Explore the vast range of titles available.

Metal ions, as abundant and vital cofactors in numerous proteins, are crucial for enzymatic activities and protein interactions. Given their pivotal role and catalytic efficiency, accurately and efficiently identifying metal-binding sites is fundamental to elucidating their biological functions and has significant implications for protein engineering and drug discovery. To address this challenge, we present SuperMetal, a generative AI framework that leverages a score-based diffusion model coupled with a confidence model to predict metal-binding sites in proteins with high precision and efficiency. Using zinc ions as an example, SuperMetal outperforms existing state-of-the-art models, achieving a precision of 94 % and coverage of 90 %, with zinc ions localization within 0.52 ± 0.55 Å of experimentally determined positions, thus marking a substantial advance in metal-binding site prediction. Furthermore, SuperMetal demonstrates rapid prediction capabilities (under 10 s for proteins with ∼ 2000 residues) and remains minimally affected by increases in protein size. Notably, SuperMetal does not require prior knowledge of the number of metal ions—unlike AlphaFold 3, which depends on this information. Additionally, SuperMetal can be readily adapted to other metal ions or repurposed as a probe framework to identify other types of binding sites, such as protein-binding pockets. Scientific contribution SuperMetal introduces a diffusion-based, SE(3)-equivariant generative model that places metal ions in proteins with 94 % precision, 90 % coverage, and sub-ångström (0.52 Å) accuracy in under 10 s, surpassing current methods and accelerating metal-aware protein engineering and drug discovery.

In-field infection of maize (Zea mays L.) ears by the fungus Aspergillus flavus Link:Fr causes pre-harvest aflatoxin contamination of maize grain. Germplasm lines with host-plant resistance to aflatoxin accumulation are available to breeders, but these lines often possess undesirable agronomic characteristics. Commercial lines with expired plant variety protection (ex-PVP lines) are a potential source of elite germplasm available to public maize breeders. A diallel cross containing three aflatoxin-accumulation-resistant germplasm lines and seven ex-PVP lines were evaluated in replicated trials for aflatoxin contamination after artificial inoculation and for yield. The resistant germplasm lines Mp313E, Mp715, and Mp717 were the only lines with significant general combining ability (GCA) for reduced aflatoxin accumulation. Of the ex-PVP lines evaluated, the Stiff-Stalk line F118 was the most promising line to use in breeding crosses. Based on its GCA, it was the only ex-PVP line that did not significantly increase aflatoxin and the only ex-PVP line that significantly increased yield. Second-cycle breeding lines derived from crosses between F118 and the resistant donor lines will be valuable if they combine the donor lines’ disease resistance with F118’s earlier maturity while introgressing the disease resistance into a genetic background that aligns with the industry’s well-defined heterotic groups.

Water molecules play a significant role in maintaining protein structural stability and facilitating molecular interactions. Accurate prediction of water molecule positions around protein structures is essential for understanding their biological roles and has significant implications for protein engineering and drug discovery. Here, we introduce SuperWater, a novel generative AI framework that integrates a score-based diffusion model with equivariant graph neural networks to predict water molecule placements around proteins with high accuracy. SuperWater surpasses existing methods, delivering state-of-the-art performance in both crystal water coverage and prediction precision, achieving water localization within 0.3  ± 0.06 Å of experimentally validated positions. We demonstrate the capabilities of SuperWater through case studies involving protein hydration, protein-ligand binding, and protein-protein binding sites. This framework can be adapted for various applications, including structural biology, binding site prediction, multi-body docking, and water-mediated drug design. Water molecules are crucial for protein stability and interactions, yet predicting their precise positions around protein structures remain challenging. Here, the authors present SuperWater, a generative AI framework combining a score-based diffusion model and equivariant graph neural networks, to achieve unprecedented accuracy in water placement, demonstrating the capabilities involving protein hydration, protein-ligand binding and protein-protein interactions.

Background and Purpose: There is a need for a simple bedside tool to improve the ability of nurses to identify skin alterations, describe wounds, and stage pressure ulcers for proper care management and present on admission documentation. This study tests the test-retest reliability and criterion validity of the NE1 Wound Assessment Tool (NE1 WAT), a single-use tool featuring wound pictures and stage descriptions according to National Pressure Ulcer Advisor Panel criteria. Methods: Registered nurses (N = 94) identified and staged 30 wound photographs under 3 test conditions: (a) without NE1 WAT, (b) with NE1 WAT after viewing a 10-min instructional presentation, (c) with NE1 WAT but no additional instruction after a 7-14-day delay. Results: Out of a possible 90 points, scores increased 12.3 points between Tests 1 and 2 (p <.001) and 14.1 points between Tests 1 and 3 (p <.001). Test-retest reliability was high: intraclass correlation coefficient (ICC; 3, 1) = .892 (95% confidence interval [CI]: 0.840-0.927). Conclusions: The NE1 WAT is a simple tool that, with little training, improved the skin assessment ability of registered nurses.

