Automatic Extraction Method Research Articles

Deep orientated distance-transform network for geometric-aware centerline detection

The detection of structure centerlines from imaging data plays a crucial role in the understanding, application and further analysis of many diverse problems, such as road mapping, crack detection, medical imaging and biometric identification. In each of these cases, pixel-wise segmentation is not sufficient to understand and quantify overall graph structure and connectivity without further processing that can lead to compound error. We thus require a method for automatic extraction of graph representations of patterning. In this paper, we propose a novel Deep Orientated Distance-transform Network (DODN), which predicts the centerline map and an orientated distance map, comprising orientation and distance in relation to the centerline and allowing exploitation of its geometric properties. This is refined by jointly modeling the relationship between neighboring pixels and connectivity to further enhance the estimated centerline and produce a graph of the structure. The proposed approach is evaluated on a diverse range of problems, including crack detection, road mapping and superficial vein centerline detection from infrared/ color images, improving over the state-of-the-art by 2.1%, 10.9% and 17.3%/ 4.6% respectively in terms of quality, demonstrating its generalizability and performance in a wide range of mapping problems.

LCE-Calib: Automatic LiDAR-Frame/Event Camera Extrinsic Calibration With a Globally Optimal Solution

The combination of light detection and rangings (LiDARs) and cameras enables a mobile robot to perceive environments with multimodal data, becoming a key factor in achieving robust perception. Traditional frame cameras are sensitive to changing illumination conditions, motivating us to introduce novel event cameras to make LiDAR-camera fusion more complete and robust. However, to jointly exploit these sensors, the challenging extrinsic calibration problem should be addressed. This article proposes an automatic checkerboard-based approach to calibrate extrinsics between a LiDAR and a frame/event camera, where the following four contributions are presented: 1) we present an automatic feature extraction and checkerboard tracking method from LiDAR's point clouds; 2) we reconstruct realistic frame images from event streams, applying traditional corner detectors to event cameras; 3) we propose an initialization-refinement procedure to estimate extrinsics using point-to-plane and point-to-line constraints in a coarse-to-fine manner; 4) we introduce a unified and globally optimal solution to address two optimization problems in calibration. Our approach has been validated with extensive experiments on 19 simulated and real-world datasets and outperforms the state-of-the-art.

An automatic extraction method for geothermal radiation sources based on an LST retrieval algorithm and semantic network

Geothermal resources are efficient, renewable and clean energy sources, and their reservoirs are usually closely associated with high-temperature regions of the land surface. Current exploration methods primarily involve migrating traditional geological techniques, which fail to fully use the unique features of geothermal radiation characteristics. Thermal infrared remote-sensing imaging technology can capture and present areas with distinctive surface thermal radiation features, providing considerable significance as a guide for localization prior to field exploration. In this study, we propose a deep learning–based method for intelligently identifying and segmenting geothermal radiation sources from thermal infrared remote-sensing images, including data preparation and model training. To improve the localization drift and anomalous interference caused by the high complexity of the Earth's surface environment, this study uses a surface temperature retrieval algorithm to calculate the land surface temperature in the research area. The retrieval results are used to train the semantic segmentation model. In addition, a pixel-level geothermal spatial segmentation network (PGSSNet) is proposed to suppress the diffuse thermal radiation and reduce the broad and blurred white areas of images to exact locations. Once the training is completed, the model directly segments and extracts the actual range of thermal radiation sources from subsequent thermal infrared remote-sensing images without temperature retrieval and/or manual calibration.

