Matthew Scicluna is a recent graduate from the Professional Masters program from the Mila (University of Montreal). Previously, he completed degrees in Statistics and Mathematics from the University of Toronto. He is interested in applying cutting edge deep learning techniques to biological data to improve in-silico medicine. In the past he applied deep learning tools on a variety of data, ranging from Zebrafish locomotion to cell microscopy. He currently is investigating how to interpret the outputs of neural networks, when applied to biological data (as opposed to the much more well understood computer vision and NLP contexts).
Contact : mattcscicluna [at] gmail.com
Address : 5000 Bélanger, Room S-1430
Phone : 514 376-3330 #4434
Representative Publications
Scicluna M†, Ni S†, Valdez Córdova CM†, Grenier J-C, Poujol R, Kanoun ME, Moon
KR, Lemieux S, Wolf G, Krishnaswamy S, Hussin JG. PHATE-Derived Ancestry Coordinates Capture Continuous Population Structure in Human Genomic Data. †contributed equally
Rochefort-Boulanger C†, Scicluna M†, Poujol R, Grenier JC, Carrier PL, Lemieux S, Hussin JG. (2025). A Transparent and Generalizable Deep Learning Framework for Genomic Ancestry Prediction. American Journal of Human Genetics. 113, 1-17 †contributed equally
Scicluna M, Grenier JC, Poujol R, Lemieux S, Hussin JG. 2023. Towards Computing Attributions for Dimensionality Reduction Techniques. Bioinformatics Advances.
Julie Hussin's Computational Biomedicine Lab 