Network analysis and machine learning assist drug repurposing and safety assessment in neurological diseases

In recent decades, two prominent trends have influenced the data modeling field, namely network analysis and machine learning. This thesis explores the practical applications of these techniques within the domain of drug research, unveiling their multifaceted potential for advancing our comprehension of complex biological systems. The research undertaken during this PhD program is situated at the intersection of network theory, computational methods, and drug research. Across six projects presented herein, there is a gradual increase in model complexity. These projects traverse a diverse range of topics, with a specific emphasis on drug repurposing and safety in the context of neurological diseases. The aim of these projects is to leverage existing biomedical knowledge to develop innovative approaches that bolster drug research. The investigations have produced practical solutions, not only providing insights into the intricacies of biological systems, but also allowing the creation of valuable tools for their analysis. In short, the achievements are: • A novel computational algorithm to identify adverse events specific to fixed-dose drug combinations. • A web application that tracks the clinical drug research response to SARS-CoV-2. • A Python package for differential gene expression analysis and the identification of key regulatory "switch genes". • The identification of pivotal events causing drug-induced impulse control disorders linked to specific medications. • An automated pipeline for discovering potential drug repurposing opportunities. • The creation of a comprehensive knowledge graph and development of a graph machine learning model for predictions. Collectively, these projects illustrate diverse applications of data science and network-based methodologies, highlighting the profound impact they can have in supporting drug research activities.

Development and testing of methodologies for the control and diagnosis of innovative combustion systems

In pursuit of aligning with the European Union's ambitious target of achieving a carbon-neutral economy by 2050, researchers, vehicle manufacturers, and original equipment manufacturers have been at the forefront of exploring cutting-edge technologies for internal combustion engines. The introduction of these technologies has significantly increased the effort required to calibrate the models implemented in the engine control units. Consequently the development of tools that reduce costs and the time required during the experimental phases, has become imperative. Additionally, to comply with ever-stricter limits on 〖"CO" 〗_"2" emissions, it is crucial to develop advanced control systems that enhance traditional engine management systems in order to reduce fuel consumption. Furthermore, the introduction of new homologation cycles, such as the real driving emissions cycle, compels manufacturers to bridge the gap between engine operation in laboratory tests and real-world conditions. Within this context, this thesis showcases the performance and cost benefits achievable through the implementation of an auto-adaptive closed-loop control system, leveraging in-cylinder pressure sensors in a heavy-duty diesel engine designed for mining applications. Additionally, the thesis explores the promising prospect of real-time self-adaptive machine learning models, particularly neural networks, to develop an automatic system, using in-cylinder pressure sensors for the precise calibration of the target combustion phase and optimal spark advance in a spark-ignition engines. To facilitate the application of these combustion process feedback-based algorithms in production applications, the thesis discusses the results obtained from the development of a cost-effective sensor for indirect cylinder pressure measurement. Finally, to ensure the quality control of the proposed affordable sensor, the thesis provides a comprehensive account of the design and validation process for a piezoelectric washer test system.

Neural Network Based UAV Fault Tolerant Control with Aerodynamic Disturbance Estimation and Compensation

In this thesis, the problem of controlling a quadrotor UAV is considered. It is done by presenting an original control system, designed as a combination of Neural Networks and Disturbance Observer, using a composite learning approach for a system of the second order, which is a novel methodology in literature. After a brief introduction about the quadrotors, the concepts needed to understand the controller are presented, such as the main notions of advanced control, the basic structure and design of a Neural Network, the modeling of a quadrotor and its dynamics. The full simulator, developed on the MATLAB Simulink environment, used throughout the whole thesis, is also shown. For the guidance and control purposes, a Sliding Mode Controller, used as a reference, it is firstly introduced, and its theory and implementation on the simulator are illustrated. Finally the original controller is introduced, through its novel formulation, and implementation on the model. The effectiveness and robustness of the two controllers are then proven by extensive simulations in all different conditions of external disturbance and faults.