A-298 Performance Analysis of Three Mpox Real Time PCR Kits With Lesion Swab Clinical Samples

Abstract Background The appearance of skin lesions can be a symptom of infection or reactivation of the HSV-1, HSV-2, VZV or T. pallidum or even monkeypox virus infection. Due to the contact-bound ease of spread of these pathogens, an accurate and fast diagnosis, such as PCR-based testing, is key to a good epidemiological management. The aim of this study was to determine the clinical performance of three qPCR assays. Methods A total of 334 cutaneous swabs collected from patients attended at the Hospital Universitario Miguel Servet were analysed using the three assays under study: VIASURE Herpes virus 1, Herpes virus 2 & Varicella Zoster Virus Real Time PCR Detection Kit, VIASURE Treponema pallidum Real Time PCR Detection Kit and VIASURE Mpox Real Time PCR Detection Kit. Samples were collected between December 2021 and November 2022. These samples were requested through the Biobanco del Sistema de Salud de Aragón (BSSA) and have the approval of the Aragón Ethics Committee (PI22/409). DNA/RNA extraction was performed using the automated extraction method magLEAD® 12gC instrument with the MagDEA Dx SV kit and amplification was performed using the thermocycler CFX96™ Real-Time PCR Detection System (BioRad). The obtained results were compared with the reference assays RealStar® Orthopoxvirus PCR Kit 1.0 (Altona) and Allplex™ Genital ulcer assay (Seegene®). Results After data analysis a very good overall agreement was obtained for all the studied targets. Conclusion The assays under study demonstrated to be a good tool for differential analysis in skin lesions compatible with HSV-1, HSV-2, VZV, T. pallidum or mpox virus infection. In addition, the shared thermal protocol of the assays allowed for the simultaneous detection in the sample, creating a personalized panel option for the user, as opposed to the reference assays employed, which required two separate analyses, taking longer to reach the full assessment of the sample.

B-267 Validation of a New Molecular Test to Quantify Plasma Cytomegalovirus Load

Abstract Background Cytomegalovirus (CMV) is a DNA virus that often causes severe disease in immunosuppressed or immunocompromised patients. With the expanding indications for immune-modulating agents and transplant patients, the number of patients at risk for developing CMV disease is increasing. Test results are used to determine active CMV disease, risk of developing active disease, response to therapy, risk of relapsed infection, and/or appropriate time to discontinue therapy. For this purpose, molecular assays are attractive because of their broad linear range and low limits of detection. CerTest Biotec has developed a quantitative real time PCR assay for the detection and quantification of cytomegalovirus in plasma samples. Methods Plasma-EDTA samples characterized as positive or negative and quantified by IU/ml were selected. The selected samples were collected from both male and female adults (except 1 sample of an infant) between July 2016 and December 2020. Two CE-marked molecular reference assays were used for the comparative analysis: RealStar® CMV PCR Kit 1.0 (Altona), using the CFX96™ Real-Time PCR Detection System (Bio-Rad) and extracted with the QIAamp® MinElute® Virus Spin Kit (QIAGEN); and cobas® CMV (Roche Diagnostics), using the cobas® 8800 system. VIASURE analysis was performed using the following workflow: the automated extraction method MagDEA® Dx SV with magLEAD® 12gC and CFX96™ Real-Time PCR Detection System (Bio-Rad). Results A total of 273 EDTA-plasma clinical samples were analysed, 120 samples were reported as CMV positive samples and quantified and 153 samples were reported as CMV negative samples. Comparative analysis determined >99% sensitivity and specificity. Regarding quantification, all methods obtained a correlation value of R2 ≥ 0.77. Conclusion With this study it was possible to observe that the VIASURE CMV q Real Time PCR Detection Kit present good clinical sensitivity and specificity compared to reference molecular assays results. No false positive results were observed. However, all variables employed on the workflow contribute to final quantification results and therefore should be taken into account as accumulative error in the calculation.

B-270 Validation of a New Molecular Assay for the Detection and Quantification of Hepatitis B Load in Plasma

