Browse Articles

Phenotypic clustering identifies heterogeneous cardiovascular risk among patients with elevated lipoprotein(a)

A novel hybrid deep learning framework for customer churn prediction using RFM and embedding clustering

Abstract Customer churn prediction in E-commerce remains a challenging task due to the lack of labeled data, and the limited ability of traditional machine learning models to capture complex and dynamic customer behavior patterns. Existing approaches either rely on handcrafted features without effective representation learning or apply deep learning models without incorporating meaningful customer segmentation. To address these limitations, this study proposes a unified hybrid framework that integrates RFM-based feature engineering, Deep Embedded Clustering (DEC), and deep learning models for joint customer segmentation and churn prediction. The proposed framework first learns compact latent representations using a deep autoencoder, followed by clustering customers into behaviorally meaningful groups using an improved DEC mechanism with validated cluster selection and refinement. These learned representations are then used as input to Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) models for multi-class churn prediction. The framework is evaluated on two real-world datasets, namely the Online Retail dataset and an Events dataset, which differ significantly in scale and behavioral complexity. Experimental results demonstrate that LSTM achieves an accuracy of 99.65% on the Online Retail dataset and 99.83% on the Events dataset, while GRU achieves 99.77% and 99.75%, respectively. Although traditional models such as Logistic Regression and Support Vector Machine achieve competitive performance, they show limited adaptability across heterogeneous data distributions. The results confirm that integrating representation learning with clustering and deep sequential models significantly enhances churn prediction performance. The proposed framework effectively transforms raw transactional data into structured, actionable insights that support customer retention strategies in E-commerce environments.

Oscillation criteria in large-scale gene regulatory networks with intrinsic fluctuations

Gene Regulatory Networks (GRNs) with feedback are essential components of many cellular processes and may exhibit oscillatory behavior. Analyzing such systems becomes increasingly complex as the number of components increases. Since gene regulation often involves a small number of molecules, fluctuations are inevitable. Therefore, it is important to understand how fluctuations affect the oscillatory dynamics of cellular processes, as this will allow comprehension of the mechanisms that enable cellular functions to remain even in the presence of fluctuations or, failing that, to determine the limit of fluctuations that permits various cellular functions. In this study, we investigated the conditions under which GRNs with feedback and intrinsic fluctuations exhibit oscillatory behavior. Our focus was on developing a procedure that would be both manageable and practical, even for extensive regulatory networks, that is, those comprising numerous nodes. Using the second-moment approach, we described the stochastic dynamics through a set of ordinary differential equations for the mean concentration and its second central moment. The system can attain either a stable equilibrium or oscillatory behavior, depending on its scale and, consequently, the intensity of fluctuations. To illustrate the procedure, we analyzed two relevant systems: a repressilator with three nodes and a system with five nodes, both incorporating intrinsic fluctuations. In both cases, it was observed that for very small systems, which therefore exhibit significant fluctuations, oscillatory behavior is inhibited. The procedure presented here for analyzing the stability of oscillations under fluctuations enables the determination of the critical minimum size of GRNs at which intrinsic fluctuations do not eliminate their cyclical behavior.

AI and simple blood tests could catch lung cancer earlier

Study of stimulation mechanism of hydraulic fracturing induced thermal shock on joint system of geothermal reservoirs

Thermally activated snap-through transitions controlled by tunable free energy landscape

The effects of thermal fluctuations on the morphology of two-dimensional elastic materials are hard to harness. We propose that such effects can be controlled and exploited in thermally activated snap-through transitions of geometrically constrained graphene nanoribbons (GNRs) with a tunable transition rate constant. The energetics and kinetics of these transitions can be fully characterized by combining enhanced sampling methods and generalized transition state theory. Using well-tempered metadynamics, we determine the complex free energy landscape and a pair of degenerate transition pathways of the GNR system. The resultant Landau free energy allows the application of generalized transition state theory (TST). Notably, generalized TST accurately captures how the transition rate constant responds to temperature and the tunable free energy landscape of our system, as substantiated by unbiased and accelerated molecular dynamics simulations for the rare event dynamics across different timescales. This work offers a theoretical framework for elastic metastability, introduces rare event methods into thermalized nanomechanical systems, and provides strategies for controlling thermally activated transitions in metastable elastic nanostructures.

