The IIS La Fe contributes to the development of an AI platform that will facilitate the early diagnosis of paediatric cancer and cardiovascular diseases.
A team of researchers from VRAIN at the UPV is coordinating the OGMIOS project, together with IIS La Fe, INCLIVA, ISABIAL and the company Bionos, which will also contribute to precision medicine with personalised treatments.
Dr. Adela Cañete, head of research in Oncopediatrics, and Dr. Esther Zorio, head of the Research Group on Familial Heart Disease, Sudden Death and Disease Mechanisms (CAFAMUSME) lead the work of the IIS La Fe in this project.
A team of researchers from the Valencian University Institute for Research in Artificial Intelligence (VRAIN) at the Universitat Politècnica de València is prototyping a platform that, through Artificial Intelligence (AI), will allow professionals to better understand the genetic characteristics of paediatric cancers and cardiovascular diseases in order to predict who is most at risk of developing them. It will also help to select pharmacological treatments that are more targeted to specific genetic alterations.
This prototype, part of the OGMIOS project, whose development began in March 2021 and will conclude in October 2023, aims to position the Valencian Region as a national benchmark in precision genomic medicine, which addresses the prevention and diagnosis of disease in a novel way.
The platform, developed by ten researchers from the UPV's Centre for Research in Software Production Methods (PROS), which is part of VRAIN, is supported by the La Fe Health Research Institute (IIS La Fe), the Health Research Institute of the University Clinical Hospital of Valencia (INCLIVA), the Foundation of the Valencian Community for the Management of the Institute for Health and Biomedical Research of Alicante (ISABIAL) and the company Bionos Biotech.
The services to be offered by OGMIOS will be the search for disease-relevant genomic data, the identification of relevant genetic variants, the loading of these variations and information into the database and the exploitation of these data, which allows the generation of the clinical report.
The OMGIOS project aims to advance the integration of genomics in clinical practice. To this end, healthcare professionals from IIS La Fe, INCLIVA and ISABIAL enter the clinical and biological data of the samples into the platform -with the prior informed consent of the patients- while Bionos performs the sequencing and generates the genetic data of the samples.
OMGIOS is designed to manage the continuous introduction of data with a sustainable strategy that allows researchers to study and develop algorithms capable of knowing with greater reliability the relevant genomic variations, with the aim of identifying them, classifying them and interpreting them appropriately using Explainable AI techniques.
In doing so, "we aim to begin to be able to understand the genomic code, taking on an immense challenge: deciphering the language of life. Identifying and interpreting the genetic cause at the origin of a cancer or a familial heart disease, as if they were "software errors in the human body" that could even be corrected when gene therapy strategies allow it. This could allow us to move towards precision medicine with benefits never before achieved," explains Óscar Pastor, the principal investigator of the UPV's VRAIN institute who is carrying out the project.
Behind the GMIOS platform is an intelligent information system, with AI techniques, which will be continuously updated as it receives and processes information.
The more information it has, the more useful it will be, from the point of view of an Explainable Artificial Intelligence (EIA), which provides the necessary tools to know the origin of the information with which informed clinical decisions can be made.
The OGMIOS project, funded by the Agència Valenciana de la Innovació (AVI), linked to the previous national research project Delfos, is in line with the Health Horizon Europe-Work Programme 2023-2024, which aims for a solid European health system in which all member states work together to improve the prevention, diagnosis, treatment and quality of life of any disease, and focuses on genetically based diseases in the field of paediatric cancer and familial heart disease.
In this sense, the team of researchers is working on OMGIOS with the intention that this project will be the seed of other more ambitious projects at national, EU or international level.
Óscar Pastor stresses that "the human genome is a huge field in which to work, but if we start in a concrete way and at a local level, with certain diseases and with specific groups of patients, we are moving in the right direction to achieve our most ambitious goal: deciphering the Language of Life".
The Valencian Research Institute for Artificial Intelligence (VRAIN) of the UPV is composed of eight research groups with more than 30 years of experience in different lines of AI research.
The process of creating VRAIN began in 2019, the result of the union of six research groups. In 2020, it merged with the Research Centre in Software Production Methods PROS and in 2021 it was finally constituted as a University Research Institute with the approval of the Generalitat Valenciana.
It currently has 130 researchers divided into nine research areas. These nine areas around which its research activity revolves mean that its developments are applied to a large number of strategic sectors such as health, mobility, earth sciences, smart cities, education, social networks, agriculture, industry, privacy/security, autonomous robots, services and energy, and environmental sustainability, among others.
These activities have been funded by more than 128 projects obtained through competitive funding, mainly from the European Union, but also from the National Research Plan, the Valencian Research Plan and Technology Transfer Projects.
Its aim is to position the Valencian Community in precision genomic medicine at national level and to lay the foundations for projects covering a greater number of data at national or EU level.