Welcome to my webpage!
I’m Deisy Morselli Gysi.
I am a Professor in Statistics at Federal University of Paraná ( UFPR). My research revolves around the fascinating field of Precision Medicine, where I harness the synergies of Network Science and Machine Learning to drive transformative advancements.
With a strong background in biomedical research, I am deeply passionate about the potential of precision medicine to revolutionize healthcare by tailoring treatments to individual patients based on their unique characteristics. Through my work, I strive to uncover intricate disease mechanisms and identify targeted therapeutic strategies that can significantly improve patient outcomes.
Prior to my current position, I held the role of Associate Research Scientist at the renowned BarabasiLab, affiliated with the Network Science Institute at Northeastern University. Simultaneously, I served as a Research Trainee at the esteemed Channing Division of Network Medicine, associated with Harvard Medical School and Brigham and Women’s Hospital, and as a Bioinformatician at the Veteran Affairs. During this period, my primary focus was on biomarker discovery for complex diseases characterized by auto-immune responses, mental disorders, and senior disorders. In addition to that, I am also highly interested in the role of ncRNA mediated interactions for disease diagnostic, progression and terapeutics. Leveraging the power of Network Science and Machine Learning, I developed innovative approaches to decipher the complexities of these conditions and explore avenues for precision interventions.
Additionally, I actively contributed to the development of methodologies and R packages to facilitate the analysis of complex biomedical data.
In response to the global COVID-19 pandemic, my research group redirected our efforts towards drug repurposing for this pressing health crisis. Our work showcased the successful application of Network Science and Machine Learning in identifying potential drug candidates. This endeavor exemplifies my commitment to utilizing cutting-edge techniques to address urgent healthcare challenges. While celebrating the 20th anniversary of the Human Genome Project in Nature we have learned that ncRNAs have a major potencial for Network Medicine. Unleashing their power in NetMed has now opened a new era for disease detection.
My academic journey commenced with a Bachelor’s degree in Biotechnology from the Pontifical Catholic University, followed by a Bachelor’s degree in Statistics from the Federal University of Paraná, both in Brazil. Throughout my undergraduate studies, I actively engaged in research activities and was honored with two awards for outstanding research projects. Concurrently, I gained valuable experience as a Risk Analyst at HSBC multibank, where I applied statistical methods in a practical setting.
Building on this foundation, I served as a Bioinformatician at the Heart Institute of the University of São Paulo (USP), where I explored co-expression networks and investigated the influence of Single Nucleotide Polymorphisms (SNPs) on these networks. Subsequently, I joined the Albert Einstein Hospital as a Statistician, offering consulting services to the research department. In pursuit of advanced knowledge, I embarked on a Ph.D. program at the University of Leipzig, Germany, under the guidance of esteemed mentors, Dr. Peter Stadler, Dr Katja Nowick, and Dr Martin Middendorf.
Driven by my unwavering passion for scientific progress, I am dedicated to pushing the boundaries of precision medicine. By combining Network Science and Machine Learning, I strive to unlock the full potential of personalized treatments, ultimately improving the lives of patients. I invite you to explore my webpage to learn more about my research, publications, and ongoing projects within the exciting realm of precision medicine.
Featured
My Publications
Improving the generalizability of protein-ligand binding predictions with AI-Bind
State-of-the-art machine learning models in drug discovery fail to reliably predict the binding properties of poorly annotated proteins and small molecules. Here, the authors present AI-Bind, a machine learning pipeline to improve generalizability and interpretability of binding predictions. Read more
Talks I've given
Network Medicine: Disease module (in)completeness and other tales
Presentation about the role of ncRNAs on disease module completeness at the Computational Biology meets Data Science Conference. Read more