Phd in NETWORK ONCOLOGY AND PRECISION MEDICINE

Research: Computational analysis of multi-omics and clinical data for early detection of solid cancers.

Education and Training
PhD Student — Network Oncology and Precision Medicine Institution: Sapienza Università di Roma Period: 31/10/2024 – Present Location: Rome, Italy
Master’s Degree in Data Science Institution: Sapienza Università di Roma Period: 01/09/2021 – 19/03/2024 Final grade: 107/110 Thesis: Identification of disease gene associations using heterogeneous graph learning on domain knowledge graphs Key topics: Neural Networks (Feedforward, CNN, RNN, LSTM, Transformers, Graph Neural Networks) Data Analysis Network Medicine Statistical Analysis Optimization Methods Signal Processing Cloud Computing
Bachelor’s Degree in Bioinformatics Institution: Sapienza Università di Roma Period: 09/10/2019 – 15/07/2021 Final grade: 110/110 cum laude Thesis: A network-based approach for drug repurposing and its application to thyroid cancer

Additional Training
Biostatistics in Public Health — Coursera (18/12/2022 – 19/03/2023)
Statistical Analysis with R for Public Health — Coursera (09/03/2022 – 01/05/2022)
Deep Learning Specialization — Coursera (31/01/2019 – 16/05/2019)

Work Experience
Biostatistician — Medtronic Period: 15/11/2025 – Present Location: Rome, Italy Design, implement, and validate statistical analyses for clinical and real-world data in accordance with study objectives, regulatory requirements, and pre-specified Statistical Analysis Plans (SAPs). Author and review Statistical Analysis Plans, including definition of estimands, endpoints, analysis populations, and handling of missing data. Perform statistical analyses using R and SAS, including descriptive statistics, regression models, survival analysis, longitudinal and repeated-measures methods. Develop and maintain analysis datasets, perform data cleaning and quality checks, and ensure traceability from raw data to analysis outputs. Produce tables, listings, and figures (TLFs) for internal decision-making, clinical study reports, and scientific publications. Interpret statistical results and communicate findings clearly to cross-functional stakeholders (clinical, medical, regulatory, and data management teams). Support protocol development and provide statistical input on study design, sample size justification, and analysis strategy. Contribute to responses to internal and external statistical queries, including reviewer comments and ad-hoc analyses.
Biostatistician — INMI Lazzaro Spallanzani Department: Epidemiology and Preclinical Research Period: 01/06/2024 – 14/11/2025 Location: Rome, Italy Statistical analysis Data analysis Data visualisation Data management
Biostatistician — INMI Lazzaro Spallanzani Department: Malattie Infettive ed Epatologia Period: 01/04/2022 – 01/06/2024 Location: Rome, Italy Data analysis Statistical analysis Data visualisation Data management

Language
Skills Mother tongue: Italian English: Listening: C2 Reading: C2 Spoken production: C2 Spoken interaction: C2 Writing: C2

Technical Skills
Software: Microsoft Access, Microsoft Excel, Microsoft Word, Microsoft PowerPoint, Microsoft Office, LaTeX Programming & Frameworks: Python, R, SAS, SQL Deep Learning frameworks: PyTorch, TensorFlow, Keras
Statistical Analysis and Modeling: Descriptive and inferential statistical analysis
Regression modeling and survival analysis Longitudinal and repeated-measures analysis
Bioinformatics and Multi-Omics Data Analysis: Analysis of transcriptomic and multi-omics data Differential expression analysis (RNA-seq) using DESeq2 Exploratory data analysis and dimensionality reduction (Principal Component Analysis, PCA)
Gene co-expression network analysis using WGCNA Biological interpretation of results (gene-level and pathway-level analysis) Management, preprocessing, and normalization of high-dimensional biological data Network medicine applied to the study of gene–disease associations
Construction and analysis of heterogeneous biological graphs (gene–gene, gene–disease, knowledge graphs) Experience with Graph Neural Network (GNN) architectures (e.g., Graph Convolutional Networks and related models) Integration of structured biological knowledge and omics data in graph-based machine learning models

Research project
The PhD project focuses on the computational analysis of clinical and multi-omics data for the early detection of solid cancers, with a specific emphasis on hepatocellular carcinoma in cirrhotic patients treated with direct-acting antivirals (DAAs) for HCV infection. The research activity, in collaboration with the National Institute for Infectious Diseases Lazzaro Spallanzani, involves the integration of clinical data with transcriptomic (miRNA) and proteomic data to identify molecular profiles associated with an increased risk of cancer development after sustained virological response (SVR). The planned analyses include preprocessing and normalization of high-dimensional data, exploratory and multivariate analyses, differential expression analysis, and network medicine approaches. The project aims to identify predictive molecular signatures and co-expression modules through the application of advanced statistical and computational methods, integrating biological and clinical information to improve oncological risk stratification and support the development of personalized surveillance strategies.