Unknown Components Research Articles

Model-Free Generalized Super-Twisting Fast Terminal Sliding Mode Control for Permanent Magnet Synchronous Motors

Permanent Magnet Synchronous Motors (PMSMs) are nonlinear, multi-parameter systems that exhibit structural symmetry but are susceptible to parameter variations and external disturbances. These challenges can disrupt the inherent symmetrical characteristics of PMSM dynamics during real-world operations, posing difficulties for achieving efficient control. To address this issue, this paper proposes a Model-Free Generalized Super-Twisting Algorithm Fast Terminal Sliding Mode Control (MFFTSMC-GSTA) method. First, a novel ultra-local model incorporating PMSM uncertainties is established, and the MFFTSMC-GSTA controller is designed to address the system’s complex dynamic behavior. By integrating the generalized super-twisting algorithm with the nonsingular fast terminal sliding mode algorithm, the proposed controller ensures finite-time convergence and effectively mitigates chattering. Second, an extended sliding mode disturbance observer is developed to estimate the unknown components of the ultra-local model and provide feedforward compensation, further enhancing system robustness and dynamic performance. The experimental results show that the total harmonic distortion (THD) value of the proposed control method is 1.38%, demonstrating significant improvements in response speed and robustness for motor speed control, and verifying the algorithm’s superior performance under complex operating conditions.

Temperature and Frequency-Dependent Dielectric Properties Prediction of Oxide Glasses by Machine Learning

The dielectric properties of oxide glasses are essential for telecommunications, where thermal and frequency stability of devices are crucial. However, predicting the temperature and frequency-dependent dielectric properties of glasses is complex using empirical models and computational methods. To address this challenge, machine learning (ML) models with descriptor sets in two different domains—the chemical composition domain and the element physical and chemical properties domain—were employed to predict the dielectric constant and loss of oxide glasses, along with their temperature and frequency dependencies. Additionally, Shapley additive explanations (SHAP) analysis was conducted to interpret the hidden relationships among the data. Compared to experimental values, the ML models perform well in terms of root mean square error (RMSE) and the coefficient of determination (R2). Moreover, the ML models using element physical and chemical properties descriptors demonstrate the potential to predict the dielectric properties of glasses with unknown components.

Serum pharmacochemistry of Panacis Japonici Rhizoma extract based on UPLC-Q-Exactive Orbitrap-MS

In this study, the chemical components of Panacis Japonici Rhizoma extract and absorbed components in rats were identified by ultra-high performance liquid chromatography-quadrupole exactive orbitrap mass spectrometry(UPLC-Q-Exactive Orbitrap-MS). The separation was performed by gradient elution on Waters UPLC BEH C_(18) column(2.1 mm×100 mm, 1.7 μm) with the mobile phase of water and acetonitrile containing 0.1% formic acid. High resolution multistage mass spectrometry data were collected by electrospray ionization in positive and negative ion modes. The chemical components of Panacis Japonici Rhizoma extract were identified by comparing with the retention time, high resolution precise molecular weight, and secondary fragment ions of reference substances and related literature. After intragastric administration of Panacis Japonici Rhizoma extract, blood was collected from the abdominal aorta of rats for separation of the serum, and the absorbed components were scanned and identified. The results showed that 43 chemical components were detected in the Panacis Japonici Rhizoma extract, including 22 saponins, 9 amino acids, 5 polysaccharides, 2 volatile oils, and 5 nucleosides. In the serum, 18 components were detected, including 10 prototype components, 6 metabolites, and 2 unknown components. This study analyzed the chemical components and absorbed components of Panacis Japonici Rhizoma extract, providing clues for clarifying the pharmacological basis of Panacis Japonici Rhizoma.

Robust parameter estimation and identifiability analysis with hybrid neural ordinary differential equations in computational biology

Parameter estimation is one of the central challenges in computational biology. In this paper, we present an approach to estimate model parameters and assess their identifiability in cases where only partial knowledge of the system structure is available. The partially known model is embedded into a system of hybrid neural ordinary differential equations, with neural networks capturing unknown system components. Integrating neural networks into the model presents two main challenges: global exploration of the mechanistic parameter space during optimization and potential loss of parameter identifiability due to the neural network flexibility. To tackle these challenges, we treat biological parameters as hyperparameters, allowing for global search during hyperparameter tuning. We then conduct a posteriori identifiability analysis, extending a well-established method for mechanistic models. The pipeline performance is evaluated on three test cases designed to replicate real-world conditions, including noisy data and limited system observability.

