A new memory framework known as DAAAM enables a robot to rapidly recall rich descriptions and precise locational information about objects it encountered while exploring its environment. This efficient approach could help an autonomous agent quickly answer complex queries about its environment in natural language. 

- ORNL researchers have developed advanced tools to immediately detect abnormal power grid conditions that lead to wildfires, equipment damage and blackouts. 

- The approach incorporates artificial intelligence to rapidly analyze grid data and automatically alert a utility to dangerous grid behaviors requiring immediate response. 

- ORNL is partnering with utility Southern California Edison (SCE) to validate the technology against five years of field-collected data.

Insilico Medicine Announces First-in-Human Dosing for AI-Designed NLRP3 Inhibitor ISM8969

CAMBRIDGE, Mass. / HONG KONG — Insilico Medicine (“Insilico”), a clinical-stage biotechnology company powered by generative artificial intelligence (AI), has reached a major milestone in its co-development collaboration with Hygtia Therapeutics with the commencement of the Phase I clinical trial for ISM8969.

ISM8969 is a potentially best-in-class, brain-penetrant small-molecule inhibitor of the NLRP3 inflammasome. By modulating the NLRP3 inflammasome, which is often over-activated in chronic neuroinflammation, the therapy aims to address the underlying drivers of debilitating central nervous system (CNS) disorders, including Parkinson’s disease.

Key Highlights of the Phase I Trial

The Phase I study is currently being conducted in Australia and is designed to evaluate the safety, tolerability, pharmacokinetics (PK), and pharmacodynamics (PD) of the drug.

Study Design: A single-center, randomized, double-blind, placebo-controlled trial featuring single ascending dose (SAD) and multiple ascending dose (MAD) cohorts.

Participant Groups: The trial aims to enroll 80 healthy participants and 20 obese adult participants at risk of cardiovascular disease.

CNS Assessment:Researchers will collect cerebrospinal fluid (CSF) samples to verify the molecule’s ability to cross the blood-brain barrier (BBB) and reach the target compartment in the central nervous system.

Strategic Goal: Data from this study will establish safety profiles and inform optimal dosing for future clinical development.

Leveraging AI for CNS Breakthroughs

The discovery of ISM8969 was powered by Insilico’s proprietary generative AI platform, Chemistry42. Historically, developing NLRP3 inhibitors that can safely penetrate the blood-brain barrier has been a significant challenge in drug development. Insilico’s platform allowed researchers to precisely optimize the molecule’s structure to ensure high permeability and potent efficacy.

“Advancing ISM8969 from an AI-generated concept to first-in-human dosing is a major step forward,” said Feng Ren, PhD, Co-CEO and Chief Scientific Officer of Insilico Medicine. “Leveraging Chemistry42, we precisely optimized the molecule to deliver strong preclinical efficacy and favorable permeability.”

Collaboration and Industry Impact

Insilico and Hygtia Therapeutics have entered into an exclusive global strategic co-development collaboration for ISM8969. Under the agreement, both parties hold a 50% stake in the global rights and interests, with Insilico leading the initial clinical trials.

This milestone highlights the efficiency of Insilico’s AI-native drug discovery pipeline, which consistently nominates preclinical candidates in 12 to 18 months—significantly faster than the industry standard of 2.5 to 4 years. Since 2021, the company has nominated 31 preclinical candidates, with 13 receiving IND approval or clearance.