Hybrid Artificial Intelligence to Extract Patterns and Rules from Argumentative and Legal Texts

This Thesis is composed of a collection of works written in the period 2019-2022, whose aim is to find methodologies of Artificial Intelligence (AI) and Machine Learning to detect and classify patterns and rules in argumentative and legal texts. We define our approach “hybrid”, since we aimed at designing hybrid combinations of symbolic and sub-symbolic AI, involving both “top-down” structured knowledge and “bottom-up” data-driven knowledge. A first group of works is dedicated to the classification of argumentative patterns. Following the Waltonian model of argument and the related theory of Argumentation Schemes, these works focused on the detection of argumentative support and opposition, showing that argumentative evidences can be classified at fine-grained levels without resorting to highly engineered features. To show this, our methods involved not only traditional approaches such as TFIDF, but also some novel methods based on Tree Kernel algorithms. After the encouraging results of this first phase, we explored the use of a some emerging methodologies promoted by actors like Google, which have deeply changed NLP since 2018-19 — i.e., Transfer Learning and language models. These new methodologies markedly improved our previous results, providing us with best-performing NLP tools. Using Transfer Learning, we also performed a Sequence Labelling task to recognize the exact span of argumentative components (i.e., claims and premises), thus connecting portions of natural language to portions of arguments (i.e., to the logical-inferential dimension). The last part of our work was finally dedicated to the employment of Transfer Learning methods for the detection of rules and deontic modalities. In this case, we explored a hybrid approach which combines structured knowledge coming from two LegalXML formats (i.e., Akoma Ntoso and LegalRuleML) with sub-symbolic knowledge coming from pre-trained (and then fine-tuned) neural architectures.

Computational methods for the analysis of protein structure and function

The vast majority of known proteins have not yet been experimentally characterized and little is known about their function. The design and implementation of computational tools can provide insight into the function of proteins based on their sequence, their structure, their evolutionary history and their association with other proteins. Knowledge of the three-dimensional (3D) structure of a protein can lead to a deep understanding of its mode of action and interaction, but currently the structures of <1% of sequences have been experimentally solved. For this reason, it became urgent to develop new methods that are able to computationally extract relevant information from protein sequence and structure. The starting point of my work has been the study of the properties of contacts between protein residues, since they constrain protein folding and characterize different protein structures. Prediction of residue contacts in proteins is an interesting problem whose solution may be useful in protein folding recognition and de novo design. The prediction of these contacts requires the study of the protein inter-residue distances related to the specific type of amino acid pair that are encoded in the so-called contact map. An interesting new way of analyzing those structures came out when network studies were introduced, with pivotal papers demonstrating that protein contact networks also exhibit small-world behavior. In order to highlight constraints for the prediction of protein contact maps and for applications in the field of protein structure prediction and/or reconstruction from experimentally determined contact maps, I studied to which extent the characteristic path length and clustering coefficient of the protein contacts network are values that reveal characteristic features of protein contact maps. Provided that residue contacts are known for a protein sequence, the major features of its 3D structure could be deduced by combining this knowledge with correctly predicted motifs of secondary structure. In the second part of my work I focused on a particular protein structural motif, the coiled-coil, known to mediate a variety of fundamental biological interactions. Coiled-coils are found in a variety of structural forms and in a wide range of proteins including, for example, small units such as leucine zippers that drive the dimerization of many transcription factors or more complex structures such as the family of viral proteins responsible for virus-host membrane fusion. The coiled-coil structural motif is estimated to account for 5-10% of the protein sequences in the various genomes. Given their biological importance, in my work I introduced a Hidden Markov Model (HMM) that exploits the evolutionary information derived from multiple sequence alignments, to predict coiled-coil regions and to discriminate coiled-coil sequences. The results indicate that the new HMM outperforms all the existing programs and can be adopted for the coiled-coil prediction and for large-scale genome annotation. Genome annotation is a key issue in modern computational biology, being the starting point towards the understanding of the complex processes involved in biological networks. The rapid growth in the number of protein sequences and structures available poses new fundamental problems that still deserve an interpretation. Nevertheless, these data are at the basis of the design of new strategies for tackling problems such as the prediction of protein structure and function. Experimental determination of the functions of all these proteins would be a hugely time-consuming and costly task and, in most instances, has not been carried out. As an example, currently, approximately only 20% of annotated proteins in the Homo sapiens genome have been experimentally characterized. A commonly adopted procedure for annotating protein sequences relies on the "inheritance through homology" based on the notion that similar sequences share similar functions and structures. This procedure consists in the assignment of sequences to a specific group of functionally related sequences which had been grouped through clustering techniques. The clustering procedure is based on suitable similarity rules, since predicting protein structure and function from sequence largely depends on the value of sequence identity. However, additional levels of complexity are due to multi-domain proteins, to proteins that share common domains but that do not necessarily share the same function, to the finding that different combinations of shared domains can lead to different biological roles. In the last part of this study I developed and validate a system that contributes to sequence annotation by taking advantage of a validated transfer through inheritance procedure of the molecular functions and of the structural templates. After a cross-genome comparison with the BLAST program, clusters were built on the basis of two stringent constraints on sequence identity and coverage of the alignment. The adopted measure explicity answers to the problem of multi-domain proteins annotation and allows a fine grain division of the whole set of proteomes used, that ensures cluster homogeneity in terms of sequence length. A high level of coverage of structure templates on the length of protein sequences within clusters ensures that multi-domain proteins when present can be templates for sequences of similar length. This annotation procedure includes the possibility of reliably transferring statistically validated functions and structures to sequences considering information available in the present data bases of molecular functions and structures.

