Directed evolution has become a central pillar in gene therapy. This engineering strategy enables the generation of more efficient variants of genetic editors and delivery vectors. Molecular diversification methods are increasingly sophisticated and are now accelerated by machine learning and AI tools, as showcased at the 29th Annual Meeting of the American Society of Gene and Cell Therapy (ASGCT) held in Boston this week.

When a tumor migrates and colonizes another tissue or organ, it can be identified as a metastasis, but its origin is not always clear. Now, a study based on machine learning has identified DNA-methylation patterns that reveal the type of tissue a cancer comes from when the primary tumor cannot be found. This technique could help guide more specific treatments for patients with cancers of unknown primary, who today often receive broad, nontargeted chemotherapy.

How much have AI applications learned, and how can one know their capabilities if they are being evaluated with an exam that is far too easy? In 2024, with the publication of the previous benchmark to measure AI performance, the field debated whether existing assessments would keep pace with the rapid progress of AI.

Prenaital ApS has filed a patent for technology that may identify risks of spontaneous pre-term birth. Spontaneous preterm birth (sPTB) is usually defined as birth occurring before 37 weeks of gestation. The invention relates to a method for predicting potential preterm birth from medical scan data, which may be used in practice by medical professionals for risk analysis and prognosis of potential pathologies.

Depending on who you ask, AI will take over the world and save it; or ruin it. Certainly, it is changing it. Science magazine dedicated its first editorial of 2026 to AI. Despite its title – “Resisting AI slop“ – editor-in-chief Holden Thorp gave the sort of nuanced review that is typical of him.

Depending on who you ask, AI will take over the world and save it; or ruin it. Certainly, it is changing it. Science magazine dedicated its first editorial of 2026 to AI. Despite its title – “Resisting AI slop“ – editor-in-chief Holden Thorp gave the sort of nuanced review that is typical of him. “Like many tools, AI will allow the scientific community to do more if it picks the right ways to use it,” he wrote. “The community needs to be careful and not be swept up by the hype surrounding every AI product.”

Depending on who you ask, AI will take over the world and save it; or ruin it. Certainly, it is changing it. Science magazine dedicated its first editorial of 2026 to AI. Despite its title – “Resisting AI slop“ – editor-in-chief Holden Thorp gave the sort of nuanced review that is typical of him. “Like many tools, AI will allow the scientific community to do more if it picks the right ways to use it,” he wrote. “The community needs to be careful and not be swept up by the hype surrounding every AI product.”

Securing a second major partnership with Sanofi SA – this time worth a potential $2.56 billion – Earendil Labs will provide its AI-driven discovery platform to find new therapeutics for autoimmune and inflammatory diseases.