Systematic Identification of Machine-Learning Models Aimed to Classify Critical Residues for Protein Function from Protein Structure.

Protein structure and protein function should be related, yet the nature of this relationship remains unsolved. Mapping the critical residues for protein function with protein structure features represents an opportunity to explore this relationship, yet two important limitations have precluded a proper analysis of the structure-function relationship of proteins: (i) the lack of a formal definition of what critical residues are and (ii) the lack of a systematic evaluation of methods and protein structure features. To address this problem, here we introduce an index to quantify the protein-function criticality of a residue based on experimental data and a strategy aimed to optimize both, descriptors of protein structure (physicochemical and centrality descriptors) and machine learning algorithms, to minimize the error in the classification of critical residues. We observed that both physicochemical and centrality descriptors of residues effectively relate protein structure and protein function, and that physicochemical descriptors better describe critical residues. We also show that critical residues are better classified when residue criticality is considered as a binary attribute (i.e., residues are considered critical or not critical). Using this binary annotation for critical residues 8 models rendered accurate and non-overlapping classification of critical residues, confirming the multi-factorial character of the structure-function relationship of proteins.

Quantitative multiplexed proteomics of Taenia solium cysts obtained from the skeletal muscle and central nervous system of pigs.

In human and porcine cysticercosis caused by the tapeworm Taenia solium, the larval stage (cysts) can infest several tissues including the central nervous system (CNS) and the skeletal muscles (SM). The cyst's proteomics changes associated with the tissue localization in the host tissues have been poorly studied. Quantitative multiplexed proteomics has the power to evaluate global proteome changes in response to different conditions. Here, using a TMT-multiplexed strategy we identified and quantified over 4,200 proteins in cysts obtained from the SM and CNS of pigs, of which 891 were host proteins. To our knowledge, this is the most extensive intermixing of host and parasite proteins reported for tapeworm infections.Several antigens in cysticercosis, i.e., GP50, paramyosin and a calcium-binding protein were enriched in skeletal muscle cysts. Our results suggested the occurrence of tissue-enriched antigen that could be useful in the improvement of the immunodiagnosis for cysticercosis. Using several algorithms for epitope detection, we selected 42 highly antigenic proteins enriched for each tissue localization of the cysts. Taking into account the fold changes and the antigen/epitope contents, we selected 10 proteins and produced synthetic peptides from the best epitopes. Nine peptides were recognized by serum antibodies of cysticercotic pigs, suggesting that those peptides are antigens. Mixtures of peptides derived from SM and CNS cysts yielded better results than mixtures of peptides derived from a single tissue location, however the identification of the 'optimal' tissue-enriched antigens remains to be discovered. Through machine learning technologies, we determined that a reliable immunodiagnostic test for porcine cysticercosis required at least five different antigenic determinants.

Machine Learnable Fold Space Representation based on Residue Cluster Classes.

MOTIVATION: Protein fold space is a conceptual framework where all possible protein folds exist and ideas about protein structure, function and evolution may be analyzed. Classification of protein folds in this space is commonly achieved by using similarity indexes and/or machine learning approaches, each with different limitations. RESULTS: We propose a method for constructing a compact vector space model of protein fold space by representing each protein structure by its residues local contacts. We developed an efficient method to statistically test for the separability of points in a space and showed that our protein fold space representation is learnable by any machine-learning algorithm. AVAILABILITY: An API is freely available at https://code.google.com/p/pyrcc/.