Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
portfolio
Classifying breast cancer cells by hypoxic and normoxic condition
A machine learning classifier that tells hypoxic from normoxic tumour cells using biological data.
Investigating Public Concerns About AI
Building a 20k-tweet and 500-article corpus to study how the public and the media frame artificial intelligence.
Simulating the 3D Ising model
A simulation of the three-dimensional Ising model using both Simulated Annealing and the Wolff cluster algorithm.
Finding the optimal visual input for cortical neurons
Generating Most Excitatory Inputs for single neurons in mouse visual cortex with CNNs, benchmarked against Gabor filters.
Deep learning for sign language recognition
Turning sign language videos into 3×3 frame grids so that a CNN can classify them as single images.
TP53 mutation prediction from cancer cell line expression
Predicting TP53 mutation status from CCLE transcriptomics with tree-based models, at ~81% F1-score.
publications
Enrichment Algorithms for Gene Regulatory Network Reconstruction
Published in CIBB 2025 — 20th International Conference on Computational Intelligence Methods for Bioinformatics and Biostatistics, Politecnico di Milano, 2025
Extending the CellOracle framework with enrichment-based methods to make inferred gene regulatory networks more biologically interpretable.
pysigscore: gene signatures scoring across bulk and single-cell transcriptomics
Published in bioRxiv (under review), 2026
A Python framework for gene set scoring in bulk and single-cell RNA-seq, bringing together 18 scoring methods behind one interface, with built-in reliability analysis.
talks
Enrichment Algorithms for Gene Regulatory Network Reconstruction
Published:
Presentation of my work on enrichment-based methods for Gene Regulatory Network reconstruction, extending the CellOracle framework with single-cell RNA-seq and ATAC-seq data to improve the biological interpretability of the inferred networks.