External Data Research Articles

Chrysalis: decoding tissue compartments in spatial transcriptomics with archetypal analysis.

Dissecting tissue compartments in spatial transcriptomics (ST) remains challenging due to limited spatial resolution and dependence on single-cell reference data. We present Chrysalis, a computational method that rapidly uncovers tissue compartments through spatially variable gene (SVG) detection and archetypal analysis without requiring external reference data. Additionally, it offers a unique visualisation approach for swift tissue characterisation and provides access to the underlying gene expression signatures, enabling the identification of spatially and functionally distinct cellular niches. Chrysalis was evaluated through various benchmarks and validated against deconvolution, independently obtained cell type abundance data, and histopathological annotations, demonstrating superior performance compared to other algorithms on both in silico and real-world test examples. Furthermore, we showcased its versatility across different technologies, such as Visium, Visium HD, Slide-seq, and Stereo-seq.

Automatic localization and deep convolutional generative adversarial network-based classification of focal liver lesions in computed tomography images: A preliminary study.

Computed tomography of the abdomen exhibits subtle and complex features of liver lesions, subjectively interpreted by physicians. We developed a deep learning-based localization and classification (DLLC) system for focal liver lesions (FLLs) in computed tomography imaging that could assist physicians in more robust clinical decision-making. We conducted a retrospective study (approval no. EMRP-109-058) on 1589 patients with 17335 slices with 3195 FLLs using data from January 2004 to December 2020. The training set included 1272 patients (male: 776, mean age 62±10.9), and the test set included 317 patients (male: 228, mean age 57±11.8). The slices were annotated by annotators with different experience levels, and the DLLC system was developed using generative adversarial networks for data augmentation. A comparative analysis was performed for the DLLC system versus physicians using external data. Our DLLC system demonstrated mean average precision at 0.81 for localization. The system's overall accuracy for multiclass classifications was 0.97 (95% confidence interval [CI]: 0.95-0.99). Considering FLLs≤3cm, the system achieved an accuracy of 0.83 (95% CI: 0.68-0.98), and for size>3cm, the accuracy was 0.87 (95% CI: 0.77-0.97) for localization. Furthermore, during classification, the accuracy was 0.95 (95% CI: 0.92-0.98) for FLLs≤3cm and 0.97 (95% CI: 0.94-1.00) for FLLs>3cm. This system can provide an accurate and non-invasive method for diagnosing liver conditions, making it a valuable tool for hepatologists and radiologists.

Validation of Left Ventricular Filling Pressure Evaluation by Order of Tricuspid and Mitral Valve Opening in Patients With Atrial Fibrillation.

Accurate assessment of left ventricular filling pressure in patients with atrial fibrillation or flutter (AF) remains difficult. A novel 2-dimensional scoring system, visually assessing time difference between mitral valve and tricuspid valve opening (VMT) score, based on temporal analysis of early diastolic valve opening, could be applied to these patients. We aimed to determine the usefulness of the VMT score in patients with AF. We analyzed 119 consecutive patients with AF who underwent cardiac catheterization as a derivation cohort. The diagnostic performance of the VMT score was further evaluated in an external data set containing 189 patients with AF. Elevated left ventricular filling pressure was defined as a mean pulmonary arterial wedge pressure ≥15 mm Hg. The time sequence of atrioventricular valve opening was visually assessed and scored (0, tricuspid valve first; 1, simultaneous; 2, mitral valve first). When the inferior vena cava was dilated, 1 point was added, and the VMT score was finally graded as 0 to 3. Conventional Doppler parameters to estimate left ventricular filling pressure were also measured. Pulmonary arterial wedge pressure was elevated with an increase in the VMT score (0: 10±3, 1: 13±5, 2: 22±7, 3: 27±6 mm Hg; P<0.001), resulting in a significant rise in pulmonary arterial wedge pressure from VMT score 1 to 2. VMT≥2 predicted elevated pulmonary arterial wedge pressure with an accuracy of 87%, and the diagnostic accuracy of the VMT score was significantly higher than that of conventional Doppler parameters (C index, 0.88 versus 0.54-0.68; P<0.001). In addition, VMT ≥2 showed an incremental predictive value over plasma brain natriuretic peptide levels (C index, 0.79-0.93; P<0.001). In the external validation cohort, VMT≥2 demonstrated acceptable accuracy of 72%. VMT scoring was a useful echocardiographic marker of elevated left ventricular filling pressure and had an incremental benefit over practical biomarkers in patients with AF.

