High-throughput technologies and platforms are facing a new challenge because of the growing numbers of biomedical data. Almost 2000 scientific articles and almost 5000 biological sequences (as DNA, RNA & Proteins) are incorporated each day in public databases. This growing mass of information is requiring specific tools to structure and organize the relation between molecules, genes and proteins. Despite new technologies, **omics still failing to solve the bottleneck. Only functional analysis of the data based on a fundamental understanding of human biology can solve it. So far, many methods are reducing knowledge to static or irrelevant procedures.
GenSodi identified a solution to formalize, organize and interpret the experimental data by 1) integrating experimental or cellular contexts for the scientist 2) to produce efficient toolkit and data visualisation 3) scalable and 4) adding a systematic learning-based system for a complete updating of scientific knowledge.
To address this challenge, GenSodi has developed PredictSearch™ 2.0, using bibliometric method to identify biological relationships based on the textual co-occurrence of gene, terms or similarities in abstract texts. Furthermore, PredictSearch™ 2.0 integrates specific features to determine among inferable associations which ones are informative and relevant to a given set of experiments.