Search Results (129)

Background: Anaplastic Lymphoma Kinase (ALK) is an oncogenic receptor tyrosine kinase implicated in several cancers. Despite the clinical success of ALK inhibitors, acquired resistance continues to drive the search for novel chemotypes. We developed a multiclass machine learning framework to classify ALK inhibitory activity using a curated ChEMBL dataset. Methods: Models were built using 2D molecular descriptors together with MACCS and ECFP4 fingerprints. Three widely used algorithms, Support Vector Machine (SVM), Random Forest (RF), and XGBoost, were applied for model development. Results: RF and XGBoost models demonstrated the best performance, achieving accuracies of ~0.75–0.79 with consistently high ROC–AUC values, particularly for fingerprint-based features. Bemis–Murcko scaffold analysis identified enriched chemotypes and underexplored scaffolds for further prioritization. The validated models were subsequently used to screen the Maybridge library, and compounds predicted to possess potential ALK inhibitory activity were prioritized for further computational evaluation. Applicability-domain filtering confirmed that the selected compounds occupied the predicted ALK inhibitor chemical space across multiple activity classes. The shortlisted compounds were subsequently evaluated by molecular docking to characterize their binding modes and interactions. Three candidate hits (SCR00078, SCR00073, and AW01085) were selected for further evaluation using 500 ns molecular dynamics simulations alongside the reference inhibitor Brigatinib. Simulation analyses revealed stable protein–ligand complexes and reduced conformational fluctuations relative to apo ALK, while MM/PBSA calculations identified SCR00078 and AW01085 as the most favorable binders. Conclusions: This integrated ML-to-simulation workflow prioritizes structurally novel candidate hits with predicted ALK inhibitory activity and provides an effective strategy for scaffold discovery and hit prioritization. Full article

The rapid proliferation of drones has raised growing concerns regarding low-altitude airspace safety. In practical UAV communication scenarios, relying solely on a single time-domain IQ signal is often insufficient to fully characterize UAV RF fingerprints. Moreover, increasingly subtle hardware differences among UAV transmitters make RF fingerprint identification more challenging. Other representations, such as STFT-based features, are commonly converted into image-like inputs for neural networks, increasing deployment complexity on edge devices. To address these challenges, this paper proposes a UAV recognition framework based on multi-domain signal representations. The proposed framework employs a multi-domain input strategy and structural reparameterization to reduce the number of parameters, computational cost, and deployment latency. Experiments under AWGN conditions demonstrate that the proposed model achieves superior recognition performance in both UAV classification and individual identification tasks. The proposed model is further deployed on the Ascend 910B platform to verify its deployment feasibility. Full article

Accurate crop mapping in middle-to-high latitude agricultural basins is essential for food security, agricultural management, and sustainable land-use planning. However, crop classification in these regions remains challenging because fragmented field patterns, mixed pixels, and overlapping phenological stages often lead to severe spectral confusion among major dryland crops. To address this issue, this study developed a Phenology–Spectral Dual-Constrained Strategy (PS-DCS) by integrating agronomic knowledge with physically constrained spectral features. The proposed framework identified August as the optimal observation window based on crop phenological divergence. Wheat was first extracted using a spectral fingerprint combining the Chlorophyll Index Red Edge (CI_RE) and Redness index. Subsequently, maize and soybean were separated within the non-wheat mask using the B6 red-edge band selected through feature separability analysis. Validation based on Sentinel-2 time-series imagery and 1056 independent field samples collected in 2025 yielded an Overall Accuracy of 95.36% with a Kappa coefficient of 0.928. Compared with RF, XGBoost, and CNN models, PS-DCS maintained competitive classification performance while substantially reducing dependence on large training datasets and complex parameter tuning. Cross-year validation during 2022–2024 further demonstrated stable spatial transferability without threshold recalibration. These results indicate that translating agronomic mechanisms into physically interpretable remote sensing rules provides an effective and transparent framework for high-precision crop mapping and long-term agricultural monitoring in complex agricultural landscapes. Full article

