Urgent.News

What's breaking now, across thousands of outlets.

AI

Waters’ new AI tool targets one of the pharmaceutical industry’s most tedious tasks

Waters took one-and-a-half years to develop its new AI tool, which it says will cut manual drug-testing work performed by scientists by 95%.

Waters’ new AI tool targets one of the pharmaceutical industry’s most tedious tasks

Brook Colangelo, Waters Corp.'s chief information officer, announced the company's newest AI tool called Peak Integration on Wednesday. This integration is designed to speed up quality testing processes for drug manufacturers by reducing manual interventions traditionally performed by scientists for quality assurance and quality control in drug discovery and manufacturing.

Waters' AI and machine learning capabilities, which are integrated within its Empower software platform used by 500,000 users, can reportedly cut down manual interventions by 95%, improve testing accuracy by 76%, and speed up the process by 50%. Waters spent approximately one-and-a-half years working closely with a top-ten pharmaceutical company to secure legal agreements and ensure safe data exchange for training the AI models.

This is the second major AI feature announced by Waters for Empower, following an AI/ML anomaly detection tool introduced in February 2025. Waters has been relatively low-key in marketing its AI capabilities compared to its competitors. The AI-powered integration targets repetitive, mundane tasks that do not effectively utilize a scientist's time or expertise but also contribute to experimental result variability.

Scientists often review hundreds of chromatograms to identify just one or two compounds that do not meet the desired profile. While AI in drug discovery is generally viewed positively due to its potential to accelerate drug development and reduce the costs and time associated with getting medicines approved, there are still concerns about its impact on jobs and other societal issues.

Written by urgent.news from Fortune's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at fortune.com →

More in AI

More from Wednesday 28 October →