Adaptive Neural Translation for Enterprises (ANTE). La traduzione automatica neurale a sostegno delle imprese emiliano-romagnole

Il progetto ANTE riguarda i nuovi sistemi di traduzione automatica (TA) e la loro applicazione nel mondo delle imprese. Lo studio prende spunto dai recenti sviluppi legati all’intelligenza artificiale e ai Big Data che negli ultimi anni hanno permesso alla TA di raggiungere livelli qualitativi molto elevati, al punto tale da essere impiegata da grandi multinazionali per raggiungere nuove quote di mercato. La TA può rispondere positivamente anche ai bisogni delle imprese di piccole dimensioni e a basso tenore tecnologico, migliorando la qualità delle comunicazioni multilingue attraverso delle traduzioni in tempi brevi e a costi contenuti. Lo studio si propone quindi di contribuire al rafforzamento della competitività internazionale delle piccole e medie imprese (PMI) emiliano- romagnole, migliorando la loro capacità di comunicazione in una o più lingue straniere attraverso l’introduzione e l’utilizzo efficace e consapevole di soluzioni ICT di ultima generazione e fornire, così, nuove opportunità di internazionalizzazione.

Security enhancements and flaws of emerging communication technologies

The multi-faced evolution of network technologies ranges from big data centers to specialized network infrastructures and protocols for mission-critical operations. For instance, technologies such as Software Defined Networking (SDN) revolutionized the world of static configuration of the network - i.e., by removing the distributed and proprietary configuration of the switched networks - centralizing the control plane. While this disruptive approach is interesting from different points of view, it can introduce new unforeseen vulnerabilities classes. One topic of particular interest in the last years is industrial network security, an interest which started to rise in 2016 with the introduction of the Industry 4.0 (I4.0) movement. Networks that were basically isolated by design are now connected to the internet to collect, archive, and analyze data. While this approach got a lot of momentum due to the predictive maintenance capabilities, these network technologies can be exploited in various ways from a cybersecurity perspective. Some of these technologies lack security measures and can introduce new families of vulnerabilities. On the other side, these networks can be used to enable accurate monitoring, formal verification, or defenses that were not practical before. This thesis explores these two fields: by introducing monitoring, protections, and detection mechanisms where the new network technologies make it feasible; and by demonstrating attacks on practical scenarios related to emerging network infrastructures not protected sufficiently. The goal of this thesis is to highlight this lack of protection in terms of attacks on and possible defenses enabled by emerging technologies. We will pursue this goal by analyzing the aforementioned technologies and by presenting three years of contribution to this field. In conclusion, we will recapitulate the research questions and give answers to them.

Deep learning and embeddings for problems of computational biology

The development of Next Generation Sequencing promotes Biology in the Big Data era. The ever-increasing gap between proteins with known sequences and those with a complete functional annotation requires computational methods for automatic structure and functional annotation. My research has been focusing on proteins and led so far to the development of three novel tools, DeepREx, E-SNPs&GO and ISPRED-SEQ, based on Machine and Deep Learning approaches. DeepREx computes the solvent exposure of residues in a protein chain. This problem is relevant for the definition of structural constraints regarding the possible folding of the protein. DeepREx exploits Long Short-Term Memory layers to capture residue-level interactions between positions distant in the sequence, achieving state-of-the-art performances. With DeepRex, I conducted a large-scale analysis investigating the relationship between solvent exposure of a residue and its probability to be pathogenic upon mutation. E-SNPs&GO predicts the pathogenicity of a Single Residue Variation. Variations occurring on a protein sequence can have different effects, possibly leading to the onset of diseases. E-SNPs&GO exploits protein embeddings generated by two novel Protein Language Models (PLMs), as well as a new way of representing functional information coming from the Gene Ontology. The method achieves state-of-the-art performances and is extremely time-efficient when compared to traditional approaches. ISPRED-SEQ predicts the presence of Protein-Protein Interaction sites in a protein sequence. Knowing how a protein interacts with other molecules is crucial for accurate functional characterization. ISPRED-SEQ exploits a convolutional layer to parse local context after embedding the protein sequence with two novel PLMs, greatly surpassing the current state-of-the-art. All methods are published in international journals and are available as user-friendly web servers. They have been developed keeping in mind standard guidelines for FAIRness (FAIR: Findable, Accessible, Interoperable, Reusable) and are integrated into the public collection of tools provided by ELIXIR, the European infrastructure for Bioinformatics.

Anticancer drug discovery using artificial intelligence: an application in pharmacological activity prediction

Hematological cancers are a heterogeneous family of diseases that can be divided into leukemias, lymphomas, and myelomas, often called “liquid tumors”. Since they cannot be surgically removable, chemotherapy represents the mainstay of their treatment. However, it still faces several challenges like drug resistance and low response rate, and the need for new anticancer agents is compelling. The drug discovery process is long-term, costly, and prone to high failure rates. With the rapid expansion of biological and chemical "big data", some computational techniques such as machine learning tools have been increasingly employed to speed up and economize the whole process. Machine learning algorithms can create complex models with the aim to determine the biological activity of compounds against several targets, based on their chemical properties. These models are defined as multi-target Quantitative Structure-Activity Relationship (mt-QSAR) and can be used to virtually screen small and large chemical libraries for the identification of new molecules with anticancer activity. The aim of my Ph.D. project was to employ machine learning techniques to build an mt-QSAR classification model for the prediction of cytotoxic drugs simultaneously active against 43 hematological cancer cell lines. For this purpose, first, I constructed a large and diversified dataset of molecules extracted from the ChEMBL database. Then, I compared the performance of different ML classification algorithms, until Random Forest was identified as the one returning the best predictions. Finally, I used different approaches to maximize the performance of the model, which achieved an accuracy of 88% by correctly classifying 93% of inactive molecules and 72% of active molecules in a validation set. This model was further applied to the virtual screening of a small dataset of molecules tested in our laboratory, where it showed 100% accuracy in correctly classifying all molecules. This result is confirmed by our previous in vitro experiments.

