Alzheimer's disease is like a tangled ball of yarn: thousands of genes are intertwined, and it's hard to tell which ones snap first. Previously, scientists looked for important genes by simply counting how many connections each node in the network had. But that approach is like judging a person by the number of acquaintances they have — the most sociable isn't always the most influential.
The new NETRA method works differently. It learns from examples and decides on its own which connections in the gene network deserve attention. First, it views the network as a map of roads along which a wanderer strolls at random. The wanderer's paths are remembered, building a picture of which genes often appear together. Then, data on how actively genes work in brain cells and other biological information are added. All of this is combined into one large network, where a special algorithm, a graph transformer, evaluates each gene's importance for the disease.
Among the genes it found were those linked to other neurodegenerative diseases, as well as a region on chromosome 12 that geneticists already knew about. This is encouraging: perhaps NETRA will help not only to better understand Alzheimer's but also to uncover common mechanisms across different brain diseases. The tangled ball of yarn is slowly unraveling.
Random walks through a gene network resemble a person wandering a unfamiliar city without a map, gradually remembering which streets lead to the center more often.