Active Learning to Maximize Area Under the ROC Curve

In active learning, a machine learning algorithmis given an unlabeled set of examples U, and is allowed to request labels for a relatively small subset of U to use for training. The goal is then to judiciously choose which examples in U to have labeled in order to optimize some performance criterion, e.g. classification accuracy. We study how active learning affects AUC. We examine two existing algorithms from the literature and present our own active learning algorithms designed to maximize the AUC of the hypothesis. One of our algorithms was consistently the top performer, and Closest Sampling from the literature often came in second behind it. When good posterior probability estimates were available, our heuristics were by far the best.

Bandit-Based Algorithms for Budgeted Learning

We explore the problem of budgeted machine learning, in which the learning algorithm has free access to the training examples’ labels but has to pay for each attribute that is specified. This learning model is appropriate in many areas, including medical applications. We present new algorithms for choosing which attributes to purchase of which examples in the budgeted learning model based on algorithms for the multi-armed bandit problem. All of our approaches outperformed the current state of the art. Furthermore, we present a new means for selecting an example to purchase after the attribute is selected, instead of selecting an example uniformly at random, which is typically done. Our new example selection method improved performance of all the algorithms we tested, both ours and those in the literature.

Particle Competition and Cooperation in Networks for Semi-Supervised Learning

Semi-supervised learning is one of the important topics in machine learning, concerning with pattern classification where only a small subset of data is labeled. In this paper, a new network-based (or graph-based) semi-supervised classification model is proposed. It employs a combined random-greedy walk of particles, with competition and cooperation mechanisms, to propagate class labels to the whole network. Due to the competition mechanism, the proposed model has a local label spreading fashion, i.e., each particle only visits a portion of nodes potentially belonging to it, while it is not allowed to visit those nodes definitely occupied by particles of other classes. In this way, a "divide-and-conquer" effect is naturally embedded in the model. As a result, the proposed model can achieve a good classification rate while exhibiting low computational complexity order in comparison to other network-based semi-supervised algorithms. Computer simulations carried out for synthetic and real-world data sets provide a numeric quantification of the performance of the method.

Transforming growth factor alpha immunoreactivity. A study in hepatocellular carcinoma and in non-neoplastic liver tissue

Background. Transforming growth factor alpha (TGF alpha) is an important mitogen that binds to epidermal growth factor receptor and is associated with the development of several tumors. Aims. Assessment of the immunoexpression of TGF alpha in hepatocellular carcinoma (HCC) and in non-neoplastic liver tissue and its relationship to morphological patterns of HCC. Material and methods. The immunohistochemical expression of TGF alpha was studied in 47 cases of HCC (27 multinodular, 20 nodular lesions). Five lesions measured up to 5 cm and 15 lesions above 5 cm. Thirty-two cases were graded as I or II and 15 as III or IV. The non-neoplastic tissue was examined in 40 cases, of which 22 had cirrhosis. HBsAg and anti-HCV were positive in 5/38 and 15/37 patients, respectively. The statistical analysis for possible association of immunostaining of TGF alpha and pathological features was performed through chi-square test. Results. TGF alpha was detected in 31.9% of the HCC and in 42.5% of the non-neoplastic. There was a statistically significant association between the expression of TGF alpha and cirrhosis (OR = 8.75, 95% CI = [1.93, 39.75]). The TGF alpha was detected more frequently in patients anti-HCV(+) than in those HBsAg(+). The immunoexpression of TGF alpha was not found related to tumor size or differentiation. In conclusion the TGF alpha is present in hepatocarcinogenesis in HBV negative patients. Further analysis is needed to examine the involvement of TGF alpha in the carcinogenesis associated with HCV and other possible agents. In addition, TGF alpha has an higher expression in hepatocyte regeneration and proliferation in cirrhotic livers than in HCC.

Semi-supervised learning guided by the modularity measure in complex networks

Semi-supervised learning techniques have gained increasing attention in the machine learning community, as a result of two main factors: (1) the available data is exponentially increasing; (2) the task of data labeling is cumbersome and expensive, involving human experts in the process. In this paper, we propose a network-based semi-supervised learning method inspired by the modularity greedy algorithm, which was originally applied for unsupervised learning. Changes have been made in the process of modularity maximization in a way to adapt the model to propagate labels throughout the network. Furthermore, a network reduction technique is introduced, as well as an extensive analysis of its impact on the network. Computer simulations are performed for artificial and real-world databases, providing a numerical quantitative basis for the performance of the proposed method.

