D8.3 - GenoMed4All Genomic Standardization Guidelines (final report)

Data standardization involves transforming data into a consistent common format to enable, among others, data interoperability. Representation of genomic information is highly varied and complex. Several well-known formats and tools have been developed to store and exchange such data. Despite this, there remains a high level of heterogeneity involving the use of different terminologies, conventions, and assumptions making genomic data integration challenging. Precise actual representation of genomic information is important for the application of artificial intelligence in a clinical context. In this report we review the current state of the art and the interoperability needs of the different scenarios of Genomed4all use cases. In addition, we outline the standardization requirements to a) include new data to keep training the AI models and b) input individual patient data to obtain clinical predictions.