Implementazione ed ottimizzazione di algoritmi per l'analisi di Biomedical Big Data

Big Data Analytics poses many challenges to the research community who has to handle several computational problems related to the vast amount of data. An increasing interest involves Biomedical data, aiming to get the so-called personalized medicine, where therapy plans are designed on the specific genotype and phenotype of an individual patient and algorithm optimization plays a key role to this purpose. In this work we discuss about several topics related to Biomedical Big Data Analytics, with a special attention to numerical issues and algorithmic solutions related to them. We introduce a novel feature selection algorithm tailored on omics datasets, proving its efficiency on synthetic and real high-throughput genomic datasets. We tested our algorithm against other state-of-art methods obtaining better or comparable results. We also implemented and optimized different types of deep learning models, testing their efficiency on biomedical image processing tasks. Three novel frameworks for deep learning neural network models development are discussed and used to describe the numerical improvements proposed on various topics. In the first implementation we optimize two Super Resolution models showing their results on NMR images and proving their efficiency in generalization tasks without a retraining. The second optimization involves a state-of-art Object Detection neural network architecture, obtaining a significant speedup in computational performance. In the third application we discuss about femur head segmentation problem on CT images using deep learning algorithms. The last section of this work involves the implementation of a novel biomedical database obtained by the harmonization of multiple data sources, that provides network-like relationships between biomedical entities. Data related to diseases and other biological relates were mined using web-scraping methods and a novel natural language processing pipeline was designed to maximize the overlap between the different data sources involved in this project.