Abstract Background Hepatitis B virus (HBV) is an enveloped DNA virus and is the most common worldwide cause of viral hepatitis in humans. It is primarily transmitted through blood or blood products. Although the diagnosis of hepatitis viral infections is usually performed with serological markers in blood, this technique has limitations and therefore the diagnosis of the disease by qPCR allows an improvement in the diagnosis of the infection, therapeutic decision making and evaluation of the response to treatment. Therefore, CerTest Biotec has developed a quantitative real-time PCR assay for the detection and quantification of hepatitis B virus in plasma samples. Methods Plasma-EDTA samples characterized as positive or negative and quantified in IU/ml were analyzed. The selected samples were collected from infants and adults of both sexes between September 2019 and August 2020. The origin of the population is diverse, with the majority being European. For comparative analysis, the cobas® HBV molecular assay (Roche Diagnostics) using the cobas® 8800 system was used. VIASURE analysis was performed using the following workflow: the MagDEA® Dx SV automated extraction method with magLEAD® 12gC and CFX96™ Opus Real-Time PCR Detection System (Bio-Rad). Results A total of 210 clinical EDTA plasma samples were tested, of which 110 were positive for hepatitis B virus and 100 were negative. The comparative analysis determined a sensitivity and specificity >99%. In addition, the positive predictive value (PPV) and negative predictive value were >99%. As for quantification, an R2 correlation value of 0.9095 was obtained. Conclusion This clinical evaluation demonstrated that the VIASURE HBV q Real Time PCR Detection Kit is a good tool for the clinical diagnosis of the virus as it has good sensitivity and specificity. No false positive or false negative results were observed. Moreover, the correlation of the quantification with the reference method gives a value of R2 > 0.9. Therefore, clinical diagnosis of hepatitis B virus by real-time PCR can encompass the limitations of the current diagnostic technique by serology.

DAHNGC: A Graph Convolution Model for Drug-Disease Association Prediction by Using Heterogeneous Network.

In the field of drug development and repositioning, the prediction of drug-disease associations is a critical task. A recently proposed method for predicting drug-disease associations based on graph convolution relies heavily on the features of adjacent nodes within the homogeneous network for characterizing information. However, this method lacks node attribute information from heterogeneous networks, which could hardly provide valuable insights for predicting drug-disease associations. In this study, a novel drug-disease association prediction model called DAHNGC is proposed, which is based on a graph convolutional neural network. This model includes two feature extraction methods that are specifically designed to extract the attribute characteristics of drugs and diseases from both homogeneous and heterogeneous networks. First, the DropEdge technique is added to the graph convolutional neural network to alleviate the oversmoothing problem and obtain the characteristics of the same nodes of drugs or diseases in the homogeneous network. Then, an automatic feature extraction method in the heterogeneous network is designed to obtain the features of drugs or diseases at different nodes. Finally, the obtained features are put into the fully connected network for nonlinear transformation, and the potential drug-disease pairs are obtained by bilinear decoding. Experimental results demonstrate that the DAHNGC model exhibits good predictive performance for drug-disease associations.

Water index and Swin Transformer Ensemble (WISTE) for water body extraction from multispectral remote sensing images

ABSTRACT Automatic surface water body mapping using remote sensing technology is greatly meaningful for studying inland water dynamics at regional to global scales. Convolutional neural networks (CNN) have become an efficient semantic segmentation technique for the interpretation of remote sensing images. However, the receptive field value of a CNN is restricted by the convolutional kernel size because the network only focuses on local features. The Swin Transformer has recently demonstrated its outstanding performance in computer vision tasks, and it could be useful for processing multispectral remote sensing images. In this article, a Water Index and Swin Transformer Ensemble (WISTE) method for automatic water body extraction is proposed. First, a dual-branch encoder architecture is designed for the Swin Transformer, aggregating the global semantic information and pixel neighbor relationships captured by fully convolutional networks (FCN) and multihead self-attention. Second, to prevent the Swin Transformer from ignoring multispectral information, we construct a prediction map ensemble module. The predictions of the Swin Transformer and the Normalized Difference Water Index (NDWI) are combined by a Bayesian averaging strategy. Finally, the experimental results obtained on two distinct datasets demonstrate that the WISTE has advantages over other segmentation methods and achieves the best results. The method proposed in this study can be used for improving regional to continental surface water mapping and related hydrological studies.

