Machine learning tools for protein annotation: the cases of transmembrane β-barrel and myristoylated proteins

Biology is now a “Big Data Science” thanks to technological advancements allowing the characterization of the whole macromolecular content of a cell or a collection of cells. This opens interesting perspectives, but only a small portion of this data may be experimentally characterized. From this derives the demand of accurate and efficient computational tools for automatic annotation of biological molecules. This is even more true when dealing with membrane proteins, on which my research project is focused leading to the development of two machine learning-based methods: BetAware-Deep and SVMyr. BetAware-Deep is a tool for the detection and topology prediction of transmembrane beta-barrel proteins found in Gram-negative bacteria. These proteins are involved in many biological processes and primary candidates as drug targets. BetAware-Deep exploits the combination of a deep learning framework (bidirectional long short-term memory) and a probabilistic graphical model (grammatical-restrained hidden conditional random field). Moreover, it introduced a modified formulation of the hydrophobic moment, designed to include the evolutionary information. BetAware-Deep outperformed all the available methods in topology prediction and reported high scores in the detection task. Glycine myristoylation in Eukaryotes is the binding of a myristic acid on an N-terminal glycine. SVMyr is a fast method based on support vector machines designed to predict this modification in dataset of proteomic scale. It uses as input octapeptides and exploits computational scores derived from experimental examples and mean physicochemical features. SVMyr outperformed all the available methods for co-translational myristoylation prediction. In addition, it allows (as a unique feature) the prediction of post-translational myristoylation. Both the tools here described are designed having in mind best practices for the development of machine learning-based tools outlined by the bioinformatics community. Moreover, they are made available via user-friendly web servers. All this make them valuable tools for filling the gap between sequential and annotated data.

Genes involved in germline regulative pathways in metazoa: an integrative approach to investigate a key feature of animal biology

In Metazoa, the germline represents the cell lineage devoted to transmission of genetic heredity across generations. Its functions intuitively evoke the crucial roles that it plays in the development of a new organism and in the evolution of the species. Germline establishment is tightly tied to animal multicellularity itself, in which the complex differentiation of cell lineages is favoured by the confinement of totipotency in specific cell populations. In the present thesis, I addressed the subject of germline characterization in animals through different approaches, in an attempt to cover different sides and scales. First, I investigated the extent and nature of shared differentially transcribed molecular factors in 10 different species germline-related lineages. I observed that newly evolved genes are less likely to be involved in germline-related mechanisms and that the mostly shared transcriptional signal across the species considered was the upregulation of genes associated to proper DNA replication, instead of the expected transcriptional and post-transcriptional regulation, that apparently have a higher level of lineage-specificity. I then focused on the evolutionary history of Tudor domain containing proteins, a gene family that underwent germline-associated expansions in animals. Using data from 24 holozoan phyla, I could confirm the previously proposed evolution of the Tudor domain secondary structure. Also, I associated lineage-specific family reductions and expansions to peculiar genomic dynamics and to the evolution of germline-associated piRNA pathway of retrotransposon silencing. Lastly, I characterized and investigated the expression of the Tudor protein TDRD7 in the clam Ruditapes philippinarum. Through immunolocalization, I could compare its expression profiles in gametogenic specimens to the previously characterized germline marker vasa. Combining results with literature, I proposed that, in this species, TDRD7 is involved in the assembly of germ granules, i.e. cytoplasmic structures associated to germline differentiation in virtually all animals, but whose assemblers can be taxon specific.