Stochastic competitive learning in complex networks

Competitive learning is an important machine learning approach which is widely employed in artificial neural networks. In this paper, we present a rigorous definition of a new type of competitive learning scheme realized on large-scale networks. The model consists of several particles walking within the network and competing with each other to occupy as many nodes as possible, while attempting to reject intruder particles. The particle's walking rule is composed of a stochastic combination of random and preferential movements. The model has been applied to solve community detection and data clustering problems. Computer simulations reveal that the proposed technique presents high precision of community and cluster detections, as well as low computational complexity. Moreover, we have developed an efficient method for estimating the most likely number of clusters by using an evaluator index that monitors the information generated by the competition process itself. We hope this paper will provide an alternative way to the study of competitive learning.

Network-based stochastic semisupervised learning

Semisupervised learning is a machine learning approach that is able to employ both labeled and unlabeled samples in the training process. In this paper, we propose a semisupervised data classification model based on a combined random-preferential walk of particles in a network (graph) constructed from the input dataset. The particles of the same class cooperate among themselves, while the particles of different classes compete with each other to propagate class labels to the whole network. A rigorous model definition is provided via a nonlinear stochastic dynamical system and a mathematical analysis of its behavior is carried out. A numerical validation presented in this paper confirms the theoretical predictions. An interesting feature brought by the competitive-cooperative mechanism is that the proposed model can achieve good classification rates while exhibiting low computational complexity order in comparison to other network-based semisupervised algorithms. Computer simulations conducted on synthetic and real-world datasets reveal the effectiveness of the model.

Retinoic acid and cAMP inhibit rat hepatocellular carcinoma cell proliferation and enhance cell differentiation

Hepatocellular carcinoma (HCC) is the third highest cause of cancer death worldwide. In general, the disease is diagnosed at an advanced stage when potentially curative therapies are no longer feasible. For this reason, it is very important to develop new therapeutic approaches. Retinoic acid (RA) is a natural derivative of vitamin A that regulates important biological processes including cell proliferation and differentiation. In vitro studies have shown that RA is effective in inhibiting growth of HCC cells; however, responsiveness to treatment varies among different HCC cell lines. The objective of the present study was to determine if the combined use of RA (0.1 µM) and cAMP (1 mM), an important second messenger, improves the responsiveness of HCC cells to RA treatment. We evaluated the proliferative behavior of an HCC cell line (HTC) and the expression profile of genes related to cancer signaling pathway (ERK and GSK-3β) and liver differentiation (E-cadherin, connexin 26 (Cx26), and Cx32). RA and cAMP were effective in inhibiting the proliferation of HTC cells independently of combined use. However, when a mixture of RA and cAMP was used, the signals concerning the degree of cell differentiation were increased. As demonstrated by Western blot, the treatment increased E-cadherin, Cx26, Cx32 and Ser9-GSK-3β (inactive form) expression while the expression of Cx43, Tyr216-GSK-3β (active form) and phosphorylated ERK decreased. Furthermore, telomerase activity was inhibited along treatment. Taken together, the results showed that the combined use of RA and cAMP is more effective in inducing differentiation of HTC cells.

A mathematical model for optimizing the indications of liver transplantation in patients with hepatocellular carcinoma

Abstract Background The criteria for organ sharing has developed a system that prioritizes liver transplantation (LT) for patients with hepatocellular carcinoma (HCC) who have the highest risk of wait-list mortality. In some countries this model allows patients only within the Milan Criteria (MC, defined by the presence of a single nodule up to 5 cm, up to three nodules none larger than 3 cm, with no evidence of extrahepatic spread or macrovascular invasion) to be evaluated for liver transplantation. This police implies that some patients with HCC slightly more advanced than those allowed by the current strict selection criteria will be excluded, even though LT for these patients might be associated with acceptable long-term outcomes. Methods We propose a mathematical approach to study the consequences of relaxing the MC for patients with HCC that do not comply with the current rules for inclusion in the transplantation candidate list. We consider overall 5-years survival rates compatible with the ones reported in the literature. We calculate the best strategy that would minimize the total mortality of the affected population, that is, the total number of people in both groups of HCC patients that die after 5 years of the implementation of the strategy, either by post-transplantation death or by death due to the basic HCC. We illustrate the above analysis with a simulation of a theoretical population of 1,500 HCC patients with tumor size exponentially. The parameter λ obtained from the literature was equal to 0.3. As the total number of patients in these real samples was 327 patients, this implied in an average size of 3.3 cm and a 95% confidence interval of [2.9; 3.7]. The total number of available livers to be grafted was assumed to be 500. Results With 1500 patients in the waiting list and 500 grafts available we simulated the total number of deaths in both transplanted and non-transplanted HCC patients after 5 years as a function of the tumor size of transplanted patients. The total number of deaths drops down monotonically with tumor size, reaching a minimum at size equals to 7 cm, increasing from thereafter. With tumor size equals to 10 cm the total mortality is equal to the 5 cm threshold of the Milan criteria. Conclusion We concluded that it is possible to include patients with tumor size up to 10 cm without increasing the total mortality of this population.

