Doctoral Candidate Position 14 - metaSysX GmbH
AI-based systems biology analysis to identify new compounds using spectral information.
Marta Costa holds a Bachelor's degree in Cellular and Molecular Biology with a specialization in Neurobiology, where she gained extensive hands-on experience in experimental and laboratory work. In 2024, she completed a Master's in Computational Biology and Bioinformatics at Nova University Lisbon, where she developed her thesis on leveraging machine learning algorithms to predict Alzheimer's disease. This experience deepened her interest in integrating biological knowledge with computational approaches to extract meaningful insights from complex data.
Currently, Marta is a PhD student within the MSCA-funded BICEPS network. Her research focuses on identifying metabolic signatures associated with Parkinson’s disease and developing automated pipelines for metabolomic data annotation. By combining her background in neuroscience with her passion for AI and data-driven discovery, Marta's work bridges experimental biology and computational modeling to advance our understanding of neurodegenerative diseases.
Description of project
Parkinson's disease (PD) is a neurodegenerative disorder associated with the progressive loss of dopaminergic neurons in the brain. Increasing evidence points to mitochondrial dysfunction as a key factor in PD pathology, with damaged mitochondria contributing to immune activation and neuroinflammation. In this context, mass spectrometry-based metabolomic and lipidomic analysis of samples collected from PD patients and mouse models will be applied to help understanding the underlying processes and the genetic and environmental factors involved in amongst all in macrophages-mediated pathogen destruction and tissue remodeling.
The studies will be concentrating on using a combination of analytics and bioinformatics to find metabolites and/or dysfunctional pathways affected in the progression of PD using the samples available from cooperation partners. The aim of metabolomics is detection, identification and quantification of as many metabolites as possible. Of highest importance are metabolites that are discriminative for the PD development. Therefore, a candidate will combine the untargeted GC- and LC-MS metabolite profiling of plasma and/or CSF samples as well as complex data analysis (classification model and predictive model) to identify candidate biomarkers and foresee the disease progression. A development of an algorithms that allow automatic identification of hundreds of detected compounds using spectral information will be part of the project.