Glacier Change in the West Kunlun Main Peak Area from 2000 to 2020

Glaciers are sensitive indicators of climate change, and investigation of their dynamics is crucial for ensuring regional ecological security as well as disaster prevention and mitigation measures. Based on Landsat Thematic Mapper (TM)/Enhanced Thematic Mapper Plus (ETM+)/Operational Land Imager (OLI) imagery, the outlines and length of glaciers in the West Kunlun Main Peak Area (WKMPA) during 2000–2020 were obtained by combining a band ratio method with manual interpretation and an automatic extraction method for the glacier centerline, respectively. There were 440 glaciers in the WKMPA in 2020, covering an area of 2964.59 ± 54.87 km2, with an average length of 2916 ± 60 m. The glacier count increased due to division, while the area and length all exhibited a declining trend from 2000 to 2020, at rates of −0.04%·a−1 (24.83 km2) and −0.11%·a−1 (66 m), respectively. Glacier retreat was primarily observed during the early period (2000–2005). Except for glaciers located above an elevation of 6250 m, the glacier area decreased with each altitude interval from 2000 to 2020, and the rate of relative change in glacier area generally decreased with increasing altitude. Moreover, except for a slight increase in north-facing glaciers, the area of glaciers facing other orientations decreased during 2000–2020. The accuracy of the empirical formula fit for glacier length was highly dependent on glacier class, with greater precision observed for smaller glaciers and lower precision for larger valley-basin glaciers due to their complex morphological structures being neglected and only a single quantitative relationship being considered. There was a time lag of 12 years between temperature changes and glacier area response in this region. The mechanism by which glacier division affects glacier change is complex, requiring dissection of multiple factors such as area, length, and terminal elevation before and after division.

The response of glaciers and glacial lakes to climate change in the Southeastern Tibetan Plateau over the past three decades

AbstractWith global warming, changes in glaciers and glacial lakes on the Tibetan Plateau call for a serious inspection. The Southeastern Tibetan Plateau (SETP) is a typical monsoonal marine glacier area that is extremely vulnerable to climate change. It is affected by both humid and warm Indian Ocean currents. Outlines of glaciers and glacial lakes in SETP have been extracted from Landsat satellite images with an automatic extraction method based on image compositing with Google Earth Engine and Random Forest algorithm. Alongside the outlines, meteorological data have been collected from 1990 to 2021. The results show that since 1990 the glacier area of SETP has retreated by about 2165.33 km2 (~25.28%), the glacial lake area has increased by about 36.41 km2 (~21.45%), and their number has increased by 477 (~27.32%). The reliability and scientific validity of this study is proven by comparison with existing glacier inventories. By analyzing the meteorological data, the inverse correlation between the glacier area and temperature has been found. Despite decreases in cumulative precipitation, the glacial lake level rise and consequent area expansion have been observed. A fitting equation for the response pattern of glacier changes to temperature and precipitation change is presented and will provide a basis for future studies.

Miniaturization and Automation Protocol of a Urinary Organic Acid Liquid-Liquid Extraction Method on GC-MS.

The aim of this study was to improve the extraction method for urinary organic acids by miniaturizing and automating the process. Currently, manual extraction methods are commonly used, which can be time-consuming and lead to variations in test results. To address these issues, we reassessed and miniaturized the in-house extraction method, reducing the number of steps and the sample-to-solvent volumes required. The evaluated miniaturized method was translated into an automated extraction procedure on a MicroLab (ML) Star (Hamilton Technologies) liquid handler. This was then validated using samples obtained from the ERNDIM External Quality Assurance program. The organic acid extraction method was successfully miniaturized and automated using the Autosampler robot. The linear range for most of the thirteen standard analytes fell between 0 to 300 mg/L in spiked synthetic urine, with low (50 mg/L), medium (100 mg/L), and high (500 mg/L) levels. The correlation coefficient (r) for most analytes was >0.99, indicating a strong relationship between the measured values. Furthermore, the automated extraction method demonstrated acceptable precision, as most organic acids had coefficients of variation (CVs) below 20%. In conclusion, the automated extraction method provided comparable or even superior results compared to the current in-house method. It has the potential to reduce solvent volumes used during extraction, increase sample throughput, and minimize variability and random errors in routine diagnostic settings.