Bluetooth Low Energy (BLE) is widely used in Internet of Things (IoT) devices due to its low power consumption and efficient wireless communication. However, BLE-based systems remain vulnerable to signal-level attacks, such as spoofing and signal forgery, which allow adversaries to impersonate legitimate devices and compromise system security. Existing security approaches mainly rely on cryptographic mechanisms or protocol-level features, while conventional signal fingerprinting methods often fail to capture subtle device-specific variations across the frequency spectrum. We propose a deep-learning-based BLE signal fingerprinting framework that uses emphasized spectral data to enhance device authentication. The proposed framework selectively highlights frequency regions exhibiting pronounced hardware-dependent variations using a hybrid filter bank design and extracts spectral features for anomaly-based device identification. Experimental evaluations conducted on BLE signals collected from multiple devices demonstrate that the proposed approach outperforms conventional methods, achieving superior authentication performance. By leveraging emphasized frequency-domain characteristics, we provide an effective authentication method for BLE-based IoT environments. Full article

The chemical composition and perceived quality of wild ginseng (WG) are influenced by its geographical origin, yet clear chemical criteria for origin authentication remain lacking, and this problem is further complicated by the confounding effect of growth year. In this study, volatile and non-volatile fingerprints of 15- and 20-year-old WG from Huanren, Tonghua, and Ji’an (China) were characterized using HS-GC-IMS and HPLC. Partial least squares discriminant analysis (PLS-DA) models constructed separately for each growth-year group achieved complete origin separation of volatile fingerprints, with ten shared VIP markers identified. However, none maintained a consistent origin ranking across years, suggesting that the geographical signal may reside in the multivariate patterns. Ginsenoside profiling revealed a hierarchical candidate marker system: Rf, Rg1, Rc, Rb2 as robust candidate markers for Huanren, and Re as a 20-year-specific discriminator for Tonghua. The pervasive origin × growth year interaction observed across both volatile and non-volatile fractions indicates that growth-year-specific chemometric models are a necessity for reliable WG origin authentication. A practical two-step workflow—growth year determination followed by age-matched origin assignment—is proposed. These findings provide a scientific foundation for the geographical traceability and quality evaluation of WG. Full article

Organometallic chemistry deals with the synthesis, structure, reactivity, and applications of compounds containing metal–carbon covalent bonds. In recent years, there has been a growing interest in predicting the catalytic activity of organometallics using machine learning. However, the major drawback in developing algorithms that can be used in predicting organometallic reactions is the availability of organometallic reaction data and organometallic filtering tools. The main aim of the current study is to develop organometallic reaction-filtering tools that are crucial for building accurate and effective ML models in organometallic chemistry. Random Forest (RF), K-Nearest Neighbors (kNN), Support Vector Classifiers (SVC), and Multi-Layer Perceptrons (MLP) were employed, using feature subsets selected via Permutation Feature Importance from Morgan fingerprints and MACCS keys. The results demonstrate that the MACCS-based MLP architecture provides the most reliable filtering performance, achieving a superior F1 score of 0.85, a Recall of 0.85, and a high AUC-ROC of 0.837. Furthermore, the MACCS-MLP exhibited the highest predictive confidence, yielding the study’s lowest Log Loss of 0.312. In contrast, while Morgan fingerprints paired with kNN offered a specialized “strict” filter with absolute Precision (1.00), the sparse dimensionality of circular fingerprints generally resulted in lower calibration for probabilistic models. These findings underscore that dense, fragment-based descriptors refined by data-driven feature selection are most effective for identifying complex organometallic motifs. This study successfully provides a validated methodology for building precise filtering tools, establishing a critical foundation for automated catalyst discovery and the expansion of effective machine learning applications in organometallic chemistry. The study is limited to only identifying organometallic reactions and cannot filter based on organometallic reaction types. Future studies should also explore integrating multiple feature representations to classify or cluster the identified organometallic reactions based on the reaction types. Full article