Anatomical biomarkers of body composition in oncological population: application and development of artificial intelligences

In the Era of precision medicine and big medical data sharing, it is necessary to solve the work-flow of digital radiological big data in a productive and effective way. In particular, nowadays, it is possible to extract information “hidden” in digital images, in order to create diagnostic algorithms helping clinicians to set up more personalized therapies, which are in particular targets of modern oncological medicine. Digital images generated by the patient have a “texture” structure that is not visible but encrypted; it is “hidden” because it cannot be recognized by sight alone. Thanks to artificial intelligence, pre- and post-processing software and generation of mathematical calculation algorithms, we could perform a classification based on non-visible data contained in radiological images. Being able to calculate the volume of tissue body composition could lead to creating clasterized classes of patients inserted in standard morphological reference tables, based on human anatomy distinguished by gender and age, and maybe in future also by race. Furthermore, the branch of “morpho-radiology" is a useful modality to solve problems regarding personalized therapies, which is particularly needed in the oncological field. Actually oncological therapies are no longer based on generic drugs but on target personalized therapy. The lack of gender and age therapies table could be filled thanks to morpho-radiology data analysis application.

Development of new tools and devices for CMB and foreground data analysis and future experiments

The discovery of the Cosmic Microwave Background (CMB) radiation in 1965 is one of the fundamental milestones supporting the Big Bang theory. The CMB is one of the most important source of information in cosmology. The excellent accuracy of the recent CMB data of WMAP and Planck satellites confirmed the validity of the standard cosmological model and set a new challenge for the data analysis processes and their interpretation. In this thesis we deal with several aspects and useful tools of the data analysis. We focus on their optimization in order to have a complete exploitation of the Planck data and contribute to the final published results. The issues investigated are: the change of coordinates of CMB maps using the HEALPix package, the problem of the aliasing effect in the generation of low resolution maps, the comparison of the Angular Power Spectrum (APS) extraction performances of the optimal QML method, implemented in the code called BolPol, and the pseudo-Cl method, implemented in Cromaster. The QML method has been then applied to the Planck data at large angular scales to extract the CMB APS. The same method has been applied also to analyze the TT parity and the Low Variance anomalies in the Planck maps, showing a consistent deviation from the standard cosmological model, the possible origins for this results have been discussed. The Cromaster code instead has been applied to the 408 MHz and 1.42 GHz surveys focusing on the analysis of the APS of selected regions of the synchrotron emission. The new generation of CMB experiments will be dedicated to polarization measurements, for which are necessary high accuracy devices for separating the polarizations. Here a new technology, called Photonic Crystals, is exploited to develop a new polarization splitter device and its performances are compared to the devices used nowadays.

Big Code Applications and Approaches

The availability of a huge amount of source code from code archives and open-source projects opens up the possibility to merge machine learning, programming languages, and software engineering research fields. This area is often referred to as Big Code where programming languages are treated instead of natural languages while different features and patterns of code can be exploited to perform many useful tasks and build supportive tools. Among all the possible applications which can be developed within the area of Big Code, the work presented in this research thesis mainly focuses on two particular tasks: the Programming Language Identification (PLI) and the Software Defect Prediction (SDP) for source codes. Programming language identification is commonly needed in program comprehension and it is usually performed directly by developers. However, when it comes at big scales, such as in widely used archives (GitHub, Software Heritage), automation of this task is desirable. To accomplish this aim, the problem is analyzed from different points of view (text and image-based learning approaches) and different models are created paying particular attention to their scalability. Software defect prediction is a fundamental step in software development for improving quality and assuring the reliability of software products. In the past, defects were searched by manual inspection or using automatic static and dynamic analyzers. Now, the automation of this task can be tackled using learning approaches that can speed up and improve related procedures. Here, two models have been built and analyzed to detect some of the commonest bugs and errors at different code granularity levels (file and method levels). Exploited data and models’ architectures are analyzed and described in detail. Quantitative and qualitative results are reported for both PLI and SDP tasks while differences and similarities concerning other related works are discussed.

Analytics and optimization for emergency healthcare processes

This thesis deals with the analysis and management of emergency healthcare processes through the use of advanced analytics and optimization approaches. Emergency processes are among the most complex within healthcare. This is due to their non-elective nature and their high variability. This thesis is divided into two topics. The first one concerns the core of emergency healthcare processes, the emergency department (ED). In the second chapter, we describe the ED that is the case study. This is a real case study with data derived from a large ED located in northern Italy. In the next two chapters, we introduce two tools for supporting ED activities. The first one is a new type of analytics model. Its aim is to overcome the traditional methods of analyzing the activities provided in the ED by means of an algorithm that analyses the ED pathway (organized as event log) as a whole. The second tool is a decision-support system, which integrates a deep neural network for the prediction of patient pathways, and an online simulator to evaluate the evolution of the ED over time. Its purpose is to provide a set of solutions to prevent and solve the problem of the ED overcrowding. The second part of the thesis focuses on the COVID-19 pandemic emergency. In the fifth chapter, we describe a tool that was used by the Bologna local health authority in the first part of the pandemic. Its purpose is to analyze the clinical pathway of a patient and from this automatically assign them a state. Physicians used the state for routing the patients to the correct clinical pathways. The last chapter is dedicated to the description of a MIP model, which was used for the organization of the COVID-19 vaccination campaign in the city of Bologna, Italy.