Terahertz detection using germanium-based photoconductive antennas on various substrates

Germanium (Ge) is emerging as a promising material for terahertz (THz) devices due to its non-polar nature, which enables gapless, broadband radiation. It also offers the advantage of CMOS compatibility and can be adapted to various substrates. In this work, we demonstrate the compatibility of Ge films deposited by DC magnetron sputtering on high-resistive silicon and on low-cost insulating substrates, glass and Kapton, for the detection of free-space THz pulses. With the growing interest in the field of flexible electronics, it is essential to explore THz devices that can be integrated onto flexible platforms for which Kapton offers a clear advantage. We demonstrate THz detection using Ge-on-glass and Ge-on-Kapton photoconductive antennas (PCAs) with ZnTe as a THz emitter, achieving spectral bandwidths of 1.5 and 1.2 THz with signal-to-noise ratios (SNRs) of 27 and 23 dB, respectively. On the other hand, with a commercial GaAs as a PCA emitter, a Ge-on-Si PCA detected up to 2 THz with an SNR of 27 dB. We report on the compatibility of laser systems and the experimental constraints that depend on the choice of substrates.

Drugs that boost immunity are making lung cancer less deadly

Supervised machine learning algorithms for classifications of gender-based violence in Somalia: a comparison of oversampling techniques

Uncertainty-aware Bayesian inference of glass transition temperatures from molecular simulations

The glass transition temperature, Tg, is a central thermophysical parameter in polymer physics, yet its extraction from molecular simulation data is typically performed using deterministic piecewise fits that assume abrupt separation and provide no rigorous quantification of uncertainty. In this work, we reformulate glass transition estimation as a Bayesian inference problem, in which Tg is treated as a latent thermodynamic parameter, and the transition is modeled explicitly as a finite-width crossover in the temperature-dependent specific volume. This probabilistic formulation yields full posterior distributions for both the transition temperature and its breadth, enabling uncertainty arising from finite sampling, temporal correlations, and discrete temperature grids to be propagated consistently. Applying the framework to coarse-grained polymer melts spanning chain lengths from N = 25 to N = 500, we show that the smooth crossover description is consistently favored over a conventional change-point formulation according to information-theoretic model evidence. The inferred posterior median Tg increases systematically with molecular weight, while both the uncertainty in Tg and the transition width decrease, reflecting the progressive sharpening of the thermodynamic crossover as finite-size and chain-end effects diminish. Posterior predictive analyses further demonstrate that a single model structure and likelihood specification remain statistically calibrated across all chain lengths without system-specific adjustment. By unifying thermodynamic modeling, uncertainty quantification, and model evidence within a single framework, this work establishes an uncertainty-aware and transferable methodology for extracting glass transition temperatures from molecular simulations and replaces heuristic fitting procedures with statistically grounded thermodynamic characterization.

Retraction: Bronchial Casts from Inhalation of Forest-Fire Smoke. N Engl J Med 2026;394:1634.

Phase-field simulation of countercurrent spontaneous imbibition in fractured porous media with heterogeneous mixed wettability

Countercurrent spontaneous imbibition governs fracture–matrix fluid exchange in fractured reservoirs. While the influence of wettability on imbibition has been widely recognized, the pore-scale mechanisms with heterogeneous mixed wettability remain inadequately understood. In this study, a pore-scale phase-field simulation of countercurrent imbibition in a two-dimensional fractured porous media is conducted by coupling the Cahn–Hilliard equation with the incompressible Navier–Stokes equations. The porous matrix is a heterogeneous packing of circular grains with different sizes arranged in an equilateral triangular pattern, and an adjacent fracture provides the wetting phase continuously. For the uniformly wettability system, a critical contact angle of π/8 is identified when θ ≤ π/2. Below this threshold, very strong water-wet conditions promote early snap-off and loss of oil-phase connectivity, resulting in the decline of the final oil recovery, whereas above it, both the imbibition rate and oil recovery increase significantly as the contact angle decreases. In heterogeneous mixed wettability systems, water from the fracture preferentially invades adjacent, more water-wet regions. The water front ceases its advance upon encountering oil-wet grains or relatively wider pore throats. The spatial distribution of wettability zones is a crucial factor influencing matrix oil recovery. Even with identical contact angle values, different spatial distributions of wettability lead to pronounced differences in invasion patterns and recovery efficiency. An increasing fraction of oil-wet regions consistently lowers the matrix oil recovery. These findings provide pore-scale insight into fracture–matrix fluid transfer under heterogeneous mixed-wettability conditions and demonstrate the capability of the phase-field method to resolve complex countercurrent imbibition phenomena in fractured porous media.