Unmanned aerial vehicle (UAV) identification in edge environments requires both high classification accuracy and efficient real-time deployment on lightweight hardware. This study presents LUMEN, a Lightweight UAV Multi-Enhanced Network designed for resource-constrained single-board computer platforms. To enable efficient edge deployment, the proposed method adopts a power spectral density (PSD)-based signal representation together with a lightweight neural network architecture. LUMEN combines multi-channel PSD stacking with multi-scale feature extraction to capture both short-term spectral variations and multi-resolution RF patterns. The proposed pipeline covers UAV RF data collection, including UAV RF data collection, dataset construction, preprocessing, model design, comparative evaluation, and deployment on an RK3582-based edge platform. In the classification experiments, LUMEN achieved the best performance among the four evaluated models, reaching an accuracy of 0.975, compared with 0.775, 0.876, and 0.942 for the baseline models. In the edge deployment test, the model maintained an average inference latency of 1.73 ms and a throughput of 578.95 FPS during a 30-min continuous run, while showing low CPU utilization, low memory usage, and stable thermal behavior. These results demonstrate that LUMEN achieves a practical balance between identification accuracy and runtime efficiency for real-time UAV identification on edge devices. Full article

Radio Frequency Fingerprinting (RFF) enables passive physical-layer device authentication by exploiting unintentional hardware variations in wireless transmitters. Neuromorphic implementations are attractive, given their potential for low-latency, energy-efficient inference capability under Size, Weight, and Power (SWaP) constraints at the edge. A new RFF capability is demonstrated here using recently introduced Radio Frequency Resonate-and-Fire (RF-RAF) neurons and eight WirelessHART devices. Performance is evaluated for RF-RAF-generated fingerprints against the established Gabor Transform (GTX) baseline using three classifier architectures: Random Forest (RndF), Convolutional Neural Network (CNN), and a Time-Incremented Spiking Neural Network (TI-SNN). The results show that RF-RAF fingerprints achieve an average classification accuracy of 96.7% across all three classifier types and consistently outperform GTX fingerprints at all evaluated fingerprint sizes. This performance persists under time-span-matched conditions, and the RF-RAF versus GTX benefit is not solely attributable to input data utilization. The TI-SNN surpasses 94% classification accuracy using M = 4 time step RF-RAF fingerprints with approximately 100 spikes per inference—a 4× larger GTX fingerprint requires approximately 1000 spikes to achieve the same classification accuracy. RF-RAF fingerprints offer two additional benefits: they are natively non-negative, which supports efficient neuromorphic hardware implementation, and they provide greater flexibility in fingerprint size selection. It is concluded that RF-RAF neurons provide an efficient neuromorphic-native encoding pathway for device RFF discrimination and offer improved accuracy–efficiency tradeoffs in training and inference for various classifier architectures. Full article

Background/Objectives: Cancer remains one of the leading global health burdens, mainly because of the lack of specificity and off-target toxicity associated with conventional therapeutic approaches. To move toward more efficient anticancer drug discovery, we have developed an advanced machine-learning-based architecture that allows for predictive modeling of anticancer small molecules. Methods: A total of 3600 compounds with experimentally validated IC₅₀ values were systematically processed to derive a comprehensive suite of molecular representations comprising 2D physicochemical descriptors, structural fingerprints, and hybrid descriptor sets generated via the Mordred and PaDEL frameworks. A total of six machine learning algorithms—Random Forest (RF), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), Extra-Trees classifier (ET), Adaptive Boosting (AdaBoost), and Light Gradient Boosting Machine (LightGBM)—were trained and benchmarked via a rigorous model evaluation protocol incorporating 10-fold cross-validation along with multiple performance metrics. Ensemble voting strategies were also examined to assess potential performance. Result: Of all configurations, the XGB-Hybrid architecture emerged as the most robust and generalizable classifier with an AUC of 0.88 and accuracy of 79.11% on the independent test set. To ensure interpretability and mechanistic insight, SHAP-based feature analysis was conducted, by which feature contributions could be quantified and the molecular determinants most influential for anticancer activity discrimination were revealed. Altogether, the current study establishes an XGB-Hybrid framework as technically rigorous, interpretable, and high-performance predictive modeling with the ability to accelerate early-stage anticancer small molecule identification. Conclusions: The study has brought into focus the transformational effect of machine learning in modern computational oncology and rational drug design pipelines. Full article