Fecal Microbiota Transplantation: Indications, Methods, and Challenges.

Over the past two decades, as the importance of gut microbiota to human health has become widely known, attempts have been made to treat diseases by correcting dysbiosis of gut microbiota through fecal microbiota transplantation (FMT). Apart from current knowledge of gut microbiota, FMT to treat disease has a long history, from the treatment of food poisoning in the fourth century to the treatment of Clostridioides difficile infections in the twentieth century. In 2013, FMT was recognized as a standard treatment for recurrent C. difficile because it consistently showed high efficacy. Though recurrent C. difficile is the only disease internationally recognized for FMT efficacy, FMT has been tested for other diseases and shown some promising preliminary results. Different FMT methods have been developed using various formulations and administration routes. Despite advances in FMT, some issues remain to be resolved, such as donor screening, manufacturing protocols, and unknown components in the fecal microbiota. In this review, we discuss the mechanisms, clinical indications, methods, and challenges of current FMT. We also discuss the development of alternative therapies to overcome the challenges of FMT.

A novel physics-constrained neural network: An illustration of ground motion models

Ground motion model (GMM) is essential for seismic hazard analysis and can be developed using either empirical or machine learning approaches. The former often results in suboptimal predictive performance, and the latter frequently faces challenges related to interpretability and explainability although providing more accurate results. To overcome these limitations, this study proposes a novel physics-constrained neural network (PCNN) that incorporates constraints on the hypothesis space through designing specialized neural network architectures informed by physical domain knowledge. This approach enables the updating or derivation of biased or unknown components through data-driven learning. Using the development of GMMs as an illustration, the PCNN is constructed to maintain the mathematical form consistent with established empirical models by reconfiguring parameters, activation functions, and layer connections within a conventional neural network. This physics-constrained approach enhances both the interpretability of the network's architecture and the explainability of its outputs. By leveraging both the advanced machine learning techniques and the domain-specific physical constraints, the PCNN refines the suboptimal coefficients in empirical models, which could achieve the globally optimal model coefficients and improve predictive performance.

Enhancing coverage of annotated compounds in traditional Chinese medicine formulas: Integrating MSE and Fast-DDA molecular network with AntDAS—Case study of Xiao Jian Zhong Tang

The chemical characterisation of traditional Chinese medicine formulas (TCMFs) using mass spectrometry poses notable challenges owing to their complex and diverse chemical compositions. While acquisition modes such as data-dependent acquisition (DDA) and data-independent acquisition (DIA) offer new insights, DDA's tendency to overlook low-abundance ions and DIA's complicated data processing, particularly in matching MS1 and MS2 information, limit the effective annotation of valuable compounds in TCMFs. Herein, we present a new integrated strategy to enhance the coverage of annotated compounds in TCMFs, using Xiao Jian Zhong Tang (XJZ) as a case study. First, we characterised the components of XJZ through UNIFI software in Fast-DDA and DIA modes. We then summarised the diagnostic ions and substituent information of the identified compounds based on the Fast-DDA data, integrating molecular networks and AntDAS to predict unknown components and uncover potential components. Ultimately, we characterised a total of 785 components in XJZ, including 43 that were unique to XJZ when compared to the individual herbs involved. The presence of these new components may result from the recombination of substituents during compatibility. In conclusion, this new integrated strategy facilitates more in-depth characterisation of components in TCMFs, providing a new direction for exploring the compatibility principles among TCMFs.

Identification of Ginseng Radix et Rhizoma, Panacis Quinquefolii Radix, Notoginseng Radix et Rhizoma, and Platycodonis Radix Based on UHPLC-QTOF-MS and “Matrix Characteristics”

Ginseng Radix et Rhizoma (GRR), Panacis Quinquefolii Radix (PQR), Notoginseng radix et rhizoma (NRR) and Platycodonis Radix (PR) are often confused in the material market because of similar appearances and characteristics. Moreover, chemical identification methods tend to characterize the whole herb with regard to a single or a few components, which is an inaccurate representation and does not demonstrate the effective utilization of unknown components, and the result is unconvincing. In order to strengthen quality control, improve identification efficiency, and realize digital identification at the individual level of traditional Chinese medicine (TCM), we have put forward the “matrix characteristics” of TCM, combined with a UHPLC-QTOF-MS analysis to explore and realize the digital identification of GRR, PQR, NRR, and PR. The mass spectrometry was quantized to extract common data from different batches of the same TCMs as their matrix characteristics, and the matching credibility (M) was given by matching the “matrix characteristics” with unknown Chinese medicines. The results show that within a reasonable parameter threshold range, the M of four TCMs was higher than 92.00% compared with their own “matrix characteristics”, which was significantly higher than the M ranked second. Furthermore, the digital identification of four TCMs can be successfully realized based on the UHPLC-QTOF-MS analysis and “matrix characteristics”. This has important reference significance for developing the digital identification of GRR at an individual level based on UPLC-QTOF-MS and “matrix characteristics”.