Comparative analyses of DNA extraction methods for whole blood quantification of HCMV DNAemia in patients with hematological diseases: false negative cases in manual method

Human cytomegalovirus (HCMV) DNA quantitation in whole blood (WB) by real-time or quantitative polymerase chain reaction (qPCR) is a highly sensitive and reproducible diagnostic procedure for monitoring HCMV DNAemia (DNAemia is the detection of DNA in samples of plasma, whole blood, isolated peripheral blood leukocytes or in buffy-coat specimens) in patients. We provided a comparative analysis of HCMV DNA extraction performance by two different techniques, one performed by an automated extractor and the other by a manual method. We observed that the automated extraction method allowed HCMV DNA detection in the presence of weak viremia while no differences are observed when the viral load is greater. Therefore, automated DNA extraction is a suitable and recommended protocol not only for early detection of HCMV infection but also for more accurate monitoring of HCMV DNAemia during post-therapy follow-up.

Feature extraction based on sparse graphs embedding for automatic depression detection

Background and Significance:Automatic detection of depression is crucial in today’s fast-paced, depression-prone society. However, the current diagnosis still relies on manual assessment by psychologists using the Patient Health Questionnaire-9 (PHQ-9), resulting in delays in early detection and treatment. This paper proposes an automatic feature extraction method called Sparse Graphs Embedding (SGE) for depression detection. The further goal is to integrate SGE into the healthcare system, enabling automatic depression diagnosis during physical examinations for early detection and early treatment. Method and Novelty:The method addresses several key challenges, including the maintenance of local information in the fNIRS signal space, the removal of outliers, and the rejection of redundant information between features. Specifically, it constructs two weighted graphs embedded in the between-class scatter and within-class scatter, preserving the neighborhood relationships within the data. To mitigate sensitivity to outliers, the ℓ2,1-norm is embedded in both the between-class and within-class scatter as a fundamental measure. Additionally, sparse orthogonality projections are employed to extract effective features for depression detection and eliminate redundant information. Results:Experimental results demonstrate promising detection rates of 86.1%, 82.8%, and 92.2% using functional near-infrared spectroscopy (fNIRS) under positive, neutral, and negative emotional stimuli, respectively. These rates surpass those achieved by other state-of-the-art methods. The promising results showcase the potential of fNIRS, and the weighted graph embedding approach sheds new light on depression detection.

Quantitative determination of organophosphorus, pyrethroid, and dithiolane pesticide residues in brown rice using supercritical fluid extraction and liquid chromatography-tandem mass spectrometry.

Supercritical fluid extraction (SFE) is a fast, versatile, and solvent-efficient automatic extraction method. Despite its advantages, the results of our proficiency tests imply that the applicability assessments of SFE for pesticide residues were insufficient. In this study, as analytical method using SFE was optimized and validated by testing the incurred and fortified brown rice samples with organophosphorus, pyrethroid, and dithiolane pesticides. Validation study using the incurred sample with etofenprox, fenitrothion, and isoprothiolane was performed by comparing the analytical results obtained using the SFE and solid-liquid extraction with homogenization (SLE), which is a well-validated official multi-residue extraction method. The tests on the fortified samples were also performed for seven pesticide residues, chlorpyrifos, diazinon, O-ethyl O-4-nitrophenyl phenylphosphonothioate (EPN), etofenprox, fenitrothion, isoxathion, and isoprothiolane, at three fortification levels, 0.001, 0.01, and 0.1 mg/kg. In the test on the incurred samples, optimized SFE-to-SLE analytical values (CSFE/CSLE) were in 99.2-100.1%, with RSD lower than 3%. In contrast, the analytical-to-spiked concentrations in the tests on the fortified samples were in 96.4-105.0%, with RSD lower than 8.8%. These results indicate that the proposed SFE method, which is well validated with the incurred brown rice sample, is useful for determining organophosphorus, pyrethroid, and dithiolane pesticide residues in brown rice. The proposed SFE method satisfies EU and Japanese maximum residue limits. The consumption of solvent can be reduced to one-fourth of that of SLE using the proposed SFE method.