Utilizing Artificial Intelligence for Microbiome Decision-Making: Autism Spectrum Disorder in Children from Bosnia and Herzegovina

Background/Objectives: The study of microbiome composition shows positive indications for application in the diagnosis and treatment of many conditions and diseases. One such condition is autism spectrum disorder (ASD). We aimed to analyze gut microbiome samples from children in Bosnia and Herzegovina to identify microbial differences between neurotypical children and those with ASD. Additionally, we developed machine learning classifiers to differentiate between the two groups using microbial abundance and predicted functional pathways. Methods: A total of 60 gut microbiome samples (16S rRNA sequences) were analyzed, with 44 from children with ASD and 16 from neurotypical children. Four machine learning algorithms (Random Forest, Support Vector Classification, Gradient Boosting, and Extremely Randomized Tree Classifier) were applied to create eight classification models based on bacterial abundance at the genus level and KEGG pathways. Model accuracy was evaluated, and an external dataset was introduced to test model generalizability. Results: The highest classification accuracy (80%) was achieved with Random Forest and Extremely Randomized Tree Classifier using genus-level taxa. The Random Forest model also performed well (78%) with KEGG pathways. When tested on an independent dataset, the model maintained high accuracy (79%), confirming its generalizability. Conclusions: This study identified significant microbial differences between neurotypical children and children with ASD. Machine learning classifiers, particularly Random Forest and Extremely Randomized Tree Classifier, achieved strong accuracy. Validation with external data demonstrated that the models could generalize across different datasets, highlighting their potential use.

Deciphering Isotopic Fine Structures of Silylated Compounds in Gas Chromatography-Vacuum Photoionization Orbitrap Mass Spectrometry of Bio-Oils.

We introduce vacuum resonance-enhanced multiphoton ionization (REMPI) with high-resolution Orbitrap Fourier transform mass spectrometry (FTMS) for analyzing silylated polar compounds. UV laser radiation at 248 nm sensitively and selectively targets aromatic constituents, while high-resolution mass spectrometry (HRMS) enables high-performance mass spectrometric detection. This workflow enhances the detection confidence of polar constituents by identifying unique isotopologue patterns, including at the isotopic fine structure (IFS) level, in analytical standards and complex bio-oils. A direct and derivatized gas chromatography (GC) procedure on a polar standard component mixture allowed us to explore the general ionization and detection characteristics of REMPI FTMS. HRMS enabled the examination of the complex isotopologue profiles, revealing distinct patterns for the CHOxSiy-class compounds. Particularly in complex mixtures, this isobaric/isonucleonic complexity exceeded the classical mass resolution capabilities of the employed Orbitrap D30 series and prompted the usage of prolonged transients via an external data acquisition system. This procedure substantially improved mass spectrometric results by recording the unreduced time-domain transient data for up to 2 s. Notably, the ability to distinguish diagnostic isotopic pairs, such as 12C/29Si vs 13C/28Si with a mass split of ∼3.79 mDa and 13C12C/28Si29Si vs 13C2/28Si2, with an approximate mass difference of ∼3.32 mDa, demonstrates a significant and expected performance improvement. Finally, we benchmark the GC HRMS methodology to identify silylated oxygenated and nitrogen-containing constituents in ultracomplex bio-oil samples. The presented approach of utilizing the silicon isotope pattern and unique isotopologue mass splits for increasing attribution confidence can be applied beyond bio-oils toward the general GC analyses of polar oxygenates.

