recent state-of-the-art models have used deep learning to improve protein contact prediction. This thesis presents a new deep learning model for protein contact prediction, TiramiProt. It is based on the Tiramisu deep learning architecture, and trained and evaluated on the same data as the PconsC4 protein contact prediction model. 228 models using different combinations of hyperparameters were trained until convergence. The final TiramiProt model performs on par with two current state-of-the-art protein contact prediction models, PconsC4 and RaptorX-Contact, across a range of different metrics. A Python package and a Singularity container for running TiramiProt are available at https://gitlab.com/nikos.t.renhuldt/TiramiProt. / Att kunna bestämma proteiners struktur har tillämpningar inom både medicin och industri. Såväl experimentell bestämning av proteinstruktur som prediktion av densamma är svårt. Predicerad kontakt mellan olika delar av ett protein underlättar prediktion av proteinstruktur. Under senare tid har djupinlärning använts för att bygga bättre modeller för kontaktprediktion. Den här uppsatsen beskriver en ny djupinlärningsmodell för prediktion av proteinkontakter, TiramiProt. Modellen bygger på djupinlärningsarkitekturen Tiramisu. TiramiProt tränas och utvärderas på samma data som kontaktprediktionsmodellen PconsC4. Totalt tränades modeller med 228 olika hyperparameterkombinationer till konvergens. Mätt över ett flertal olika parametrar presterar den färdiga TiramiProt-modellen resultat i klass med state-of-the-art-modellerna PconsC4 och RaptorX-Contact. TiramiProt finns tillgängligt som ett Python-paket samt en Singularity-container via https://gitlab.com/nikos.t.renhuldt/TiramiProt.

Correlated mutation analysis is an effective approach for predicting functional and structural residue interactions from protein multiple sequence alignments. A prediction pipeline over the Pfam database was developed to predict residue contacts within protein domains. Cross- reference with the PDB showed these contacts are spatially close. Furthermore, we found our predictions to be biochemically reasonable and correspond closely with known contact matrices. This large-scale search for coevolving regions within protein domains revealed that if two sites in an alignment covary, then neighboring sites in the alignment would also typically covary, resulting in clusters of covarying residues. The program PatchD was developed to measure the covariation between disconnected sequence clusters to reveal patch covariation. Patches that exhibited strong covariation identified multiple residues that were generally nearby in the protein structures, suggesting that the detection of covarying patches can be used in addition to traditional CMA approaches to reveal functional interaction partners.

Correlated mutation analysis is an effective approach for predicting functional and structural residue interactions from protein multiple sequence alignments. A prediction pipeline over the Pfam database was developed to predict residue contacts within protein domains. Cross- reference with the PDB showed these contacts are spatially close. Furthermore, we found our predictions to be biochemically reasonable and correspond closely with known contact matrices. This large-scale search for coevolving regions within protein domains revealed that if two sites in an alignment covary, then neighboring sites in the alignment would also typically covary, resulting in clusters of covarying residues. The program PatchD was developed to measure the covariation between disconnected sequence clusters to reveal patch covariation. Patches that exhibited strong covariation identified multiple residues that were generally nearby in the protein structures, suggesting that the detection of covarying patches can be used in addition to traditional CMA approaches to reveal functional interaction partners.

Despite the fundamental role of experimental protein structure determination, computational methods are of essential importance to bridge the ever growing gap between available protein sequence and structure data. Common structure prediction methods rely on experimental data, which is not available for about half of the known protein families. Recent advancements in amino acid contact prediction have revolutionized the field of protein structure prediction. Contacts can be used to guide template-free structure predictions that do not rely on experimentally solved structures of homologous proteins. Such methods are now able to produce accurate models for a wide range of protein families. We developed PconsC2, an approach that improved existing contact prediction methods by recognizing intra-molecular contact patterns and noise reduction. An inherent problem of contact prediction based on maximum entropy models is that large alignments with over 1000 effective sequences are needed to infer contacts accurately. These are however not available for more than 80% of all protein families that do not have a representative structure in PDB. With PconsC3, we could extend the applicability of contact prediction to families as small as 100 effective sequences by combining global inference methods with machine learning based on local pairwise measures. By introducing PconsFold, a pipeline for contact-based structure prediction, we could show that improvements in contact prediction accuracy translate to more accurate models. Finally, we applied a similar technique to Pfam, a comprehensive database of known protein families. In addition to using a faster folding protocol we employed model quality assessment methods, crucial for estimating the confidence in the accuracy of predicted models. We propose models tobe accurate for 558 families that do not have a representative known structure. Out of those, over 75% have not been reported before. / <p>At the time of the doctoral defense, the following papers were unpublished and had a status as follows: Paper 2: Submitted. Paper 4: In press.</p><p> </p>

This thesis introduces a framework for enhancing DTN (Delay-/Disruption-Tolerant Networking) routing in dynamic LEO satellite constellations based on the prediction of contacts. The solution is developed with a clear focus on the requirements imposed by the 'Ring Road' use case, mandating a concept for dynamic contact prediction and its integration into a state-of-the-art routing approach. The resulting system does not restrict possible applications to the 'Ring Road,' but allows for flexible adaptation to further use cases. A thorough evaluation shows that employing proactive routing in concert with a prediction mechanism offers significantly improved performance when compared to alternative opportunistic routing techniques.