Structure learning of graphical models for task-oriented robot grasping

In the collective imaginaries a robot is a human like machine as any androids in science fiction. However the type of robots that you will encounter most frequently are machinery that do work that is too dangerous, boring or onerous. Most of the robots in the world are of this type. They can be found in auto, medical, manufacturing and space industries. Therefore a robot is a system that contains sensors, control systems, manipulators, power supplies and software all working together to perform a task. The development and use of such a system is an active area of research and one of the main problems is the development of interaction skills with the surrounding environment, which include the ability to grasp objects. To perform this task the robot needs to sense the environment and acquire the object informations, physical attributes that may influence a grasp. Humans can solve this grasping problem easily due to their past experiences, that is why many researchers are approaching it from a machine learning perspective finding grasp of an object using information of already known objects. But humans can select the best grasp amongst a vast repertoire not only considering the physical attributes of the object to grasp but even to obtain a certain effect. This is why in our case the study in the area of robot manipulation is focused on grasping and integrating symbolic tasks with data gained through sensors. The learning model is based on Bayesian Network to encode the statistical dependencies between the data collected by the sensors and the symbolic task. This data representation has several advantages. It allows to take into account the uncertainty of the real world, allowing to deal with sensor noise, encodes notion of causality and provides an unified network for learning. Since the network is actually implemented and based on the human expert knowledge, it is very interesting to implement an automated method to learn the structure as in the future more tasks and object features can be introduced and a complex network design based only on human expert knowledge can become unreliable. Since structure learning algorithms presents some weaknesses, the goal of this thesis is to analyze real data used in the network modeled by the human expert, implement a feasible structure learning approach and compare the results with the network designed by the expert in order to possibly enhance it.

Learning for scheduling a portfolio of constraint solvers

Nel lavoro di tesi qui presentato si indaga l'applicazione di tecniche di apprendimento mirate ad una più efficiente esecuzione di un portfolio di risolutore di vincoli (constraint solver). Un constraint solver è un programma che dato in input un problema di vincoli, elabora una soluzione mediante l'utilizzo di svariate tecniche. I problemi di vincoli sono altamente presenti nella vita reale. Esempi come l'organizzazione dei viaggi dei treni oppure la programmazione degli equipaggi di una compagnia aerea, sono tutti problemi di vincoli. Un problema di vincoli è formalizzato da un problema di soddisfacimento di vincoli(CSP). Un CSP è descritto da un insieme di variabili che possono assumere valori appartenenti ad uno specico dominio ed un insieme di vincoli che mettono in relazione variabili e valori assumibili da esse. Una tecnica per ottimizzare la risoluzione di tali problemi è quella suggerita da un approccio a portfolio. Tale tecnica, usata anche in am- biti come quelli economici, prevede la combinazione di più solver i quali assieme possono generare risultati migliori di un approccio a singolo solver. In questo lavoro ci preoccupiamo di creare una nuova tecnica che combina un portfolio di constraint solver con tecniche di machine learning. Il machine learning è un campo di intelligenza articiale che si pone l'obiettivo di immettere nelle macchine una sorta di `intelligenza'. Un esempio applicativo potrebbe essere quello di valutare i casi passati di un problema ed usarli in futuro per fare scelte. Tale processo è riscontrato anche a livello cognitivo umano. Nello specico, vogliamo ragionare in termini di classicazione. Una classicazione corrisponde ad assegnare ad un insieme di caratteristiche in input, un valore discreto in output, come vero o falso se una mail è classicata come spam o meno. La fase di apprendimento sarà svolta utilizzando una parte di CPHydra, un portfolio di constraint solver sviluppato presso la University College of Cork (UCC). Di tale algoritmo a portfolio verranno utilizzate solamente le caratteristiche usate per descrivere determinati aspetti di un CSP rispetto ad un altro; queste caratteristiche vengono altresì dette features. Creeremo quindi una serie di classicatori basati sullo specifico comportamento dei solver. La combinazione di tali classicatori con l'approccio a portfolio sara nalizzata allo scopo di valutare che le feature di CPHydra siano buone e che i classicatori basati su tali feature siano affidabili. Per giusticare il primo risultato, eettueremo un confronto con uno dei migliori portfolio allo stato dell'arte, SATzilla. Una volta stabilita la bontà delle features utilizzate per le classicazioni, andremo a risolvere i problemi simulando uno scheduler. Tali simulazioni testeranno diverse regole costruite con classicatori precedentemente introdotti. Prima agiremo su uno scenario ad un processore e successivamente ci espanderemo ad uno scenario multi processore. In questi esperimenti andremo a vericare che, le prestazioni ottenute tramite l'applicazione delle regole create appositamente sui classicatori, abbiano risultati migliori rispetto ad un'esecuzione limitata all'utilizzo del migliore solver del portfolio. I lavoro di tesi è stato svolto in collaborazione con il centro di ricerca 4C presso University College Cork. Su questo lavoro è stato elaborato e sottomesso un articolo scientico alla International Joint Conference of Articial Intelligence (IJCAI) 2011. Al momento della consegna della tesi non siamo ancora stati informati dell'accettazione di tale articolo. Comunque, le risposte dei revisori hanno indicato che tale metodo presentato risulta interessante.

