Machine Learning (ML) enables computers to assist humans in making sense of large and complex data sets. With the fall in the cost of high-throughput technologies, large amounts of omics data are being generated and made accessible to researchers. Analysing these complex high-volume data is not trivial, and the use of classical statistics cannot explore their full potential. The ELIXIR Machine Learning Focus Group, co-chaired by Fotis Psomopoulos (ELIXIR-GR), Silvio Tosatto (ELIXIR-IT) and Jennifer Harrow (ELIXIR-Hub) was initiated in October 2019, in order to capture the emerging need in Machine Learning expertise across the network.
A major effort of the focus group was to define a set of recommendations for reviewing Machine Learning approaches in Life Sciences. DOME-ML (or simply DOME) is an acronym standing for Data, Optimization, Model and Evaluation in Machine Learning. DOME is a set of community-wide guidelines, recommendations and checklists spanning these four areas aiming to help establish standards of supervised machine learning validation in biology. The recommendations are formulated as questions to anyone wishing to pursue implementation of a machine learning algorithm. Answers to these questions can be easily included in the supplementary material of published papers.
Main purpose of this project will be to establish a strategic roadmap for the Machine Learning Focus Group, aiming for the definition of a process towards a governance structure around the DOME recommendations, involving ELIXIR and relevant stakeholders such as Industry (Pistoia Alliance) and other academic networks (CLAIRE). Direct outcome of this collaboration will be the successful publication of the DOME recommendations as an Open Access, Comment article in Nature Methods, a clear and high-impact milestone of the efforts done across Nodes and communities within the ELIXIR Focus Group. This effort will be done with continuous sharing among team members and in close collaboration with the ELIXIR Hub.