About
My name is Ugo Lomoio, I'm a Biomedical engineer and now a PhD Student in Digital Medicine at the Magna Graecia University of Catanzaro. My research focus on Artificial Intelligence applications in healthcare.
I love computers, gaming, playing violin, listen to music while doing AI research.
During my three year PhD period I have joined the Department of Computer Science and Technology, University of Cambridge (UK) for my six month abroad period.
My PhD fellow was partially co-funded by Relatech S.p.A 
where I worked for one year as a research intern.
AI & Machine Learning & Network Science
After the Bachelor's degree in Informatic and Biomedical Engineering and the Master degree in Biomedical Engineering, both at University of Catanzaro, I decided to continue my studies with a PhD in Digital Medicine focusing on Artificial Intelligence in healthcare.
- Birthday: 22 July 1996
- Website: https://ugolomoio.github.io
- Phone: +39 388 3787548
- City: Catanzaro, Calabria, IT
- Age:
- Degree: Master degree in Biomedical Engineering
- Email: lomoiougo@gmail.com
Facts
I've been a computer enthusiast since young age, but i learned how to code only at 19 years old thanks to my University and thanks to the professor of the course in "Informatics Fundamentals", now my PhD supervisor, Pietro Hiram Guzzi.
Skills
Programming and Markup Languages
Python Libraries
Scikit-Learn
SciPy
PIL
Networkx
TensorFlow
PyTorch
TorchVision
Plotly - Dash
Matplotlib
Pytorch Lightning
NumPy
Pandas
Transformers
Diffusers
Torch Geometric
Graph Outlier Detection (pygod)
Cloud Services
Google Cloud Platform
Google Colaboratory
Databases and Other
Mongo DB
MySQL
RedCap
Apache Superset
Operating Systems
Windows
Linux
MacOs
Resume
I have a MSc in Biomedical Engineering. I'm now a PhD student in Digital Medicine that focus his research on developing and applying Artificial Intelligence models in healthcare.
I love computers, programming and AI. In my research i work on the development of AI models, and decision support systems softwares, to support clinicians in their daily work routine. I like learning and experimenting new things involving AI research. I'm a native Italian speaker with advanced English skills in reading, writing, understanding and speaking.
Summary
Lomoio Ugo
MSc in Biomedical Engineering
I'm particularly interessed in Deep Learning, Machine Learning and Network Science.
- Catanzaro, Calabria, IT
- +39 388 3787548
- lomoiougo@gmail.com
Education
Bachelor's Degree: Informatic and Biomedical Engineering
2016 - 2019
Magna Graecia University of Catanzaro, Italy
Thesis: "Italian normative for nuclear medicine sites".
Degree Score: 94/110.
Master's Degree: Biomedical Engineering
2019 - 2022
Magna Graecia University of Catanzaro, Italy
Thesis: "Sperimentation of network community detection algorithms for the analysis of Protein Contact Networks ".
Degree Score: 110/110 with honors.
PhD in Digital Medicine
2022 - 2025 (ending in November 2025)
Magna Graecia University of Catanzaro, Italy
PhD cofounded by Relatech S.p.A
PhD visiting scholar
September 2023 - February 2024
Department of Computer Science and Technology, Cambridge University, United Kingdom
PhD cofounded by Relatech S.p.A
Teaching activities
Teaching Assistant for the course of "Advanced Bioinformatics Techniques"
2022 - 2025
Magna Graecia University of Catanzaro, Italy
Assisting students in the course of Advanced Bioinformatics Techniques, providing support in Python programming and data analysis.
Teaching Assistant for the course of "Machine Learning and Artificial Intelligence"
2022 - 2025
Magna Graecia University of Catanzaro, Italy
Assisting students in the course of Machine Learning and Artificial Intelligence, providing support in Python programming and data analysis.
Experience
Research Intern at Relatech S.p.A, Rende, Italy
May 2024 – May 2025
Working on research related projects such:
- Agritech, Italian National Center for the Development of new Technologies in Agriculture;
- InMoto, home rehabilitation for patients suffering from neuromotor pathologies and neurocognitive.
Multiple occasional self-employment contracts as a Research Collaborator for the PON VQA project at UNICZ:
February - July 2022
:
Working on the development of the PCN-Miner tool, a Python-based GUI for Protein Contact Networks analysis. Available at: https://github.com/hguzzi/ProteinContactNetworksAugust 2022 - January 2023
:
Working on the development of a decision support system tool for ECG anomaly detection, a Python-based GUI to detect and annotate abnormalities inside 12-lead ECGs using AutoEncoders. Available at: https://github.com/UgoLomoio/ECG_DSS_CAEDecember 2023 - June 2024
:
Developing the demo tool for the final PON VQA project, writing documentation and user manuals. Developing also various systems for clinical data management for internal hospital usage using MySQL and RedCap.