A systematic UHPLC-Q-TOF-MS/MS-based strategy for analysis of chemical constituents and related in vivo metabolites of Buyang Huanwu decoction

Ethnopharmacological relevanceBuyang Huanwu Decoction (BYHWD), a traditional Chinese medicine, is one of the classic prescriptions for the treatment of ischemic stroke in clinical practice. It has the effects of tonifying qi, activating blood circulation, and promoting meridian circulation. However, its chemical analysis has not been clarified, which greatly hinders its further clinical application. Therefore, it is necessary to clarify the chemical constituents and metabolites profile of BYHWD in vivo. Aim of the studyCharacterizing the chemical basis of BYHWD in vitro, and combing studies of related metabolism in vivo to screen out the potential active components of BYHWD with pharmacological effects in vivo. Materials and methodsTwelve male rats weighed 200 ± 20 each were selected for the experiments. According to the fragmentation of different structural types of components and diagnostic ions, UHPLC-Q-TOF-MS/MS was used to classify and clarify the unknown components of BYHWD and identify the material basis of BYHWD in vitro. Then, rat plasma, tissues, feces, and urine were collected for analysis. Based on the similarity of MS responses (accurate molecular weight and secondary fragmentation) and chromatographic behavior (retention time), the in vivo prototype and metabolites were analyzed. Through the phase I and phase II metabolism law, a metabolite library was established to analyze the prototype-matched metabolites. ResultsA total of 121 in vitro compounds and 55 in vivo prototypes of BYHWD were identified, corresponding to 123 matched prototypes. It was mainly composed of flavonoids, triterpene saponins, nucleosides and lactones both in vitro and in vivo. Quercetin, ligustilide, astragaloside IV, calycosin, paeoniflorin and ferulic acid were the main prototypes and metabolites in plasma and urine. ConclusionQuercetin, ligustilide, astragaloside IV, calycosin, paeoniflorin and ferulic acid were the main active ingredients of BYHWD.

Transmit Precoding via Block Diagonalization with Approximately Optimized Distance Measures for Limited Feedback in Dense Cellular Networks with Multiantenna Base Stations

This study introduces distance metrics for quantized-channel-based precoding in multiuser multiantenna systems, aiming to enhance spectral efficiency in dense cellular networks. Traditional metrics, such as the chordal distance, face limitations when dealing with scenarios involving limited feedback and multiple receive antennas. We address these challenges by developing distance measures that more accurately reflect network conditions, including the impact of intercell interference. Our distance measures are specifically designed to approximate the instantaneous rate of each user by estimating the unknown components during the quantization stage. This approach enables the associated users to efficiently estimate their achievable rates during the quantization process. Our distance measures are specifically designed for block diagonalization precoding, a method known for its computational efficiency and strong performance in multi-user multiple-input and multiple-output systems. The proposed metrics outperform conventional distance measures, particularly in environments where feedback resources are constrained, as is often the case in 5G and emerging 6G networks. The enhancements are especially significant in dense cellular networks, where accurate channel state information is critical for maintaining high spectral efficiency. Our findings suggest that these new distance measures offer a robust solution for improving the performance of limited-feedback-based precoding in cellular networks.

Non-negative least-squares variance and covariance component estimation using the positive-valued function for errors-in-variables models

