Artificial intelligence to improve the treatment of rare diseases

The lack of available data on rare diseases or minorities, which affect between 5% and 7% of the population, makes their research extremely difficult. In this context, an international team of scientists, coordinated by the Barcelona Supercomputing Center – Centro Nacional de Supercomputación (BSC-CNS), has developed a technology based on it Artificial Intelligence (AI) to study them.

The study, published in the journal Nature communicationrepresents, in particular, progress in the use of AI technologies Networks multi-layeredto connect and relate information from different databases. In this way, open questions in the research of these very rare diseases can be addressed.

Multi-layered AI networks make it possible to connect and correlate information from different databases to study rare diseases

The authors led by the ICREA researcher and director of the Biological Sciences Division of the BSC-CNS Alfonso Valencia have successfully applied the method to discover the possible causes that lead to the occurrence of the congenital myasthenic syndromesa series of rare hereditary diseases that limit the ability to move and cause muscle weakness to varying degrees in patients.

The study required more than ten years of collaboration among researchers 20 scientific institutions from Spain, Canada, Japan, the United Kingdom, the Netherlands, Bulgaria and Germany.

“Minor diseases continue to represent an unexplored challenge for biomedical research. The most advanced AI technologies are currently designed to analyze large amounts of data and are not trained for scenarios in which this is the case The availability of patient data is limitedthe main characteristic of rare diseases,” explains the BSC researcher Iker Núñez-Carpintero.

“This creates the need for large and very long collaborative efforts like the one we are now presenting,” adds this member of the BSC’s Machine Learning Unit for Biomedical Research, led by Davide Cirilloand from the Computational Biology group led by Valencia, both co-authors of the study.

Co-authors of the study at the Barcelona Supercomputing Center. /BSC-CSN

In the study, in which a cohort of 20 patients from a small town in BulgariaResearchers have developed a method that uses AI to overcome the limitation of available data and understand why patients with the same disease and mutations experience very different levels of severity.

This methodology uses information from large biomedical databases on all types of biological processes to explore the relationships between each patient’s genes. “The goal is to identify a type of functional relationship This can help us recover the lost pieces of the disease puzzle that we have not seen because there are not enough patients,” says Núñez-Carpintero.

The role of supercomputing and AI

The development of AI methods based on multilayer networks and recent advances in supercomputing have made it possible to find the missing pieces that the BSC researcher refers to as they are a Big data analysis biomedically much faster than a decade ago when the study began.

Read Also:  Jihadists are considering using artificial intelligence to better spread their messages

This provides researchers with the capacity to find information about patients with rare diseases that will help understand their symptoms and clinical manifestations.

Rare disease research requires analyzing each patient’s information with general biomedical knowledge, a task that supercomputers like MareNostrum5 can help with.

“The latest advances in supercomputing infrastructure, such as the new Mare Nostrum 5 The research centers recently inaugurated at the BSC represent a tremendous opportunity for the development of new strategies for rare disease research. Studying these conditions requires the simultaneous analysis of each patient’s information with the general biomedical knowledge accumulated over the last decade. This task requires a strong computing infrastructure, which is only now becoming a reality,” adds Núñez-Carpintero.

According to the researchers, this is where the relevance of their research lies opens up new paths for the development of computer applications specifically designed to work with minority diseases.

Likewise, it represents an advance in the application of multilayer networks to solve fundamental questions about the nature of these diseases. In this case, the results show that the different degrees of severity of congenital myasthenic syndromes are linked to specific mutations in the correct muscle contraction process.

Identify possible genetic causes

In addition, this study is the first to allow us to understand the possible genetic causes of the positive effects of certain effective treatments in some patients with this disease, such as: Salbutamoloften used to treat breathing problems such as asthma.

This enables the development of new strategies Repositioning of medicationswhich is essential in the case of rare diseases due to the difficulty of developing specific treatments and the lack of interest from the pharmaceutical industry.

It is the first study that can genetically explain why some patients with congenital myasthenic syndrome respond well to treatments such as salbutamol

“This is the first study that can genetically explain why some patients suffer from this rare disease respond well to treatments like salbutamol. “This discovery highlights the importance of drug repositioning, an area where biomedical research is currently focused, and opens new possibilities for understanding and treating minority diseases through precision medicine methods,” concludes Núñez. -Carpenter.

In this way, the researchers show the benefits of artificial intelligence for Improving the diagnosis and treatment of rare diseaseswhere the low prevalence makes it difficult to collect samples for research purposes.

Recent Articles

Related News

Leave A Reply

Please enter your comment!
Please enter your name here