Outcome of HIV-infected patients with hepatocellular carcinoma: a comparison with HIV negative controls

Background and rationale for the study. This study investigated whether human immunodeficiency virus (HIV) infection adversely affects the prognosis of patients diagnosed with hepatocellular carcinoma (HCC).Thirty-four HIV-positive patients with chronic liver disease, consecutively diagnosed with HCC from 1998 to 2007 were one-to-one matched with 34 HIV negative controls for: sex, liver function (Child-Turcotte-Pugh class [CTP]), cancer stage (BCLC model) and, whenever possible, age, etiology of liver disease and modality of cancer diagnosis. Survival in the two groups and independent prognostic predictors were assessed. Results. Among HIV patients 88% were receiving HAART. HIV-RNA was undetectable in 65% of cases; median lymphocyte CD4+ count was 368.5/mmc. Etiology of liver disease was mostly related to HCV infection. CTP class was: A in 38%, B in 41%, C in 21% of cases. BCLC cancer stage was: early in 50%, intermediate in 23.5%, advanced in 5.9%, end-stage in 20.6% of cases. HCC treatments and death causes did not differ between the two groups. Median survival did not differ, being 16 months (95% CI: 6-26) in HIV positive and 23 months (95% CI: 5-41) in HIV negative patients (P=0.391). BCLC cancer stage and HCC treatment proved to be independent predictors of survival both in the whole population and in HIV patients. Conclusions. Survival of HIV infected patients receiving antiretroviral therapy and diagnosed with HCC is similar to that of HIV negative patients bearing this tumor. Prognosis is determined by the cancer bulk and its treatment.

Role of Notch signalling in human hepatocellular carcinoma

The Notch signalling is a cellular pathway that results conserved from Drosophila to Homo sapiens controlling a wide range of cellular processes in development and in differentiated organs. It induces cell proliferation or differentiation, increased survival or apoptosis, and it is involved in stemness maintainance. These functions are conserved, but exerted with a high tissue and cellular context specificity. Signalling activation determs nuclear translocation of the receptor’s cytoplasmic domain and activation of target genes transcription. As many developmental pathway, Notch deregulation is involved in cancer, leading to oncogenic or tumour suppressive role depending on the functions exerted in normal tissue. Notch1 and Notch3 resulted aberrantly expressed in human hepatocellular carcinoma (HCC) that is the more frequent tumour of the liver and the sixth most common tumour worldwide. This thesis has the aim to investigate the role of the signalling in HCC, with particular attention to dissect common and uncommon regulatory pathways between Notch1 and Notch3 and to define the role of the signalling in HCC. Nocth1 and Notch3 were analysed on their regulation on Hes1 target and involvement in cell cycle control. They showed to regulate CDKN1C/p57kip2 expression through Hes1 target. CDKN1C/p57kip2 induces not only cell cycle arrest, but also senescence in HCC cell lines. Moreover, the involvement of Notch1 in cancer progression and epithelial to mesenchymal transition was investigated. Notch1 showed to induce invasion of HCC, regulating EMT and E- Cadherin expression. Moreover, Notch3 showed specific regulation on p53 at post translational levels. In vitro and ex vivo analysis on HCC samples suggests a complex role of both receptors in regulate HCC, with an oncogenic role but also showing tumour suppressive effects, suggesting a complex and deep involvement of this signalling in HCC.