High-Resolution Spaceborne SAR Geolocation Accuracy Analysis and Error Correction

High-accuracy geolocation is crucial for high-resolution spaceborne SAR images. Most advanced SAR satellites have a theoretical geolocation accuracy better than 1 m, but this may be unrealizable with less accurate external data, such as atmospheric parameters and ground elevations. To investigate the actual SAR geolocation accuracy in common applications, we analyze the properties of different geolocation errors, propose a geolocation procedure, and conduct experiments on TerraSAR-X images and a pair of Tianhui-2 images. The results show that based on GNSS elevations, the geolocation accuracy is better than 1 m for TerraSAR-X and 2 m/4 m for the Tianhui-2 reference/secondary satellites. Based on the WorldDEM and the SRTM, additional geolocation errors of 2 m and 4 m are introduced, respectively. By comparing the effectiveness of different tropospheric correction methods, we find that the GACOS mapping method has advantages in terms of resolution and computational efficiency. We conclude that tropospheric errors and ground elevation errors are the primary factors influencing geolocation accuracy, and the key to improving accuracy is to use higher-accuracy DEMs. Additionally, we propose and validate a geolocation model for the Tianhui-2 secondary satellite.

ELPGPT: Large Language Models Enhancing Link Prediction in Electrical Knowledge Graph

Graphs provide essential means for organizing and analyzing complex equipment data. Although link prediction techniques have been widely applied to enhance knowledge graphs, existing methods still show room for improvement in accuracy, especially when dealing with sparse data. To address this, we introduce ELPGPT (Large Language Models Enhancing Link Prediction in Electrical Equipment Knowledge Graph), a novel approach that integrates large language models into link prediction to enhance the accuracy of relation prediction within electrical equipment knowledge graphs. The core of the ELPGPT method lies in the combination of large language models with traditional knowledge graph link prediction techniques. By leveraging the deep semantic understanding capabilities of large language models, this method effectively extracts relational features and enhances the handling of sparse data. Additionally, we employ a Retrieval-Augmented Generation (RAG) approach, which, by integrating external data sources, further enhances the precision and relevance of predictions. Experiments on the Electrical Equipment Knowledge Graph (EEKG) demonstrate that ELPGPT significantly improves performance across several metrics, including Hit@k, Mean Rank (MR), and Mean Reciprocal Rank (MRR). These results validate the effectiveness and potential applications of this method in the domain of link prediction for electrical equipment knowledge graphs.

On the Implications of Ground‐Based High‐Definition Imaging of Io's Surface

AbstractThe capability to observe temporal changes on Io's surface at optical wavelengths has recently been demonstrated by Conrad et al. (2024, https://doi.org/10.1029/2024GL108609) using new instrumentation at the Large Binocular Telescope. Monitoring of Io's surface morphology would be impactful since preexisting metrics of the degree, location and composition of Io's plume activities are severely limited. Relationships with external data sets appear especially fruitful. Comparisons with spatially resolved data on gas distributions and thermal hots spots would better characterize composition and chemistry in Io's volcanic plumes. Comparisons with measurements remote from Io are posed to advance our understanding of atmospheric escape and how eruptions connect to transient enhancements at disparate size and time scales in the extended neutral clouds and plasma torus.

StructuGraphRAG: Structured Document-Informed Knowledge Graphs for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external data sources beyond their training sets and querying predefined knowledge bases to generate accurate, context-rich responses. Most RAG implementations use vector similarity searches, but the effectiveness of this approach and the representation of knowledge bases remain underexplored. Emerging research suggests knowledge graphs as a promising solution. Therefore, this paper presents StructuGraphRAG, which leverages document structures to inform the extraction process and constructs knowledge graphs to enhance RAG for social science research, specifically using NSDUH datasets. Our method parses document structures to extract entities and relationships, constructing comprehensive and relevant knowledge graphs. Experimental results show that StructuGraphRAG outperforms traditional RAG methods in accuracy, comprehensiveness, and contextual relevance. This approach provides a robust tool for social science researchers, facilitating precise analysis of social determinants of health and justice, and underscores the potential of structured document-informed knowledge graph construction in AI and social science research.

Drug Efficacy Estimation for Follow-on Companion Diagnostic Devices Through External Studies.