New Methods in Organocatalysis

In the following chapters new methods in organocatalysis are described. The design of new catalysts is explored starting from the synthesis and the study of ion tagged prolines to their applications and recycle, then moving to the synthesis of new bicyclic diarylprolinol silyl ethers and their use in organocatalytic transformations. The study of new organocatalytic reaction is also investigated, in particular bifunctional thioureas are employed to catalyse the conjugate addition of nitro compounds to 3-yilidene oxindoles in sequential and domino reactions. Finally, preliminary results on photochemical organocatalytic atom transfer radical addition to alkenes are discussed in the last chapter.

Structure, Dynamics and Reactivity in the Organic Solid State: Anthracene Derivatives and Charge Transfer Crystals

The work presented in this thesis tackles some important points concerning the collective properties of two typical categories of molecular crystals, i.e., anthracene derivatives and charge transfer crystals. Anthracene derivatives have constituted the class of materials from which systematical investigations of crystal-to-crystal photodimerization reactions started, developed and have been the subject of a new awakening in the recent years. In this work some of these compounds, namely, 9-cyanoanthacene, 9-anthacenecarboxylic acid and 9-methylanthracene, have been selected as model systems for a phenomenological approach to some key properties of the solid state, investigated by spectroscopic methods. The present results show that, on the basis of the solid state organization and the chemical nature of each compound, photo-reaction dynamics and kinetics display distinctive behaviors, which allows for a classification of the various processes in topochemical, non topochemical, reversible or topophysical. The second part of the thesis was focused on charge transfer crystals, binary systems formed by stoichiometric combinations of the charge donating perylene (D) and the charge accepting tetracyano-quinodimethane (A), this latter also in its fluorinated derivatives. The work was focused on the growth of single crystals, some of which not yet reported in the literature, by PVT technique. Structural and spectroscopic characterizations have been performed, with the aim of determining the degree of charge transfer between donor and acceptor in the co-crystals. An interesting outcome of the systematic search performed in this work is the definition of the experimental conditions which drive the crystal growth of the binary systems either towards the low (1:1) or the high ratio (3:1 or 3:2) stoichiometries.

Neonatal outcomes following maternal SARS-CoV-2 infection in pregnancy - longitudinal follow-up and assessment of transplacental antibody transfer

BACKGROUND: Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection in pregnancy has been associated with multiple adverse pregnancy outcomes, including the risk of in utero mother-to-child transmission. Short- and long-term outcomes of SARS-CoV-2 exposed neonates and the extent to which maternal SARS-CoV-2 antibodies are transferred to neonates are still unclear. METHODS: Prospective observational study enrolling neonates born to mothers with SARS-CoV-2 infection in pregnancy, between April 2020-April 2021. Neonates were evaluated at birth and enrolled in a 12-month follow-up. SARS-CoV-2 IgG transplacental transfer ratio was assessed in mother-neonate dyads at birth. Maternal derived IgG were followed in infants until negativizing. RESULTS: Of 2745 neonates, 106 (3.9%) were delivered by mothers with SARS-CoV-2 infection in pregnancy. Seventy-six of 106 (71.7%) mothers were symptomatic. Median gestational age and mean birth weight were 39 weeks (range 25+5-41+4) and 3305 grams (SD 468). Six of 106 (6%) neonates were born preterm, without significant differences between asymptomatic and symptomatic mothers (P=0.67). No confirmed cases of in utero infection were detected. All infants had normal cerebral ultrasound and clinical evaluation at birth and during follow-up, until a median age of 7 months (range 5-12). All mothers and 96/106 (90.5%) neonates had detectable SARS-CoV-2 IgG at birth. Transplacental transfer ratio was higher following second trimester maternal infections (mean 0.940.46 versus 1.070.64 versus 0.750.44, P=0.039), but was not significantly different between asymptomatic and symptomatic women (P=0.20). IgG level in infants progressively decreased after birth: at 3 months 53% (51/96) and at four months 68% (63/96) had lost maternal antibodies respectively. The durability of maternal antibodies was positively correlated to the IgG level at birth (r=0.66; P<0.00001). CONCLUSIONS: Maternal SARS-CoV-2 infection was not associated with increased neonatal or long-term morbidity. No cases of confirmed in utero infection were detected. Efficient transplacental IgG transfer was found following second trimester maternal infections.