Fabrizio Angaroni

Fabrizio Angaroni, Kevin Chen, Chiara Damiani et al.

Motivation: Driver (epi)genomic alterations underlie the positive selection of cancer subpopulations, which promotes drug resistance and relapse. Even though substantial heterogeneity is witnessed in most cancer types, mutation accumulation patterns can be regularly found and can be exploited to reconstruct predictive models of cancer evolution. Yet, available methods cannot infer logical formulas connecting events to represent alternative evolutionary routes or convergent evolution. Results: We introduce PMCE, an expressive framework that leverages mutational profiles from cross-sectional sequencing data to infer probabilistic graphical models of cancer evolution including arbitrary logical formulas, and which outperforms the state-of-the-art in terms of accuracy and robustness to noise, on simulations. The application of PMCE to 7866 samples from the TCGA database allows us to identify a highly significant correlation between the predicted evolutionary paths and the overall survival in 7 tumor types, proving that our approach can effectively stratify cancer patients in reliable risk groups. Availability: PMCE is freely available at https://github.com/BIMIB-DISCo/PMCE, in addition to the code to replicate all the analyses presented in the manuscript. Contacts: daniele.ramazzotti@unimib.it, alex.graudenzi@ibfm.cnr.it.

Francesco Craighero, Fabrizio Angaroni, Fabio Stella et al.

A key challenge in computer vision and deep learning is the definition of robust strategies for the detection of adversarial examples. Here, we propose the adoption of ensemble approaches to leverage the effectiveness of multiple detectors in exploiting distinct properties of the input data. To this end, the ENsemble Adversarial Detector (ENAD) framework integrates scoring functions from state-of-the-art detectors based on Mahalanobis distance, Local Intrinsic Dimensionality, and One-Class Support Vector Machines, which process the hidden features of deep neural networks. ENAD is designed to ensure high standardization and reproducibility to the computational workflow. Importantly, extensive tests on benchmark datasets, models and adversarial attacks show that ENAD outperforms all competing methods in the large majority of settings. The improvement over the state-of-the-art and the intrinsic generality of the framework, which allows one to easily extend ENAD to include any set of detectors, set the foundations for the new area of ensemble adversarial detection.

Francesco Craighero, Fabrizio Angaroni, Alex Graudenzi et al.

The current understanding of deep neural networks can only partially explain how input structure, network parameters and optimization algorithms jointly contribute to achieve the strong generalization power that is typically observed in many real-world applications. In order to improve the comprehension and interpretability of deep neural networks, we here introduce a novel theoretical framework based on the compositional structure of piecewise linear activation functions. By defining a direct acyclic graph representing the composition of activation patterns through the network layers, it is possible to characterize the instances of the input data with respect to both the predicted label and the specific (linear) transformation used to perform predictions. Preliminary tests on the MNIST dataset show that our method can group input instances with regard to their similarity in the internal representation of the neural network, providing an intuitive measure of input complexity.