Discovering genes involved in complex human genetic disorders is a major challenge. Many have suggested that machine learning (ML) algorithms using gene networks can be used to supplement traditional genetic association-based approaches to predict or prioritize disease genes. However, questions have been raised about the utility of ML methods for this type of task due to biases within the data, and poor real-world performance. Using autism spectrum disorder (ASD) as a test case, we sought to investigate the question: can machine learning aid in the discovery of disease genes? We collected 13 published ASD gene prioritization studies and evaluated their performance using known and novel high-confidence ASD genes. We also investigated their biases towards generic gene annotations, like number of association publications. We found that ML methods which do not incorporate genetics information have limited utility for prioritization of ASD risk genes. These studies perform at a comparable level to generic measures of likelihood for the involvement of genes in any condition, and do not out-perform genetic association studies. Future efforts to discover disease genes should be focused on developing and validating statistical models for genetic association, specifically for association between rare variants and disease, rather than developing complex machine learning methods using complex heterogeneous biological data with unknown reliability.

No abstract

he federal government of Canada provided a sys tem for therapeutic access to cannabis in 2001 after a series of successful constitutional challenges on cannabis prohibitions. [1][2][3] Clinicians provide authoriza tions, rather than prescriptions, for medical cannabis owing to its current status and regulation within Health Canada. 4 Two decades later, the position of medical cannabis within Canadian legislation, health care and society continues to evolve. 1,5,6 Driven largely by public awareness, anecdotes of benefit and expanded approvals for oral administration of derivative products, medical cannabis has become an increas ingly prevalent treatment option for children with neuro developmental and lifelimiting conditions including brain and other cancers. 4,5,[7][8][9][10][11] Despite this trend, data on potential medical properties and clinical applications of cannabis are generally lacking, and standards regarding use in children are largely absent. 4,5 Clinicians are practising, therefore, in a landscape defined by high patient and caregiver interest, little medical data, and tensions arising from an absence of regulations and treatment