Why AI Isn’t Ready to Tackle Our Convoluted Genomes
Biologists are struggling to decode the complex regulatory processes of the human genome, which go far beyond simple gene sequences. While some hope AI foundation models can solve these mysteries, critics argue that these computational black boxes lack the true understanding required for biological breakthroughs.
Why it matters
The debate highlights the limitations of AI in scientific discovery and the ongoing challenge of understanding the fundamental mechanisms of human life.
In fact, the human genome is less a script than a puzzle that gets harder the closer they look. Knowing the entire sequence—the order of all 3 billion or so of our DNA’s chemical building blocks, nearly fully deduced by the international Human Genome Project between 1990 and 2003—hasn’t helped much. That investigation showed that barely 2 percent of the human genome consists of actual genes, the information-coding sequences of DNA.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in