According to a new analysis, about 55% of the observed variation in longevity across a population is attributable to genetics - challenging previous estimates of 10-25%. Researchers say that earlier numbers were much too low because they did not effectively separate deaths caused by extrinsic factors, such as accidents, from intrinsic ones such as the gradual decline of organ function. Not all intrinsic causes of death are equally heritable, the researchers found - and the results don't indicate a genetically encoded 'destiny' for lifespan, because so much is determined by environment and lifestyle choices.
Generalist models "fail miserably" at the benchmarks used to measure how AI performs scientific tasks, Alex Zhavoronkov, Insilico's founder and CEO, told Fortune. " You test it five times at the same task, and you can see that it's so far from state of the art...It's basically worse than random. It's complete garbage." Far better are specialist AI models that are trained directly on chemistry or biology data.
Data is the key. The depth of biological data, the depth of demographical data, the depth of epidemiological data has to be properly collected,