Nevenka Dimitrova, PhD

Visiting Computational Oncology Scientist
Memorial Sloan Kettering Cancer Center

Nevenka Dimitrova, PhD is a biomedical data science leader, currently on sabbatical at Memorial Sloan Kettering Cancer Center. Her recent position was a Vice President of Data Science and Data Engineering at GlaxoSmithKline, where she combined her technology innovation in AI/ML, with advanced cloud data architectures and healthcare informatics to serve the whole biopharma R&D (10,000people) including target discovery, biomarker, clinical and manufacturing. She led a data science and applied AI and Machine Learning team that utilizes deep learning technologies for image and multi-omics based cell line selection for biopharma discovery, cutting edge algorithms for drug target engines and biomarkers, perturbation sequencing analysis and differential gene expression at scale. Previously, as CTO of Oncology Informatics and Genomics in Philips, she took products from research to market success and helped open new business opportunities in clinical informatics. With a PhD in Computer Science, 140 scientific articles and over 70 granted patents in machine learning, information retrieval, and decision support, Nevenka was recognized for her technical leadership and external collaborations with the Gilles Holst award, the highest peer recognition at Philips. Her expertise and interests are in improving clinical outcomes in oncology, epidemiology, and immunology, and she is excited about impact in clinical settings. In her time away from work she enjoys creating health food recipes, active meditation, music, and travel with family.

ABSTRACT

Data Science Approaches Applied in Novel Systems Biology Frameworks for Biomarker Discovery

Characterizing the complex interplay of cellular processes in cancer would enable the discovery of key mechanisms underlying its development and progression. In this presentation I will talk about several data science approaches applied in novel systems biology frameworks. In the first example, I will talk about characterizing complex biological processes using a unique multidimensional framework integrating transcriptomic, genomic and/or epigenomic profiles for any given cancer sample. I will show that InFlo robustly characterizes tissue-specific differences in activities of signaling networks on a genome scale using unique probabilistic models of molecular interactions on a per-sample basis. We evaluated multi-omics profiles of primary high-grade serous ovarian cancer tumors to delineate mechanisms underlying resistance to frontline platinum-based chemotherapy. InFlo was the only algorithm to identify hyperactivation of the cAMP-CREB1. Next, I will talk about single cell sequencing and using advanced algorithms to show that loss of p53—the ‘guardian of the genome’—is not merely a gateway to genetic chaos but, rather, can enable deterministic patterns of genome evolution that may point to new strategies for the treatment of TP53-mutant tumors.