A therapeutic product is usually not suitable for all patients but for only a subpopulation. The safe and effective use of such a therapeutic product requires the co-approval of a companion diagnostic device which can be used to identify suitable patients. While the first-of-a-kind companion diagnostic device is often developed in conjunction with its intended therapeutic product and simultaneously validated through a randomized clinical trial, there remains room for the innovation of new and improved follow-on companion diagnostic devices designed for the same therapeutic product. However, conducting a new randomized trial or a bridging study for the follow on companion devices may be unethical, expensive or unpractical. Hence, there arises a need for an external study to evaluate the concordance between the FDA-approved comparator companion diagnostic device (CCD) and the subsequent follow-on companion diagnostic devices (FCD), indirectly validating the latter. In this article, we introduce a novel external study design, referred to as the targeted treatment design, as an extension of the existing concordance design. Additionally, we present corresponding statistical analysis methods. Our approach combines the CCD randomized trial data and the FCD external study data, enabling the estimation of drug efficacy within the FCD+ and FCD- subpopulations-the parameters crucial for the validation of the FCD. Theoretical results and simulation studies validate the proposed methods and we further illustrate the proposed methods through an application in a real example of non-small-cell lung cancer.

Recovering Lost Revenue by Augmenting Internal Customer Data with External Data for Accurate Invoicing for Large B2B Enterprises

Recovering Lost Revenue by Augmenting Internal Customer Data with External Data for Accurate Invoicing for Large B2B Enterprises

Личностные особенности и самоотношение лиц с психогенным перееданием

&lt;p&gt;&lt;strong&gt;Background. &lt;/strong&gt;According to the World Health Organization, in 2023, excess weight was observed in 2,5 billion adults aged 18 and older. Individuals with obesity suffer from chronic somatic diseases, face social isolation. Understanding the psychological and social factors behind weight gain allows us to develop effective programs to prevent obesity and help people lose weight. &lt;strong&gt;Objective.&lt;/strong&gt; The aim of this study is to analyze the analysis of personality traits and self-attitudes in individuals with excess body mass. &lt;strong&gt;Hypothesis.&lt;/strong&gt; Individuals with psychogenic overeating have an increased level of neuroticism, perfectionism and internal conflict, as well as reduced self-acceptance. &lt;strong&gt;Materials and methods. &lt;/strong&gt;101 people with eating disorders were examined. All respondents were divided into three groups according to the criterion of body mass index (BMI): 1 group - 33 people with pre-obesity and obesity of the first degree, average age 40&amp;plusmn;13 years; 2 group - 20 people with second degree obesity, average age 35&amp;plusmn;12 years; group 3 - 48 people with third degree obesity, average age 44&amp;plusmn;10 years. The socio-demographic characteristics of the respondents and medical documentation data were studied. Psychological testing was conducted using: the KON-2006 Neurotic Personality Questionnaire to assess neurotic personality traits, the Multidimensional Perfectionism Scale (MPS), a questionnaire to study self-esteem. &lt;strong&gt;Results. &lt;/strong&gt;Analysis of the study results showed a high level of neuroticism for individuals with different BMIs in all groups, the violation of self-attitude is primarily associated with the perception of one's appearance, perfectionism is not a personal feature associated with psychogenic overeating. Low self-esteem of external data is combined in them with narcissism and a positive assessment of their personal characteristics. &lt;strong&gt;Conclusions. &lt;/strong&gt;The results obtained can be used to develop and improve the effectiveness of psychological weight correction programs for psychogenic overeating, based on taking into account the personal factors of obesity.&lt;/p&gt;

Liver transcriptome analysis reveals PSC-attributed gene set associated with fibrosis progression