The SCD inhibitor MTI-301 reduces steatohepatitis and ratio of C18:1/C18:0 levels in diet-induced murine models of MASH

Direct Boltzmann inversion method from particle configurations at arbitrary state points

We introduce a direct Boltzmann inversion method to infer the interaction potential in particle systems using as input particle configurations generated at an arbitrary state point of the system. Unlike iterative Boltzmann inversion, the proposed method does not require performing a new Monte Carlo simulation at each step of the iteration process. It relies instead on enforcing consistency between two independent estimates of the pair correlation function, respectively obtained from interparticle distances and from pairwise forces. As a result, the approach is computationally inexpensive and straightforward to implement. Because it relies on the sole expression of interparticle forces, our method naturally applies to any state point, including when the density is large and alternative methods may fail. Here, we present the basic principles of the method and benchmark its performance on a diverse set of test potentials studied using computer simulations. Practical aspects and detailed implementation of the method are also discussed. Owing to its simplicity and generality, the method should be broadly applicable, from the construction of coarse-grained interaction potentials to the inference of effective interactions in non-equilibrium systems.

Cardiovascular Risk Factors — Hypertension

Micrometer-scale displacement and thickness sensing using a single terahertz resonant-tunneling diode

Resonant-tunneling diodes (RTDs) support room-temperature terahertz (THz) oscillation and simultaneous THz-band detection, enabling compact monostatic THz sensors for practical and cost-effective sensing applications. In this paper, we present a highly integrated 280 GHz-band radar system based on a single RTD that exploits the self-mixing effect to generate a low-frequency interferometric signal. The resulting self-mixing signal is further analyzed from a radar perspective and processed to extract micrometer-scale displacement and thin-film thickness variations. Experimentally, the proposed system demonstrates a minimum detectable displacement of approximately 5 μm and quantitatively resolves polymer film thicknesses of 12.5, 25, and 50 μm.

Nature is expanding Registered Reports to all the fields in which we publish

A Bioactive PLGA-modified SIS scaffold loaded with astragaloside IV–preconditioned BMSCs promotes infected wound healing

Quantifying ion–ion association in mixed electrolyte systems using bulk thermodynamic experimental data

For single electrolytes, it is already well established that the net affinities between salt–salt, salt–solvent, and solvent–solvent can be derived from bulk thermodynamic volumetric and chemical potential composition-derivative data via Kirkwood–Buff integrals (KBIs). In this simplest case, it is also widely known how to reinterpret those component-based KBIs to obtain the species-based KBIs (cation–cation, cation–anion, etc.). However, this process has never been performed for systems with more than one species of cation and/or anion—a severe restriction. Here, we show how to obtain the ion–ion KBIs for bulk mixed electrolyte solutions regardless of the ion concentration, valency, molecular complexity, degree of ion pairing, etc., assuming one has correlating equations for the bulk thermodynamic data and the system is miscible. This is achieved using a combination of Kirkwood–Buff theory and global and local electroneutrality constraints and is illustrated for mixtures of NaCl + KBr (aq) at 298 K and 1 bar and MgCl2 + KBr (aq) at 373 K and 1 bar. The single electrolyte and select common ion subsystems are also studied. A comparison of the experimental KBIs to those obtained from molecular dynamics simulations shows excellent agreement for the ambient NaCl + KBr (aq) system using the KBFF + SPC/E force field.

Case 15-2026: A 64-Year-Old Woman with Fatigue, Memory Changes, and Falls