Autonomous Pricing using Policy-Gradient Reinforcement Learning

Nella letteratura economica e di teoria dei giochi vi è un dibattito aperto sulla possibilità di emergenza di comportamenti anticompetitivi da parte di algoritmi di determinazione automatica dei prezzi di mercato. L'obiettivo di questa tesi è sviluppare un modello di reinforcement learning di tipo actor-critic con entropy regularization per impostare i prezzi in un gioco dinamico di competizione oligopolistica con prezzi continui. Il modello che propongo esibisce in modo coerente comportamenti cooperativi supportati da meccanismi di punizione che scoraggiano la deviazione dall'equilibrio raggiunto a convergenza. Il comportamento di questo modello durante l'apprendimento e a convergenza avvenuta aiuta inoltre a interpretare le azioni compiute da Q-learning tabellare e altri algoritmi di prezzo in condizioni simili. I risultati sono robusti alla variazione del numero di agenti in competizione e al tipo di deviazione dall'equilibrio ottenuto a convergenza, punendo anche deviazioni a prezzi più alti.

Analysis of human posterior EEG alpha frequency as a function of implicit learning of probabilistic lateralized stimuli in a visual detection task

Alpha oscillatory activity has long been associated with perceptual and cognitive processes related to attention control. The aim of this study is to explore the task-dependent role of alpha frequency in a lateralized visuo-spatial detection task. Specifically, the thesis focuses on consolidating the scientific literature's knowledge about the role of alpha frequency in perceptual accuracy, and deepening the understanding of what determines trial-by-trial fluctuations of alpha parameters and how these fluctuations influence overall task performance. The hypotheses, confirmed empirically, were that different implicit strategies are put in place based on the task context, in order to maximize performance with optimal resource distribution (namely alpha frequency, associated positively with performance): “Lateralization” of the attentive resources towards one hemifield should be associated with higher alpha frequency difference between contralateral and ipsilateral hemisphere; “Distribution” of the attentive resources across hemifields should be associated with lower alpha frequency difference between hemispheres; These strategies, used by the participants according to their brain capabilities, have proven themselves adaptive or maladaptive depending on the different tasks to which they have been set: "Distribution" of the attentive resources seemed to be the best strategy when the distribution probability between hemifields was balanced: i.e. the neutral condition task. "Lateralization" of the attentive resources seemed to be more effective when the distribution probability between hemifields was biased towards one hemifield: i.e., the biased condition task.

A deep learning model for controlling the galvanizing process in a production line

In the industry of steelmaking, the process of galvanizing is a treatment which is applied to protect the steel from corrosion. The air knife effect (AKE) occurs when nozzles emit a steam of air on the surfaces of a steel strip to remove excess zinc from it. In our work we formalized the problem to control the AKE and we implemented, with the R&D dept.of MarcegagliaSPA, a DL model able to drive the AKE. We call it controller. It takes as input the tuple : a tuple of the physical conditions of the process line (t,h,s) with the target value of the zinc coating (c); and generates the expected tuple of (pres and dist) to drive the mechanical nozzles towards the (c). According to the requirements we designed the structure of the network. We collected and explored the data set of the historical data of the smart factory. Finally, we designed the loss function as sum of three components: the minimization between the coating addressed by the network and the target value we want to reach; and two weighted minimization components for both pressure and distance. In our solution we construct a second module, named coating net, to predict the coating of zinc resulting from the AKE when the conditions are applied to the prod. line. Its structure is made by a linear and a deep nonlinear “residual” component learned by empirical observations. The predictions made by the coating nets are used as ground truth in the loss function of the controller. By tuning the weights of the different components of the loss function, it is possible to train models with slightly different optimization purposes. In the tests we compared the regularization of different strategies with the standard one in condition of optimal estimation for both; the overall accuracy is ± 3 g/m^2 dal target for all of them. Lastly, we analyze how the controller modeled the current solutions with the new logic: the sub-optimal values of pres and dist can be optimize of 50% and 20%.