BackgroundPrimary Sclerosing Cholangitis (PSC) is a chronic heterogenous cholangiopathy with unknown etiology where chronic inflammation of the bile ducts leads to multifocal biliary strictures and biliary fibrosis with consecutive cirrhosis development. We here aimed to identify a PSC-specific gene signature associated with biliary fibrosis development. MethodsWe performed RNA-sequencing of 47 liver biopsies from people with PSC (n = 16), primary biliary cholangitis (PBC, n = 15), and metabolic dysfunction-associated steatotic liver disease (MASLD, n = 16) with different fibrosis stages to identify a PSC-specific gene signature associated with biliary fibrosis progression. For validation, we compared an external transcriptome data set of liver biopsies from people with PSC (n = 73) with different fibrosis stages (DOI: 10.1002/hep.31488; baseline samples from NCT01672853). ResultsDifferential gene expression analysis of the liver transcriptome from PSC patients with advanced versus early fibrosis revealed 431 genes associated with fibrosis development. Of those, 367 were identified as PSC-associated when compared to PBC or MASLD. Validation against an external data set of 73 liver biopsies from PSC patients with different fibrosis stages led to a condensed set of 150 (out of 367) DEGs. Cell type specificity assignment of those genes by using published single cell RNA-seq data revealed genetic disease drivers expressed by cholangiocytes (e.g. CXCL1, SPP1), fibroblasts, innate and adaptive immune cells while deconvolution along fibrosis progression of the PSC, PBC, MASLD samples highlighted an early involvement of macrophage- and neutrophil-associated genes in PSC fibrosis. ConclusionWe reveal a PSC-attributed gene signature associated with biliary fibrosis development that may enable the identification of potential new biomarkers and therapeutic targets in PSC-related fibrogenesis. IMPACT AND IMPLICATIONSPrimary sclerosing cholangitis (PSC) is an inflammatory liver disease that is characterized by multifocal inflammation of bile ducts and subsequent biliary fibrosis. Herein, we identify a PSC-specific gene set of biliary fibrosis progression attributing to a uniquely complex milieu of different cell types, including innate and adaptive immune cells while neutrophils and macrophages showed an earlier involvement in fibrosis initiation in PSC in contrast to PBC and MASLD. Thus, our unbiased approach lays an important groundwork for further mechanistic studies for research into PSC-specific fibrosis.

Incorporating external controls in the design of randomized clinical trials: a case study in solid tumors

BackgroundThe use of historical external control data in clinical trials has grown in interest and needs when considering the design of future trials. Hybrid control designs can be more efficient to achieve the same power with fewer patients and limited resources. The literature is sparse on appropriate statistical methods which can account for the differences between historical external controls and the control patients in a study. In this article, we illustrate the analysis framework of a clinical trial if a hybrid control design was used after determining an RCT may not be feasible.MethodsWe utilize two previously completed RCTs in nonsquamous NSCLC and a nationwide electronic health record derived de-identified database as examples and compare 5 analysis methods on each trial, as well as a set of simulations to determine operating characteristics of such designs.ResultsIn single trial estimation, the Case Weighted Adaptive Power Prior provided estimated treatment hazard ratios consistent with the original trial’s conclusions with narrower confidence intervals. The simulation studies showed that the Case Weighted Adaptive Power Prior achieved the highest power (and well controlled type-1 error) across all 5 methods with consistent study sample size.ConclusionsBy following the proposed hybrid control framework, one can design a hybrid control trial transparently and accounting for differences between control groups while controlling type-1 error and still achieving efficiency gains from the additional contribution from external controls.

Unveiling Novel Hybrids Quinazoline/Phenylsulfonylfuroxan Derivatives with Potent Multi‐Anticancer Inhibition: DFT and In Silico Approach Combining 2D‐QSAR, Molecular Docking, Dynamics Simulations, and ADMET Properties

