Smart sampling approaches for Decision-Focused Learning

Many real-word decision- making problems are defined based on forecast parameters: for example, one may plan an urban route by relying on traffic predictions. In these cases, the conventional approach consists in training a predictor and then solving an optimization problem. This may be problematic since mistakes made by the predictor may trick the optimizer into taking dramatically wrong decisions. Recently, the field of Decision-Focused Learning overcomes this limitation by merging the two stages at training time, so that predictions are rewarded and penalized based on their outcome in the optimization problem. There are however still significant challenges toward a widespread adoption of the method, mostly related to the limitation in terms of generality and scalability. One possible solution for dealing with the second problem is introducing a caching-based approach, to speed up the training process. This project aims to investigate these techniques, in order to reduce even more, the solver calls. For each considered method, we designed a particular smart sampling approach, based on their characteristics. In the case of the SPO method, we ended up discovering that it is only necessary to initialize the cache with only several solutions; those needed to filter the elements that we still need to properly learn. For the Blackbox method, we designed a smart sampling approach, based on inferred solutions.

Metodi di deep learning per la decodifica di segnali neurali registrati dalla corteccia posteriore parietale di macaco

Le interfacce cervello-macchina (BMIs) permettono di guidare devices esterni utilizzando segnali neurali. Le BMIs rappresentano un’importante tecnologia per tentare di ripristinare funzioni perse in patologie che interrompono il canale di comunicazione tra cervello e corpo, come malattie neurodegenerative o lesioni spinali. Di importanza chiave per il corretto funzionamento di una BCI è la decodifica dei segnali neurali per trasformarli in segnali idonei per guidare devices esterni. Negli anni sono stati implementati diversi tipi di algoritmi. Tra questi gli algoritmi di machine learning imparano a riconoscere i pattern neurali di attivazione mappando con grande efficienza l’input, possibilmente l’attività dei neuroni, con l’output, ad esempio i comandi motori per guidare una possibile protesi. Tra gli algoritmi di machine learning ci si è focalizzati sulle deep neural networks (DNN). Un problema delle DNN è l’elevato tempo di training. Questo infatti prevede il calcolo dei parametri ottimali della rete per minimizzare l’errore di predizione. Per ridurre questo problema si possono utilizzare le reti neurali convolutive (CNN), reti caratterizzate da minori parametri di addestramento rispetto ad altri tipi di DNN con maggiori parametri come le reti neurali ricorrenti (RNN). In questo elaborato è esposto uno studio esplorante l’utilizzo innovativo di CNN per la decodifica dell’attività di neuroni registrati da macaco sveglio mentre svolgeva compiti motori. La CNN risultante ha consentito di ottenere risultati comparabili allo stato dell’arte con un minor numero di parametri addestrabili. Questa caratteristica in futuro potrebbe essere chiave per l’utilizzo di questo tipo di reti all’interno di BMIs grazie ai tempi di calcolo ridotti, consentendo in tempo reale la traduzione di un segnale neurale in segnali per muovere neuroprotesi.

Synthetic generation of amyloid PET images by non-linear dimensionality reduction inversion

Privacy issues and data scarcity in PET field call for efficient methods to expand datasets via synthetic generation of new data that cannot be traced back to real patients and that are also realistic. In this thesis, machine learning techniques were applied to 1001 amyloid-beta PET images, which had undergone a diagnosis of Alzheimer’s disease: the evaluations were 540 positive, 457 negative and 4 unknown. Isomap algorithm was used as a manifold learning method to reduce the dimensions of the PET dataset; a numerical scale-free interpolation method was applied to invert the dimensionality reduction map. The interpolant was tested on the PET images via LOOCV, where the removed images were compared with the reconstructed ones with the mean SSIM index (MSSIM = 0.76 ± 0.06). The effectiveness of this measure is questioned, since it indicated slightly higher performance for a method of comparison using PCA (MSSIM = 0.79 ± 0.06), which gave clearly poor quality reconstructed images with respect to those recovered by the numerical inverse mapping. Ten synthetic PET images were generated and, after having been mixed with ten originals, were sent to a team of clinicians for the visual assessment of their realism; no significant agreements were found either between clinicians and the true image labels or among the clinicians, meaning that original and synthetic images were indistinguishable. The future perspective of this thesis points to the improvement of the amyloid-beta PET research field by increasing available data, overcoming the constraints of data acquisition and privacy issues. Potential improvements can be achieved via refinements of the manifold learning and the inverse mapping stages during the PET image analysis, by exploring different combinations in the choice of algorithm parameters and by applying other non-linear dimensionality reduction algorithms. A final prospect of this work is the search for new methods to assess image reconstruction quality.

