Adsorption in nanoporous materials is crucial to addressing global challenges such as carbon capture, gas separation, and water harvesting. While machine learning potentials (MLPs) offer a revolutionary way to predict material behavior with high accuracy, integrating them into traditional simulation tools has been a major technical bottleneck. Researchers have now developed HULU, a universal Python-based framework that acts as a "bridge," allowing scientists to seamlessly apply diverse atomistic foundation models to Monte Carlo simulations. This breakthrough paves the way for faster, more accurate discovery of the next generation of sustainable materials.

FDA Fast Track Designation (FTD) aims to accelerate the review process of high-value assets, and ISM6331 marks Insilico’s first FTD, recognizing the clinical potential in advanced mesothelioma.

ISM6331 is a novel, potential best-in-class, pan-TEAD inhibitor engineered via Chemistry42 to restore Hippo pathway balance, and its Phase I first-in-human data has been accepted for a brief oral presentation at ESMO 2026.

The FTD grants ISM6331 enhanced FDA engagement to accelerate the clinical development processes, alongside eligibility for Rolling Review, Accelerated Approval, and Priority Review, if relevant criteria are met.

Researchers at the University of Osaka have developed a new mathematical framework that helps identify optimization problems that can be solved efficiently using optical computing hardware. The approach allows complex, high-dimensional problems to be transformed into forms compatible with spatial photonic Ising machines and can also accelerate computation using fast Fourier transforms. These findings could broaden the applications of optical computing to areas such as logistics, data analysis, and infrastructure optimization.

In a paper published in ENGINEERING Management, researchers from Shanghai University and Tsinghua University propose a cross-city transfer learning framework that enables rapid planning of shared e-scooter parking stations in new cities without requiring local operational data. Using operational data from 25 European cities and multi-source open-space data, the study demonstrates that a multi-dimensional urban similarity matching strategy, integrating socio-economic, POI distribution, and spatial structure features, achieves more stable and generalizable predictions than conventional geographic or economic grouping methods, with the TOP-3 similarity match yielding the best overall performance.