A5078001324- Gene expression and cancer classification
- Genomics and Phylogenetic Studies
- Machine Learning in Bioinformatics
- Data Mining Algorithms and Applications
- Bioinformatics and Genomic Networks
- Algorithms and Data Compression
- Particle physics theoretical and experimental studies
- Machine Learning and Algorithms
- Machine Learning and Data Classification
- Scheduling and Optimization Algorithms
- Vehicle Routing Optimization Methods
- Quantum Chromodynamics and Particle Interactions
- RNA and protein synthesis mechanisms
- Identification and Quantification in Food
- High-Energy Particle Collisions Research
- Optimization and Search Problems
- Genomics and Chromatin Dynamics
- Web Data Mining and Analysis
- Rough Sets and Fuzzy Logic
- Superconducting Materials and Applications
- Environmental DNA in Biodiversity Studies
- Biomedical Text Mining and Ontologies
- Multi-Criteria Decision Making
- Data Management and Algorithms
- Advanced Optimization Algorithms Research
National Research Council
2009-2024
Istituto di Analisi dei Sistemi ed Informatica Antonio Ruberti
2014-2024
Sapienza University of Rome
1995-2015
Istituto Nazionale di Fisica Nucleare, Sezione di Roma I
2003-2015
National Academies of Sciences, Engineering, and Medicine
2011-2014
Consorzio Roma Ricerche
2006-2014
Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di Frascati
1991-2012
Institute for Systems Analysis
2012
University of Milano-Bicocca
2010
National Research Council
2006
Machine-learning ML enables computers to learn how recognise patterns, make unintended decisions, or react a dynamic environment. The effectiveness of trained machines varies because more suitable algorithms superior training sets. Although are known and publicly released, sets may not be reasonably ascertainable and, indeed, guarded as trade secrets. In this paper we focus our attention on classifiers the statistical information that can unconsciously maliciously revealed from them. We show...
Recently diverged species are challenging for identification, yet they frequently of special interest scientifically as well from a regulatory perspective. DNA barcoding has proven instrumental in especially insects and vertebrates, but the identification recently it been reported to be problematic some cases. Problems mostly due incomplete lineage sorting or simply lack 'barcode gap' probably related large effective population size and/or low mutation rate. Our objective was compare six...
The identification of early and stage-specific biomarkers for Alzheimer's disease (AD) is critical, as the development disease-modification therapies may depend on discovery validation such markers. reliable depends new diagnostic algorithms to computationally exploit information in large biological datasets. To identify potential from mRNA expression profile data, we used Logic Mining method unbiased analysis a microarray dataset anti-NGF AD11 transgenic mouse model. gene brain regions was...
Alzheimer's Disease (AD) is a neurodegenaritive disorder characterized by progressive dementia, for which actually no cure known. An early detection of patients affected AD can be obtained analyzing their electroencephalography (EEG) signals, show reduction the complexity, perturbation synchrony, and slowing down rhythms. In this work, we apply procedure that exploits feature extraction classification techniques to EEG whose aim distinguish patient from ones Mild Cognitive Impairment (MCI)...
The existence of a new force beyond the Standard Model is compelling because it could explain several striking astrophysical observations which fail standard interpretations. We searched for light vector mediator this dark force, $\mathrm{U}$ boson, with KLOE detector at DA$\Phi$NE $\mathrm{e}^{+}\mathrm{e}^{-}$ collider. Using an integrated luminosity 1.54 fb$^{-1}$, we studied process $\mathrm{e}^{+}\mathrm{e}^{-} \to \mathrm{U}\gamma$, $\mathrm{U} \mathrm{e}^{+}\mathrm{e}^{-}$, using...
Specific fragments, coming from short portions of DNA (e.g., mitochondrial, nuclear, and plastid sequences), have been defined as Barcode can be used markers for organisms the main life kingdoms. Species classification with sequences has proven effective on different organisms. Indeed, specific gene regions identified Barcode: COI in animals, rbcL matK plants, ITS fungi. The problem assigns an unknown specimen to a known species by analyzing its Barcode. This task supported reliable methods...