Abstract Although (co)variance component estimation has been widely applied in the errors-in-variables (EIV) model, the occurrence of negative variance components is still a major issue in the estimated variance components. This problem may be due to the following unfavorable factors: 1) unreasonable selection of initial variance values; 2) low redundancy in the EIV functional model; 3) improper design in the EIV stochastic model, and 4) other data quality problems. Many attempts have been made to prevent the appearance of negative variance components. In this contribution, a novel and efficient non-negative least-squares variance component estimation using the PVF (PVF-NLS-VCE) is introduced, which can simultaneously estimate the unknown (co)variance components in the EIV stochastic model and the parameters in the EIV functional model. Its principle is to implicitly impose a non-negative constraint by replacing the variance component with the positive-valued function (PVF) whose range is the set of positive real numbers. Two numerical examples using real and simulated data are presented. The numerical results of linear regression are identical to those obtained based on least-squares variance component estimation (LS-VCE) with positive initial values of variance components. The numerical results of two-dimensional affine transformation are shown to prevent negative variance components and precede those obtained by LS-VCE with a negative initial value of variance component. Both numerical examples verify the effectiveness of the PVF-NLS-VCE method whether the initial values of variance components are positive or negative. The proposed PVF-NLS-VCE is a simple, convenient and flexible method to achieve the non-negative estimates of variance components, which can reduce sensitivity to initial value selection and automatically guarantee a non-negative definite covariance matrix.

The PulE ATPase is required for twitching motility and DNA donation during Thermus thermophilus transjugation.

Thermus thermophilus can acquire DNA through natural competence and through transjugation, a mechanism that involves a two-step process of DNA secretion (push) and DNA internalization (pull) between mating cells of related species. The natural competence apparatus (NCA) is required in the recipient mate for the pull step. However, how the DNA exits of the donor cell is only partially known. The putative DNA translocase TdtA, encoded in mobile genetic element ICETh1 of T. thermophilus HB27, was shown to be required for DNA donation as reported by (Blesa et al.2017a). This ring-shaped hexameric ATPase binds to the membrane and likely interacts with yet unknown secretory components that allow the extrusion of DNA through the membrane; thus, a genetic screening to identify additional putative secretory components was performed. Here, we describe that mutants in gene TT_C1844, which encodes a putative AAA-ATPase named PulE, do not synthesize the recently described "narrow" type 4 pili required for twitching motility and made up of the major PilA5 pilin. Concomitantly, pulE mutants also exhibited DNA donation defects during transjugation, suggesting a role of narrow pili in the donation process. However, single pilA5 null mutants still function as DNA donors in transjugation experiments, so we conclude that the need for PulE in transjugation is independent of its role in narrow pili synthesis and twitching motility.

Unveiling the Intercompartmental Signaling Axis: Mitochondrial to ER Stress Response (MERSR) and its Impact on Proteostasis.

Maintaining protein homeostasis is essential for cellular health. Our previous research uncovered a cross-compartmental Mitochondrial to Cytosolic Stress Response, activated by the perturbation of mitochondrial proteostasis, which ultimately results in the improvement of proteostasis in the cytosol. Here, we found that this signaling axis also influences the unfolded protein response of the endoplasmic reticulum (UPR ER ), suggesting the presence of a Mitochondria to ER Stress Response (MERSR). During MERSR, the IRE1 branch of UPR ER is inhibited, introducing a previously unknown regulatory component of MCSR. Moreover, proteostasis is enhanced through the upregulation of the PERK-eIF2α signaling pathway, increasing phosphorylation of eIF2α and improving the ER's ability to handle proteostasis. MERSR activation in both polyglutamine and amyloid-beta peptide-expressing C. elegans disease models also led to improvement in both aggregate burden and overall disease outcome. These findings shed light on the coordination between the mitochondria and the ER in maintaining cellular proteostasis and provide further evidence for the importance of intercompartmental signaling.

Combining High-Resolution Mass Spectrometry and Chemiluminescence Analysis to Characterize the Composition and Fate of Total N-Nitrosamines in Wastewater Treatment Plants.

Monitoring the prevalence and persistence of N-nitrosamines and their precursors in wastewater treatment plants (WWTPs) and effluent-receiving aquatic compartments is a priority for utilities practicing wastewater recycling or exploiting wastewater-impacted source waters. In this work, we developed an analytical framework that combines liquid chromatography-high-resolution mass spectrometry (LC-HRMS) with acidic triiodide-chemiluminescence analysis to characterize the composition and fate of total N-nitrosamines (TONO) and their precursors along the treatment trains of eight WWTPs in New York. Through the parallel application of LC-HRMS and chemiluminescence methods, the TONO scores for 41 N-nitrosamines containing structurally diverse substituents on their amine nitrogen were derived based on their solid-phase extraction recoveries and conversion efficiencies to nitric oxide. Correcting the compositional analysis of TONO using the TONO scores of target N-nitrosamines refined the assessment of the reduction or accumulation of TONO and their precursors across treatment steps in WWTPs. Nontargeted analysis prioritized seven additional N-nitrosamines for confirmation by reference standards, including three previously uncharacterized species: N-nitroso-tert-butylphenylamine, N-nitroso-2-pyrrolidinmethanol, and N-nitrosodesloratadine, although they only served as minor components of TONO. Overall, our study establishes an adaptable methodological framework for advancing the quantitative and qualitative analysis of specific and unknown components of TONO across water treatment and reuse scenarios.