Reviewer for the following journals\conferences:
- BMC Bioinformatics
- IEEE Transactions on Computational Biology and Bioinformatics
- Frontiers in Digital Health
- Workshop of Networks and Graph Neural Networks for Bridging Bioinformatics and Medicine, CIBB2025
- Computational and Structural Biotechnology Journal
- Journal of Healthcare Informatics Research
- LLMs and Graph Neural Networks for computational biology and medicine Workshop, IEEE BIBM 2024
Workshop Organizer \ Program Committee:
- Workshop Programme Committee at IEEE BIBM 2024. Workshop of “LLMs and Graph Neural Networks for computational biology and medicine”
- Workshop organizer at CIBB 2025. Workshop of “Networks and Graph Neural Networks for Bridging Bioinformatics and Medicine”
- Workshop organizer at IEEE BIBM 2025. Workshop of “Network Science and Artificial Intelligence for Biomedicine & Health informatics”
Scientific societies membership:
- IEEE Student Member, from 2023
- Bioinformatics Italian Society (BITS), from 2025
- Italian National Group of Bioengineering (GNB), from 2023
Research Metrics:
Portfolio
Only some of my projects are publicly available on GitHub, here you can find a list of them.
PhD project research
Study, definition and implementation of innovative techniques for the analysis of medical clinical data.
Omics techniques (genomics, lipidomics, proteomics, radiomics, connectomics) generates heterogeneous, multidimensional and often redundant data that require a large amounts of space, a management in terms of models and technological approaches that are scalable and efficient. The innovative approaches of analysis are based on integration according to one holistic perspective of all data and on the analysis of the same with innovative algorithms and methodologies. The integration of the same, also using distributed and cloud architectures, in archives (such as advanced health files), allows you to build the sub-layer of data necessary for building personalized medicine applications and of accuracy (P4 medicines). This approach, recently also applied to patients affected by SARS-CoV-2, also finds numerous applications in different contexts clinicians for the development of appropriate therapies in the field of cardiovascular diseases, neurological diseases and diseases aging related. The proposed research program consists in the study and definition of advanced, distributed, high-performance, data integration, based architectures on advanced mathematical models such as knowledge graphs and multilevel networks. The result main part of this project will be the definition and prototyping of this infrastructure, even using existing elastic or cloud architectures. The feedback in terms of application provides for the application in the field of pathologies chronic such as neurodegenerative and cardiological. This project on the one hand goes to corroborate biomedical research within the healthcare system, providing for a close collaboration with the clinical part. In parallel the software tools produced they can then be prototyped and then developed in collaboration with companies in order to improve the growth effects of the local productive fabric.
GTex Visualizer
An open source, cloud-based, web application for the analysis of gene expression data in the GTex database to study changes in gene expression ralated to aging and diseases.
ECG Decision Support System
An open source and offline Decision Support System tool for the analysis, automatic identification of abnormalities and annotation of 12-lead ECG signals. The anomaly detection task is performed using an AutoEncoder model trained to reconstruct 2-seconds lenght healthy ECG windowsof. Trained and tested using both synthetical generated data and real ECG signals from the PTB and PTB-XL datasets. The tool provides a user-friendly interface for clinicians to upload and analyze ECG signals. Once the ECG signal is uploaded, the tool automatically detects and shows them to the clinician for the final annotation. Explanations of the prediction are provided to increase clinician trust so they can perform the final annotation.
