Search Results

New preprint by Jianghui Xiong, PhD, and the DeepoMe team introduces SteeraMed, a steerable biomedical world model for N-of-1 intervention reasoning across chronic diseases and aging

AmesNet’s Task-Conditioned Learning architecture outperforms FDA, MIT, Tencent, and the University of Sydney models in both sensitivity and balanced accuracy on out-of-domain chemical data on a public dataset; AmesNet is built on top of ChemPrint, the core and proprietary deep-learning engine of the GALILEO platform that powers the company’s drug pipeline.

Three proprietary foundation models: AINN-P1, AINN-Basemodel, and AINN-Peptide are now available to partners as secure, on-demand APIs that plug directly into existing discovery pipelines.

Through the proposal, the FDA could clear barriers to distributed manufacturing approaches intended to enhance emergency preparedness and supply chain resilience.