MiRAI is a method that uses available data produced by biologists to perform predictions. We first applied it to the micro-RNA topic.
MicroRNAs play critical roles in many physiological processes. Their dysregulations are also closely related to the development and progression of various human diseases, including cancer. Therefore, identifying new microRNAs that are associated with diseases contributes to a better understanding of pathogenicity mechanisms. MicroRNAs also represent a tremendous opportunity in biotechnology for early diagnosis.
Our basic approach is to represent distributional information on miRNAs and diseases in a high-dimensional vector space and to define associations between miRNAs and diseases in terms of their vector similarity. Parameters of MiRAI were tuned using an evolutionary algorithm. Cross validations performed on a dataset of known miRNA-disease associations demonstrate the excellent performance of our method.
MiRAI highlighted new miRNA-disease associations, especially the potential implication of mir-188 and mir-795 in various diseases. In addition, our method allowed detecting several putative false associations contained in the reference database.
 |
“ I am a bioinformatician specialized in DNA decryption and genetics. My favorite topic is the study of evolutionary mechanisms whose the impacts affect all branches of Biology. In 2013, I created Biomanda, a private company providing services in bioinformatics ” |
 |
“ I am an associate professor in Computer Science and working on hybridization of Evolutionary Algorithms in a data mining context; for instance, I combined Support Vector Machine with a Multi-Objective Evolutionary Algorithm for fine-grained Content Based Image Retrieval. I also investigated the use and adaptation of Evolutionary Computation for considering user preferences via Eye-Tracking technology, water current prediction in Hydrology. ” |
 |
“ I am researcher at French National Center for Scientific Research (CNRS). My current research interests lie in the intersection of artificial intelligence and computational biology. This includes machine learning, semantic data integration and natural language processing. ” |
|
“ I am a bioinformatician specialized in DNA decryption and genetics. My favorite topic is the study of evolutionary mechanisms whose the impacts affect all branches of Biology. In 2013, I created Biomanda, a private company providing services in bioinformatics ” |
|
“ I am an associate professor in Computer Science and working on hybridization of Evolutionary Algorithms in a data mining context; for instance, I combined Support Vector Machine with a Multi-Objective Evolutionary Algorithm for fine-grained Content Based Image Retrieval. I also investigated the use and adaptation of Evolutionary Computation for considering user preferences via Eye-Tracking technology, water current prediction in Hydrology. ” |
|
“ I am researcher at French National Center for Scientific Research (CNRS). My current research interests lie in the intersection of artificial intelligence and computational biology. This includes machine learning, semantic data integration and natural language processing. ” |
 |
 |
|
|
 |
 |
Consult the supplementary data |
Consult the supplementary data |
|
Consult the supplementary data |
|
Consult the supplementary data |