Abstract BLOG (Barcoding with LOG ic) is a diagnostic and character‐based DNA Barcode analysis method. Its aim to classify specimens species based on sequences supervised machine learning approach, using classification rules that compactly characterize in terms of locations key nucleotides. The 2.0 software, its fundamental modules, online/offline user interfaces recent improvements are described. These affect both methodology software design, lead the availability different releases website...
Abstract Background According to many field experts, specimens classification based on morphological keys needs be supported with automated techniques the analysis of DNA fragments. The most successful results in this area are those obtained from a particular fragment mitochondrial DNA, gene cytochrome c oxidase I (COI) (the "barcode"). Since 2004 Consortium for Barcode Life (CBOL) promotes collection barcode and development methods analyze several tasks, among which identification rules...
Increasing evidence points to a key role played by epithelial-mesenchymal transition (EMT) in cancer progression and drug resistance. In this study, we used wet silico approaches investigate whether EMT phenotypes are associated resistance target therapy non-small cell lung model system harboring activating mutations of the epidermal growth factor receptor. The combination different analysis techniques allowed us describe intermediate/hybrid complete respectively HCC827- HCC4006-derived...
Prediction of binding sites for transcription factors is important to understand how the latter regulate gene expression and this regulation can be modulated therapeutic purposes. A consistent number references address issue with different approaches, Machine Learning being one most successful. Nevertheless, we note that many such approaches fail propose a robust meaningful method embed genetic data under analysis. We try overcome problem by proposing bidirectional transformer-based encoder,...
The Urban Intelligence approach views the city as a complex system that needs to be studied through interaction of its different subsystems. Such complexity is addressed also in virtual dimension, construction Digital Twins allow understand, control, and optimize urban dynamics according multidimensional objectives.In this context, we describe here model assess evaluate risks incurred by pedestrians vehicles under severe extreme rainfall events results increasing surface runoff, causing...
Alzheimer's Disease (AD) and its preliminary stage - Mild Cognitive Impairment (MCI) are the most widespread neurodegenerative disorders, their investigation remains an open challenge. ElectroEncephalography (EEG) appears as a non-invasive repeatable technique to diagnose brain abnormalities. Despite technical advances, analysis of EEG spectra is usually carried out by experts that must manually perform laborious interpretations. Computational methods may lead quantitative these signals...
Abstract Motivation: Nowadays, knowledge extraction methods from Next Generation Sequencing data are highly requested. In this work, we focus on RNA-seq gene expression analysis and specifically case–control studies with rule-based supervised classification algorithms that build a model able to discriminate cases controls. State of the art compute single contains few features (genes). On contrary, our goal is elicit higher amount by computing many models, therefore identify most genes...
The multidisciplinary nature of nutrition research is one its main strengths. At the same time, however, it presents a major obstacle to integrate data analysis, especially for terminological and semantic interpretations that specific fields or communities are used to. To date, proper ontology structure formalize concepts description nutritional studies still lacking. We have developed Ontology Nutritional Studies (ONS) by harmonizing selected pre-existing de facto ontologies with novel...
In the Next Generation Sequencing (NGS) era a large amount of biological data is being sequenced, analyzed, and stored in many public databases, whose interoperability often required to allow an enhanced accessibility. The combination heterogeneous NGS genomic open challenge: analysis from different experiments fundamental practice for study diseases. this work, we propose combine DNA methylation RNA sequencing at gene level supervised knowledge extraction cancer.We retrieve datasets Cancer...
Machine Learning (ML) algorithms are used to train computers perform a variety of complex tasks and improve with experience. Computers learn how recognize patterns, make unintended decisions, or react dynamic environment. Certain trained machines may be more effective than others because they based on suitable ML were through superior training sets. Although known publicly released, sets not reasonably ascertainable and, indeed, guarded as trade secrets. While much research has been...
This paper describes a method for learning logic relationships that correctly classify given data set. The derives from certain minimum cost satisfiability problems, solves these and deduces the solutions desired relationships. Uses of include mining, in expert systems, identification critical characteristics recognition systems. Computational tests have proved is fast effective.