Continual learning on nano drones

Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize the autonomous robots industry sector thanks to their very small form factor. The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for the on-board computations. Therefore, traditional computer vision and control algorithms are too computationally expensive to be executed on board these palm-sized robots, and we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight pipelines for autonomous tasks. However, relying on deep learning exposes us to the problem of generalization since the deployment scenario of a convolutional neural network (CNN) is often composed by different visual cues and different features from those learned during training, leading to poor inference performances. Our objective is to develop and deploy and adaptation algorithm, based on the concept of latent replays, that would allow us to fine-tune a CNN to work in new and diverse deployment scenarios. To do so we start from an existing model for visual human pose estimation, called PULPFrontnet, which is used to identify the pose of a human subject in space through its 4 output variables, and we present the design of our novel adaptation algorithm, which features automatic data gathering and labeling and on-device deployment. We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment scenarios, improving the R2 scores of the four network outputs, with respect to an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1]. Finally we demonstrate how it is possible to fine-tune our neural network in real time (i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip on board the nano-drone, and we show how all adaptation operations can take place using less than 2mWh of energy, a small fraction of the available battery power.

Hypothalamic Inflammation And The Central Nervous System Control Of Energy Homeostasis.

The control of energy homeostasis relies on robust neuronal circuits that regulate food intake and energy expenditure. Although the physiology of these circuits is well understood, the molecular and cellular response of this program to chronic diseases is still largely unclear. Hypothalamic inflammation has emerged as a major driver of energy homeostasis dysfunction in both obesity and anorexia. Importantly, this inflammation disrupts the action of metabolic signals promoting anabolism or supporting catabolism. In this review, we address the evidence that favors hypothalamic inflammation as a factor that resets energy homeostasis in pathological states.

Chitosan/tripolyphosphate Nanoparticles Loaded With Paraquat Herbicide: An Environmentally Safer Alternative For Weed Control.

Paraquat is a fast acting nonselective contact herbicide that is extensively used worldwide. However, the aqueous solubility and soil sorption of this compound can cause problems of toxicity in nontarget organisms. This work investigates the preparation and characterization of nanoparticles composed of chitosan and sodium tripolyphosphate (TPP) to produce an efficient herbicidal formulation that was less toxic and could be used for safer control of weeds in agriculture. The toxicities of the formulations were evaluated using cell culture viability assays and the Allium cepa chromosome aberration test. The herbicidal activity was investigated in cultivations of maize (Zea mays) and mustard (Brassica sp.), and soil sorption of the nanoencapsulated herbicide was measured. The efficiency association of paraquat with the nanoparticles was 62.6 ± 0.7%. Encapsulation of the herbicide resulted in changes in its diffusion and release as well as its sorption by soil. Cytotoxicity and genotoxicity assays showed that the nanoencapsulated herbicide was less toxic than the pure compound, indicating its potential to control weeds while at the same time reducing environmental impacts. Measurements of herbicidal activity showed that the effectiveness of paraquat was preserved after encapsulation. It was concluded that the encapsulation of paraquat in nanoparticles can provide a useful means of reducing adverse impacts on human health and the environment, and that the formulation therefore has potential for use in agriculture.

Influence Of Gastric Emptying On The Control Of Postprandial Glycemia: Physiology And Therapeutic Implications.

The maintenance of glucose homeostasis is complex and involves, besides the secretion and action of insulin and glucagon, a hormonal and neural mechanism, regulating the rate of gastric emptying. This mechanism depends on extrinsic and intrinsic factors. Glucagon-like peptide-1 secretion regulates the speed of gastric emptying, contributing to the control of postprandial glycemia. The pharmacodynamic characteristics of various agents of this class can explain the effects more relevant in fasting or postprandial glucose, and can thus guide the individualized treatment, according to the clinical and pathophysiological features of each patient.

Self-reported Diabetes In Older People: Comparison Of Prevalences And Control Measures.