Reliable analytical methods are essential for the assessment, effective quality control, and guarantee of consistent and reproducible performance of chemical profiles of non-psychoactive low-THC Cannabis sativa L. samples and their products. An integrated analytical approach was applied for the first time to evaluate low-THC C. sativa products on the Serbian legal market using chemometrics combined with five complementary techniques: ultraviolet–visible spectroscopy (UV–Vis), high-performance thin-layer chromatography (HPTLC), portable Raman spectroscopy, Fourier transform infrared spectroscopy (FTIR) and gas chromatography–mass spectrometry (GC–MS). HPTLC rapidly differentiated key cannabinoids with R_F at 0.39 and 0.61, while GC–MS enabled comprehensive identification of major cannabinoids (CBG and CBD). Spectroscopic fingerprints provided characteristic UV–Vis absorption maximum (215, 235, and 275 nm), Raman (1700, 1550, 1517, 1224, 1096 cm⁻¹) and FTIR marker bands (615, 1059, 1288, 1620, 2932 cm⁻¹), supporting robust monitoring. Principal component analysis (PCA) across all five techniques revealed two major distinct sample clusters and identified the most influential analytical signals. The combined separation, spectroscopic, and multivariate approach is proven to be effective for systematic cannabinoid content assessment, authentication, and chemical profiling within a process-oriented context, thus enabling effective quality control in the cultivation process by targeting compounds of interest. Full article

The acid dissociation constant (pK_a) is a fundamental parameter governing the environmental fate of organic compounds. Accurate pK_a prediction remains challenging, as traditional binary Morgan fingerprints (B-MF) fail to capture stoichiometric information critical for modeling substituent effects. This study developed an interpretable machine learning framework for pK_a prediction by integrating count-based Morgan fingerprints (C-MF) with ensemble algorithms. Through systematic comparison across four algorithms (Catboost, XGBoost, GBDT, RF), C-MF consistently outperformed B-MF due to its ability to quantify functional group multiplicity. Subsequent SHAP-based recursive feature elimination (SHAP-RFE) optimized the model, identifying Catboost with only 81 features as the optimal architecture, achieving a test-set R² of 0.890 and RMSE of 1.026. SHAP analysis revealed that the model’s decisions are driven by chemically intuitive features, forming a hierarchical framework where primary ionizable sites set the baseline pK_a and electronic modifiers fine-tune it. The applicability domain, defined using the AD_SAL method, yielded high-confidence predictions (R² = 0.926). External validation on an independent open-source dataset containing 6876 acidic compounds, combined with results from AD_SAL application domain characterization, enabled accurate pK_a prediction for 390 compounds within the application domain (R² = 0.890, RMSE = 0.942). This further confirms the model’s strong generalizability. This work provides a robust and generalizable tool for high-performance pK_a prediction, with significant potential for applications in environmental risk assessment. Full article

Radio frequency fingerprints (RFFs), arising from inherent hardware imperfections, serve as distinctive features for device identification. The location- and time-dependent nature of the wireless channel directly affects RFF-based device identification, making it challenging under different channel conditions. This is primarily because the training and test datasets containing RFFs may not overlap within the same feature-space domain. In this work, the mentioned issue is addressed as a domain adaptation problem. For this objective, we propose the use of a triplet-learning-based domain-adversarial neural network within a hybrid framework named TripletDANN. We leverage the triplet loss, enabling the network to focus exclusively on device-specific latent representations under different channel conditions, while employing an adversarial loss to prevent the network from exploiting channel-specific characteristics. With this aim, data aggregation is performed together with channel labeling. The generalization capability of TripletDANN is evaluated on previously unseen test data collected across different locations under two distinct scenarios. Raw I/Q signals of 15 Wi-Fi devices are used as a case study. The proposed TripletDANN model achieves up to $88.52\%$ average device classification accuracy across the different data collection locations. On average, TripletDANN attains up to a $5\%$ performance improvement over its counterpart model. Moreover, data augmentation is employed to improve the overall performance, and a highest accuracy of $96.71\%$ is achieved on experimentally collected test data from an unseen location. Full article

