PNA is currently part of a personalized healthcare alliance (PHC) with other parties interested in joining efforts to improve the developments on the field of personalized medicine. As part of his internship at PNA, Lucas Giovanni Uberti-Bona Marin (student at Data Science and Knowledge Engineering, Maastricht University), is working on two fundamental aspects of this alliance. Find out more in this article.

The ageing population in different regions of the world compounds many of the challenges faced by medicine. One of the most critical and enduring challenges has been the need for more effective ways to treat cancer.

In 2015, cancer was responsible for around 25% of the total number of deaths in the EU. Cancer is a complex group of diseases which involves abnormal cell growth by altering the genes that regulate cell growth and differentiation. Therefore it’s a disease deeply tied to our DNA.

Recently, due to the decrease in the cost of genome sequencing and computational power, a new approach to treat diseases such as cancer has been getting more and more attention. This approach, called personalized medicine, tries to group individuals based on their genomic characteristics and to treat them on the bases of their specific (genetic) characteristics.

For this it’s essential to develop pharmacogenomic datasets, that is, datasets that contain data on patients’ genomes and how their tissues react to different chemical compounds. This allows us to focus on different possible treatments depending on the patients’ gene expressions.

However, the development of said datasets carries big costs, which means cooperation is of critical importance. With this, it’s also essential to be able to combine pharmacogenomic datasets and find agreements and disagreements between them to allow us to improve the precision of our predictive models. This entails the ability to narrow down how resistant or sensitive a patient will be to a specific compound according to their DNA composition.

PNA is currently part of a personalized healthcare alliance (PHC) with other parties interested in joining efforts to improve the developments on the field of personalized medicine. As part of my internship at PNA I am currently working on two fundamental aspects of this alliance.

One of them is exploring different types of data sharing platforms where companies, researchers and hospitals can share their data to enhance and accelerate the advancements in the field while taking into account the needs and requirements of each group.

The other one is developing tools to merge these pharmacogenomic datasets, that is, exploring how different methods of Transfer Learning (a subfield of Machine Learning) can be used to develop predictive models that combine the insights of different datasets to give better results overall.

I hope that, with this project, I will contribute to fostering a more cooperative environment in personalized medicine that allows us to more effectively treat patients by reducing mortality rates and treatment costs and increasing their wellbeing.

Lucas Giovanni Uberti-Bona Marin

Next article personalized medicine