An interdisciplinary research project with the aim to contribute to the personalized treatment in multiple sclerosis
The FindingMS project is an interdisciplinary research project funded within the joint transnational call ERA PerMed (2018) with the aim to contribute to the personalized treatment in multiple sclerosis.
Multiple Sclerosis is a chronic, autoimmune disorder of the central nervous system, a leading cause of non-traumatic disability in young adults. It is a very heterogeneous disease, with high variability in both clinical manifestations and individual response to treatments, suggesting that specific individual characteristics could play a role and be implicated in disease expression. Starting an effective treatment as early as possible is extremely important, to reduce inflammatory activity and to limit disability progression. This aspect is even more relevant in the present era, characterized by a dramatic increase in the range of treatment options currently available for multiple sclerosis patients.
The main objective of FindingMS is to carry out a thorough investigation of molecular events that could confer risk of disease activity, incorporating clinical data, lifestyle features and multiple - omics profiles, and to build a predictive algorithm of MS disease activity that will enable personalized treatment of MS. The underlying hypothesis is that a comprehensive characterization of a large set of patients, integrating multi-layer data, could contribute to accelerate personalized medicine in MS through the identification of biomarkers of inflammatory activity and the development of network-based and AI approaches able to predict disease activity in the early phases of the disease. Moreover, we expect to disentangle the biological basis of MS inflammatory activity by identifying relevant pathways and modules implicated in disease activity.
The specific aims are:
AIM 1: Identification of molecular markers and signatures of disease activity. Taking advantage of available large MS cohorts, we plan to dissect the baseline molecular characteristics that appear to be associated with MS disease activity and to assess the role of lifestyle factors. For this purpose, we will pursue a multi-layer characterization of MS patients in the search of genetic variations, transcriptomic and miRNA, signatures,and methylation profiles, lifestyle features and vitamin D levels that appear to be associated with inflammatory activity.
AIM 2: Development of a systems biology based approach. We will analyze the different layers of information mentioned above in the context of genome-scale biological networks to infer modules of interacting genes underlying disease activity, suitable to be used as a more reproducible set of predictive variables.
AIM 3: Development of a predictive model of disease activity. We will design a deep-learning based algorithm model able to predict MS disease activity using a relative small set of biomarkers, suitable for potential personalized medicine application in the clinical setting.
We plan to study a large cohort of Italian and French patients, combining together clinical, molecular (e.g. genetics, gene expression, methylation) and life-style data. This composite information will be used to stratify patients in subgroups, using advanced bioinformatics tools. These approaches, together with artificial intelligence models, will be used to identify biomarkers able to predict disease activity, with the final aim of supporting treatment choice in the early phases of the disease.
Overall we estimate that this project is clinically relevant and could have a positive impact in multiple sclerosis patient’s management, towards a more tailored use of available treatment options. We expect that this project will contribute to produce personalized medicine tools, potentially applicable in the future in the clinical setting.
Multiple Sclerosis is a chronic, autoimmune disorder of the central nervous system, a leading cause of non-traumatic disability in young adults. It is a very heterogeneous disease, with high variability in both clinical manifestations and individual response to treatments, suggesting that specific individual characteristics could play a role and be implicated in disease expression. Starting an effective treatment as early as possible is extremely important, to reduce inflammatory activity and to limit disability progression. This aspect is even more relevant in the present era, characterized by a dramatic increase in the range of treatment options currently available for multiple sclerosis patients.
The main objective of FindingMS is to carry out a thorough investigation of molecular events that could confer risk of disease activity, incorporating clinical data, lifestyle features and multiple - omics profiles, and to build a predictive algorithm of MS disease activity that will enable personalized treatment of MS. The underlying hypothesis is that a comprehensive characterization of a large set of patients, integrating multi-layer data, could contribute to accelerate personalized medicine in MS through the identification of biomarkers of inflammatory activity and the development of network-based and AI approaches able to predict disease activity in the early phases of the disease. Moreover, we expect to disentangle the biological basis of MS inflammatory activity by identifying relevant pathways and modules implicated in disease activity.
The specific aims are:
AIM 1: Identification of molecular markers and signatures of disease activity. Taking advantage of available large MS cohorts, we plan to dissect the baseline molecular characteristics that appear to be associated with MS disease activity and to assess the role of lifestyle factors. For this purpose, we will pursue a multi-layer characterization of MS patients in the search of genetic variations, transcriptomic and miRNA, signatures,and methylation profiles, lifestyle features and vitamin D levels that appear to be associated with inflammatory activity.
AIM 2: Development of a systems biology based approach. We will analyze the different layers of information mentioned above in the context of genome-scale biological networks to infer modules of interacting genes underlying disease activity, suitable to be used as a more reproducible set of predictive variables.
AIM 3: Development of a predictive model of disease activity. We will design a deep-learning based algorithm model able to predict MS disease activity using a relative small set of biomarkers, suitable for potential personalized medicine application in the clinical setting.
We plan to study a large cohort of Italian and French patients, combining together clinical, molecular (e.g. genetics, gene expression, methylation) and life-style data. This composite information will be used to stratify patients in subgroups, using advanced bioinformatics tools. These approaches, together with artificial intelligence models, will be used to identify biomarkers able to predict disease activity, with the final aim of supporting treatment choice in the early phases of the disease.
Overall we estimate that this project is clinically relevant and could have a positive impact in multiple sclerosis patient’s management, towards a more tailored use of available treatment options. We expect that this project will contribute to produce personalized medicine tools, potentially applicable in the future in the clinical setting.
The FindingMS project is funded by the Fondazione Regionale per la Ricerca Biomedica (Italy), the Agence Nationale de la Recherche (France) and the Federal Ministry of Education and Research (Germany), within the ERA-Net Cofund Joint Transnational Calls ERA PerMed. The contents of this website are the sole responsibility of the FindingMS project and do not necessarily reflect the views of the European Union and funding agencies.