Water molecules play a significant role in maintaining protein structural stability and facilitating molecular interactions. Accurate prediction of water molecule positions around protein structures is essential for understanding their biological roles and has significant implications for protein engineering and drug discovery. Here, we introduce SuperWater, a novel generative AI framework that integrates a score-based diffusion model with equivariant graph neural networks to predict water molecule placements around proteins with high accuracy. SuperWater surpasses existing methods, delivering state-of-the-art performance in both crystal water coverage and prediction precision, achieving water localization within 0.3 ± 0.06 Å of experimentally validated positions. We demonstrate the capabilities of SuperWater through case studies involving protein hydration, protein-ligand binding, and protein-protein binding sites. This framework can be adapted for various applications, including structural biology, binding site prediction, multi-body docking, and water-mediated drug design.

This article reframes the potential of generative AI in qualitative analysis, shifting from a focus on efficiency and automation toward opportunities to deepen analysis and strengthen core commitments of qualitative inquiry. We introduce “AI-in-the-loop analysis” as a term to describe the intentional incorporation of computational capabilities into analytic processes that remain grounded in human sensemaking, interpretation, and reflexive judgment. Building from foundational commitments of qualitative inquiry such as sustained attention to fine-grained data in relation to its larger context and intentional engagement of positionalities to support noticing and interpretation, we examine how properties of large language models (LLMs) can be mobilized to extend these practices. We focus on affordances provided by AI’s large-scale pre-training, rich semantic representations, attention mechanisms, long-context capacities, and interactive prompting, and describe ways that thoughtful engagement with these capabilities can help researchers maintain close attention to the details of the data across multiple iterations while situating interpretations in context, expand interpretive perspectives in dialogue with each other to layer meaning, and surface both confirming and disconfirming evidence across complex datasets. We connect these possibilities to established criteria for trustworthiness such as credibility, dependability, confirmability, transferability, and authenticity, showing how AI-in-the-loop approaches can offer new mechanisms for achieving and demonstrating analytic rigor. Rather than replacing human interpretive labor, generative AI can be used to augment researchers’ capacity for noticing, questioning, and synthesizing across large and complex qualitative data sets. When used critically and transparently, AI-in-the-loop analysis offers the possibility to expand the methodological repertoire of qualitative researchers for supporting rigorous, trustworthy, reflexive, contextually grounded analyses.

Archaeologists tend to produce slow data that is contextually rich but often difficult to generalize. An example is the analysis of lithic microdebitage, or knapping debris, that is smaller than 6.3 mm (0.25 in.). So far, scholars have relied on manual approaches that are prone to intra- and interobserver errors. In the following, we present a machine learning–based alternative together with experimental archaeology and dynamic image analysis. We use a dynamic image particle analyzer to measure each particle in experimentally produced lithic microdebitage ( N = 5,299) as well as an archaeological soil sample ( N = 73,313). We have developed four machine learning models based on Naïve Bayes, glmnet (generalized linear regression), random forest, and XGBoost (“Extreme Gradient Boost[ing]”) algorithms. Hyperparameter tuning optimized each model. A random forest model performed best with a sensitivity of 83.5%. It misclassified only 28 or 0.9% of lithic microdebitage. XGBoost models reached a sensitivity of 67.3%, whereas Naïve Bayes and glmnet models stayed below 50%. Except for glmnet models, transparency proved to be the most critical variable to distinguish microdebitage. Our approach objectifies and standardizes microdebitage analysis. Machine learning allows studying much larger sample sizes. Algorithms differ, though, and a random forest model offers the best performance so far. Arqueólogos tienden a producir “slow data,” quiere decir datos complejos de contextos locales pero muchas veces difícil de generalizar. Un buen ejemplo es el análisis de microdesechos líticos o escombros de la talla lítica menor de 6.3 mm (0.25 in.). Hasta ahora, investigadores han usado enfoques manuales que son propensos a errores intra- e ínterobservador. A continuación, presentamos una alternativa basada en machine learning, la arqueología experimental y el análisis dinámico de imágenes. Usamos un analizador de partículas de imagen dinámica para medir cada partícula en una muestra de microdesechos líticos producidos experimentalmente ( N = 5,299), así como en una muestra de suelo arqueológico ( N = 73,313). Desarrollamos cuatro modelos de machine learning basados en algoritmos Naïve Bayes, glmnet (regresión lineal generalizada), random forest y XGBoost (“Extreme Gradient Boost[ing]”). El ajuste de hiperparámetros optimizó cada modelo. Un modelo de random forest resultó mejor. Tiene una sensibilidad del 83,5% y clasificó mal solo el 28 o el 0,9% de los microdebitos líticos. Los modelos XGBoost alcanzan una sensibilidad del 67,3%, mientras que los modelos Naïve Bayes y glmnet se mantienen por debajo del 50%. A excepción de los modelos glmnet, la transparencia demostró ser la variable más crítica para distinguir los microdesechos del suelo. Nuestro enfoque objetiviza y estandariza el análisis de microdesechos. Machine learning permite estudiar tamaños de muestra mucho más grandes. Sin embargo, algoritmos difieren y un modelo random forest ofrece el mejor rendimiento haste ahora.