The objective of this study was to analyze the prevalence of diabetes in older people and the adopted control measures. Data regarding older diabetic individuals who participated in the Health Surveys conducted in the Municipality of Sao Paulo, SP, ISA-Capital, in 2003 and 2008, which were cross-sectional studies, were analyzed. Prevalences and confidence intervals were compared between 2003 and 2008, according to sociodemographic variables. The combination of the databases was performed when the confidence intervals overlapped. The Chi-square (level of significance of 5%) and the Pearson's Chi-square (Rao-Scott) tests were performed. The variables without overlap between the confidence intervals were not tested. The age of the older adults was 60-69 years. The majority were women, Caucasian, with an income of between > 0.5 and 2.5 times the minimum salary and low levels of schooling. The prevalence of diabetes was 17.6% (95%CI 14.9;20.6) in 2003 and 20.1% (95%CI 17.3;23.1) in 2008, which indicates a growth over this period (p at the limit of significance). The most prevalent measure adopted by the older adults to control diabetes was hypoglycemic agents, followed by diet. Physical activity was not frequent, despite the significant differences observed between 2003 and 2008 results. The use of public health services to control diabetes was significantly higher in older individuals with lower income and lower levels of education. Diabetes is a complex and challenging disease for patients and the health systems. Measures that encourage health promotion practices are necessary because they presented a smaller proportion than the use of hypoglycemic agents. Public health policies should be implemented, and aimed mainly at older individuals with low income and schooling levels. These changes are essential to improve the health condition of older diabetic patients.

Incidence Of Basilar Invagination In Patients With Tonsillar Herniation? A Case Control Craniometrical Study.

A retrospective case-control study based on craniometrical evaluation was performed to evaluate the incidence of basilar invagination (BI). Patients with symptomatic tonsillar herniation treated surgically had craniometrical parameters evaluated based on CT scan reconstructions before surgery. BI was diagnosed when the tip of the odontoid trespassed the Chamberlain's line in three different thresholds found in the literature: 2, 5 or 6.6 mm. In the surgical group (SU), the mean distance of the tip of the odontoid process above the Chamberlain's line was 12 mm versus 1.2 mm in the control (CO) group (p<0.0001). The number of patients with BI according to the threshold used (2, 5 or 6.6 mm) in the SU group was respectively 19 (95%), 16 (80%) and 15 (75%) and in the CO group it was 15 (37%), 4 (10%) and 2 (5%).

Going Beyond Seizure Control: Can Pharmacotherapy Help To Restore Cognitive Network Function?

83

Control Of The Properties Of Porous Chitosan-alginate Membranes Through The Addition Of Different Proportions Of Pluronic F68.

This work addresses the development and characterization of porous chitosan-alginate based polyelectrolyte complexes, obtained by using two different proportions of the biocompatible surfactant Pluronic F68. These biomaterials are proposed for applications as biodegradable and biocompatible wound dressing and/or scaffolds. The results indicate that thickness, roughness, porosity and liquid uptake of the membranes increase with the amount of surfactant used, while their mechanical properties and stability in aqueous media decrease. Other important properties such as color and surface hydrophilicity (water contact angle) are not significantly altered or did not present a clear tendency of variation with the increase of the amount of surfactant added to the polyelectrolyte complexes, such as real density, average pore diameter, total pore volume and surface area. The prepared biomaterials were not cytotoxic to L929 cells. In conclusion, it is possible to tune the physicochemical properties of chitosan-alginate polyelectrolyte complexes, through the variation of the proportion of surfactant (Pluronic F68) added to the mixture, so as to enable the desired application of these biomaterials.

Sci1 Is A Component Of The Auxin-dependent Control Of Cell Proliferation In Arabidopsis Upper Pistil.

To characterize the recently described SCI1 (stigma/style cell cycle inhibitor 1) gene relationship with the auxin pathway, we have taken the advantage of the Arabidopsis model system and its available tools. At first, we have analyzed the At1g79200 T-DNA insertion mutants and constructed various transgenic plants. The loss- and gain-of-function plants displayed cell number alterations in upper pistils that were controlled by the amino-terminal domain of the protein. These data also confirmed that this locus holds the functional homolog (AtSCI1) of the Nicotiana tabacum SCI1 gene. Then, we have provided some evidences the auxin synthesis/signaling pathways are required for downstream proper AtSCI1 control of cell number: (a) its expression is downregulated in yuc2yuc6 and npy1 auxin-deficient mutants, (b) triple (yuc2yuc6sci1) and double (npy1sci1) mutants mimicked the auxin-deficient phenotypes, with no synergistic interactions, and (c) the increased upper pistil phenotype in these last mutants, which is a consequence of an increased cell number, was able to be complemented by AtSCI1 overexpression. Taken together, our data strongly suggests SCI1 as a component of the auxin signaling transduction pathway to control cell proliferation/differentiation in stigma/style, representing a molecular effector of this hormone on pistil development.