SARS CoV 2 Spike protein variants analysis trough Protein Contact Networks (PCNs)
PCN-Miner is our open source and offline tool for the analysis of protein structures based on the concept of PCN. A PCN of a given protein is a graph rappresentation of the protein structure. In our research, we constructed and analyzed the PCNs of the SARS CoV 2 Spike variants. Then, we compared our results (for example: aminoacid/node centralities, network communities) to find differences between variants.Comparing Kolmogorov-Arnold Network Autoencoders against vanilla ones
In this work we compared the performance of Kolmogorov-Arnold Network Autoencoders (KAE) against vanilla Autoencoders (AE) in the analysis of biomedical data. Both linear and convolutional autoencoders were trained and tested on the same datasets. We used a dataset of stetoscopic heart sounds and compared both models for multiple tasks: reconstruction, denoising and inpainting. We found that convolutional KAEs with PixelShuffle layers outperformed all the other models in all tasks.Transthyretin
We proposed a new approach to study the transthyretin protein (TTR), a protein involved in amyloidosis. Given the low availability of experimental structures of TTR in the tetramer conformation, we focused on computational methods to model the protein using AlphaFold 3. Predicted structures were validated against experimental data when available A total of 133 TTR mutations were analyzed using various computational tools. - Structural analysis of the protein using Protein Contact Networks (PCNs) was used to identify central residues and functional domains. - We computed TM-scores between each variant and wild-type TTR to assess their structural similarity. - We used ESM2 embeddings and UMAP to visualize the variants distribution in a 2-dimensional space: benign mutations were found near the wild-type TTR, while pathogenic variants were found in more distant regions. - We also performed tafamidis ligand optimization and de-novo ligand generation using DiffSBDD: optimization increased binding affinity, generation gives best QED drug-likeness. - We performed docking and binding affinity prediction of the transthyretin protein with its ligands using AutoDock Vina and DiffDock. - We performed 100-ns molecular dynamics simulations of the V50M TTR variant to study its stability and the stabilizing effects of each ligand.E-ABIN
We proposed a new tool to analyze gene expression data from the gene expression omnibus (GEO) database. E-ABIN is an explainable module for anomaly detection in biological networks, incorporates both machine and deep learning techniques to perform anomaly detection in gene expression and dna methylation datasets. The tool was evaluated on several benchmark datasets (celiac disease, parkinson, bladder and colorectal cancer), demonstrating its effectiveness in identifying anomalous patterns and providing insights into the underlying biological processes. An explainability module is available to provide different level of explanations (most influential genes for the prediction of the abnormal class): from patient level to dataset level. Most influential genes found using E-ABIN align with known disease-related genes, demonstrating the tool's potential for identifying novel biomarkers and therapeutic targets.ExDiff
A modular and explainable framework combining network simulation and graph neural networks to study spreading dynamics in complex networks. The framework allows to simulate the spreading of a disease in a network, and then to use graph neural networks to learn the patterns of the spreading. The SIRVD model is used to simulate the spreading of a disease in a network, where nodes represent individuals and edges represent interactions between them. The framework is modular and can be easily extended to include other spreading models (e.g., SIR, SIS).ExDiff Mpox
A slightly modified version of ExDiff was develped to simulate the multispecies interactions between the populations of humans and rodents for the Mpox disease in Nigeria and Congo. The SEIRVD (SEID) model is used to simulate the spreading of a disease for humans (rodents). Different techniques were simulated to control the spreading of the disease, such as vaccination (random or targeted), quarantine and rodent culling. Results shows that: targeted vaccination, togheter with quarantine and rodent culling, is the most effective strategy to control the spreading of the disease. With culling having more effects in the early stages of the epidemic.DCAE-SR
A deep learning model that reconstruct electrocardiogram (ECG) signals at super resolution. The model is trained on a large dataset of ECG signals (PTB-XL dataset) and is able to reconstruct the ECG signal at a resolution of 500Hz, while the original signal is sampled at 50Hz and corrupted by ECG artifacts such as EMG, baseline wander, and noise. The model is based on a denoising convolutional autoencoder (DCAE) architecture and explainability techniques are used to undestand the impact of each sample of the signal for the final super-resoluted signal. Performances are evaluated in terms of MSE, RMSE, PSNR and SSIM. Down-stream tasks such as classification shows that applying super-resolution leads to improved classification performance when compared against the interpolation of the original signal.Publications
Here you can find a list of my publications in peer-reviwed scientific journals and conferences.
Conference Procedings
- Puccio B., Lomoio U., Di Paola L, Guzzi P.H. and Veltri P. (2022). Annotating Protein Structures for Understanding SARS-CoV-2 Interactome. SEBD 2022. SEBD 2022 Presentation.
- Giancotti R., Lomoio U., Veltri P., Guzzi P. H., & Vizza P. (2022). A machine-learning based tool for bioimages managing and annotation. 2589–2594. IEEE BIBM 2022.
- Guzzi P. H., Lomoio U., Scicchitano R., & Veltri P. (2022). NOMA-DB: a framework for management and analysis of ageing-related gene-expression data. 1905–1910. IEEE BIBM 2022.
- Guzzi P. H., Lomoio U., & Veltri P. (2022). Enabling analysis of transcriptomic data related to Ageing Processes through the GTEx-Visualizer web portal. BBCC 2022 Poster.