AbstractIn this work, the biological activities of 29 novel quinazoline/phenylsulfonylfuroxan derivatives (1a–z, 1aa, 1ab, 2a, 2b, 2d, and 2f) were computationally investigated as potential anti‐cancer inhibitors against five cell lines, i.e., H1975, MCF‐7, Eca‐109, MGC‐803, and A549, which are involved in various diseases, including lung, breast, esophageal squamous carcinoma, and gastric cancer. The 2D‐QSAR predictive approach, exploiting multiple linear regression (MLR) models and rigorous internal and external cross‐validation, showed a correlation factor R2 of range: 0.68−0.82. Moreover, the MLR‐derived R2test and Y randomization (R2rand) values for the five cell lines are higher than 0.60 and less than 0.3, respectively, indicating a strong alignment with the internal and external validation data. New 70 quinazoline hybrids based on the most effective in vivo 1q inhibitor were designed, and their pIC50 activity was predicted. The best‐scoring 15 (N1–N15) compounds were further evaluated using molecular docking and dynamics simulations (100 ns) with the VEGFR‐2 kinase target (PDB code: 3U6J). All the data sets accurately predict the strongest binding affinity for the selected (N6, N7, N9, and N11) molecules, as evidenced by the highest docking score, hydrogen bond energy, and significant amino acid steric interactions. Furthermore, the RMS/RMSF/Rg dynamics parameters show that the formed complexes are satisfactorily stable. The ADMET properties indicate that the selected new ligands have shown a promising drug‐like profile and can be considered potential candidates for future anti‐cancer therapies, with perspective validating their anticancer activity by in vitro and in vivo studies.

Integration analysis using bioinformatics and experimental validation on cellular signalling for sex differences of hypertrophic cardiomyopathy.

There is a paucity of research examining the molecular mechanisms underlying sex differences of clinical phenotypes and the prognosis in hypertrophic cardiomyopathy (HCM). The dataset GSE36961 was retrieved from Gene Expression Omnibus (GEO) database and comprehensive bioinformatics was employed to identify the core genes linked to sex differences in HCM patients. Additionally, gene set enrichment analysis (GSEA) was conducted to detect downstream signalling pathways. Furthermore, experimental validation was carried out using hearts from spontaneously hypertensive rats (SHRs). A comprehensive analysis revealed the identification of 208 differentially expressed genes (DEGs) in female patients with HCM with a notable downregulation of seven core genes. Notably, there were sex differences in the expression of ras dexamethasone-induced protein 1 (RASD1) and myosin 6 (MYH6) in HCM. Gene ontology (GO) analysis and GSEA demonstrated an enrichment of autophagy-related processes in disease progression in HCM females. Specifically, spearman's correlation analysis revealed a positive correlation between nicotinamide phosphoribosyl transferase (NAMPT) and RASD1 levels, particularly among female patients (R = 0.569, p < 0.001). Additionally, animal models confirmed that cardiac hypertrophy was more pronounced in SHR females compared to males. SHR females exhibited lower mRNA and protein expressions of RASD1 and NAMPT, which were associated with impaired autophagy. In this study, bioinformatics and validation using external data sets and animal models of left ventricular hypertrophy suggested that the RASD1/NAMPT axis is potentially a crucial mechanism underlying the elevated risk of cardiovascular disorders in HCM females, also pointing potentially prognostic biomarkers.

Estimating Stellar Atmospheric Parameters and [α/Fe] for LAMOST O-M-type Stars Using a Spectral Emulator

In this paper, we developed a spectral emulator based on the Mapping Nearby Galaxies at Apache Point Observatory Stellar Library (MaStar) and a grouping optimization strategy to estimate effective temperature (T eff), surface gravity (log g), metallicity ([Fe/H]), and the abundance of alpha elements with respect to iron ([α/Fe]) for O-M-type stars within the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) low-resolution spectra. The primary aim is to use a rapid spectral-fitting method, specifically the spectral emulator with the grouping optimization strategy, to create a comprehensive catalog for stars of all types within LAMOST, addressing the shortcomings in parameter estimations for both cold and hot stars present in the official LAMOST AFGKM-type catalog. This effort is part of our series of studies dedicated to establishing an empirical spectral library for LAMOST. Experimental results demonstrate that our method is effectively applicable to parameter prediction for LAMOST, with the single-machine processing time within 70 hr. We observed that the internal error dispersions for T eff, log g, [Fe/H], and [α/Fe] across different spectral types lie within the ranges of 15–594 K, 0.03–0.27 dex, 0.02–0.10 dex, and 0.01–0.04 dex, respectively, indicating a good consistency. A comparative analysis with external data highlighted deficiencies in the official LAMOST catalog and issues with MaStar parameters, as well as potential limitations of our method in processing spectra with strong emission lines and bad pixels. The derived atmospheric parameters as a part of this work are available via doi:10.12149/101402.

