Accurate structure prediction of biomolecular interactions with AlphaFold 3.

The introduction of AlphaFold 21 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2-6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein-ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein-nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody-antigen prediction accuracy compared with AlphaFold-Multimer v.2.37,8. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

Human-level performance in 3D multiplayer games with population-based reinforcement learning.

Reinforcement learning (RL) has shown great success in increasingly complex single-agent environments and two-player turn-based games. However, the real world contains multiple agents, each learning and acting independently to cooperate and compete with other agents. We used a tournament-style evaluation to demonstrate that an agent can achieve human-level performance in a three-dimensional multiplayer first-person video game, Quake III Arena in Capture the Flag mode, using only pixels and game points scored as input. We used a two-tier optimization process in which a population of independent RL agents are trained concurrently from thousands of parallel matches on randomly generated environments. Each agent learns its own internal reward signal and rich representation of the world. These results indicate the great potential of multiagent reinforcement learning for artificial intelligence research.

Human-level control through deep reinforcement learning.

The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

The economic benefit of organizational restructuring of the cardiothoracic intensive care unit.

OBJECTIVES: Compare cost/benefits of organizational restructuring of the cardiac intensive care unit (CICU). DESIGN: Prospective, with a retrospective control period. SETTING: Academic medical center. PARTICIPANTS: Sixty-six CICU patients (prospective) and 57 patients who received care before restructuring (retrospective) were compared. Entrance criteria were constant for both study periods. INTERVENTIONS: The CICU was restructured from a level III ICU to a level I ICU with the initiation of a consultant CICU service. The CICU service provided an attending physician dedicated to ICU care daily. All cardiac patients admitted into the CICU received consultation by the CICU service. MEASUREMENTS AND MAIN RESULTS: The average postoperative intubation time decreased during the intervention period (61% extubated within 6 hours v 12%, p = 0.004). Pharmacy, radiology, laboratory, and ICU costs decreased 279 US dollars (p = 0.004), 196 US dollars (p = 0.003), 190 US dollars (p = 0.15), and 470 US dollars (p = 0.12), respectively. The ICU length of stay (0.28 days shorter) as well as the overall postsurgery stay (0.54 days shorter) were reduced in the intervention period (p = 0.11 and 0.10, respectively). CONCLUSIONS: The CICU service significantly reduced both total ICU-related costs ($1,173/patient) and overall costs (2,285 US dollars/patient) during the intervention period. Professional fees only reduced overall savings by 8%. These results indicate that organizational restructuring of the CICU to newer models can reduce costs associated with cardiac surgery.

The modified nasal trumpet maneuver.

UNLABELLED: The last decade has witnessed a proliferation of devices or methods that facilitate intubation in difficult circumstances, maintain ventilation, or which do both. These all require properly functioning and specially designed apparatus, the use of which requires variable degrees of expertise. This technical communication describes the author's experience with a simple technique that uses virtually universally available materials--a nasal trumpet (airway) and an endotracheal tube (ETT) connector--to rescue patients in the cannot-ventilate/cannot-intubate scenario. The methodology is straightforward, ventilation is usually immediate, stomach contents can be evacuated while ventilation proceeds, and it does not require mouth opening. Moreover, while ventilation and oxygenation is continuing, a fiber-optic intubation can proceed without interference. IMPLICATIONS: A simple technique is proposed that can be used to rescue patients who are in a condition of cannot intubate/cannot ventilate. The described maneuver may save patients from requiring a surgical airway.