A new machine-learning approach for prostate-specific membrane antigen (PSMA) treatment of metastatic castration-resistant prostate cancer (mCRPC) could estimate radiation dose to tumors and healthy organs before therapy begins. Using data already available from pre-therapy PET/CT scans, this novel prediction tool could help personalize treatment plans, improve patient selection, and reduce toxicity risk. This research was presented at the Society of Nuclear Medicine and Molecular Imaging 2026 Annual Meeting.

In an environment of radiation, extreme temperatures and razor-sharp dust, researchers are designing how humans will build, and ultimately survive, on the moon.

Researchers have developed a fully light-controlled artificial synapse that could improve how computers process visual information. The device uses a rare-earth-doped crystal to mimic how biological synapses strengthen and weaken connections based on past activity, but operates entirely with optical signals rather than electricity. By modeling and validating how trapped charge carriers govern this behavior, the team demonstrated both signal enhancement and suppression, key features of neural function. Integrated with an imaging sensor, the system can reduce noise and enhance contrast directly at the point of capture. When applied to a neural network, the approach achieved nearly 96% accuracy on handwritten digit recognition, highlighting its potential for low-power, efficient neuromorphic vision systems.

Insilico Medicine will present its latest advances in generative AI-driven drug discovery, quantum-enabled research, and clinical development at the BIO 2026 International Convention in San Diego. The company will participate in three featured speaking sessions covering China’s impact on biotech business development, quantum computing in drug discovery, and strategies for building smarter pipelines for challenging targets. Insilico will also showcase its Pharma.AI platform, LifeStar 2 laboratory, and MMAI Gym for Science while meeting with biopharma partners, investors, and researchers at Booth #4021.

Insilico highlighted progress across its growing pipeline, including Rentosertib, the world’s first AI-discovered anti-fibrotic candidate with a novel mechanism of action, which has completed a Phase 2a proof-of-concept trial. The company also shared updates on ISM5411 for inflammatory bowel disease and multiple oncology programs that have reached first-in-patient dosing. Since its founding in 2014, Insilico has published more than 200 peer-reviewed papers and was recently recognized among the top global corporate research institutions in Nature Index rankings.