"Improving clinical decisions in cancer"

OVERVIEW

In Europe, over 40 000 women die of ovarian cancer every year. In addition to surgery, most patients are treated with platinum-based chemotherapy. Unfortunately, the effect of chemotherapy often decreases during the treatment cycles, and currently, there are few effective treatments for those patients who develop resistance to platinum-based drugs. The survival of these patients has not improved much in the past decades, and new solutions are in urgent need.

In the DECIDER project, a patient's response to treatments is predicted using methods that use, among others, histopathological and genomic data from the patient. Genomic changes and aberrations in gene functions are used to find effective, personalized treatments. This point will be made by developing an open-source program to integrate and visualize all relevant data from a patient. Doctors can more easily identify effective drugs for their patients using this information. All patients participating in the research are treated in Finland, and Finnish patient organizations have an essential advisory role in the project.

MAIN GOALS

DECIDER is a multidisciplinary research project bringing together expertise from 16 research groups and companies in 14 organizations located in 7 European countries to develop diagnostic tools and improve the treatment options for high-grade serous ovarian cancer. The partners' expertise ranges from clinical medicine, genomics, molecular biology, computer science, and Artificial Intelligence to biomedical and privacy laws.

The main goals of DECIDER are to develop diagnostic tools and treatments for high-grade serous ovarian cancer with the help of AI methods. In addition, the aim is to identify those patients who do not respond well to the first-line treatments and find effective treatments for patients with drug-resistant cancer.

We also study the legal issues that impede or slow down the use of new treatments to facilitate the commercialization and availability of personalized therapies ethically and legally sustainable.

MAIN ACTIVITIES

• Integration of histopathology and genetics to predict chemotherapy response

  Recent advancements in histopathology and genetics have enabled the development of personalized medicine approaches that can improve patient outcomes by tailoring treatments based on individualized genetic and clinical characteristics. In the field of oncology, chemotherapy is often used as a treatment option, but the efficacy of chemotherapy varies between patients due to differences in genetic makeup and tumor characteristics. Therefore, identifying predictive biomarkers of chemotherapy response is crucial for effective treatment planning. In this context, we integrate histopathology images with genetic features to predict chemotherapy response in ovarian cancer patients. Ultimately, the convergence of histopathology and genetics can transform cancer treatment by enabling the development of more personalized and effective treatment plans based on an individual patient's unique molecular profile.

• Gene fusion detection on RNA and DNA samples

  Gene fusions, resulting from genomic rearrangements, have emerged as important drivers of oncogenesis and potential therapeutic targets in various types of cancer. Detecting gene fusions accurately is crucial for understanding tumor biology and developing targeted therapies. In recent years, advancements in RNA and DNA-based approaches have significantly improved gene fusion detection capabilities. 

  We aim to unravel genomic rearrangements through RNA and DNA-based gene fusion detection tools, which are promising for advancing precision medicine in oncology and improving patient outcomes.

• OncoDash: software for clinical decision making

  The increasing amounts of biological and patient clinical data and the rapid pace of associated research results offer new opportunities for improved treatment decisions but also increase the complexity of the decision-making process. The Oncodash software addresses this problem by assisting clinicians with patient review and prioritizing treatment options. OncoDash not only provides interactive interfaces on patient data but also a rich environment to interact with models. In particular, it includes AI-driven models, which show surprising performance levels in health and across other applications.

   

   

   

Publications

1	Lovino, Marta; Randazzo, Vincenzo; Ciravegna, Gabriele; Barbiero, Pietro; Ficarra, Elisa; Cirrincione, Giansalvo "A survey on data integration for multi-omics sample clustering" NEUROCOMPUTING, vol. 488, pp. 494 -508 , 2022 | DOI: 10.1016/j.neucom.2021.11.094 Journal