Large language models generate functional protein sequences across diverse families.

Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here we describe ProGen, a language model that can generate protein sequences with a predictable function across large protein families, akin to generating grammatically and semantically correct natural language sentences on diverse topics. The model was trained on 280 million protein sequences from >19,000 families and is augmented with control tags specifying protein properties. ProGen can be further fine-tuned to curated sequences and tags to improve controllable generation performance of proteins from families with sufficient homologous samples. Artificial proteins fine-tuned to five distinct lysozyme families showed similar catalytic efficiencies as natural lysozymes, with sequence identity to natural proteins as low as 31.4%. ProGen is readily adapted to diverse protein families, as we demonstrate with chorismate mutase and malate dehydrogenase.

The Safety and Utility of Ground Transport of Traumatic Cardiopulmonary Arrest Patients by Helicopter Emergency Medical Services Crews.

OBJECTIVE: Patients suffering from traumatic cardiopulmonary arrest (TCPA) typically demonstrate dismal survival rates. Some helicopter emergency medical services (HEMS) systems transport TCPA patients via ground with a referring agency when cardiopulmonary pulmonary resuscitation is in progress. With expanding research on the inherent risk of ground emergency medical services (GEMS) transport with the use of lights and sirens to both crew and the general public, the benefits may not outweigh the risks of transporting these patients by GEMS. The aim of this study was to determine the number of TCPA patients transported by GEMS with HEMS crews on board who survived to hospital discharge. METHODS: A retrospective chart review was performed of approximately 10 years of data from a regional Midwest HEMS service. Survival to hospital discharge was the primary outcome. RESULTS: Flight crews transported 54 patients via ambulance with GEMS crews; 31 patients met all inclusion and exclusion criteria. Of the 31 patients transported, 0 survived to hospital discharge. CONCLUSION: Based on our 0% survival rate and the inherent risk of injury and death to emergency medical services crews and the general public, the risk of transporting adult TCPA patients by GEMS using lights and sirens outweighs the benefit.