Background/Objectives: Sodium-glucose co-transporter 2 (SGLT2) inhibitors are essential antidiabetic medications. However, their side effects warrant careful consideration. The search for novel SGLT2 inhibitors with high affinity remains an ongoing endeavor. Medicine food homology (MFH) herbs show promise for drug development due to their nutritional and medicinal value. Methods: This study aims to address the shortcomings of existing virtual screening models for SGLT2 inhibitors by optimizing feature selection and integrating multidimensional molecular fingerprints. Subsequently, an integrated virtual screening pipeline is constructed to identify potential SGLT2 inhibitors from eight selected MFH herbs. Results: The results indicate that the optimal model (LightGBM and RF) achieved an accuracy of 0.97 and an AUC of 0.98. Following rigorous filtering, a total of 44 potential SGLT2 inhibitors were identified, among which, Isoononin (from Gancao) and Ononin (from Huangqi, Gegen, and Gancao) exhibit favorable drug likeness and safety. Molecular docking demonstrate that both compounds can effectively bind to the SGLT2 active site, establishing stable hydrophobic interactions with critical residues such as Phe98 and Phe453. Furthermore, molecular dynamics simulations confirm the stability of the interactions between the two compounds and SGLT2. Conclusions: This study significantly enhances the accuracy and stability of SGLT2 inhibitor virtual screening models by addressing deficiencies in structural characterization and feature selection. It provides candidate molecules for the development of novel SGLT2 inhibitors and offers new scientific evidence for the application of MFH herbs in the prevention and treatment of chronic metabolic diseases. Full article

This study examines how the seven pillars of ZTA are implemented in a CDS environment that demands high security reliability, similar to the defense and finance sectors, and identifies the technological advancements and integration patterns that emerge during this process. With the introduction of user- and device-centric authentication methods like distributed identity and RF fingerprinting in the Identity and Device areas, there is a growing trend towards strengthening trust even in domains where distrust is prevalent. In the Network and Application domains, the focus is on using micro-segmentation and SDN to segment and control internal traffic flows, while dynamically enforcing the principle of least privilege. In the Data, Visibility, and Orchestration domains, AI analysis is being applied in real-time, leveraging log and visibility data, and orchestration is automating policy execution and response. In conclusion, it is clear that each pillar of ZTA operates in tandem with the others, rather than as isolated components within the CDS environment. This fusion structure demonstrates its ability to function as a unified security strategy that balances trust with comprehensive coverage of diverse domains. Full article

Grain aging during storage leads to quality deterioration and significant economic losses. Traditional analytical approaches are often labor-intensive, slow, and inadequate for modern intelligent grain storage management. This review summarizes recent advances in the intelligent discrimination of grain aging using volatile organic compound (VOC) fingerprints combined with machine learning (ML) techniques. It first outlines the biochemical mechanisms underlying grain aging and identifies VOCs as early and sensitive biomarkers for timely determination. The review then examines VOC determination methodologies, with a focus on headspace solid-phase microextraction coupled with gas chromatography-mass spectrometry (HS-SPME-GC-MS), for constructing volatile fingerprinting profiles, and discusses related method standardization. A central theme is the application of ML algorithms, including Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machines (SVM), Random Forest (RF), and Convolutional Neural Networks (CNN)) for feature extraction and pattern recognition in high-dimensional datasets, enabling effective discrimination of aging stages, spoilage types, and grain varieties. Despite these advances, key challenges remain, such as limited model generalizability, the lack of large-scale multi-source databases, and insufficient validation under real storage conditions. Finally, future directions are proposed that emphasize methodological standardization, algorithmic innovation, and system-level integration to support intelligent, non-destructive, real-time grain quality monitoring. This emerging framework provides a promising powerful pathway for enhancing global food security. Full article