Milton is a postdoctoral researcher who joined the GreeneLab in 2020. He received his PhD in Information Systems Engineering in 2016 from Universidad Tecnológica Nacional (Argentina), at the Research institute for signals, systems and computational intelligence.
Milton’s research is focused on data mining and machine learning, and their application to bioinformatics and genetic medicine. He is interested in the design and implementation of unsupervised learning approaches with a particular focus on clustering and ensemble methods, which are fundamental tools to understand the distribution of patterns in large datasets. This makes them appealing to extract novel knowledge from what we now call “big data,” which presents very interesting challenges, such as the integration of highly heterogeneous data sources and the analysis of huge amounts of information. He has worked with data in systems biology studies that inherently have these characteristics. For example, in multi-holistic approaches in the field of fruit biology, data sources can include a mix of measurements, such as morpho-agronomic traits, different kinds of molecules and consumer preferences. In the study of complex human diseases, large biobanks provide tons of genetic and phenotypic data, including quantitative and qualitative features with possibly non-linear relationships between them.
In his recent research experience, he has learned about an exciting, new field: he has worked with experts in complex human traits and contributed to better understand the heterogeneity of asthma, the most prevalent respiratory disease worldwide. He is deeply inspired by the complex interplay between genetic and environmental factors present in common diseases, where the application of unsupervised learning approaches can be very useful in precision medicine.