Antibody-Antigen Interface Characterization with Contextualized Pre-trained Embeddings

Artificial Intelligence (AI) has substantially influenced numerous disciplines in recent years. Biology, chemistry, and bioinformatics are among them, with significant advances in protein structure prediction, paratope prediction, protein-protein interactions (PPIs), and antibody-antigen interactions. Understanding PPIs is critical since they are responsible for practically everything living and have several uses in vaccines, cancer, immunology, and inflammatory illnesses. Machine Learning (ML) offers enormous potential for effectively simulating antibody-antigen interactions and improving in-silico optimization of therapeutic antibodies for desired features, including binding activity, stability, and low immunogenicity. This research looks at the use of AI algorithms to better understand antibody-antigen interactions, and it further expands and explains several difficulties encountered in the field. Furthermore, we contribute by presenting a method that outperforms existing state-of-the-art strategies in paratope prediction from sequence data.

Gene Expression Complex Networks: Synthesis, Identification, and Analysis

Thanks to recent advances in molecular biology, allied to an ever increasing amount of experimental data, the functional state of thousands of genes can now be extracted simultaneously by using methods such as cDNA microarrays and RNA-Seq. Particularly important related investigations are the modeling and identification of gene regulatory networks from expression data sets. Such a knowledge is fundamental for many applications, such as disease treatment, therapeutic intervention strategies and drugs design, as well as for planning high-throughput new experiments. Methods have been developed for gene networks modeling and identification from expression profiles. However, an important open problem regards how to validate such approaches and its results. This work presents an objective approach for validation of gene network modeling and identification which comprises the following three main aspects: (1) Artificial Gene Networks (AGNs) model generation through theoretical models of complex networks, which is used to simulate temporal expression data; (2) a computational method for gene network identification from the simulated data, which is founded on a feature selection approach where a target gene is fixed and the expression profile is observed for all other genes in order to identify a relevant subset of predictors; and (3) validation of the identified AGN-based network through comparison with the original network. The proposed framework allows several types of AGNs to be generated and used in order to simulate temporal expression data. The results of the network identification method can then be compared to the original network in order to estimate its properties and accuracy. Some of the most important theoretical models of complex networks have been assessed: the uniformly-random Erdos-Renyi (ER), the small-world Watts-Strogatz (WS), the scale-free Barabasi-Albert (BA), and geographical networks (GG). The experimental results indicate that the inference method was sensitive to average degree k variation, decreasing its network recovery rate with the increase of k. The signal size was important for the inference method to get better accuracy in the network identification rate, presenting very good results with small expression profiles. However, the adopted inference method was not sensible to recognize distinct structures of interaction among genes, presenting a similar behavior when applied to different network topologies. In summary, the proposed framework, though simple, was adequate for the validation of the inferred networks by identifying some properties of the evaluated method, which can be extended to other inference methods.

Transcriptional responses of host peripheral blood cells to tuberculosis infection

Host responses following exposure to Mycobacterium tuberculosis (TB) are complex and can significantly affect clinical outcome. These responses, which are largely mediated by complex immune mechanisms involving peripheral blood cells (PBCs) such as T-lymphocytes, NK cells and monocyte-derived macrophages, have not been fully characterized. We hypothesize that different clinical outcome following TB exposure will be uniquely reflected in host gene expression profiles, and expression profiling of PBCs can be used to discriminate between different TB infectious outcomes. In this study, microarray analysis was performed on PBCs from three TB groups (BCG-vaccinated, latent TB infection, and active TB infection) and a control healthy group. Supervised learning algorithms were used to identify signature genomic responses that differentiate among group samples. Gene Set Enrichment Analysis was used to determine sets of genes that were co-regulated. Multivariate permutation analysis (p < 0.01) gave 645 genes differentially expressed among the four groups, with both distinct and common patterns of gene expression observed for each group. A 127-probeset, representing 77 known genes, capable of accurately classifying samples into their respective groups was identified. In addition, 13 insulin-sensitive genes were found to be differentially regulated in all three TB infected groups, underscoring the functional association between insulin signaling pathway and TB infection. Published by Elsevier Ltd.