Learning with Kernels on Graphs: DAG-based kernels, data streams and RNA function prediction.

In many application domains data can be naturally represented as graphs. When the application of analytical solutions for a given problem is unfeasible, machine learning techniques could be a viable way to solve the problem. Classical machine learning techniques are defined for data represented in a vectorial form. Recently some of them have been extended to deal directly with structured data. Among those techniques, kernel methods have shown promising results both from the computational complexity and the predictive performance point of view. Kernel methods allow to avoid an explicit mapping in a vectorial form relying on kernel functions, which informally are functions calculating a similarity measure between two entities. However, the definition of good kernels for graphs is a challenging problem because of the difficulty to find a good tradeoff between computational complexity and expressiveness. Another problem we face is learning on data streams, where a potentially unbounded sequence of data is generated by some sources. There are three main contributions in this thesis. The first contribution is the definition of a new family of kernels for graphs based on Directed Acyclic Graphs (DAGs). We analyzed two kernels from this family, achieving state-of-the-art results from both the computational and the classification point of view on real-world datasets. The second contribution consists in making the application of learning algorithms for streams of graphs feasible. Moreover,we defined a principled way for the memory management. The third contribution is the application of machine learning techniques for structured data to non-coding RNA function prediction. In this setting, the secondary structure is thought to carry relevant information. However, existing methods considering the secondary structure have prohibitively high computational complexity. We propose to apply kernel methods on this domain, obtaining state-of-the-art results.

Terapie sistemiche dell'epatocarcinoma (HCC): dalla preclinica alla clinica

Introduzione Attualmente i principali punti critici del trattamento dell’HCC avanzato sono: 1) la mancanza di predittori di risposta alla terapia con sorafenib, 2) lo sviluppo resistenze al sorafenib, 3) la mancanza di terapie di seconda linea codificate. Scopo della tesi 1) ricerca di predittori clinico-laboratoristici di risposta al sorafenib in pazienti ambulatoriali con HCC; 2) valutazione dell’impatto della sospensione temporanea-definitiva del sorafenib in un modello murino di HCC mediante tecniche ecografiche; 3) valutazione dell’efficacia della capecitabina metronomica come seconda linea dell’HCC non responsivo a sorafenib. Risultati Studio-1: 94 pazienti con HCC trattato con sorafenib: a presenza di metastasi e PVT-neoplastica non sembra inficiare l’efficacia del sorafenib. AFP basale <19 ng/ml è risultata predittrice di maggiore sopravvivenza, mentre lo sviluppo di nausea di una peggiore sopravvivenza. Studio -2: 14 topi con xenografts di HCC: gruppo-1 trattato con placebo, gruppo-2 trattato con sorafenib con interruzione temporanea del farmaco e gruppo-3 trattato con sorafenib con sospensione definitiva del sorafenib. La CEUS targettata per il VEGFR2 ha mostrato al giorno 13 valori maggiori di dTE nel gruppo-3 confermato da un aumento del VEGFR2 al Western-Blot. I tumori del gruppo-2 dopo 2 giorni di ritrattamento, hanno mostrato un aumento dell’elasticità tissutale all’elastonografia. Studio-3:19 pazienti trattati con capecitabina metronomica dopo sorafenib. Il TTP è stato di 5 mesi (95% CI 0-10), la PFS di 3,6 mesi (95% CI 2,8-4,3) ed la OS di 6,3 mesi (95% CI 4-8,6). Conclusioni Lo sviluppo di nausea ed astenia ed AFP basale >19, sono risultati predittivi di una minore risposta al sorafenib. La sospensione temporanea del sorafenib in un modello murino di HCC non impedisce il ripristino della risposta tumorale, mentre una interruzione definitiva tende a stimolare un “effetto rebound” dell’angiogenesi. La capecitabina metronomica dopo sorafenib ha mostrato una discreta attività anti-neoplastica ed una sicurezza accettabile.