Multimodal Molecular Imaging Reveals a Novel Membrane Component in Sporangia of the Rare Actinomycete Actinoplanes missouriensis.

The bacterium Actinoplanes missouriensis belongs to the genus Actinoplanes, a prolific source of useful natural products. This microbe forms globular structures called sporangia, which contain many dormant spores. Recent studies using transmission electron microscopy have shown that the A. missouriensis sporangium membrane has an unprecedented three-layer structure, but its molecular components remain unclear. Here, we present multimodal (spontaneous Raman scattering, coherent anti-Stokes Raman scattering, second harmonic generation, sum frequency generation, and third-order sum frequency generation) label-free molecular imaging of intact A. missouriensis sporangia. Spontaneous Raman imaging assisted with multivariate curve resolution-alternating least-squares analysis revealed a novel component in the sporangium membrane that exhibits unique Raman bands at 1550 and 1615 cm-1 in addition to those characteristic of lipids. A plausible candidate for this component is an unsaturated carbonyl compound with an aliphatic moiety derived from fatty acid. Furthermore, second harmonic generation imaging revealed that a layer(s) of the sporangium membrane containing this unknown component has an ordered, noncentrosymmetric structure like fibrillar proteins and amylopectin. Our results suggest that the sporangium membrane is a new type of biological membrane, not only in terms of architecture but also in terms of components. We demonstrate that multimodal molecular imaging with Raman scattering as the core technology will provide a promising platform for interrogating the chemical components, whether known or unknown, of diverse biological structures produced by microbes.

Mutational mechanisms in multiply relapsed pediatric acute lymphoblastic leukemia

Pediatric acute lymphoblastic leukemia (ALL) is marked by low mutational load at initial diagnosis, which increases at relapse. To determine which processes are active in (relapsed) ALL and how they behave during disease progression before and after therapy, we performed whole genome sequencing on 97 tumor samples of 29 multiply relapsed ALL patients. Mutational load increased upon relapse in 28 patients and upon every subsequent relapse in 22 patients. In addition to two clock-like mutational processes, we identified UV-like damage, APOBEC activity, reactive oxygen species, thiopurine-associated damage and an unknown therapy component as drivers of mutagenesis. Mutational processes often affected patients over longer time periods, but could also occur in isolated events, suggesting the requirement of additional triggers. Thiopurine exposure was the most prominent source of new mutations in relapse, affecting over half of the studied patients in first and/or later relapse and causing potential relapse-driving mutations in multiple patients. Our data demonstrate that multiple mutational processes frequently act in parallel as prominent secondary drivers with dynamic activity during ALL development and progression.

Identification Analysis of Angelicae sinensis radix and Angelicae pubescentis radix Based on Quantized "Digital Identity" and UHPLC-QTOF-MSE Analysis.

Angelicae sinensis radix (ASR) and Angelicae pubescentis radix (APR), as traditional herbal medicines, are often confused and doped in the material market. However, the traditional identification method is to characterize the whole herb with a single or a few components, which do not have representation and cannot realize the effective utilization of unknown components. Consequently, the result is not convincing. In addition, the whole process is time-consuming and labor-intensive. To avoid the confusion and adulteration of ASR and APR as well as to strengthen quality control and improve identification efficiency, in this study, a UHPLC-QTOF-MSE method was used to analyze ASR and APR. Based on digital representation, the shared data with high ionic strength were extracted from different batches of the same herbal medicine as their "digital identity". Further, the above "digital identity" was used as the benchmark for matching and identifying unknown samples to feedback on matching credibility (MC). The results showed that based on the "digital identities" of ASR and APR, the digital identification of two herbal samples can be realized efficiently and accurately at the individual level. And the matching credibility (MC) was higher than 94.00%, even if only 1% of APR or ASR in the mixed samples can still be identified efficiently and accurately. The study is of great practical significance for improving the efficiency of the identification of ASR and APR, cracking down on adulterated and counterfeit drugs, and strengthening the quality control of ASR and APR. In addition, it has important reference significance for developing nontargeted digital identification of herbal medicines at the individual level based on UHPLC-QTOF-MSE and "digital identity", which is beneficial to the construction of digital Chinese medicine and digital quality control.

Identification of Δ8-Tetrahydrocannabinol (THC) and Δ9-THC Analogs, with Different Lengths of Alkyl Chain at C-3 Position, in Oil Products Distributed on the Internet

Since around 2021, products claiming to contain a Δ9-tetrahydrocannabinol (THC) analog with different lengths of alkyl chain at C-3 position have been sold on the internet in Japan. Δ9-THC has a pentyl group derived from the precursor olivetol at the C-3 position. These products include liquid cartridges for electronic cigarettes, herbal products, and gummy products. This study analyzed and determined the ingredients in five oil products distributed on the internet from 2022 to 2023 that claim to contain THC analogs. Samples of each product were used for GC-MS and LC-MS measurements. After isolating and purifying the unknown components from the products, structural analysis was performed by measuring 1H, 13C-NMR and various two-dimensional NMR [HH correlation spectroscopy (H-H COSY), heteronuclear multiple quantum coherence (HMQC), heteronuclear multiple-bond correlation (HMBC), and nuclear Overhauser effect spectroscopy (NOESY)]. The analysis identified Δ8-tetrahydrocannabivarin (THCV), Δ9-THCV, Δ8-tetrahydrocannabutol (THCB), Δ9-THCB, Δ8-tetrahydrocannabihexol (THCH), Δ9-THCH, Δ8-3-octyl-THC (THCjd) and Δ9-THCjd. These compounds were Δ8-THC or Δ9-THC analogs with different lengths of alkyl chain at C-3 position. Meanwhile, Δ4(8)-iso-THCV and Δ11-THCB were identified as minor components of the product, and were considered to be the reaction byproducts of the synthesis of the Δ8-THC or Δ9-THC analogs. In the future, there are concerns about the distribution of products containing new THC analogs. Therefore, continuous provision monitoring of newly detected in the products is important.

Tropical beetles more sensitive to impacts are less likely to be known to science

Insects are posited to be declining globally. This is particularly pertinent in tropical forests, which exhibit both the highest levels of biodiversity and the highest rates of biodiversity loss. However, for the hyper-diverse tropical insects there are scant data available to evidence declines. Understanding tropical insect diversity and its response to environmental change has therefore become a challenge, but it is estimated that 80% of tropical insect species remain undescribed1. Insect biodiversity predictions are based mostly on well-studied taxa and extrapolated to other groups, but no one knows whether resilience to environmental change varies between undescribed and described species. Here, we collected staphylinid beetles from unlogged and logged tropical forests in Borneo and investigated their responses to environmental change. Out of 252 morphospecies collected, 76% were undescribed. Undescribed species showed higher community turnover, reduced abundance and decreased probability of occurrence in logged forests. Thus the unknown components of tropical insect biodiversity are likely more impacted by human-induced environmental change. If these patterns are widespread, how accurate will assessments of insect declines in the tropics be?

Digital identification of Aucklandiae radix, Vladimiriae radix, and Inulae radix based on multivariate algorithms and UHPLC-QTOF-MS analysis.

The identification of Aucklandiae Radix (AR), Vladimiriae Radix (VR), and Inulae Radix (IR) based on traits and microscopic features is susceptible to the state of samples and the subjective awareness of personnel, and the identification based on a few or single chemical compositions is a cumbersome and time-consuming procedure and fails to rationally and effectively utilize the information of unknown components and is not specificity enough. This study aimed to improve the identification efficiency, strengthen supervision, and realize digital identification of three Chinese medicines. Ultra-high-performance liquid chromatography with quadrupole time-of-flight mass spectrometry (UHPLC-QTOF-MS) combined with multivariate algorithms was used to explore the digital identification of AR, VR, and IR. UHPLC-QTOF-MS was used to analyze AR, VR, and IR. The MS data combined with multivariate algorithms such as partial least squares discrimination analysis (PLS-DA) and artificial neural networks (ANNs) was used to filter important variables and data modeling. Finally, the optimal model was selected for the digital identification of three herbs. The results showed that three herbs can be distinguished on the whole level, and through feature screening, 591 characteristic variables combined with multivariate algorithms to construct data models. The ANN model was the best with accuracy = 0.983, precision = 0.984, and external verification showed the reliability and practicability of ANN model. ANN model combined with MS data is of great significance for tdigital identification of AR, VR, and IR. It is an important reference for developing the digital identification of traditional Chinese medicines at the individual level based on UHPLC-QTOF-MS and multivariate algorithms.