Image-based analysis of single jersey loop parameters

Quality Control is crucial when it comes to fine and technical knits. Digital Twins are common in product design and are necessary for heat and mass flow simulations of textile fabrics. In both cases primarily, the exact geometry of the knitted loop is necessary for following processes. Wale spacing W and course spacing C are the essential geometrical characteristics of the representative unit cell of single jersey fabrics. The loop parameters can be obtained manually by counting loops per unit length or by microscopic measurements, which both are time consuming and are not applicable in integrated digital processes. Therefore, a new method for automatic extraction of major loop geometry parameters is described. A state-of-the-art method, which analyzes the microscopic images automatically, works with Fourier-Transformation of the image brightness and is used as a benchmark. The new loop-based method extracts the geometrical data from the distances between the center points of the loops. The methods are evaluated on single jersey fabrics of three different yarns. In addition, the impact of magnification on the measurement is shown for one fabric. The new method gives same results as manual measurements and even more precise results as the benchmark method.

Cartesian genetic programming for image analysis of the developing drosophila eye

Automatic feature extraction methods have gained increasing attention in modern image processing. The confocal images of the single-layered epithelium of the developing Drosophila eye may form an excellent model system to develop methods for complex feature extraction. The aim of this work was to explore Cartesian genetic programming for determination of the boundaries of ommatidia, the light-sensitive units in the presumptive eye region. Application of Cartesian genetic programming for the analysis of Fasciclin III expression has shown good results. This opens interesting perspectives for further use of this technology in the automatic analysis of confocal images.

A novel online tool condition monitoring method for milling titanium alloy with consideration of tool wear law

Due to issues such as limited variability in monitoring data across different tool wear conditions and interference during the machining process, data-driven monitoring models are susceptible to misclassification. Therefore, this paper proposes a pioneering approach that takes into account the tool wear law and the characteristic distribution of tool wear monitoring data. Specifically, the paper proposes an automatic feature extraction and tool condition monitoring method based on Siamese Long Short-term Memory Networks (SLSTMs) to transform the original data distribution, enhance the differentiation of different tool wear condition monitoring data, and achieve accurate prediction of tool wear condition. Additionally, a hybrid data and mechanism-driven tool wear monitoring method is proposed that takes advantage of the fact that tool wear is continuous and irreversible to enable reliable adjustment of the monitoring results of the data-driven model without human intervention. The study conducted milling experiments on a three-axis vertical machining center, using TA2 titanium alloy as the workpiece material. Vibration signals from the spindle in three directions were collected as input to the network, with tool wear state labeled as “0″ or ”1″ as the output. Classical machine learning algorithms such as Decision Trees, K-Nearest Neighbors (KNN) and Support Vector Machines (SVM), as well as classical deep learning algorithms such as Convolutional Neural Networks (CNN), Sparse Stacked Autoencoders (SSAE) and Long Short-Term Memory Neural Networks (LSTM), were used to construct and compare feature extraction and state monitoring models. The proposed model based on Siamese Long Short-Term Memory Neural Networks (SLSTMs) achieved testing average accuracy of 98.2% (σ2 = 0.44), outperforming typical deep learning algorithms such as CNN, LSTM and SSAE as well as traditional machine learning algorithms such as Decision Trees, KNN and SVM in terms of accuracy and robustness. Moreover, the proposed data and mechanism hybrid-driven tool wear monitoring method can effectively improve the monitoring accuracy and robustness of data-driven models such as CNN and SSAE. The monitoring accuracy of CNN and SSAE increased from 95.9% to 97.6% and 91.0% to 94.3%, respectively.

