ANDREA MASTROPIETRO

PhD Student

PhD program:: XXXV
email: mastropietro@diag.uniroma1.it
building: DIAG A101
room: A101




supervisor: Aris Anagnostopoulos
co-supervisor: Simone Scardapane
co-supervisor (2): Paolo Tieri

PhD student in Data Science with a computer engineering background. My research area is AI for medicine, with a particular focus on neural network explainability techniques for bioinformatics, chemoinformatics and medical applications.

Position:

2019 - present: PhD Student in Data Science (Sapienza University of Rome)

Research visits:

Sept 2022 - Feb 2023: Visiting PhD Student at the Department of Life Science Informatics at the University of Bonn (Germany) under the supervision of Prof. Jürgen Bajorath. During my visit, I worked on projects focused on graph neural network explainability in chemoinformatics.

Education:

2017 - 2019: MSc in Engineering in Computer Science (110/110 cum Laude - Sapienza University of Rome) - Excellent Graduate, Honors Program, Erasmus Program (Polytechnic University of Catalonia, Spain)
2014 - 2017: BSc in Computer and System Engineering (110/110 cum Laude - Sapienza University of Rome) - Honors Program

Awards and grants:

2022: Avvio alla Ricerca Tipo 2 with the project "Explaining Graph Neural Networks in Medicinal Chemistry"
2021: Avvio alla Ricerca Tipo 1 with the project "Neural Network Interpretability in Bioinformatics"
2021: Best poster award at ACDL 2021 - “Feature Selection in Neural Networks via Rank Aggregation”
2020: Copernicus Masters - Winner of European Space Agency DTE Challenge and Italian Space Agency Prize

Additional roles:

Activist for the Network Medicine Exploratory in the SoBigData++ project

Research interests:

Deep Learning
Machine Learning
XAI
Bioinformatics
Network Medicine
Chemoinformatics

Research products

  • 11573/1687346 - 2023 - XGDAG: explainable gene–disease associations via graph neural networks (01a Articolo in rivista)
    ANDREA MASTROPIETRO, GIANLUCA DE CARLO, ARISTIDIS ANAGNOSTOPOULOS
  • 11573/1668281 - 2023 - NIAPU: Network-Informed Adaptive Positive-Unlabeled learning for disease gene identification (01a Articolo in rivista)
    PAOLA STOLFI, ANDREA MASTROPIETRO, GIUSEPPE PASCULLI, Davide VERGNI
  • 11573/1691854 - 2023 - Learning characteristics of graph neural networks predicting protein–ligand affinities (01a Articolo in rivista)
    ANDREA MASTROPIETRO, GIUSEPPE PASCULLI
  • 11573/1691795 - 2023 - Calculation of exact Shapley values for explaining support vector machine models using the radial basis function kernel (01a Articolo in rivista)
    ANDREA MASTROPIETRO
  • 11573/1631720 - 2022 - NETWORK PROXIMITY-BASED DRUG REPURPOSING STRATEGY FOR PRIMARY BILIARY CHOLANGITIS (01h Abstract in rivista)
    GIUSEPPE PASCULLI, ANDREA MASTROPIETRO, PAOLA STOLFI, Davide VERGNI
  • 11573/1665431 - 2022 - PROCONSUL: PRObabilistic exploration of CONnectivity Significance patterns for disease modULe discovery (04b Atto di convegno in volume)
    ANDREA MASTROPIETRO, MANUELA PETTI
  • 11573/1652545 - 2022 - EdgeSHAPer: Bond-Centric Shapley Value-Based Explanation Method for Graph Neural Networks (01a Articolo in rivista)
    ANDREA MASTROPIETRO, GIUSEPPE PASCULLI
  • 11573/1661039 - 2022 - Protocol to explain graph neural network predictions using an edge-centric Shapley value-based approach (01a Articolo in rivista)
    ANDREA MASTROPIETRO, GIUSEPPE PASCULLI
  • 11573/1650880 - 2022 - Network Proximity-Based Drug Repurposing Strategy for Early and Late Stages of Primary Biliary Cholangitis (01a Articolo in rivista)
    GIUSEPPE PASCULLI, ANDREA MASTROPIETRO, PAOLA STOLFI, Davide VERGNI, Francesco PESCE
  • 11573/1565282 - 2021 - Adaptive Positive-Unlabelled Learning via Markov Diffusion (02a Capitolo o Articolo)
    ANDREA MASTROPIETRO, GIUSEPPE PASCULLI
  • 11573/1444275 - 2020 - A CNN approach for audio classification in construction sites (04b Atto di convegno in volume)
    ANDREA MASTROPIETRO, MICHELE SCARPINITI, Aurelio UNCINI

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma