The multi-scale study of rock properties is a necessary step in the planning of oil and gas reservoir developments. The amount of core samples available for research is usually limited, and some of the samples can be distracted. The investigation of core reconstruction possibilities is an important task. An approach to the real-size reconstruction of porous media with a given (target) porosity and permeability by controlling the parameters of FFF 3D printing using CT images of the original core is proposed. Real-size synthetic core specimens based on CT images were manufactured using FFF 3D printing. The possibility of reconstructing the reservoir properties of a sandstone core sample was proven. The results of gas porometry measurements showed that the porosity of specimens No.32 and No.46 was 13.5% and 12.8%, and the permeability was 442.3 mD and 337.8 mD, respectively. The porosity of the original core was 14% and permeability was 271 mD. It was found that changing the layer height and nozzle diameter, as well as the retract and restart distances, has a direct effect on the porosity and permeability of synthetic specimens. This study shows that porosity and permeability of synthetic specimens depend on the flow of the material and the percentage of overlap between the infill and the outer wall. Full article

Battery cell finalization is a crucial process chain in battery manufacturing, contributing to a significant share of CAPEX and OPEX. Thus, there is a high cost-saving potential by improving the process chain. This research paper investigates various crucial facets of the cell finalization process in battery cell production through an expert survey. These include investment cost allocation, potential cost savings in sub-processes, reject generation, early detection of faulty cells, quality measurement techniques, and the utilization of inline data for early quality determination and real-time process control during the formation process. A solution approach for the implementation of electrochemical impedance spectroscopy for inline early quality determination is given. The results yield valuable insights for optimizing the formation process and enhancing product quality. Full article

Traditionally, the assessment of heavy metal concentrations using remote sensing technology is sample-intensive, with expensive model development. Using a mining area case study of Daxigou, China, we propose a cross-time-domain transfer learning model to monitor heavy metal pollution using samples collected from different time domains. Specifically, spectral indices derived from Landsat 8 multispectral images, terrain, and other auxiliary data correlative to soil heavy metals were prepared. A cross time-domain sample transfer learning model proposed in the paper based on the TrAdaBoost algorithm was used for the Cu content mapping in the topsoil by selective use of soil samples acquired in 2017 and 2019. We found that the proposed model accurately estimated the concentration of Cu in the topsoil of the mining area in 2019 and performed better than the traditional TrAdaBoost algorithms. The goodness of fit (R²) of the test set increased from 0.55 to 0.66; the relative prediction deviation (RPD) increased from 1.37 to 1.76; and finally, the root-mean-square deviation (RMSE), decreased from 8.33 to 7.24 mg·kg⁻¹.The proposed model is potentially applicable to more accurate and inexpensive monitoring of heavy metals, facilitating remediation-related efforts. Full article

Nanomagnetism and spintronics are currently active areas of research, with one of the main goals being the creation of low-energy-consuming magnetic memories based on nanomagnet switching. These types of devices could also be implemented in neuromorphic computing by crafting artificial neurons (ANs) that emulate the characteristics of biological neurons through the implementation of neuron models such as the widely used leaky integrate-and-fire (LIF) with a refractory period. In this study, we have carried out numerical simulations of a 120 nm diameter, 250 nm length ferromagnetic nanowire (NW) with the aim of exploring the design of an artificial neuron based on the creation and destruction of a Bloch-point domain wall. To replicate signal integration, we applied pulsed trains of spin currents to the opposite faces of the ferromagnetic NW. These pulsed currents (previously studied only in the continuous form) are responsible for inducing transitions between the stable single vortex (SV) state and the metastable Bloch point domain wall (BP-DW) state. To ensure the system exhibits leak and refractory properties, the NW was placed in a homogeneous magnetic field of the order of mT in the axial direction. The suggested configuration fulfills the requirements and characteristics of a biological neuron, potentially leading to the future creation of artificial neural networks (ANNs) based on reversible changes in the topology of magnetic NWs. Full article

Bacterial infections are the second-leading cause of death, globally. The prevalence of antibacterial resistance has kept the demand strong for the development of new and potent drug candidates. It has been demonstrated that Src protein tyrosine kinases (TKs) play an important role in the regulation of inflammatory responses to tissue injury, which can trigger the onset of several severe diseases. We carried out a search for novel Src protein TK inhibitors, commencing from reported highly potent anti-bacterial compounds obtained using the Mannich reaction, using a combination of e-pharmacophore modeling, virtual screening, ensemble docking, and core hopping. The top-scoring compounds from ligand-based virtual screening were modified using protein structure-based design approaches, and their binding to the Src homology-2 domain of p56^lck TK was predicted using ensemble molecular docking. We have prepared a database of 202 small molecules and have identified six novel top hits that can be subjected to further investigation. We have also performed in silico ADMET property prediction for the hit compounds. This combined computer-aided drug design approach can serve as a starting point for identifying novel TK inhibitors that could be further subjected to in vitro studies and validation of antimicrobial activity. Full article

Virtual Reality Exposure Therapy (VRET), particularly immersive Virtual Reality Exposure Therapy (iVRET), has gained attraction as an innovative approach in exposure therapy (ET), notably for some anxiety disorders with a fear of contamination component, such as spider phobia (SP) and obsessive–compulsive disorder (OCD). This systematic work investigates iVRET’s effectiveness in modulating disgust emotion—a shared aberrant feature across these disorders. Recent reviews have evaluated VRET’s efficacy against in vivo ET. However, emerging evidence also highlights iVRET’s potential in diminishing atypical disgust and related avoidance behaviors, expanding beyond traditional fear-focused outcomes. Our systematic synthesis, adhering to PRISMA guidelines, aims to fill this gap by assessing iVRET’s efficacy in regulating disgust emotion within both clinical and at-risk populations, identified through standardized questionnaires and subjective disgust ratings. This research analyzes data from eight studies on clinical populations and five on healthy populations, offering an insight into iVRET’s potential to mitigate the aberrant disgust response, a common transdiagnostic feature in varied psychopathologies. The findings support iVRET’s clinical relevance in disgust management, providing evidence for a broader therapeutic application of iVRET and pointing out the need for more focused and complete investigations in this emergent field. Full article

This study evaluates the efficacy of the salts sodium metabisulfite (SMB), ammonium bicarbonate, sodium bicarbonate, and potassium dihydrogen orthophosphate first in vitro against the main postharvest fruit rot fungi, Alternaria alternata, Botrytis cinerea, Penicillium italicum, and Penicillium digitatum. Results showed that 0.2% SMB completely inhibited the mycelium growth of the fungal species. Ammonium bicarbonate and sodium bicarbonate were less effective at 0.2% in inhibiting mycelial growth, ranging from 57.6% to 77.6%. The least effective was potassium dihydrogen orthophosphate. Experiments were also performed in vivo on wounded apples inoculated with the most pathogenic fungus, B. cinerea, and treated with SMB at concentrations of 0.2, 0.5, 1, 2, and 3%, both preventively and curatively. Results based on the decay size showed that SMB, when used as a preventive treatment, had a reduced efficacy, even with the highest concentration. However, this salt proved to be very effective at 0.5% in curative treatment since the decay was completely blocked. Our results suggest that the appropriate concentration of SMB for post-harvest treatment is 0.5% as a curative treatment. On the other hand, the 1% dose induced the onset of phytotoxicity around the wound. To assess the extent of the phytotoxicity reaction, higher concentrations of 1–4% SMB were applied to wounded fruit. Apples and oranges were inoculated or not with B. cinerea and P. digitatum, respectively. Doses of 1–4% induced phytotoxicity in the form of a discolored ring surrounding the wound on the epidermis of the fruit; this phytotoxicity enlarged as the concentration of SMB increased. The phytotoxic features were similar on apples and oranges. The methodological procedure made it possible to carry out a quantitative assessment of SMB phytotoxicity. This method is proposed as an easy-to-use technique for quantitatively estimating the phytotoxicity of antifungal compounds on post-harvest fruit. Full article

Circulating cfRNA in plasma has emerged as a fascinating area of research with potential applications in disease diagnosis, monitoring, and personalized medicine. Circulating RNA sequencing technology allows for the non-invasive collection of important information about the expression of target genes, eliminating the need for biopsies. This comprehensive review aims to provide a detailed overview of the current knowledge and advancements in the study of plasma cfRNA, focusing on its diverse landscape and biological functions, detection methods, its diagnostic and prognostic potential in various diseases, challenges, and future perspectives. Full article

The safe and efficient production of marine natural gas hydrates faces the challenges of seabed geological risk issues. Geological risk issues can be categorized from weak to strong threats in four aspects: sand production, wellbore instability, seafloor subsidence, and submarine landslides, with the potential risk of natural gas leakage, and the geological risk problems that can cause secondary disasters dominated by gas eruptions and seawater intrusion. If the gas in a reservoir is not discharged in a smooth and timely manner during production, it can build up inside the formation to form super pore pressure leading to a sudden gas eruption when the overburden is damaged. There is a high risk of overburden destabilization around production wells, and reservoirs are prone to forming a connection with the seafloor resulting in seawater intrusion under osmotic pressure. This paper summarizes the application of field observation, experimental research, and numerical simulation methods in evaluating the stability problem of the seafloor surface. The theoretical model of multi-field coupling can be used to describe and evaluate the seafloor geologic risk issues during depressurization production, and the controlling equations accurately describing the characteristics of the reservoir are the key theoretical basis for evaluating the stability of the seafloor geomechanics. It is necessary to seek a balance between submarine formation stability and reservoir production efficiency in order to assess the optimal production and predict the region of plastic damage in the reservoir. Prediction and assessment allow measures to be taken at fixed points to improve reservoir mechanical stability with the numerical simulation method. Hydrate reservoirs need to be filled with gravel to enhance mechanical strength and permeability, and overburden need to be grouted to reinforce stability. Full article

Transmission electron microscopy imaging provides a unique opportunity to inspect the detailed structure of infected lung cells with SARS-CoV-2. Unlike previous studies, this novel study aims to investigate COVID-19 classification at the lung cellular level in response to SARS-CoV-2. Particularly, differentiating between healthy and infected human alveolar type II (hAT2) cells with SARS-CoV-2. Hence, we explore the feasibility of deep transfer learning (DTL) and introduce a highly accurate approach that works as follows: First, we downloaded and processed 286 images pertaining to healthy and infected hAT2 cells obtained from the electron microscopy public image archive. Second, we provided processed images to two DTL computations to induce ten DTL models. The first DTL computation employs five pre-trained models (including DenseNet201 and ResNet152V2) trained on more than one million images from the ImageNet database to extract features from hAT2 images. Then, it flattens and provides the output feature vectors to a trained, densely connected classifier with the Adam optimizer. The second DTL computation works in a similar manner, with a minor difference in that we freeze the first layers for feature extraction in pre-trained models while unfreezing and jointly training the next layers. The results using five-fold cross-validation demonstrated that TFeDenseNet201 is 12.37× faster and superior, yielding the highest average ACC of 0.993 (F1 of 0.992 and MCC of 0.986) with statistical significance ( from a t-test) compared to an average ACC of 0.937 (F1 of 0.938 and MCC of 0.877) for the counterpart (TFtDenseNet201), showing no significance results ( from a t-test). Full article

This paper proposes transforming actual monitoring data into risk quantities and establishing a Long Short-Term Memory (LSTM) safety risk warning model for predicting the deformation of super-large and ultra-deep foundation pits in river–round gravel strata based on safety evaluation methods. Using this model, short-term deformation predictions at various monitoring points of the foundation pits are made and compared with monitoring data. The results from the LSTM safety risk warning model indicate an absolute error range between the predicted deformation values and on-site monitoring values of −0.24 to 0.16 mm, demonstrating the model’s accuracy in predicting pit deformation. Additionally, calculations reveal that both the overall risk level based on on-site monitoring data and the overall safety risk level based on predicted data are classified as level four. The acceptance criteria for the overall risk level of the foundation pit are defined as “unacceptable and requiring decision-making”, with the risk warning control scheme being “requiring decision-making, formulation of control, and warning measures”. These research findings offer valuable insights for predicting and warning about safety risks in similar foundation pit engineering projects. Full article

Major Depressive Disorder (MDD) is a significant neurological condition associated with aberrations in brain functional networks. Traditional studies have predominantly analyzed these from a network topology perspective. However, given the brain’s dynamic and complex nature, exploring its mechanisms from a network control standpoint provides a fresh and insightful framework. This research investigates the integration of network controllability and machine learning to pinpoint essential biomarkers for MDD using functional magnetic resonance imaging (fMRI) data. By employing network controllability methods, we identify crucial brain regions that are instrumental in facilitating transitions between brain states. These regions demonstrate the brain’s ability to navigate various functional states, emphasizing the utility of network controllability metrics as potential biomarkers. Furthermore, these metrics elucidate the complex dynamics of MDD and support the development of precision medicine strategies that incorporate machine learning to improve the precision of diagnostics and the efficacy of treatments. This study underscores the value of merging machine learning with network neuroscience to craft personalized interventions that align with the unique pathological profiles of individuals, ultimately enhancing the management and treatment of MDD. Full article

EpCAM is expressed in many epithelial tumors and is used for the distinction of malignant mesotheliomas from adenocarcinomas and as a surrogate pan-epithelial marker. A tissue microarray containing 14,832 samples from 120 different tumor categories was analyzed by immunohistochemistry. EpCAM staining was compared with TROP2 and CKpan. EpCAM staining was detectable in 99 tumor categories. Among 78 epithelial tumor types, the EpCAM positivity rate was ≥90% in 60 categories—including adenocarcinomas, neuroendocrine neoplasms, and germ cell tumors. EpCAM staining was the lowest in hepatocellular carcinomas, adrenocortical tumors, renal cell neoplasms, and in poorly differentiated carcinomas. A comparison of EpCAM and CKpan staining identified a high concordance but EpCAM was higher in testicular seminomas and neuroendocrine neoplasms and CKpan in hepatocellular carcinomas, mesotheliomas, and poorly differentiated non-neuroendocrine tumors. A comparison of EpCAM and TROP2 revealed a higher rate of TROP2 positivity in squamous cell carcinomas and lower rates in many gastrointestinal adenocarcinomas, testicular germ cell tumors, neuroendocrine neoplasms, and renal cell tumors. These data confirm EpCAM as a surrogate epithelial marker for adenocarcinomas and its diagnostic utility for the distinction of malignant mesotheliomas. In comparison to CKpan and TROP2 antibodies, EpCAM staining is particularly common in seminomas and in neuroendocrine neoplasms. Full article

The degradation and loss of natural wetlands has caused severe crises for wetland taxa. Meanwhile, constructed wetlands are expanding significantly and facing dramatic environmental changes. Exploring the responses of wetland organisms, particularly zooplankton, may have important implications for the management of wetlands. Environmental and zooplankton samples were collected from 34 subsidence wetlands created by underground coal mining across the North China Plain in August 2021. We used generalized linear models and redundancy analysis to test zooplankton responses to environmental variables, with the relative importance quantified by variation partitioning. We identified 91 species, divided into 7 functional groups, with the highest density of rotifer filter feeders (RF, 2243.4 ± 499.4 ind./L). Zooplankton species richness was negatively correlated with electrical conductivity (EC), chlorophyll-a, total phosphorus, and pH. The Shannon–Weiner and Pielou evenness indices were positively correlated with transparency and negatively correlated with the photovoltaic panel area (AS). Rotifer predators (RCs) and RF densities were positively correlated with cropland area and dissolved oxygen, but negatively correlated with AS. Small crustacean filter feeders positively correlated with AS, whereas medium crustacean feeders (MCFs) positively correlated with EC. AS was the most critical variable affecting the zooplankton community. Our study showed that the spatial pattern of zooplankton communities was shaped by environmental heterogeneity across the subsidence wetlands, providing implications for the management and conservation of these constructed wetlands. Full article

Alcoholism presents a significant health concern with notable socioeconomic implications. Alcohol withdrawal syndrome (AWS) can manifest when individuals cease or drastically reduce their alcohol consumption after prolonged use. Non-alcoholic fatty liver disease (NAFLD) is characterized by substantial lipid accumulation in the liver cells of individuals with no history of alcohol consumption. There is evidence suggesting an association between cognitive impairment and both conditions. This study aimed to evaluate cognitive impairment in patients with NAFLD and AWS using the Mini-Mental State Examination (MMSE). This study involved 120 patients admitted to two hospitals in Craiova, Romania. Results indicated that patients with NAFLD did not exhibit cognitive impairment as measured by MMSE (Mean = 29.27, SD = 0.785). Conversely, patients with AWS showed more pronounced cognitive dysfunction, with a mean MMSE score at admission of 16.60 ± 4.097 and 24.60 ± 2.832 after 2 weeks under treatment with Vitamins B1 and B6 and Cerebrolysin. Additionally, our findings suggested that cognitive dysfunction among alcohol consumers was correlated with the severity of clinical symptoms, as demonstrated by the severity of tremors in our study. The two-week period under treatment and alcohol withdrawal was insufficient for cognitive function to return to normal levels. Observational studies on longer periods of time are advised. Full article

Background and Objectives: Cardiac autonomic neuropathy (CAN) is a severe complication of diabetes mellitus (DM) strongly linked to a nearly five-fold higher risk of cardiovascular mortality. Patients with Type 2 Diabetes Mellitus (T2DM) are a significant cohort in which these assessments have particular relevance to the increased cardiovascular risk inherent in the condition. Materials and Methods: This study aimed to explore the subtle correlation between the Ewing test, Sudoscan-cardiovascular autonomic neuropathy score, and cardiovascular risk calculated using SCORE 2 Diabetes in individuals with T2DM. The methodology involved detailed assessments including Sudoscan tests to evaluate sudomotor function and various cardiovascular reflex tests (CART). The cohort consisted of 211 patients diagnosed with T2DM with overweight or obesity without established ASCVD, aged between 40 to 69 years. Results: The prevalence of CAN in our group was 67.2%. In the study group, according SCORE2-Diabetes, four patients (1.9%) were classified with moderate cardiovascular risk, thirty-five (16.6%) with high risk, and one hundred seventy-two (81.5%) with very high cardiovascular risk. Conclusions: On multiple linear regression, the SCORE2-Diabetes algorithm remained significantly associated with Sudoscan CAN-score and Sudoscan Nephro-score and Ewing test score. Testing for the diagnosis of CAN in very high-risk patients should be performed because approximately 70% of them associate CAN. Increased cardiovascular risk is associated with sudomotor damage and that Sudoscan is an effective and non-invasive measure of identifying such risk. Full article

Energy markets are crucial for integrating Distributed Energy Resources (DER) into modern power grids. However, this integration presents challenges due to the inherent variability and decentralized nature of DERs, as well as poorly adapted regulatory environments. This paper proposes a medium-term decision-making approach based on a comprehensive suite of computational tools for integrating DERs into Colombian energy markets. The proposed framework consists of modular tools that are aligned with the operation of a Commercial Virtual Power Plant (CVPP). The tools aim to optimize participation in bilateral contracts and short-term energy markets. They use forecasting, uncertainty management, and decision-making modules to create an optimal portfolio of DER assets. The suite’s effectiveness and applicability are demonstrated and analyzed through its implementation with heterogeneous DER assets across various operational scenarios. Full article

Exploring the combined effects of multisensory interactions in open spaces can help improve the comfort of campus environments. Nine typical spaces on a university campus in Fuzhou were selected for this study. Subjects perceived the environment and then completed an on-site subjective questionnaire. At the same time, meteorological data (global radiation, air temperature, globe temperature, wind speed, relative humidity, and illumination intensity) were measured to determine the interactions between visual and acoustic and thermal perceptions. Differences in the meteorological parameters between the measuring points were described using a one-way ANOVA and Tukey’s post hoc test, and a chi-square test of independence was used to determine significant associations between thermal, acoustic, and visual comfort, which in turn led to the study of interactions between visual, acoustic, and thermal comfort using a two-way ANOVA. The following conclusions were drawn: (1) the Thermal Comfort Vote (TCV) increased with the increasing Acoustic Comfort Vote (ACV) at all levels of thermal stress. (2) The highest and lowest Acoustic Sensation Vote (ASV) values for each sound type were derived from either “slightly cold” or “warm” conditions. Both the Thermal Comfort Vote (TCV) and the Acoustic Comfort Vote (ACV) were positively correlated. (3) When “neutral”, the Thermal Sensation Vote (TSV) increased with increasing illumination intensity (LUX). (4) The Sunlight Sensation Vote (SSV) increased with the increasing Universal Thermal Climate Index (UTCI) when illumination intensity (LUX) was moderate and bright. (5) The highest and lowest Acoustic Sensation Vote (ASV) values for each sound type came from either “slightly cold” or “warm” conditions. Full article

The objective of this study was to prepare zein–gum Arabic nanocapsules with rosehip oil (NC-RH), apply them to pork tenderloin, and analyze the changes in collagen structure under different conditions (pH 6.5 and 4.0) and temperatures (25 °C and 4 °C). NC-RHs were prepared using the nanoprecipitation method. Nanocapsules had a particle size of 423 ± 4.1 nm, a polydispersity index of 0.125 ± 3.1, a zeta potential value of −20.1 ± 0.41 mV, an encapsulation efficiency of 75.84 ± 3.1%, and backscattering (ΔBS = 10%); the antioxidant capacity of DPPH was 1052 ± 4.2 µM Eq Trolox and the radical scavenging capacity was 84 ± 0.4%. The dispersions exhibited Newtonian behavior at 25 °C and 4 °C. Incorporating NC-RH into acid marination benefited the tenderness, water-holding capacity, and collagen swelling, and favored changes in myofibrillar proteins corroborated with histological tests. The conditions with the best changes in pork tenderloin were a pH of 4.0 at 4 °C with an NC-RH-administered 11.47 ± 2.2% collagen area. Incorporating rosehip nanocapsules modifies collagen fibers and can be applied in pork marinades to increase the shelf life of a functional product. Full article

ZrCo alloy is easily poisoned by impurity gases such as O₂, CO, and CO₂, resulting in a deterioration in hydrogen storage performance. In this study, we conducted a comprehensive investigation into the adsorption and dissociation characteristics of oxygen on the ZrCo(110) surface using first-principles calculations. Previous studies indicated that the anti-disproportionation properties of ZrCo alloy can be significantly improved by Hf substitution, but the effect of Hf doping on the anti-poisoning properties has not been reported. We also examined the effect of Hf doping on the adsorption, dissociation, and diffusion characteristics of oxygen. It is found that on the ZrCo(110) surface, O₂ molecules are easily dissociated and then stably adsorbed at the hollow site. Oxygen atoms will fill the surface preferentially and then diffuse inward. The doping of Hf has an insignificant impact on the adsorption or dissociation behavior of oxygen in comparison to the pure ZrCo surface. However, a notable observation is that the doping of Hf resulted in a reduction in the diffusion barrier for oxygen from the surface to the subsurface by 0.61 eV. Consequently, our study suggests that doping Hf is not an advisable strategy for improving the ZrCo(110) surface’s resistance to O₂ poisoning because of improved oxygen permeability. Full article

Nitrogen is one of the important factors restricting the development of sesame planting and industry in China. Cultivating sesame varieties tolerant to low nitrogen is an effective way to solve the problem of crop nitrogen deficiency. To date, the mechanism of low nitrogen tolerance in sesame has not been elucidated at the transcriptional level. In this study, two sesame varieties Zhengzhi HL05 (ZZ, nitrogen efficient) and Burmese prolific (MD, nitrogen inefficient) in low nitrogen were used for RNA-sequencing. A total of 3964 DEGs (differentially expressed genes) and 221 DELs (differentially expressed lncRNAs) were identified in two sesame varieties at 3d and 9d after low nitrogen stress. Among them, 1227 genes related to low nitrogen tolerance are mainly located in amino acid metabolism, starch and sucrose metabolism and secondary metabolism, and participate in the process of transporter activity and antioxidant activity. In addition, a total of 209 pairs of lncRNA-mRNA were detected, including 21 pairs of trans and 188 cis. WGCNA (weighted gene co-expression network analysis) analysis divided the obtained genes into 29 modules; phenotypic association analysis identified three low-nitrogen response modules; through lncRNA-mRNA co-expression network, a number of hub genes and cis/trans-regulatory factors were identified in response to low-nitrogen stress including GS1-2 (glutamine synthetase 1–2), PAL (phenylalanine ammonia-lyase), CHS (chalcone synthase, CHS), CAB21 (chlorophyll a-b binding protein 21) and transcription factors MYB54, MYB88 and NAC75 and so on. As a trans regulator, lncRNA MSTRG.13854.1 affects the expression of some genes related to low nitrogen response by regulating the expression of MYB54, thus responding to low nitrogen stress. Our research is the first to provide a more comprehensive understanding of DEGs involved in the low nitrogen stress of sesame at the transcriptome level. These results may reveal insights into the molecular mechanisms of low nitrogen tolerance in sesame and provide diverse genetic resources involved in low nitrogen tolerance research. Full article

When analyzing cancer sample genomes in clinical practice, many structural variants (SVs), other than single nucleotide variants (SNVs), have been identified. To identify driver variants, the leading candidates must be narrowed down. When fusion genes are involved, selection is particularly difficult, and highly accurate predictions from AI is important. Furthermore, we also wanted to determine how the prediction can make more reliable diagnoses. Here, we developed an explainable AI (XAI) suitable for SVs with gene fusions, based on the XAI technology we previously developed for the prediction of SNV pathogenicity. To cope with gene fusion variants, we added new data to the previous knowledge graph for SVs and we improved the algorithm. Its prediction accuracy was as high as that of existing tools. Moreover, our XAI could explain the reasons for these predictions. We used some variant examples to demonstrate that the reasons are plausible in terms of pathogenic basic mechanisms. These results can be seen as a hopeful step toward the future of genomic medicine, where efficient and correct decisions can be made with the support of AI. Full article