A Novel Method for Recognizing Space Radiation Sources Based on Multi-Scale Residual Prototype Learning Network

As a basic task and key link of space situational awareness, space target recognition has become crucial in threat analysis, communication reconnaissance and electronic countermeasures. Using the fingerprint features carried by the electromagnetic signal to recognize is an effective method. Because traditional radiation source recognition technologies are difficult to obtain satisfactory expert features, automatic feature extraction methods based on deep learning have become popular. Although many deep learning schemes have been proposed, most of them are only used to solve the inter-class separable problem and ignore the intra-class compactness. In addition, the openness of the real space may invalidate the existing closed-set recognition methods. In order to solve the above problems, inspired by the application of prototype learning in image recognition, we propose a novel method for recognizing space radiation sources based on a multi-scale residual prototype learning network (MSRPLNet). The method can be used for both the closed- and open-set recognition of space radiation sources. Furthermore, we also design a joint decision algorithm for an open-set recognition task to identify unknown radiation sources. To verify the effectiveness and reliability of the proposed method, we built a set of satellite signal observation and receiving systems in a real external environment and collected eight Iridium signals. The experimental results show that the accuracy of our proposed method can reach 98.34% and 91.04% for the closed- and open-set recognition of eight Iridium targets, respectively. Compared to similar research works, our method has obvious advantages.

Pursuing new periodontal pathogens with an improved RNA-oligonucleotide quantification technique (ROQT)

ObjectiveThe aim of this study was to optimize the sensitivity, specificity and cost-effectiveness of the RNA-Oligonucleotide Quantification Technique (ROQT) in order to identify periodontal pathogens that remain unrecognized or uncultured in the oral microbiome. DesignTotal nucleic acids (TNA) were extracted from subgingival biofilm samples using an automated process. RNA, DNA and Locked Nucleic Acid (LNA) digoxigenin-labeled oligonucleotide probes targeting 5 cultivated/named species and 16 uncultivated or unnamed bacterial taxa were synthesized. Probe specificity was determined by targeting 96 oral bacterial species; sensitivity was assessed using serial dilutions of reference bacterial strains. Different stringency temperatures were compared and new standards were tested. The tested conditions were evaluated analyzing samples from periodontally healthy individuals, and patients with moderate or severe periodontitis. ResultsThe automated extraction method at 63⁰C along with LNA-oligunucleotides probes, and use of reverse RNA sequences for standards yielded stronger signals without cross-reactions. In the pilot clinical study, the most commonly detected uncultivated/unrecognized species were Selenomonas sp. HMT 134, Prevotella sp. HMT 306, Desulfobulbus sp. HMT 041, Synergistetes sp. HMT 360 and Bacteroidetes HMT 274. In the cultivated segment of the microbiota, the most abundant taxa were T. forsythia HMT 613 and Fretibacterium fastidiosum (formerly Synergistetes) HMT 363. ConclusionsIn general, samples from severe patients had the greatest levels of organisms. Classic (T. forsythia, P. gingivalis) and newly proposed (F. alocis and Desulfobulbus sp. HMT 041) pathogens were present in greater amounts in samples from severe periodontitis sites, followed by moderate periodontitis sites.

Prediction of drug-target interactions via neural tangent kernel extraction feature matrix factorization model

Drug discovery is a complex and lengthy process that often requires years of research and development. Therefore, drug research and development require a lot of investment and resource support, as well as professional knowledge, technology, skills, and other elements. Predicting of drug-target interactions (DTIs) is an important part of drug development. If machine learning is used to predict DTIs, the cost and time of drug development can be significantly reduced. Currently, machine learning methods are widely used to predict DTIs. In this study neighborhood regularized logistic matrix factorization method based on extracted features from a neural tangent kernel (NTK) to predict DTIs. First, the potential feature matrix of drugs and targets is extracted from the NTK model, then the corresponding Laplacian matrix is constructed according to the feature matrix. Next, the Laplacian matrix of the drugs and targets is used as the condition for matrix factorization to obtain two low-dimensional matrices. Finally, the matrix of the predicted DTIs was obtained by multiplying these two low-dimensional matrices. For the four gold standard datasets, the present method is significantly better than the other methods that is compared to, indicating that the automatic feature extraction method using the deep learning model is competitive compared with the manual feature selection method.