- Guzzi P. H., Cannistra M., Giancotti R., Lomoio U., Puccio B., Vizza P., … & Veltri P. (2023). Annotating omics Data with sex and age of samples: Enabling powerful omics studies. 3886–3890. IEEE BIBM 2023.
- Puccio B., Lomoio U., Giancotti R., Cannistra M., Flesca S., Scala F., … & Vizza P. (2023). Validating biomedical and clinical data via an annotations based framework: experiences within the PON VQA project. Patron Editore Srl. GNB 2023 Poster.
- Lomoio U., Vizza P., Giancotti R., Tradigo G., Petrolo S., Flesca S., … & Veltri P. (2023). A tool to perform semi-supervised anomaly detection and annotation on 15 lead ECG signals. Patron Editore Srl. GNB 2023 Poster.
- Guzzi P. H., Lomoio U., Mazza T., & Veltri P. (2024). Anomaly Detection in Individual Specific Networks through Explainable Generative Adversarial Attributed Networks. 5764–5769. IEEE BIBM 2024.
- Lomoio U., Defilippo A., Puccio B., Guzzi P.H., & Veltri P. (2025). A Framework based on Explainable Graph Neural Networks For Modelling Spreading Processes in Networks. GNB 2025 Poster.
- Puccio B., Defilippo A., Lomoio U., Scalise S., Parrotta E.I., Veltri P., & Guzzi P.H. (2025). Network Modeling and Graph Neural Networks for Integrating Single-Cell and Bulk RNA-seq in Disease Progression. BITS 2025 Poster.
Journal Articles
- Lomoio U., Veltri P., Guzzi P. H., & Liò P. (2025). Design and use of a Denoising Convolutional Autoencoder for reconstructing electrocardiogram signals at super resolution. Artificial Intelligence in Medicine, 160, 103058.
- Lomoio U., Vizza P., Giancotti R., Petrolo S., Flesca S., Boccuto F., … Tradigo G. (2025). A convolutional autoencoder framework for ECG signal analysis. Heliyon, 11(2).
- Guzzi P. H., Di Paola L., Puccio B., Lomoio U., Giuliani A., & Veltri P. (2023). Computational analysis of the sequence-structure relation in SARS-CoV-2 spike protein using protein contact networks. Scientific Reports, 13(1), 2837.
- Guzzi P. H., Lomoio U., Puccio B., & Veltri P. (2022). Structural analysis of SARS-CoV-2 Spike protein variants through graph embedding. Network Modeling Analysis in Health Informatics and Bioinformatics, 12(1), 3.
- Guzzi P. H., Lomoio U., & Veltri P. (2023). GTExVisualizer: a web platform for supporting ageing studies. Bioinformatics, 39(5), btad303.
- Lomoio U., Puccio B., Tradigo G., Guzzi P. H., & Veltri P. (2023). SARS-CoV-2 protein structure and sequence mutations: Evolutionary analysis and effects on virus variants. PLoS One, 18(7), e0283400.
- Giancotti R., Lomoio U., Puccio B., Tradigo G., Vizza P., Torti C., … Guzzi P. H. (2024). The Omicron XBB.1 variant and its descendants: genomic mutations, rapid dissemination and notable characteristics. Biology, 13(2), 90.
Currently under revision:
- Defilippo A., Lomoio U., Puccio B., Veltri P., Guzzi P.H. (2025). ExDiff: A Framework for Simulating Diffusion Processes on Complex Networks with Explainable AI Integration. On Review at NAR Genomics and Bioinformatics.
- Lomoio U., Mazza T., Veltri P., Guzzi P.H. (2025). E-ABIN: an Explainable module for Anomaly detection in BIological Networks. On Review at NAR Genomics and Bioinformatics.
- Branda F., Ceccarelli G., Ciccozzi M., Scarpa F., Lomoio U., Chiodo F., Veltri P., & Guzzi P.H. (2025). Comparing Epidemics Controls through Simulations and Explainable Graph Convolution Networks. On Review at Scientific Reports Nature.
- Lomoio U., Carbonari V., Giorgi F.M., Ortuso F., Liò P., Veltri P., & Guzzi P.H. (2025). Integrative Structural Profiling and Ligand optimisation Across the Transthyretin Mutational Landscape. On Review at npj Systems Biology and Applications.
Contact
Location:
Catanzaro, Calabria (IT), 88100
Email:
lomoiougo@gmail.com
Call:
+39 388 3787548