Search Results

AINN-P1: Small Model, Big IntelligenceHow does a 167M-parameter protein foundation model outperform a 650M general-purpose model on the tasks that matter?

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

Human iPSC-derived cardiovascular tissues, 3D computational modeling, and biofabrication will define the causal mechanisms behind a leading cause of ischemia in women

Ainnocence’s foundation model trained from scratch, requiring no structure, no multiple sequence alignment, no fine-tuning, training in hours rather than weeks.

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.