Targeting Casitas B-lineage lymphoma-b (CBLB), Insilico Medicine announced the nomination of ISM3830, its 23rd AI-empowered preclinical candidate (PCC) since 2021, in late November 2025, which demonstrated low toxicity risks, favorable ADME/PK profiles, as well as induction of long-term tumor immunity, cracking the bottleneck in metabolism and absorption of previously reported CBLB inhibitors.

Shortly beforehand, the discovery process and evaluation of CBLB inhibitors with a different scaffold were published in the Journal of Medicinal Chemistry. The paper highlights Compound 10, a potent, orally available lead compound with novel scaffold promising druggability, providing an AI-driven optimization roadmap for CBLB inhibition strategies.

Dementia, including Alzheimer’s (AD) and frontotemporal dementia (FTD), often causes overlapping symptoms, making diagnosis challenging. Traditional imaging is costly and slow, while EEG offers a cheaper, portable option—but interpreting signals has been difficult. FAU researchers have developed a deep learning model that analyzes EEG brain activity to accurately detect both type and severity of dementia. This AI-driven approach identifies key brainwave patterns, enabling faster, noninvasive, and precise monitoring of disease progression, transforming dementia diagnosis and care.

A novel fiber optic sensing platform captures real-time bubble dynamics during hydrogen evolution, revealing how bubble growth and detachment impact catalyst performance. This breakthrough bridges interfacial gas behavior with electrochemical efficiency, offering new strategies for green hydrogen optimization.