The appearance at the anatomical level of a canonical laminar microcircuit suggests that each six-layer column of granular cortex may mediate a canonical computation. Hypotheses for such computations include predictive coding, predictive routing, efficient coding, and others. However, single-neuron recordings capture only the individual elements of the hypothesized laminar microcircuit, while local field potentials (LFPs) from a laminar probe offer insight into the broader population activity. Through the Allen Institute's OpenScope Brain Observatory, data in mice performing a visual oddball task during multi-area laminar recording was used to test predictive processing hypotheses in the spectral domain. Histological labeling of the cortical laminae enabled a fine-grained examination of their roles in the task, and frequency bands capturing both feedforward and feedback effects were analyzed. ɣ-band local-field potential (LFP) oscillations conveyed feedforward prediction errors in lower sensory areas of cortex; ⍺/β-band oscillations weakened in unpredictable conditions compared to predictable ones; and θ-band oscillations additionally signalled slower, longer-scale temporal prediction errors. In combination with the previous findings, predictive routing explains these experiments where neither ubiquitous predictive coding nor feedforward adaptation can. Cortical columns robustly signal perceptual features through the firing rates of spiking neurons. In accordance with this rate coding, predictive processing theories hypothesized that neuronal firing rates ubiquitously signal surprise. However, a recent large-scale study of spike rates did not support this conjecture. An alternate model, predictive routing, suggests that neuronal oscillations rather than spike rates could encode surprise. These neuronal oscillations, which can affect the timing but not rate of spiking, formed coherent ɣ rhythms which consistently signaled both simpler and more complex forms of surprise in mouse visual cortex. Together with the findings on spike-rates in the same experiment, our findings suggest that cortical circuits encode surprise in the rhythmic timing of spikes rather than in their rate.

Pre-harvest contamination of maize grain with aflatoxin is a chronic problem worldwide and particularly in the southeastern U.S. Aflatoxin is a mycotoxin produced by the fungus Aspergillus flavus, an opportunistic ear-rot pathogen of maize (Zea mays). Resistance to aflatoxin accumulation is heritable, and resistant germplasm-lines are available. These lines are derived from “exotic” genetic backgrounds and were released as sources of resistance, not parental inbreds. However, all current sources of resistance are quantitative, which complicates conventional efforts to introgress resistance alleles from unadapted but resistant donor lines to adapted but susceptible recipient lines. Mapping quantitative trait loci (QTL) and their linked markers enables targeted introgression of the desired alleles via marker-assisted selection. Quantitative trait loci were identified in two F2:3 mapping populations, derived from crossing resistant inbreds Mp715 and Mp717 to a common susceptible parent (Va35). The Mp715 x Va35 population was phenotyped for aflatoxin accumulation under artificial inoculation in replicated field trials at Mississippi State (MSU) in 2015 and 2016. The Mp717 x Va35 population was phenotyped at MSU and Lubbock, TX in 2016. Populations were genotyped using simple sequence repeat (SSR) and single nucleotide polymorphism (SNP) markers and linkage maps created in JoinMap4. To locate QTL, linkage maps, genotypes, and phenotypes were analyzed jointly in QTL Cartographer 2.5 using composite interval mapping (CIM) and multiple interval mapping (MIM) procedures. Five QTL with the beneficial allele contributed by Mp715 were identified during CIM in bins 5.01, 6.06, 7.03 10.04 and 10.05. Three QTL with the beneficial allele contributed by Mp717 were identified during CIM in bins 3.07/3.08, 7.02/7.03, and 10.05. In both populations, QTL were identified with the beneficial allele contributed by Va35. Those QTL did not co-locate across populations but four of the six were on chromosome 1. Significant QTL effects from CIM were used as the initial model terms in MIM, where all QTL effects were fit simultaneously and their gene-action and epistatic interactions estimated.

Metal ions, as abundant and vital cofactors in numerous proteins, are crucial for enzymatic activities and protein interactions. Given their pivotal role and catalytic efficiency, accurately and efficiently identifying metal-binding sites is fundamental to elucidating their biological functions and has significant implications for protein engineering and drug discovery. To address this challenge, we present SuperMetal, a generative AI framework that leverages a score-based diffusion model coupled with a confidence model to predict metal-binding sites in proteins with high precision and efficiency. Using zinc ions as an example, SuperMetal outperforms existing state-of-the-art models, achieving a precision of 94 % and coverage of 90 %, with zinc ions localization within 0.52 ± 0.55 Å of experimentally determined positions, thus marking a substantial advance in metal-binding site prediction. Furthermore, SuperMetal demonstrates rapid prediction capabilities (under 10 seconds for proteins with ∼ 2000 residues) and remains minimally affected by increases in protein size. Notably, SuperMetal does not require prior knowledge of the number of metal ions-unlike AlphaFold 3, which depends on this information. Additionally, SuperMetal can be readily adapted to other metal ions or repurposed as a probe framework to identify other types of binding sites, such as protein-binding pockets.