Hyperplane navigation: A method to set individual scores in fMRI group datasets

Recent studies have demonstrated that spatial patterns of fMRI BOLD activity distribution over the brain may be used to classify different groups or mental states. These studies are based on the application of advanced pattern recognition approaches and multivariate statistical classifiers. Most published articles in this field are focused on improving the accuracy rates and many approaches have been proposed to accomplish this task. Nevertheless, a point inherent to most machine learning methods (and still relatively unexplored in neuroimaging) is how the discriminative information can be used to characterize groups and their differences. In this work, we introduce the Maximum Uncertainty Linear Discrimination Analysis (MLDA) and show how it can be applied to infer groups` patterns by discriminant hyperplane navigation. In addition, we show that it naturally defines a behavioral score, i.e., an index quantifying the distance between the states of a subject from predefined groups. We validate and illustrate this approach using a motor block design fMRI experiment data with 35 subjects. (C) 2008 Elsevier Inc. All rights reserved.

A decision support system to facilitate management of patients with acute gastrointestinal bleeding

Objective: To develop a model to predict the bleeding source and identify the cohort amongst patients with acute gastrointestinal bleeding (GIB) who require urgent intervention, including endoscopy. Patients with acute GIB, an unpredictable event, are most commonly evaluated and managed by non-gastroenterologists. Rapid and consistently reliable risk stratification of patients with acute GIB for urgent endoscopy may potentially improve outcomes amongst such patients by targeting scarce health-care resources to those who need it the most. Design and methods: Using ICD-9 codes for acute GIB, 189 patients with acute GIB and all. available data variables required to develop and test models were identified from a hospital medical records database. Data on 122 patients was utilized for development of the model and on 67 patients utilized to perform comparative analysis of the models. Clinical data such as presenting signs and symptoms, demographic data, presence of co-morbidities, laboratory data and corresponding endoscopic diagnosis and outcomes were collected. Clinical data and endoscopic diagnosis collected for each patient was utilized to retrospectively ascertain optimal management for each patient. Clinical presentations and corresponding treatment was utilized as training examples. Eight mathematical models including artificial neural network (ANN), support vector machine (SVM), k-nearest neighbor, linear discriminant analysis (LDA), shrunken centroid (SC), random forest (RF), logistic regression, and boosting were trained and tested. The performance of these models was compared using standard statistical analysis and ROC curves. Results: Overall the random forest model best predicted the source, need for resuscitation, and disposition with accuracies of approximately 80% or higher (accuracy for endoscopy was greater than 75%). The area under ROC curve for RF was greater than 0.85, indicating excellent performance by the random forest model Conclusion: While most mathematical models are effective as a decision support system for evaluation and management of patients with acute GIB, in our testing, the RF model consistently demonstrated the best performance. Amongst patients presenting with acute GIB, mathematical models may facilitate the identification of the source of GIB, need for intervention and allow optimization of care and healthcare resource allocation; these however require further validation. (c) 2007 Elsevier B.V. All rights reserved.

Maximum Likelihood Estimation of Mixture Densities for Binned and Truncated Multivariate Data

Binning and truncation of data are common in data analysis and machine learning. This paper addresses the problem of fitting mixture densities to multivariate binned and truncated data. The EM approach proposed by McLachlan and Jones (Biometrics, 44: 2, 571-578, 1988) for the univariate case is generalized to multivariate measurements. The multivariate solution requires the evaluation of multidimensional integrals over each bin at each iteration of the EM procedure. Naive implementation of the procedure can lead to computationally inefficient results. To reduce the computational cost a number of straightforward numerical techniques are proposed. Results on simulated data indicate that the proposed methods can achieve significant computational gains with no loss in the accuracy of the final parameter estimates. Furthermore, experimental results suggest that with a sufficient number of bins and data points it is possible to estimate the true underlying density almost as well as if the data were not binned. The paper concludes with a brief description of an application of this approach to diagnosis of iron deficiency anemia, in the context of binned and truncated bivariate measurements of volume and hemoglobin concentration from an individual's red blood cells.