Identifying periods impacted by sewer inflow and infiltration using time series anomaly detection

Accurate diagnosis of sewer inflow and infiltration (I/I) is crucial for ensuring the safe transportation of sewage and the stability of wastewater treatment processes. Identifying periods impacted by I/I is essential for I/I diagnosis, but current methods lack a standard criterion and require adaptation to specific conditions, resulting in low accuracy, complexity, and limited generalizability. This paper proposes a novel approach to distinguish I/I periods from time series of sewer measurements based on anomaly detection theory through an iterative use of a time-series reconstruction model. This method eliminates the need for external data such as rainfalls and avoids intensive manual data analysis. Operating directly on in-sewer data, it enhances accuracy compared to existing approaches and is applicable to various external factors such as rainfall, snowmelt, and seawater intrusion. The method can be applicable to a broad range of monitoring data, including flow rate, temperature, and conductivity. Validated through simulation studies and demonstrated via real-life applications, this method offers an efficient solution for I/I detection, facilitating further I/I diagnosis, including I/I quantification and location identification.

Mass Spectrometry Probe Combined with Machine Learning to Capture the Relationship between Metabolites and Mitochondrial Complex Activity at the Whole-Cell Level.

Mitochondrial complex activity controls a multitude of physiological processes by regulating the cellular metabolism. Current methods for evaluating mitochondrial complex activity mainly focus on single metabolic reactions within mitochondria. These methods often require fresh samples in large quantities for mitochondria purification or intact mitochondrial membranes for real-time monitoring. Confronting these limitations, we shifted the analytical perspective toward interactive metabolic networks at the whole-cell level to reflect mitochondrial complex activity. To this end, we compiled a panel of mitochondrial respiratory chain-mapped metabolites (MRCMs), whose perturbations theoretically provide an overall reflection on mitochondrial complex activity. By introducing N-dimethyl-p-phenylenediamine and N-methyl-p-phenylenediamine as a pair of mass spectrometry probes, an ultraperformance liquid chromatography-tandem mass spectrometry method with high sensitivity (LLOQ as low as 0.2 fmol) was developed to obtain accurate quantitative data of MRCMs. Machine learning was then combined to capture the relationship between MRCMs and mitochondrial complex activity. Using Complex I as a proof-of-concept, we identified NADH, alanine, and phosphoenolpyruvate as metabolites associated with Complex I activity based on the whole-cell level. The effectiveness of using their concentrations to reflect Complex I activity was further validated in external data sets. Hence, by capturing the relationship between metabolites and mitochondrial complex activity at the whole-cell level, this study explores a novel analytical paradigm for the interrogation of mitochondrial complex activity, offering a favorable complement to existing methods particularly when sample quantities, type, and treatment timeliness pose challenges. More importantly, it shifts the focus from individual metabolic reactions within mitochondria to a more comprehensive view of an interactive metabolic network, which should serve as a promising direction for future research into the functional architecture between mitochondrial complexes and metabolites.

Enhancing Predictive Maintenance of Power Transformers Through Machine Learning Approaches

This paper focuses on the use of machine learning algorithms to assist in predictive maintenance, aiming to reduce downtime and associated costs for electrical equipment. It introduces two machine learning predictive indicators: the Chromatographic Assay Indicator (CAI) and the Electrical Failure Risk Indicator (EFRI), which leverage chromatographic and sensor data, respectively. The CAI indicator was trained on external data, and its generalization capability was assessed using company-specific chromatographic data with expert assistance. The evaluation involved two heuristics, both focusing on keyword identification in free-text diagnoses. Results showed over 90% accuracy in predicting failures in reactors and power transformers, and an AUC of nearly 85% for reactors. Additionally, CAI outperformed classical Dissolved Gas Analysis (DGA) methods. On the other hand, the EFRI indicator was trained using company’s internal data from a monitoring system of operational sensors and maintaining power transformer data. The classification model achieved over 95% accuracy and an AUC of almost 90% on the test set. These results indicate that both indicators can be integrated into a solution to support maintenance specialists in their decision-making processes.