Dr. Alejandro Cisterna-García

Short Biography:Alejandro Cisterna-García earned his Ph.D. in Bioinformatics in 2023 from the University of Murcia, where he previously completed a Master’s degree in Bioinformatics and a Bachelor’s degree in Biotechnology. He is currently a postdoctoral researcher at the Biomedical Data Science Lab at ETH Zurich.

His research centers on the development and application of machine learning and deep learning methodologies for biomedical challenges, with a particular focus on disease diagnosis. His work has primarily addressed neurodegenerative and infectious diseases, alongside bioinformatics tool development. More recently, his research has expanded into deep learning approaches for antimicrobial activity prediction, integrating computational modeling with translational biomedical applications

Title: “ Artificial Intelligence and Bioinformatics: Transforming Personalized Medicine”

Abstract: The convergence of artificial intelligence (AI) and bioinformatics is reshaping the landscape of personalized medicine. Advances in high-throughput sequencing, multi-omics technologies, and digital health platforms have generated vast amounts of biological and clinical data. However, transforming this data into actionable medical insights requires sophisticated computational approaches.

This talk explores how AI, particularly machine learning and deep learning, integrated with bioinformatics pipelines enables the identification of disease-associated biomarkers, prediction of potential new treatments, and stratification of patients into clinically meaningful subgroups. By leveraging genomic, transcriptomic, proteomic, and clinical data, AI-driven models can uncover complex biological patterns that traditional analytical methods often miss.

We will discuss real-world applications in neurodegenerative diseases, infectious diseases, and antimicrobial peptides generation, highlighting how computational tools support precision diagnostics and improved clinical decision-making. Key challenges including data integration, model interpretability, bias and reproducibility will also be addressed.