Artificial neural networks for automatic modelling of the pectus excavatum corrective prosthesis

Pectus excavatum is the most common deformity of the thorax and usually comprises Computed Tomography (CT) examination for pre-operative diagnosis. Aiming at the elimination of the high amounts of CT radiation exposure, this work presents a new methodology for the replacement of CT by a laser scanner (radiation-free) in the treatment of pectus excavatum using personally modeled prosthesis. The complete elimination of CT involves the determination of ribs external outline, at the maximum sternum depression point for prosthesis placement, based on chest wall skin surface information, acquired by a laser scanner. The developed solution resorts to artificial neural networks trained with data vectors from 165 patients. Scaled Conjugate Gradient, Levenberg-Marquardt, Resilient Back propagation and One Step Secant gradient learning algorithms were used. The training procedure was performed using the soft tissue thicknesses, determined using image processing techniques that automatically segment the skin and rib cage. The developed solution was then used to determine the ribs outline in data from 20 patient scanners. Tests revealed that ribs position can be estimated with an average error of about 6.82±5.7 mm for the left and right side of the patient. Such an error range is well below current prosthesis manual modeling (11.7±4.01 mm) even without CT imagiology, indicating a considerable step forward towards CT replacement by a 3D scanner for prosthesis personalization.

Computer-aided recognition of dental implants in X-ray images

Dental implant recognition in patients without available records is a time-consuming and not straightforward task. The traditional method is a complete user-dependent process, where the expert compares a 2D X-ray image of the dental implant with a generic database. Due to the high number of implants available and the similarity between them, automatic/semi-automatic frameworks to aide implant model detection are essential. In this study, a novel computer-aided framework for dental implant recognition is suggested. The proposed method relies on image processing concepts, namely: (i) a segmentation strategy for semi-automatic implant delineation; and (ii) a machine learning approach for implant model recognition. Although the segmentation technique is the main focus of the current study, preliminary details of the machine learning approach are also reported. Two different scenarios are used to validate the framework: (1) comparison of the semi-automatic contours against implant’s manual contours of 125 X-ray images; and (2) classification of 11 known implants using a large reference database of 601 implants. Regarding experiment 1, 0.97±0.01, 2.24±0.85 pixels and 11.12±6 pixels of dice metric, mean absolute distance and Hausdorff distance were obtained, respectively. In experiment 2, 91% of the implants were successfully recognized while reducing the reference database to 5% of its original size. Overall, the segmentation technique achieved accurate implant contours. Although the preliminary classification results prove the concept of the current work, more features and an extended database should be used in a future work.

QSAR modeling of antitubercular activity of diverse organic compounds

Tuberculosis (TB) is a worldwide infectious disease that has shown over time extremely high mortality levels. The urgent need to develop new antitubercular drugs is due to the increasing rate of appearance of multi-drug resistant strains to the commonly used drugs, and the longer durations of therapy and recovery, particularly in immuno-compromised patients. The major goal of the present study is the exploration of data from different families of compounds through the use of a variety of machine learning techniques so that robust QSAR-based models can be developed to further guide in the quest for new potent anti-TB compounds. Eight QSAR models were built using various types of descriptors (from ADRIANA.Code and Dragon software) with two publicly available structurally diverse data sets, including recent data deposited in PubChem. QSAR methodologies used Random Forests and Associative Neural Networks. Predictions for the external evaluation sets obtained accuracies in the range of 0.76-0.88 (for active/inactive classifications) and Q(2)=0.66-0.89 for regressions. Models developed in this study can be used to estimate the anti-TB activity of drug candidates at early stages of drug development (C) 2011 Elsevier B.V. All rights reserved.